Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +61 -0
- added_tokens.json +24 -0
- all_results.json +8 -0
- config.json +29 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +346 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- train_results.json +8 -0
- trainer_log.jsonl +183 -0
- trainer_state.json +2772 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- training_rewards_accuracies.png +0 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: other
|
4 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- full
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: simpo_trained_1
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# simpo_trained_1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the lightblue_orpo_data dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 1e-06
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 8
|
44 |
+
- gradient_accumulation_steps: 16
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- total_eval_batch_size: 8
|
47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 1.0
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.46.1
|
59 |
+
- Pytorch 2.4.0+cu121
|
60 |
+
- Datasets 3.1.0
|
61 |
+
- Tokenizers 0.20.3
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9982859101816935,
|
3 |
+
"total_flos": 58779245903872.0,
|
4 |
+
"train_loss": 1.1193010831599708,
|
5 |
+
"train_runtime": 13670.339,
|
6 |
+
"train_samples_per_second": 1.707,
|
7 |
+
"train_steps_per_second": 0.013
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 28,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.1",
|
26 |
+
"use_cache": false,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 152064
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.46.1"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c54c66db42fa82fe5847dbacc47dd223170339572089ebc336a195fc0a18fd99
|
3 |
+
size 4877660776
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8ff40a68ab8f646969d08226933892a38b53c0260587a95b65e69d4ad4e1995
|
3 |
+
size 4932751008
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c768cda91e51eccd3e57063a23579529958a3a430c4a40c08db0c72d1457d975
|
3 |
+
size 4330865200
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61651c2ce64e5cd654f636513187540b2f5f8dd77b1ba130e0da3b3bba5a0f67
|
3 |
+
size 1089994880
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 15231233024
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
224 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
248 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
344 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
345 |
+
}
|
346 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"padding_side": "right",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9982859101816935,
|
3 |
+
"total_flos": 58779245903872.0,
|
4 |
+
"train_loss": 1.1193010831599708,
|
5 |
+
"train_runtime": 13670.339,
|
6 |
+
"train_samples_per_second": 1.707,
|
7 |
+
"train_steps_per_second": 0.013
|
8 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 182, "loss": 2.2106, "accuracy": 0.328125, "lr": 5.2631578947368416e-08, "epoch": 0.005485087418580734, "percentage": 0.55, "elapsed_time": "0:01:19", "remaining_time": "3:59:54"}
|
2 |
+
{"current_steps": 2, "total_steps": 182, "loss": 2.1187, "accuracy": 0.3671875, "lr": 1.0526315789473683e-07, "epoch": 0.010970174837161468, "percentage": 1.1, "elapsed_time": "0:02:33", "remaining_time": "3:49:39"}
|
3 |
+
{"current_steps": 3, "total_steps": 182, "loss": 2.0561, "accuracy": 0.375, "lr": 1.5789473684210525e-07, "epoch": 0.0164552622557422, "percentage": 1.65, "elapsed_time": "0:03:52", "remaining_time": "3:51:05"}
|
4 |
+
{"current_steps": 4, "total_steps": 182, "loss": 2.1332, "accuracy": 0.4140625, "lr": 2.1052631578947366e-07, "epoch": 0.021940349674322936, "percentage": 2.2, "elapsed_time": "0:05:08", "remaining_time": "3:48:30"}
|
5 |
+
{"current_steps": 5, "total_steps": 182, "loss": 2.0846, "accuracy": 0.3359375, "lr": 2.631578947368421e-07, "epoch": 0.027425437092903668, "percentage": 2.75, "elapsed_time": "0:06:25", "remaining_time": "3:47:23"}
|
6 |
+
{"current_steps": 6, "total_steps": 182, "loss": 2.1337, "accuracy": 0.375, "lr": 3.157894736842105e-07, "epoch": 0.0329105245114844, "percentage": 3.3, "elapsed_time": "0:07:40", "remaining_time": "3:44:59"}
|
7 |
+
{"current_steps": 7, "total_steps": 182, "loss": 2.0016, "accuracy": 0.4140625, "lr": 3.684210526315789e-07, "epoch": 0.03839561193006513, "percentage": 3.85, "elapsed_time": "0:08:55", "remaining_time": "3:43:05"}
|
8 |
+
{"current_steps": 8, "total_steps": 182, "loss": 2.1026, "accuracy": 0.390625, "lr": 4.2105263157894733e-07, "epoch": 0.04388069934864587, "percentage": 4.4, "elapsed_time": "0:10:13", "remaining_time": "3:42:32"}
|
9 |
+
{"current_steps": 9, "total_steps": 182, "loss": 2.425, "accuracy": 0.265625, "lr": 4.7368421052631574e-07, "epoch": 0.049365786767226603, "percentage": 4.95, "elapsed_time": "0:11:31", "remaining_time": "3:41:37"}
|
10 |
+
{"current_steps": 10, "total_steps": 182, "loss": 2.435, "accuracy": 0.296875, "lr": 5.263157894736842e-07, "epoch": 0.054850874185807336, "percentage": 5.49, "elapsed_time": "0:12:47", "remaining_time": "3:39:54"}
|
11 |
+
{"current_steps": 11, "total_steps": 182, "loss": 2.3341, "accuracy": 0.3359375, "lr": 5.789473684210526e-07, "epoch": 0.06033596160438807, "percentage": 6.04, "elapsed_time": "0:14:02", "remaining_time": "3:38:18"}
|
12 |
+
{"current_steps": 12, "total_steps": 182, "loss": 2.2512, "accuracy": 0.296875, "lr": 6.31578947368421e-07, "epoch": 0.0658210490229688, "percentage": 6.59, "elapsed_time": "0:15:17", "remaining_time": "3:36:40"}
|
13 |
+
{"current_steps": 13, "total_steps": 182, "loss": 2.1644, "accuracy": 0.328125, "lr": 6.842105263157895e-07, "epoch": 0.07130613644154954, "percentage": 7.14, "elapsed_time": "0:16:32", "remaining_time": "3:35:07"}
|
14 |
+
{"current_steps": 14, "total_steps": 182, "loss": 2.3949, "accuracy": 0.3203125, "lr": 7.368421052631578e-07, "epoch": 0.07679122386013026, "percentage": 7.69, "elapsed_time": "0:17:51", "remaining_time": "3:34:12"}
|
15 |
+
{"current_steps": 15, "total_steps": 182, "loss": 2.2735, "accuracy": 0.328125, "lr": 7.894736842105263e-07, "epoch": 0.082276311278711, "percentage": 8.24, "elapsed_time": "0:19:04", "remaining_time": "3:32:20"}
|
16 |
+
{"current_steps": 16, "total_steps": 182, "loss": 2.2617, "accuracy": 0.34375, "lr": 8.421052631578947e-07, "epoch": 0.08776139869729174, "percentage": 8.79, "elapsed_time": "0:20:21", "remaining_time": "3:31:17"}
|
17 |
+
{"current_steps": 17, "total_steps": 182, "loss": 2.3686, "accuracy": 0.265625, "lr": 8.947368421052631e-07, "epoch": 0.09324648611587247, "percentage": 9.34, "elapsed_time": "0:21:38", "remaining_time": "3:30:02"}
|
18 |
+
{"current_steps": 18, "total_steps": 182, "loss": 2.0268, "accuracy": 0.3984375, "lr": 9.473684210526315e-07, "epoch": 0.09873157353445321, "percentage": 9.89, "elapsed_time": "0:22:53", "remaining_time": "3:28:30"}
|
19 |
+
{"current_steps": 19, "total_steps": 182, "loss": 2.0874, "accuracy": 0.3046875, "lr": 1e-06, "epoch": 0.10421666095303393, "percentage": 10.44, "elapsed_time": "0:24:03", "remaining_time": "3:26:23"}
|
20 |
+
{"current_steps": 20, "total_steps": 182, "loss": 2.0832, "accuracy": 0.34375, "lr": 9.999071352056673e-07, "epoch": 0.10970174837161467, "percentage": 10.99, "elapsed_time": "0:25:18", "remaining_time": "3:25:00"}
|
21 |
+
{"current_steps": 21, "total_steps": 182, "loss": 2.1691, "accuracy": 0.3046875, "lr": 9.996285753181497e-07, "epoch": 0.11518683579019541, "percentage": 11.54, "elapsed_time": "0:26:31", "remaining_time": "3:23:23"}
|
22 |
+
{"current_steps": 22, "total_steps": 182, "loss": 1.9912, "accuracy": 0.34375, "lr": 9.99164423811074e-07, "epoch": 0.12067192320877614, "percentage": 12.09, "elapsed_time": "0:27:46", "remaining_time": "3:22:01"}
|
23 |
+
{"current_steps": 23, "total_steps": 182, "loss": 1.9723, "accuracy": 0.3203125, "lr": 9.985148530977764e-07, "epoch": 0.12615701062735687, "percentage": 12.64, "elapsed_time": "0:28:59", "remaining_time": "3:20:26"}
|
24 |
+
{"current_steps": 24, "total_steps": 182, "loss": 1.8305, "accuracy": 0.4140625, "lr": 9.976801044672607e-07, "epoch": 0.1316420980459376, "percentage": 13.19, "elapsed_time": "0:30:12", "remaining_time": "3:18:54"}
|
25 |
+
{"current_steps": 25, "total_steps": 182, "loss": 1.9472, "accuracy": 0.3828125, "lr": 9.966604879945656e-07, "epoch": 0.13712718546451835, "percentage": 13.74, "elapsed_time": "0:31:26", "remaining_time": "3:17:28"}
|
26 |
+
{"current_steps": 26, "total_steps": 182, "loss": 1.8902, "accuracy": 0.4140625, "lr": 9.954563824255877e-07, "epoch": 0.14261227288309908, "percentage": 14.29, "elapsed_time": "0:32:41", "remaining_time": "3:16:10"}
|
27 |
+
{"current_steps": 27, "total_steps": 182, "loss": 1.9858, "accuracy": 0.3046875, "lr": 9.94068235036391e-07, "epoch": 0.1480973603016798, "percentage": 14.84, "elapsed_time": "0:33:57", "remaining_time": "3:14:54"}
|
28 |
+
{"current_steps": 28, "total_steps": 182, "loss": 1.9039, "accuracy": 0.3828125, "lr": 9.924965614670628e-07, "epoch": 0.15358244772026053, "percentage": 15.38, "elapsed_time": "0:35:12", "remaining_time": "3:13:38"}
|
29 |
+
{"current_steps": 29, "total_steps": 182, "loss": 2.0302, "accuracy": 0.28125, "lr": 9.90741945530174e-07, "epoch": 0.15906753513884128, "percentage": 15.93, "elapsed_time": "0:36:24", "remaining_time": "3:12:06"}
|
30 |
+
{"current_steps": 30, "total_steps": 182, "loss": 1.9332, "accuracy": 0.421875, "lr": 9.888050389939172e-07, "epoch": 0.164552622557422, "percentage": 16.48, "elapsed_time": "0:37:39", "remaining_time": "3:10:47"}
|
31 |
+
{"current_steps": 31, "total_steps": 182, "loss": 1.9123, "accuracy": 0.3671875, "lr": 9.866865613400006e-07, "epoch": 0.17003770997600273, "percentage": 17.03, "elapsed_time": "0:38:58", "remaining_time": "3:09:50"}
|
32 |
+
{"current_steps": 32, "total_steps": 182, "loss": 1.9177, "accuracy": 0.3515625, "lr": 9.843872994963912e-07, "epoch": 0.17552279739458349, "percentage": 17.58, "elapsed_time": "0:40:15", "remaining_time": "3:08:40"}
|
33 |
+
{"current_steps": 33, "total_steps": 182, "loss": 1.7645, "accuracy": 0.4921875, "lr": 9.819081075450013e-07, "epoch": 0.1810078848131642, "percentage": 18.13, "elapsed_time": "0:41:27", "remaining_time": "3:07:09"}
|
34 |
+
{"current_steps": 34, "total_steps": 182, "loss": 1.8363, "accuracy": 0.375, "lr": 9.792499064044342e-07, "epoch": 0.18649297223174494, "percentage": 18.68, "elapsed_time": "0:42:43", "remaining_time": "3:06:00"}
|
35 |
+
{"current_steps": 35, "total_steps": 182, "loss": 1.8242, "accuracy": 0.40625, "lr": 9.764136834878985e-07, "epoch": 0.1919780596503257, "percentage": 19.23, "elapsed_time": "0:44:00", "remaining_time": "3:04:48"}
|
36 |
+
{"current_steps": 36, "total_steps": 182, "loss": 1.8998, "accuracy": 0.390625, "lr": 9.734004923364256e-07, "epoch": 0.19746314706890641, "percentage": 19.78, "elapsed_time": "0:45:20", "remaining_time": "3:03:53"}
|
37 |
+
{"current_steps": 37, "total_steps": 182, "loss": 1.8343, "accuracy": 0.40625, "lr": 9.702114522275216e-07, "epoch": 0.20294823448748714, "percentage": 20.33, "elapsed_time": "0:46:35", "remaining_time": "3:02:34"}
|
38 |
+
{"current_steps": 38, "total_steps": 182, "loss": 1.6697, "accuracy": 0.4921875, "lr": 9.66847747759402e-07, "epoch": 0.20843332190606786, "percentage": 20.88, "elapsed_time": "0:47:47", "remaining_time": "3:01:04"}
|
39 |
+
{"current_steps": 39, "total_steps": 182, "loss": 1.8336, "accuracy": 0.359375, "lr": 9.63310628410961e-07, "epoch": 0.21391840932464862, "percentage": 21.43, "elapsed_time": "0:49:05", "remaining_time": "2:59:59"}
|
40 |
+
{"current_steps": 40, "total_steps": 182, "loss": 1.8315, "accuracy": 0.40625, "lr": 9.596014080776421e-07, "epoch": 0.21940349674322934, "percentage": 21.98, "elapsed_time": "0:50:21", "remaining_time": "2:58:46"}
|
41 |
+
{"current_steps": 41, "total_steps": 182, "loss": 1.7842, "accuracy": 0.4140625, "lr": 9.55721464583379e-07, "epoch": 0.22488858416181007, "percentage": 22.53, "elapsed_time": "0:51:36", "remaining_time": "2:57:29"}
|
42 |
+
{"current_steps": 42, "total_steps": 182, "loss": 1.9825, "accuracy": 0.3203125, "lr": 9.516722391687902e-07, "epoch": 0.23037367158039082, "percentage": 23.08, "elapsed_time": "0:52:54", "remaining_time": "2:56:20"}
|
43 |
+
{"current_steps": 43, "total_steps": 182, "loss": 1.6144, "accuracy": 0.4453125, "lr": 9.474552359558165e-07, "epoch": 0.23585875899897155, "percentage": 23.63, "elapsed_time": "0:54:07", "remaining_time": "2:54:56"}
|
44 |
+
{"current_steps": 44, "total_steps": 182, "loss": 1.648, "accuracy": 0.4453125, "lr": 9.430720213890029e-07, "epoch": 0.24134384641755227, "percentage": 24.18, "elapsed_time": "0:55:19", "remaining_time": "2:53:31"}
|
45 |
+
{"current_steps": 45, "total_steps": 182, "loss": 1.9336, "accuracy": 0.46875, "lr": 9.385242236536259e-07, "epoch": 0.24682893383613302, "percentage": 24.73, "elapsed_time": "0:56:35", "remaining_time": "2:52:16"}
|
46 |
+
{"current_steps": 46, "total_steps": 182, "loss": 1.4913, "accuracy": 0.5234375, "lr": 9.338135320708911e-07, "epoch": 0.25231402125471375, "percentage": 25.27, "elapsed_time": "0:57:47", "remaining_time": "2:50:51"}
|
47 |
+
{"current_steps": 47, "total_steps": 182, "loss": 1.4505, "accuracy": 0.6171875, "lr": 9.289416964704185e-07, "epoch": 0.2577991086732945, "percentage": 25.82, "elapsed_time": "0:59:11", "remaining_time": "2:50:00"}
|
48 |
+
{"current_steps": 48, "total_steps": 182, "loss": 1.5693, "accuracy": 0.671875, "lr": 9.239105265402525e-07, "epoch": 0.2632841960918752, "percentage": 26.37, "elapsed_time": "1:00:24", "remaining_time": "2:48:39"}
|
49 |
+
{"current_steps": 49, "total_steps": 182, "loss": 1.4994, "accuracy": 0.75, "lr": 9.187218911546361e-07, "epoch": 0.2687692835104559, "percentage": 26.92, "elapsed_time": "1:01:38", "remaining_time": "2:47:18"}
|
50 |
+
{"current_steps": 50, "total_steps": 182, "loss": 1.686, "accuracy": 0.640625, "lr": 9.133777176798012e-07, "epoch": 0.2742543709290367, "percentage": 27.47, "elapsed_time": "1:02:52", "remaining_time": "2:45:59"}
|
51 |
+
{"current_steps": 51, "total_steps": 182, "loss": 1.1265, "accuracy": 0.7265625, "lr": 9.078799912580303e-07, "epoch": 0.27973945834761743, "percentage": 28.02, "elapsed_time": "1:04:07", "remaining_time": "2:44:43"}
|
52 |
+
{"current_steps": 52, "total_steps": 182, "loss": 1.0881, "accuracy": 0.7578125, "lr": 9.022307540702576e-07, "epoch": 0.28522454576619816, "percentage": 28.57, "elapsed_time": "1:05:19", "remaining_time": "2:43:17"}
|
53 |
+
{"current_steps": 53, "total_steps": 182, "loss": 1.2003, "accuracy": 0.734375, "lr": 8.964321045774806e-07, "epoch": 0.2907096331847789, "percentage": 29.12, "elapsed_time": "1:06:31", "remaining_time": "2:41:54"}
|
54 |
+
{"current_steps": 54, "total_steps": 182, "loss": 1.4033, "accuracy": 0.6640625, "lr": 8.904861967412701e-07, "epoch": 0.2961947206033596, "percentage": 29.67, "elapsed_time": "1:07:45", "remaining_time": "2:40:36"}
|
55 |
+
{"current_steps": 55, "total_steps": 182, "loss": 1.3969, "accuracy": 0.8125, "lr": 8.843952392236593e-07, "epoch": 0.30167980802194033, "percentage": 30.22, "elapsed_time": "1:08:59", "remaining_time": "2:39:18"}
|
56 |
+
{"current_steps": 56, "total_steps": 182, "loss": 1.2378, "accuracy": 0.765625, "lr": 8.781614945667168e-07, "epoch": 0.30716489544052106, "percentage": 30.77, "elapsed_time": "1:10:15", "remaining_time": "2:38:04"}
|
57 |
+
{"current_steps": 57, "total_steps": 182, "loss": 1.0947, "accuracy": 0.8125, "lr": 8.717872783521047e-07, "epoch": 0.31264998285910184, "percentage": 31.32, "elapsed_time": "1:11:32", "remaining_time": "2:36:54"}
|
58 |
+
{"current_steps": 58, "total_steps": 182, "loss": 1.0673, "accuracy": 0.78125, "lr": 8.652749583409339e-07, "epoch": 0.31813507027768256, "percentage": 31.87, "elapsed_time": "1:12:45", "remaining_time": "2:35:33"}
|
59 |
+
{"current_steps": 59, "total_steps": 182, "loss": 1.0082, "accuracy": 0.8359375, "lr": 8.586269535942385e-07, "epoch": 0.3236201576962633, "percentage": 32.42, "elapsed_time": "1:13:57", "remaining_time": "2:34:11"}
|
60 |
+
{"current_steps": 60, "total_steps": 182, "loss": 1.2004, "accuracy": 0.7734375, "lr": 8.518457335743924e-07, "epoch": 0.329105245114844, "percentage": 32.97, "elapsed_time": "1:15:16", "remaining_time": "2:33:04"}
|
61 |
+
{"current_steps": 61, "total_steps": 182, "loss": 1.07, "accuracy": 0.78125, "lr": 8.449338172278058e-07, "epoch": 0.33459033253342474, "percentage": 33.52, "elapsed_time": "1:16:30", "remaining_time": "2:31:46"}
|
62 |
+
{"current_steps": 62, "total_steps": 182, "loss": 1.1342, "accuracy": 0.7578125, "lr": 8.378937720492383e-07, "epoch": 0.34007541995200546, "percentage": 34.07, "elapsed_time": "1:17:48", "remaining_time": "2:30:35"}
|
63 |
+
{"current_steps": 63, "total_steps": 182, "loss": 0.9218, "accuracy": 0.8203125, "lr": 8.307282131280804e-07, "epoch": 0.34556050737058625, "percentage": 34.62, "elapsed_time": "1:19:03", "remaining_time": "2:29:20"}
|
64 |
+
{"current_steps": 64, "total_steps": 182, "loss": 1.0545, "accuracy": 0.796875, "lr": 8.23439802176954e-07, "epoch": 0.35104559478916697, "percentage": 35.16, "elapsed_time": "1:20:20", "remaining_time": "2:28:07"}
|
65 |
+
{"current_steps": 65, "total_steps": 182, "loss": 0.8092, "accuracy": 0.828125, "lr": 8.160312465429952e-07, "epoch": 0.3565306822077477, "percentage": 35.71, "elapsed_time": "1:21:41", "remaining_time": "2:27:03"}
|
66 |
+
{"current_steps": 66, "total_steps": 182, "loss": 1.0525, "accuracy": 0.7734375, "lr": 8.085052982021847e-07, "epoch": 0.3620157696263284, "percentage": 36.26, "elapsed_time": "1:22:55", "remaining_time": "2:25:44"}
|
67 |
+
{"current_steps": 67, "total_steps": 182, "loss": 0.8161, "accuracy": 0.84375, "lr": 8.008647527371022e-07, "epoch": 0.36750085704490915, "percentage": 36.81, "elapsed_time": "1:24:06", "remaining_time": "2:24:22"}
|
68 |
+
{"current_steps": 68, "total_steps": 182, "loss": 1.0579, "accuracy": 0.765625, "lr": 7.931124482984801e-07, "epoch": 0.37298594446348987, "percentage": 37.36, "elapsed_time": "1:25:22", "remaining_time": "2:23:06"}
|
69 |
+
{"current_steps": 69, "total_steps": 182, "loss": 1.3453, "accuracy": 0.7265625, "lr": 7.85251264550948e-07, "epoch": 0.3784710318820706, "percentage": 37.91, "elapsed_time": "1:26:36", "remaining_time": "2:21:50"}
|
70 |
+
{"current_steps": 70, "total_steps": 182, "loss": 1.2675, "accuracy": 0.7890625, "lr": 7.772841216033532e-07, "epoch": 0.3839561193006514, "percentage": 38.46, "elapsed_time": "1:27:50", "remaining_time": "2:20:33"}
|
71 |
+
{"current_steps": 71, "total_steps": 182, "loss": 1.096, "accuracy": 0.828125, "lr": 7.69213978924061e-07, "epoch": 0.3894412067192321, "percentage": 39.01, "elapsed_time": "1:29:01", "remaining_time": "2:19:10"}
|
72 |
+
{"current_steps": 72, "total_steps": 182, "loss": 1.0171, "accuracy": 0.8046875, "lr": 7.610438342416319e-07, "epoch": 0.39492629413781283, "percentage": 39.56, "elapsed_time": "1:30:14", "remaining_time": "2:17:52"}
|
73 |
+
{"current_steps": 73, "total_steps": 182, "loss": 0.6614, "accuracy": 0.8515625, "lr": 7.527767224312882e-07, "epoch": 0.40041138155639355, "percentage": 40.11, "elapsed_time": "1:31:28", "remaining_time": "2:16:35"}
|
74 |
+
{"current_steps": 74, "total_steps": 182, "loss": 0.9105, "accuracy": 0.8359375, "lr": 7.444157143875819e-07, "epoch": 0.4058964689749743, "percentage": 40.66, "elapsed_time": "1:32:41", "remaining_time": "2:15:17"}
|
75 |
+
{"current_steps": 75, "total_steps": 182, "loss": 1.0358, "accuracy": 0.75, "lr": 7.359639158836827e-07, "epoch": 0.411381556393555, "percentage": 41.21, "elapsed_time": "1:34:00", "remaining_time": "2:14:07"}
|
76 |
+
{"current_steps": 76, "total_steps": 182, "loss": 0.9974, "accuracy": 0.8046875, "lr": 7.274244664177097e-07, "epoch": 0.41686664381213573, "percentage": 41.76, "elapsed_time": "1:35:16", "remaining_time": "2:12:52"}
|
77 |
+
{"current_steps": 77, "total_steps": 182, "loss": 0.8174, "accuracy": 0.8046875, "lr": 7.188005380465364e-07, "epoch": 0.4223517312307165, "percentage": 42.31, "elapsed_time": "1:36:32", "remaining_time": "2:11:39"}
|
78 |
+
{"current_steps": 78, "total_steps": 182, "loss": 0.8695, "accuracy": 0.8203125, "lr": 7.100953342075009e-07, "epoch": 0.42783681864929723, "percentage": 42.86, "elapsed_time": "1:37:48", "remaining_time": "2:10:24"}
|
79 |
+
{"current_steps": 79, "total_steps": 182, "loss": 0.7876, "accuracy": 0.8359375, "lr": 7.013120885284598e-07, "epoch": 0.43332190606787796, "percentage": 43.41, "elapsed_time": "1:39:02", "remaining_time": "2:09:07"}
|
80 |
+
{"current_steps": 80, "total_steps": 182, "loss": 0.9434, "accuracy": 0.859375, "lr": 6.924540636266272e-07, "epoch": 0.4388069934864587, "percentage": 43.96, "elapsed_time": "1:40:16", "remaining_time": "2:07:50"}
|
81 |
+
{"current_steps": 81, "total_steps": 182, "loss": 0.8759, "accuracy": 0.8046875, "lr": 6.83524549896646e-07, "epoch": 0.4442920809050394, "percentage": 44.51, "elapsed_time": "1:41:37", "remaining_time": "2:06:43"}
|
82 |
+
{"current_steps": 82, "total_steps": 182, "loss": 0.6727, "accuracy": 0.875, "lr": 6.745268642883404e-07, "epoch": 0.44977716832362014, "percentage": 45.05, "elapsed_time": "1:42:52", "remaining_time": "2:05:26"}
|
83 |
+
{"current_steps": 83, "total_steps": 182, "loss": 0.8406, "accuracy": 0.875, "lr": 6.654643490746041e-07, "epoch": 0.4552622557422009, "percentage": 45.6, "elapsed_time": "1:44:07", "remaining_time": "2:04:12"}
|
84 |
+
{"current_steps": 84, "total_steps": 182, "loss": 0.844, "accuracy": 0.78125, "lr": 6.563403706098832e-07, "epoch": 0.46074734316078164, "percentage": 46.15, "elapsed_time": "1:45:21", "remaining_time": "2:02:54"}
|
85 |
+
{"current_steps": 85, "total_steps": 182, "loss": 0.9392, "accuracy": 0.8046875, "lr": 6.47158318079712e-07, "epoch": 0.46623243057936237, "percentage": 46.7, "elapsed_time": "1:46:37", "remaining_time": "2:01:40"}
|
86 |
+
{"current_steps": 86, "total_steps": 182, "loss": 0.6221, "accuracy": 0.9140625, "lr": 6.379216022417695e-07, "epoch": 0.4717175179979431, "percentage": 47.25, "elapsed_time": "1:47:56", "remaining_time": "2:00:29"}
|
87 |
+
{"current_steps": 87, "total_steps": 182, "loss": 0.9602, "accuracy": 0.8125, "lr": 6.286336541589223e-07, "epoch": 0.4772026054165238, "percentage": 47.8, "elapsed_time": "1:49:10", "remaining_time": "1:59:13"}
|
88 |
+
{"current_steps": 88, "total_steps": 182, "loss": 0.8718, "accuracy": 0.796875, "lr": 6.192979239247242e-07, "epoch": 0.48268769283510454, "percentage": 48.35, "elapsed_time": "1:50:24", "remaining_time": "1:57:56"}
|
89 |
+
{"current_steps": 89, "total_steps": 182, "loss": 0.8724, "accuracy": 0.8359375, "lr": 6.099178793818478e-07, "epoch": 0.48817278025368527, "percentage": 48.9, "elapsed_time": "1:51:39", "remaining_time": "1:56:40"}
|
90 |
+
{"current_steps": 90, "total_steps": 182, "loss": 0.9605, "accuracy": 0.796875, "lr": 6.004970048339225e-07, "epoch": 0.49365786767226605, "percentage": 49.45, "elapsed_time": "1:52:51", "remaining_time": "1:55:21"}
|
91 |
+
{"current_steps": 91, "total_steps": 182, "loss": 0.7882, "accuracy": 0.859375, "lr": 5.910387997512573e-07, "epoch": 0.4991429550908468, "percentage": 50.0, "elapsed_time": "1:54:03", "remaining_time": "1:54:03"}
|
92 |
+
{"current_steps": 92, "total_steps": 182, "loss": 0.8483, "accuracy": 0.8359375, "lr": 5.815467774709313e-07, "epoch": 0.5046280425094275, "percentage": 50.55, "elapsed_time": "1:55:20", "remaining_time": "1:52:49"}
|
93 |
+
{"current_steps": 93, "total_steps": 182, "loss": 0.8819, "accuracy": 0.8203125, "lr": 5.720244638917323e-07, "epoch": 0.5101131299280083, "percentage": 51.1, "elapsed_time": "1:56:35", "remaining_time": "1:51:34"}
|
94 |
+
{"current_steps": 94, "total_steps": 182, "loss": 1.0174, "accuracy": 0.796875, "lr": 5.624753961644281e-07, "epoch": 0.515598217346589, "percentage": 51.65, "elapsed_time": "1:57:43", "remaining_time": "1:50:12"}
|
95 |
+
{"current_steps": 95, "total_steps": 182, "loss": 0.98, "accuracy": 0.7890625, "lr": 5.529031213778614e-07, "epoch": 0.5210833047651697, "percentage": 52.2, "elapsed_time": "1:58:57", "remaining_time": "1:48:56"}
|
96 |
+
{"current_steps": 96, "total_steps": 182, "loss": 0.8177, "accuracy": 0.8125, "lr": 5.433111952413494e-07, "epoch": 0.5265683921837504, "percentage": 52.75, "elapsed_time": "2:00:13", "remaining_time": "1:47:41"}
|
97 |
+
{"current_steps": 97, "total_steps": 182, "loss": 0.7902, "accuracy": 0.8671875, "lr": 5.33703180763884e-07, "epoch": 0.5320534796023312, "percentage": 53.3, "elapsed_time": "2:01:27", "remaining_time": "1:46:25"}
|
98 |
+
{"current_steps": 98, "total_steps": 182, "loss": 0.5899, "accuracy": 0.9140625, "lr": 5.240826469306186e-07, "epoch": 0.5375385670209119, "percentage": 53.85, "elapsed_time": "2:02:46", "remaining_time": "1:45:14"}
|
99 |
+
{"current_steps": 99, "total_steps": 182, "loss": 0.8516, "accuracy": 0.796875, "lr": 5.144531673771363e-07, "epoch": 0.5430236544394926, "percentage": 54.4, "elapsed_time": "2:04:05", "remaining_time": "1:44:02"}
|
100 |
+
{"current_steps": 100, "total_steps": 182, "loss": 0.8378, "accuracy": 0.828125, "lr": 5.048183190619903e-07, "epoch": 0.5485087418580734, "percentage": 54.95, "elapsed_time": "2:05:23", "remaining_time": "1:42:49"}
|
101 |
+
{"current_steps": 101, "total_steps": 182, "loss": 0.669, "accuracy": 0.8828125, "lr": 4.951816809380097e-07, "epoch": 0.5539938292766541, "percentage": 55.49, "elapsed_time": "2:06:36", "remaining_time": "1:41:32"}
|
102 |
+
{"current_steps": 102, "total_steps": 182, "loss": 0.8745, "accuracy": 0.8046875, "lr": 4.855468326228638e-07, "epoch": 0.5594789166952349, "percentage": 56.04, "elapsed_time": "2:07:51", "remaining_time": "1:40:16"}
|
103 |
+
{"current_steps": 103, "total_steps": 182, "loss": 0.7655, "accuracy": 0.8515625, "lr": 4.7591735306938134e-07, "epoch": 0.5649640041138155, "percentage": 56.59, "elapsed_time": "2:09:03", "remaining_time": "1:38:59"}
|
104 |
+
{"current_steps": 104, "total_steps": 182, "loss": 0.9818, "accuracy": 0.796875, "lr": 4.6629681923611603e-07, "epoch": 0.5704490915323963, "percentage": 57.14, "elapsed_time": "2:10:18", "remaining_time": "1:37:43"}
|
105 |
+
{"current_steps": 105, "total_steps": 182, "loss": 0.7142, "accuracy": 0.8515625, "lr": 4.5668880475865067e-07, "epoch": 0.575934178950977, "percentage": 57.69, "elapsed_time": "2:11:28", "remaining_time": "1:36:24"}
|
106 |
+
{"current_steps": 106, "total_steps": 182, "loss": 0.624, "accuracy": 0.8671875, "lr": 4.4709687862213864e-07, "epoch": 0.5814192663695578, "percentage": 58.24, "elapsed_time": "2:12:44", "remaining_time": "1:35:10"}
|
107 |
+
{"current_steps": 107, "total_steps": 182, "loss": 0.779, "accuracy": 0.8515625, "lr": 4.3752460383557194e-07, "epoch": 0.5869043537881385, "percentage": 58.79, "elapsed_time": "2:13:58", "remaining_time": "1:33:54"}
|
108 |
+
{"current_steps": 108, "total_steps": 182, "loss": 0.8094, "accuracy": 0.8359375, "lr": 4.2797553610826797e-07, "epoch": 0.5923894412067192, "percentage": 59.34, "elapsed_time": "2:15:11", "remaining_time": "1:32:37"}
|
109 |
+
{"current_steps": 109, "total_steps": 182, "loss": 0.6594, "accuracy": 0.84375, "lr": 4.184532225290686e-07, "epoch": 0.5978745286253, "percentage": 59.89, "elapsed_time": "2:16:26", "remaining_time": "1:31:22"}
|
110 |
+
{"current_steps": 110, "total_steps": 182, "loss": 0.9853, "accuracy": 0.7734375, "lr": 4.089612002487428e-07, "epoch": 0.6033596160438807, "percentage": 60.44, "elapsed_time": "2:17:40", "remaining_time": "1:30:06"}
|
111 |
+
{"current_steps": 111, "total_steps": 182, "loss": 0.6273, "accuracy": 0.875, "lr": 3.995029951660776e-07, "epoch": 0.6088447034624614, "percentage": 60.99, "elapsed_time": "2:18:54", "remaining_time": "1:28:50"}
|
112 |
+
{"current_steps": 112, "total_steps": 182, "loss": 0.5671, "accuracy": 0.875, "lr": 3.9008212061815207e-07, "epoch": 0.6143297908810421, "percentage": 61.54, "elapsed_time": "2:20:07", "remaining_time": "1:27:34"}
|
113 |
+
{"current_steps": 113, "total_steps": 182, "loss": 1.0423, "accuracy": 0.8203125, "lr": 3.8070207607527585e-07, "epoch": 0.6198148782996229, "percentage": 62.09, "elapsed_time": "2:21:18", "remaining_time": "1:26:17"}
|
114 |
+
{"current_steps": 114, "total_steps": 182, "loss": 0.7409, "accuracy": 0.84375, "lr": 3.7136634584107783e-07, "epoch": 0.6252999657182037, "percentage": 62.64, "elapsed_time": "2:22:28", "remaining_time": "1:24:59"}
|
115 |
+
{"current_steps": 115, "total_steps": 182, "loss": 0.8674, "accuracy": 0.8359375, "lr": 3.6207839775823047e-07, "epoch": 0.6307850531367843, "percentage": 63.19, "elapsed_time": "2:23:44", "remaining_time": "1:23:44"}
|
116 |
+
{"current_steps": 116, "total_steps": 182, "loss": 0.6846, "accuracy": 0.890625, "lr": 3.5284168192028805e-07, "epoch": 0.6362701405553651, "percentage": 63.74, "elapsed_time": "2:24:57", "remaining_time": "1:22:28"}
|
117 |
+
{"current_steps": 117, "total_steps": 182, "loss": 0.9343, "accuracy": 0.8046875, "lr": 3.4365962939011693e-07, "epoch": 0.6417552279739458, "percentage": 64.29, "elapsed_time": "2:26:12", "remaining_time": "1:21:13"}
|
118 |
+
{"current_steps": 118, "total_steps": 182, "loss": 0.6338, "accuracy": 0.90625, "lr": 3.345356509253958e-07, "epoch": 0.6472403153925266, "percentage": 64.84, "elapsed_time": "2:27:29", "remaining_time": "1:19:59"}
|
119 |
+
{"current_steps": 119, "total_steps": 182, "loss": 0.7826, "accuracy": 0.859375, "lr": 3.2547313571165967e-07, "epoch": 0.6527254028111072, "percentage": 65.38, "elapsed_time": "2:28:48", "remaining_time": "1:18:46"}
|
120 |
+
{"current_steps": 120, "total_steps": 182, "loss": 0.6904, "accuracy": 0.84375, "lr": 3.1647545010335395e-07, "epoch": 0.658210490229688, "percentage": 65.93, "elapsed_time": "2:30:02", "remaining_time": "1:17:31"}
|
121 |
+
{"current_steps": 121, "total_steps": 182, "loss": 0.9172, "accuracy": 0.7578125, "lr": 3.075459363733727e-07, "epoch": 0.6636955776482688, "percentage": 66.48, "elapsed_time": "2:31:14", "remaining_time": "1:16:14"}
|
122 |
+
{"current_steps": 122, "total_steps": 182, "loss": 0.868, "accuracy": 0.8125, "lr": 2.9868791147154025e-07, "epoch": 0.6691806650668495, "percentage": 67.03, "elapsed_time": "2:32:26", "remaining_time": "1:14:58"}
|
123 |
+
{"current_steps": 123, "total_steps": 182, "loss": 0.659, "accuracy": 0.84375, "lr": 2.8990466579249917e-07, "epoch": 0.6746657524854303, "percentage": 67.58, "elapsed_time": "2:33:43", "remaining_time": "1:13:44"}
|
124 |
+
{"current_steps": 124, "total_steps": 182, "loss": 0.6562, "accuracy": 0.875, "lr": 2.811994619534637e-07, "epoch": 0.6801508399040109, "percentage": 68.13, "elapsed_time": "2:34:58", "remaining_time": "1:12:29"}
|
125 |
+
{"current_steps": 125, "total_steps": 182, "loss": 0.5385, "accuracy": 0.921875, "lr": 2.725755335822903e-07, "epoch": 0.6856359273225917, "percentage": 68.68, "elapsed_time": "2:36:15", "remaining_time": "1:11:15"}
|
126 |
+
{"current_steps": 126, "total_steps": 182, "loss": 0.6031, "accuracy": 0.875, "lr": 2.640360841163174e-07, "epoch": 0.6911210147411725, "percentage": 69.23, "elapsed_time": "2:37:28", "remaining_time": "1:09:59"}
|
127 |
+
{"current_steps": 127, "total_steps": 182, "loss": 0.6676, "accuracy": 0.859375, "lr": 2.5558428561241816e-07, "epoch": 0.6966061021597532, "percentage": 69.78, "elapsed_time": "2:38:42", "remaining_time": "1:08:43"}
|
128 |
+
{"current_steps": 128, "total_steps": 182, "loss": 0.7803, "accuracy": 0.828125, "lr": 2.472232775687119e-07, "epoch": 0.7020911895783339, "percentage": 70.33, "elapsed_time": "2:40:00", "remaining_time": "1:07:30"}
|
129 |
+
{"current_steps": 129, "total_steps": 182, "loss": 0.5901, "accuracy": 0.875, "lr": 2.3895616575836806e-07, "epoch": 0.7075762769969146, "percentage": 70.88, "elapsed_time": "2:41:18", "remaining_time": "1:06:16"}
|
130 |
+
{"current_steps": 130, "total_steps": 182, "loss": 0.7432, "accuracy": 0.8515625, "lr": 2.3078602107593897e-07, "epoch": 0.7130613644154954, "percentage": 71.43, "elapsed_time": "2:42:31", "remaining_time": "1:05:00"}
|
131 |
+
{"current_steps": 131, "total_steps": 182, "loss": 0.7962, "accuracy": 0.828125, "lr": 2.2271587839664668e-07, "epoch": 0.7185464518340761, "percentage": 71.98, "elapsed_time": "2:43:47", "remaining_time": "1:03:45"}
|
132 |
+
{"current_steps": 132, "total_steps": 182, "loss": 0.7871, "accuracy": 0.859375, "lr": 2.1474873544905203e-07, "epoch": 0.7240315392526568, "percentage": 72.53, "elapsed_time": "2:45:01", "remaining_time": "1:02:30"}
|
133 |
+
{"current_steps": 133, "total_steps": 182, "loss": 0.7131, "accuracy": 0.8671875, "lr": 2.0688755170151994e-07, "epoch": 0.7295166266712376, "percentage": 73.08, "elapsed_time": "2:46:12", "remaining_time": "1:01:13"}
|
134 |
+
{"current_steps": 134, "total_steps": 182, "loss": 0.5673, "accuracy": 0.8828125, "lr": 1.991352472628978e-07, "epoch": 0.7350017140898183, "percentage": 73.63, "elapsed_time": "2:47:23", "remaining_time": "0:59:57"}
|
135 |
+
{"current_steps": 135, "total_steps": 182, "loss": 0.9743, "accuracy": 0.8125, "lr": 1.9149470179781529e-07, "epoch": 0.7404868015083991, "percentage": 74.18, "elapsed_time": "2:48:39", "remaining_time": "0:58:43"}
|
136 |
+
{"current_steps": 136, "total_steps": 182, "loss": 0.5596, "accuracy": 0.8984375, "lr": 1.8396875345700496e-07, "epoch": 0.7459718889269797, "percentage": 74.73, "elapsed_time": "2:49:55", "remaining_time": "0:57:28"}
|
137 |
+
{"current_steps": 137, "total_steps": 182, "loss": 0.7156, "accuracy": 0.875, "lr": 1.76560197823046e-07, "epoch": 0.7514569763455605, "percentage": 75.27, "elapsed_time": "2:51:09", "remaining_time": "0:56:13"}
|
138 |
+
{"current_steps": 138, "total_steps": 182, "loss": 0.5443, "accuracy": 0.875, "lr": 1.6927178687191952e-07, "epoch": 0.7569420637641412, "percentage": 75.82, "elapsed_time": "2:52:20", "remaining_time": "0:54:56"}
|
139 |
+
{"current_steps": 139, "total_steps": 182, "loss": 0.7399, "accuracy": 0.8359375, "lr": 1.6210622795076167e-07, "epoch": 0.762427151182722, "percentage": 76.37, "elapsed_time": "2:53:33", "remaining_time": "0:53:41"}
|
140 |
+
{"current_steps": 140, "total_steps": 182, "loss": 0.6289, "accuracy": 0.859375, "lr": 1.5506618277219408e-07, "epoch": 0.7679122386013028, "percentage": 76.92, "elapsed_time": "2:54:49", "remaining_time": "0:52:26"}
|
141 |
+
{"current_steps": 141, "total_steps": 182, "loss": 0.623, "accuracy": 0.8671875, "lr": 1.481542664256075e-07, "epoch": 0.7733973260198834, "percentage": 77.47, "elapsed_time": "2:56:05", "remaining_time": "0:51:12"}
|
142 |
+
{"current_steps": 142, "total_steps": 182, "loss": 0.6692, "accuracy": 0.8359375, "lr": 1.413730464057616e-07, "epoch": 0.7788824134384642, "percentage": 78.02, "elapsed_time": "2:57:18", "remaining_time": "0:49:56"}
|
143 |
+
{"current_steps": 143, "total_steps": 182, "loss": 0.6601, "accuracy": 0.890625, "lr": 1.3472504165906612e-07, "epoch": 0.7843675008570449, "percentage": 78.57, "elapsed_time": "2:58:33", "remaining_time": "0:48:41"}
|
144 |
+
{"current_steps": 144, "total_steps": 182, "loss": 0.564, "accuracy": 0.890625, "lr": 1.2821272164789543e-07, "epoch": 0.7898525882756257, "percentage": 79.12, "elapsed_time": "2:59:46", "remaining_time": "0:47:26"}
|
145 |
+
{"current_steps": 145, "total_steps": 182, "loss": 0.7226, "accuracy": 0.8515625, "lr": 1.2183850543328312e-07, "epoch": 0.7953376756942063, "percentage": 79.67, "elapsed_time": "3:01:00", "remaining_time": "0:46:11"}
|
146 |
+
{"current_steps": 146, "total_steps": 182, "loss": 0.544, "accuracy": 0.875, "lr": 1.1560476077634069e-07, "epoch": 0.8008227631127871, "percentage": 80.22, "elapsed_time": "3:02:16", "remaining_time": "0:44:56"}
|
147 |
+
{"current_steps": 147, "total_steps": 182, "loss": 0.7967, "accuracy": 0.828125, "lr": 1.0951380325872977e-07, "epoch": 0.8063078505313679, "percentage": 80.77, "elapsed_time": "3:03:31", "remaining_time": "0:43:41"}
|
148 |
+
{"current_steps": 148, "total_steps": 182, "loss": 0.8025, "accuracy": 0.84375, "lr": 1.0356789542251936e-07, "epoch": 0.8117929379499486, "percentage": 81.32, "elapsed_time": "3:04:48", "remaining_time": "0:42:27"}
|
149 |
+
{"current_steps": 149, "total_steps": 182, "loss": 0.7674, "accuracy": 0.8515625, "lr": 9.776924592974256e-08, "epoch": 0.8172780253685293, "percentage": 81.87, "elapsed_time": "3:06:02", "remaining_time": "0:41:12"}
|
150 |
+
{"current_steps": 150, "total_steps": 182, "loss": 0.6909, "accuracy": 0.8671875, "lr": 9.212000874196952e-08, "epoch": 0.82276311278711, "percentage": 82.42, "elapsed_time": "3:07:19", "remaining_time": "0:39:57"}
|
151 |
+
{"current_steps": 151, "total_steps": 182, "loss": 0.7332, "accuracy": 0.8359375, "lr": 8.662228232019875e-08, "epoch": 0.8282482002056908, "percentage": 82.97, "elapsed_time": "3:08:41", "remaining_time": "0:38:44"}
|
152 |
+
{"current_steps": 152, "total_steps": 182, "loss": 0.6407, "accuracy": 0.875, "lr": 8.127810884536402e-08, "epoch": 0.8337332876242715, "percentage": 83.52, "elapsed_time": "3:09:55", "remaining_time": "0:37:29"}
|
153 |
+
{"current_steps": 153, "total_steps": 182, "loss": 0.8117, "accuracy": 0.8359375, "lr": 7.608947345974759e-08, "epoch": 0.8392183750428522, "percentage": 84.07, "elapsed_time": "3:11:10", "remaining_time": "0:36:14"}
|
154 |
+
{"current_steps": 154, "total_steps": 182, "loss": 0.6658, "accuracy": 0.8671875, "lr": 7.105830352958142e-08, "epoch": 0.844703462461433, "percentage": 84.62, "elapsed_time": "3:12:24", "remaining_time": "0:34:59"}
|
155 |
+
{"current_steps": 155, "total_steps": 182, "loss": 0.5643, "accuracy": 0.8984375, "lr": 6.618646792910893e-08, "epoch": 0.8501885498800137, "percentage": 85.16, "elapsed_time": "3:13:37", "remaining_time": "0:33:43"}
|
156 |
+
{"current_steps": 156, "total_steps": 182, "loss": 0.7727, "accuracy": 0.8359375, "lr": 6.147577634637413e-08, "epoch": 0.8556736372985945, "percentage": 85.71, "elapsed_time": "3:14:51", "remaining_time": "0:32:28"}
|
157 |
+
{"current_steps": 157, "total_steps": 182, "loss": 0.5738, "accuracy": 0.875, "lr": 5.692797861099718e-08, "epoch": 0.8611587247171751, "percentage": 86.26, "elapsed_time": "3:16:08", "remaining_time": "0:31:13"}
|
158 |
+
{"current_steps": 158, "total_steps": 182, "loss": 0.6284, "accuracy": 0.8671875, "lr": 5.25447640441834e-08, "epoch": 0.8666438121357559, "percentage": 86.81, "elapsed_time": "3:17:19", "remaining_time": "0:29:58"}
|
159 |
+
{"current_steps": 159, "total_steps": 182, "loss": 0.6382, "accuracy": 0.8828125, "lr": 4.832776083120982e-08, "epoch": 0.8721288995543367, "percentage": 87.36, "elapsed_time": "3:18:33", "remaining_time": "0:28:43"}
|
160 |
+
{"current_steps": 160, "total_steps": 182, "loss": 0.6011, "accuracy": 0.875, "lr": 4.427853541662091e-08, "epoch": 0.8776139869729174, "percentage": 87.91, "elapsed_time": "3:19:44", "remaining_time": "0:27:27"}
|
161 |
+
{"current_steps": 161, "total_steps": 182, "loss": 0.8583, "accuracy": 0.8203125, "lr": 4.039859192235778e-08, "epoch": 0.8830990743914982, "percentage": 88.46, "elapsed_time": "3:20:56", "remaining_time": "0:26:12"}
|
162 |
+
{"current_steps": 162, "total_steps": 182, "loss": 0.5664, "accuracy": 0.8984375, "lr": 3.668937158903901e-08, "epoch": 0.8885841618100788, "percentage": 89.01, "elapsed_time": "3:22:08", "remaining_time": "0:24:57"}
|
163 |
+
{"current_steps": 163, "total_steps": 182, "loss": 0.5001, "accuracy": 0.90625, "lr": 3.3152252240598086e-08, "epoch": 0.8940692492286596, "percentage": 89.56, "elapsed_time": "3:23:20", "remaining_time": "0:23:42"}
|
164 |
+
{"current_steps": 164, "total_steps": 182, "loss": 0.6246, "accuracy": 0.875, "lr": 2.978854777247841e-08, "epoch": 0.8995543366472403, "percentage": 90.11, "elapsed_time": "3:24:31", "remaining_time": "0:22:26"}
|
165 |
+
{"current_steps": 165, "total_steps": 182, "loss": 0.5817, "accuracy": 0.890625, "lr": 2.6599507663574384e-08, "epoch": 0.905039424065821, "percentage": 90.66, "elapsed_time": "3:25:45", "remaining_time": "0:21:11"}
|
166 |
+
{"current_steps": 166, "total_steps": 182, "loss": 0.5111, "accuracy": 0.8828125, "lr": 2.358631651210141e-08, "epoch": 0.9105245114844018, "percentage": 91.21, "elapsed_time": "3:27:01", "remaining_time": "0:19:57"}
|
167 |
+
{"current_steps": 167, "total_steps": 182, "loss": 0.6247, "accuracy": 0.8671875, "lr": 2.0750093595565733e-08, "epoch": 0.9160095989029825, "percentage": 91.76, "elapsed_time": "3:28:16", "remaining_time": "0:18:42"}
|
168 |
+
{"current_steps": 168, "total_steps": 182, "loss": 0.6335, "accuracy": 0.8828125, "lr": 1.8091892454998593e-08, "epoch": 0.9214946863215633, "percentage": 92.31, "elapsed_time": "3:29:32", "remaining_time": "0:17:27"}
|
169 |
+
{"current_steps": 169, "total_steps": 182, "loss": 0.79, "accuracy": 0.8359375, "lr": 1.5612700503608967e-08, "epoch": 0.926979773740144, "percentage": 92.86, "elapsed_time": "3:30:46", "remaining_time": "0:16:12"}
|
170 |
+
{"current_steps": 170, "total_steps": 182, "loss": 0.6073, "accuracy": 0.8671875, "lr": 1.3313438659999399e-08, "epoch": 0.9324648611587247, "percentage": 93.41, "elapsed_time": "3:32:02", "remaining_time": "0:14:58"}
|
171 |
+
{"current_steps": 171, "total_steps": 182, "loss": 0.6478, "accuracy": 0.8984375, "lr": 1.119496100608297e-08, "epoch": 0.9379499485773054, "percentage": 93.96, "elapsed_time": "3:33:17", "remaining_time": "0:13:43"}
|
172 |
+
{"current_steps": 172, "total_steps": 182, "loss": 0.4678, "accuracy": 0.921875, "lr": 9.258054469825972e-09, "epoch": 0.9434350359958862, "percentage": 94.51, "elapsed_time": "3:34:27", "remaining_time": "0:12:28"}
|
173 |
+
{"current_steps": 173, "total_steps": 182, "loss": 0.8124, "accuracy": 0.8515625, "lr": 7.503438532937168e-09, "epoch": 0.948920123414467, "percentage": 95.05, "elapsed_time": "3:35:39", "remaining_time": "0:11:13"}
|
174 |
+
{"current_steps": 174, "total_steps": 182, "loss": 0.5972, "accuracy": 0.875, "lr": 5.931764963608865e-09, "epoch": 0.9544052108330476, "percentage": 95.6, "elapsed_time": "3:36:57", "remaining_time": "0:09:58"}
|
175 |
+
{"current_steps": 175, "total_steps": 182, "loss": 0.8845, "accuracy": 0.8046875, "lr": 4.543617574412184e-09, "epoch": 0.9598902982516284, "percentage": 96.15, "elapsed_time": "3:38:12", "remaining_time": "0:08:43"}
|
176 |
+
{"current_steps": 176, "total_steps": 182, "loss": 0.7588, "accuracy": 0.8203125, "lr": 3.3395120054343086e-09, "epoch": 0.9653753856702091, "percentage": 96.7, "elapsed_time": "3:39:26", "remaining_time": "0:07:28"}
|
177 |
+
{"current_steps": 177, "total_steps": 182, "loss": 0.603, "accuracy": 0.875, "lr": 2.3198955327393686e-09, "epoch": 0.9708604730887899, "percentage": 97.25, "elapsed_time": "3:40:43", "remaining_time": "0:06:14"}
|
178 |
+
{"current_steps": 178, "total_steps": 182, "loss": 0.478, "accuracy": 0.921875, "lr": 1.4851469022233997e-09, "epoch": 0.9763455605073705, "percentage": 97.8, "elapsed_time": "3:41:55", "remaining_time": "0:04:59"}
|
179 |
+
{"current_steps": 179, "total_steps": 182, "loss": 0.5532, "accuracy": 0.8984375, "lr": 8.35576188926046e-10, "epoch": 0.9818306479259513, "percentage": 98.35, "elapsed_time": "3:43:14", "remaining_time": "0:03:44"}
|
180 |
+
{"current_steps": 180, "total_steps": 182, "loss": 0.692, "accuracy": 0.84375, "lr": 3.71424681850141e-10, "epoch": 0.9873157353445321, "percentage": 98.9, "elapsed_time": "3:44:33", "remaining_time": "0:02:29"}
|
181 |
+
{"current_steps": 181, "total_steps": 182, "loss": 0.6545, "accuracy": 0.84375, "lr": 9.286479433257e-11, "epoch": 0.9928008227631128, "percentage": 99.45, "elapsed_time": "3:45:49", "remaining_time": "0:01:14"}
|
182 |
+
{"current_steps": 182, "total_steps": 182, "loss": 0.3779, "accuracy": 0.953125, "lr": 0.0, "epoch": 0.9982859101816935, "percentage": 100.0, "elapsed_time": "3:47:10", "remaining_time": "0:00:00"}
|
183 |
+
{"current_steps": 182, "total_steps": 182, "epoch": 0.9982859101816935, "percentage": 100.0, "elapsed_time": "3:47:48", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,2772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9982859101816935,
|
5 |
+
"eval_steps": 0,
|
6 |
+
"global_step": 182,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.005485087418580734,
|
13 |
+
"grad_norm": 12.289390049252361,
|
14 |
+
"learning_rate": 5.2631578947368416e-08,
|
15 |
+
"logits/chosen": -0.3854110836982727,
|
16 |
+
"logits/rejected": -0.38843637704849243,
|
17 |
+
"logps/chosen": -0.5867404937744141,
|
18 |
+
"logps/rejected": -0.7349259853363037,
|
19 |
+
"loss": 2.2106,
|
20 |
+
"rewards/accuracies": 0.328125,
|
21 |
+
"rewards/chosen": -1.8373150825500488,
|
22 |
+
"rewards/margins": -0.37046387791633606,
|
23 |
+
"rewards/rejected": -1.4668511152267456,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.010970174837161468,
|
28 |
+
"grad_norm": 9.808910529487358,
|
29 |
+
"learning_rate": 1.0526315789473683e-07,
|
30 |
+
"logits/chosen": -0.4200110137462616,
|
31 |
+
"logits/rejected": -0.4337027370929718,
|
32 |
+
"logps/chosen": -0.5888247489929199,
|
33 |
+
"logps/rejected": -0.7141146659851074,
|
34 |
+
"loss": 2.1187,
|
35 |
+
"rewards/accuracies": 0.3671875,
|
36 |
+
"rewards/chosen": -1.7852866649627686,
|
37 |
+
"rewards/margins": -0.31322479248046875,
|
38 |
+
"rewards/rejected": -1.4720618724822998,
|
39 |
+
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0164552622557422,
|
43 |
+
"grad_norm": 7.82623444940022,
|
44 |
+
"learning_rate": 1.5789473684210525e-07,
|
45 |
+
"logits/chosen": -0.3889790177345276,
|
46 |
+
"logits/rejected": -0.3634672164916992,
|
47 |
+
"logps/chosen": -0.6838980317115784,
|
48 |
+
"logps/rejected": -0.6908231973648071,
|
49 |
+
"loss": 2.0561,
|
50 |
+
"rewards/accuracies": 0.375,
|
51 |
+
"rewards/chosen": -1.727057933807373,
|
52 |
+
"rewards/margins": -0.01731281727552414,
|
53 |
+
"rewards/rejected": -1.709745168685913,
|
54 |
+
"step": 3
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.021940349674322936,
|
58 |
+
"grad_norm": 11.908990882185469,
|
59 |
+
"learning_rate": 2.1052631578947366e-07,
|
60 |
+
"logits/chosen": -0.41128796339035034,
|
61 |
+
"logits/rejected": -0.44201532006263733,
|
62 |
+
"logps/chosen": -0.6115437150001526,
|
63 |
+
"logps/rejected": -0.7170974612236023,
|
64 |
+
"loss": 2.1332,
|
65 |
+
"rewards/accuracies": 0.4140625,
|
66 |
+
"rewards/chosen": -1.7927436828613281,
|
67 |
+
"rewards/margins": -0.2638842463493347,
|
68 |
+
"rewards/rejected": -1.5288593769073486,
|
69 |
+
"step": 4
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.027425437092903668,
|
73 |
+
"grad_norm": 9.763139044795885,
|
74 |
+
"learning_rate": 2.631578947368421e-07,
|
75 |
+
"logits/chosen": -0.4671156406402588,
|
76 |
+
"logits/rejected": -0.4450330138206482,
|
77 |
+
"logps/chosen": -0.5787723064422607,
|
78 |
+
"logps/rejected": -0.6804812550544739,
|
79 |
+
"loss": 2.0846,
|
80 |
+
"rewards/accuracies": 0.3359375,
|
81 |
+
"rewards/chosen": -1.7012031078338623,
|
82 |
+
"rewards/margins": -0.2542722821235657,
|
83 |
+
"rewards/rejected": -1.4469308853149414,
|
84 |
+
"step": 5
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.0329105245114844,
|
88 |
+
"grad_norm": 10.006426324247332,
|
89 |
+
"learning_rate": 3.157894736842105e-07,
|
90 |
+
"logits/chosen": -0.3141833543777466,
|
91 |
+
"logits/rejected": -0.3982672095298767,
|
92 |
+
"logps/chosen": -0.6082320213317871,
|
93 |
+
"logps/rejected": -0.7216463088989258,
|
94 |
+
"loss": 2.1337,
|
95 |
+
"rewards/accuracies": 0.375,
|
96 |
+
"rewards/chosen": -1.8041157722473145,
|
97 |
+
"rewards/margins": -0.2835356295108795,
|
98 |
+
"rewards/rejected": -1.5205800533294678,
|
99 |
+
"step": 6
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.03839561193006513,
|
103 |
+
"grad_norm": 11.019623612251491,
|
104 |
+
"learning_rate": 3.684210526315789e-07,
|
105 |
+
"logits/chosen": -0.41403576731681824,
|
106 |
+
"logits/rejected": -0.4747769236564636,
|
107 |
+
"logps/chosen": -0.6087530851364136,
|
108 |
+
"logps/rejected": -0.6581674814224243,
|
109 |
+
"loss": 2.0016,
|
110 |
+
"rewards/accuracies": 0.4140625,
|
111 |
+
"rewards/chosen": -1.6454188823699951,
|
112 |
+
"rewards/margins": -0.12353596091270447,
|
113 |
+
"rewards/rejected": -1.5218827724456787,
|
114 |
+
"step": 7
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.04388069934864587,
|
118 |
+
"grad_norm": 13.106807696358263,
|
119 |
+
"learning_rate": 4.2105263157894733e-07,
|
120 |
+
"logits/chosen": -0.3825553059577942,
|
121 |
+
"logits/rejected": -0.4531961679458618,
|
122 |
+
"logps/chosen": -0.6047242879867554,
|
123 |
+
"logps/rejected": -0.7030869722366333,
|
124 |
+
"loss": 2.1026,
|
125 |
+
"rewards/accuracies": 0.390625,
|
126 |
+
"rewards/chosen": -1.7577173709869385,
|
127 |
+
"rewards/margins": -0.24590645730495453,
|
128 |
+
"rewards/rejected": -1.5118108987808228,
|
129 |
+
"step": 8
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.049365786767226603,
|
133 |
+
"grad_norm": 11.770594063909739,
|
134 |
+
"learning_rate": 4.7368421052631574e-07,
|
135 |
+
"logits/chosen": -0.3712048828601837,
|
136 |
+
"logits/rejected": -0.40800797939300537,
|
137 |
+
"logps/chosen": -0.5091754794120789,
|
138 |
+
"logps/rejected": -0.7823854684829712,
|
139 |
+
"loss": 2.425,
|
140 |
+
"rewards/accuracies": 0.265625,
|
141 |
+
"rewards/chosen": -1.9559637308120728,
|
142 |
+
"rewards/margins": -0.683025062084198,
|
143 |
+
"rewards/rejected": -1.27293860912323,
|
144 |
+
"step": 9
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.054850874185807336,
|
148 |
+
"grad_norm": 12.669444366856121,
|
149 |
+
"learning_rate": 5.263157894736842e-07,
|
150 |
+
"logits/chosen": -0.4165411591529846,
|
151 |
+
"logits/rejected": -0.3989042639732361,
|
152 |
+
"logps/chosen": -0.5609541535377502,
|
153 |
+
"logps/rejected": -0.8160127997398376,
|
154 |
+
"loss": 2.435,
|
155 |
+
"rewards/accuracies": 0.296875,
|
156 |
+
"rewards/chosen": -2.040031909942627,
|
157 |
+
"rewards/margins": -0.637646496295929,
|
158 |
+
"rewards/rejected": -1.4023855924606323,
|
159 |
+
"step": 10
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.06033596160438807,
|
163 |
+
"grad_norm": 18.900235847859772,
|
164 |
+
"learning_rate": 5.789473684210526e-07,
|
165 |
+
"logits/chosen": -0.39879918098449707,
|
166 |
+
"logits/rejected": -0.4029804468154907,
|
167 |
+
"logps/chosen": -0.5685741901397705,
|
168 |
+
"logps/rejected": -0.7790898084640503,
|
169 |
+
"loss": 2.3341,
|
170 |
+
"rewards/accuracies": 0.3359375,
|
171 |
+
"rewards/chosen": -1.9477243423461914,
|
172 |
+
"rewards/margins": -0.5262887477874756,
|
173 |
+
"rewards/rejected": -1.4214354753494263,
|
174 |
+
"step": 11
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.0658210490229688,
|
178 |
+
"grad_norm": 11.34517381440851,
|
179 |
+
"learning_rate": 6.31578947368421e-07,
|
180 |
+
"logits/chosen": -0.43950849771499634,
|
181 |
+
"logits/rejected": -0.4288792312145233,
|
182 |
+
"logps/chosen": -0.6902109980583191,
|
183 |
+
"logps/rejected": -0.7512154579162598,
|
184 |
+
"loss": 2.2512,
|
185 |
+
"rewards/accuracies": 0.296875,
|
186 |
+
"rewards/chosen": -1.8780386447906494,
|
187 |
+
"rewards/margins": -0.15251119434833527,
|
188 |
+
"rewards/rejected": -1.7255275249481201,
|
189 |
+
"step": 12
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.07130613644154954,
|
193 |
+
"grad_norm": 12.242091991409806,
|
194 |
+
"learning_rate": 6.842105263157895e-07,
|
195 |
+
"logits/chosen": -0.3881993591785431,
|
196 |
+
"logits/rejected": -0.38021671772003174,
|
197 |
+
"logps/chosen": -0.5799139738082886,
|
198 |
+
"logps/rejected": -0.714693546295166,
|
199 |
+
"loss": 2.1644,
|
200 |
+
"rewards/accuracies": 0.328125,
|
201 |
+
"rewards/chosen": -1.7867339849472046,
|
202 |
+
"rewards/margins": -0.3369489908218384,
|
203 |
+
"rewards/rejected": -1.4497849941253662,
|
204 |
+
"step": 13
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.07679122386013026,
|
208 |
+
"grad_norm": 15.332493592901395,
|
209 |
+
"learning_rate": 7.368421052631578e-07,
|
210 |
+
"logits/chosen": -0.4336930215358734,
|
211 |
+
"logits/rejected": -0.4184849262237549,
|
212 |
+
"logps/chosen": -0.6871960163116455,
|
213 |
+
"logps/rejected": -0.8031256794929504,
|
214 |
+
"loss": 2.3949,
|
215 |
+
"rewards/accuracies": 0.3203125,
|
216 |
+
"rewards/chosen": -2.0078141689300537,
|
217 |
+
"rewards/margins": -0.28982412815093994,
|
218 |
+
"rewards/rejected": -1.7179901599884033,
|
219 |
+
"step": 14
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.082276311278711,
|
223 |
+
"grad_norm": 14.281514936865825,
|
224 |
+
"learning_rate": 7.894736842105263e-07,
|
225 |
+
"logits/chosen": -0.420330286026001,
|
226 |
+
"logits/rejected": -0.39623183012008667,
|
227 |
+
"logps/chosen": -0.6022149324417114,
|
228 |
+
"logps/rejected": -0.7605262398719788,
|
229 |
+
"loss": 2.2735,
|
230 |
+
"rewards/accuracies": 0.328125,
|
231 |
+
"rewards/chosen": -1.901315450668335,
|
232 |
+
"rewards/margins": -0.39577823877334595,
|
233 |
+
"rewards/rejected": -1.5055372714996338,
|
234 |
+
"step": 15
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.08776139869729174,
|
238 |
+
"grad_norm": 17.350845573103634,
|
239 |
+
"learning_rate": 8.421052631578947e-07,
|
240 |
+
"logits/chosen": -0.4929282069206238,
|
241 |
+
"logits/rejected": -0.4550182521343231,
|
242 |
+
"logps/chosen": -0.5783462524414062,
|
243 |
+
"logps/rejected": -0.7597732543945312,
|
244 |
+
"loss": 2.2617,
|
245 |
+
"rewards/accuracies": 0.34375,
|
246 |
+
"rewards/chosen": -1.8994331359863281,
|
247 |
+
"rewards/margins": -0.45356735587120056,
|
248 |
+
"rewards/rejected": -1.4458656311035156,
|
249 |
+
"step": 16
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.09324648611587247,
|
253 |
+
"grad_norm": 13.387104362920853,
|
254 |
+
"learning_rate": 8.947368421052631e-07,
|
255 |
+
"logits/chosen": -0.4294038414955139,
|
256 |
+
"logits/rejected": -0.4245000183582306,
|
257 |
+
"logps/chosen": -0.6331275105476379,
|
258 |
+
"logps/rejected": -0.7878226041793823,
|
259 |
+
"loss": 2.3686,
|
260 |
+
"rewards/accuracies": 0.265625,
|
261 |
+
"rewards/chosen": -1.9695566892623901,
|
262 |
+
"rewards/margins": -0.3867378830909729,
|
263 |
+
"rewards/rejected": -1.582818865776062,
|
264 |
+
"step": 17
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.09873157353445321,
|
268 |
+
"grad_norm": 11.747460293777701,
|
269 |
+
"learning_rate": 9.473684210526315e-07,
|
270 |
+
"logits/chosen": -0.43416640162467957,
|
271 |
+
"logits/rejected": -0.41705217957496643,
|
272 |
+
"logps/chosen": -0.6964335441589355,
|
273 |
+
"logps/rejected": -0.7354090213775635,
|
274 |
+
"loss": 2.0268,
|
275 |
+
"rewards/accuracies": 0.3984375,
|
276 |
+
"rewards/chosen": -1.8385226726531982,
|
277 |
+
"rewards/margins": -0.09743872284889221,
|
278 |
+
"rewards/rejected": -1.741084098815918,
|
279 |
+
"step": 18
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.10421666095303393,
|
283 |
+
"grad_norm": 16.166401888969105,
|
284 |
+
"learning_rate": 1e-06,
|
285 |
+
"logits/chosen": -0.42683446407318115,
|
286 |
+
"logits/rejected": -0.49105304479599,
|
287 |
+
"logps/chosen": -0.5967155694961548,
|
288 |
+
"logps/rejected": -0.6899043917655945,
|
289 |
+
"loss": 2.0874,
|
290 |
+
"rewards/accuracies": 0.3046875,
|
291 |
+
"rewards/chosen": -1.724760890007019,
|
292 |
+
"rewards/margins": -0.2329719066619873,
|
293 |
+
"rewards/rejected": -1.4917889833450317,
|
294 |
+
"step": 19
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.10970174837161467,
|
298 |
+
"grad_norm": 8.619811148509852,
|
299 |
+
"learning_rate": 9.999071352056673e-07,
|
300 |
+
"logits/chosen": -0.3747601807117462,
|
301 |
+
"logits/rejected": -0.41268259286880493,
|
302 |
+
"logps/chosen": -0.5958091616630554,
|
303 |
+
"logps/rejected": -0.7304958701133728,
|
304 |
+
"loss": 2.0832,
|
305 |
+
"rewards/accuracies": 0.34375,
|
306 |
+
"rewards/chosen": -1.8262397050857544,
|
307 |
+
"rewards/margins": -0.33671680092811584,
|
308 |
+
"rewards/rejected": -1.489522933959961,
|
309 |
+
"step": 20
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.11518683579019541,
|
313 |
+
"grad_norm": 8.74498909781148,
|
314 |
+
"learning_rate": 9.996285753181497e-07,
|
315 |
+
"logits/chosen": -0.4670315086841583,
|
316 |
+
"logits/rejected": -0.4540305733680725,
|
317 |
+
"logps/chosen": -0.6016995906829834,
|
318 |
+
"logps/rejected": -0.7677630186080933,
|
319 |
+
"loss": 2.1691,
|
320 |
+
"rewards/accuracies": 0.3046875,
|
321 |
+
"rewards/chosen": -1.9194074869155884,
|
322 |
+
"rewards/margins": -0.4151587188243866,
|
323 |
+
"rewards/rejected": -1.504248857498169,
|
324 |
+
"step": 21
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.12067192320877614,
|
328 |
+
"grad_norm": 12.710357284461692,
|
329 |
+
"learning_rate": 9.99164423811074e-07,
|
330 |
+
"logits/chosen": -0.4635859429836273,
|
331 |
+
"logits/rejected": -0.49371862411499023,
|
332 |
+
"logps/chosen": -0.9511612057685852,
|
333 |
+
"logps/rejected": -0.7291851043701172,
|
334 |
+
"loss": 1.9912,
|
335 |
+
"rewards/accuracies": 0.34375,
|
336 |
+
"rewards/chosen": -1.8229626417160034,
|
337 |
+
"rewards/margins": 0.5549403429031372,
|
338 |
+
"rewards/rejected": -2.3779029846191406,
|
339 |
+
"step": 22
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.12615701062735687,
|
343 |
+
"grad_norm": 7.521146349471263,
|
344 |
+
"learning_rate": 9.985148530977764e-07,
|
345 |
+
"logits/chosen": -0.44370928406715393,
|
346 |
+
"logits/rejected": -0.4425956606864929,
|
347 |
+
"logps/chosen": -0.6404778361320496,
|
348 |
+
"logps/rejected": -0.7111139297485352,
|
349 |
+
"loss": 1.9723,
|
350 |
+
"rewards/accuracies": 0.3203125,
|
351 |
+
"rewards/chosen": -1.777784824371338,
|
352 |
+
"rewards/margins": -0.17659035325050354,
|
353 |
+
"rewards/rejected": -1.6011945009231567,
|
354 |
+
"step": 23
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.1316420980459376,
|
358 |
+
"grad_norm": 9.114160770658133,
|
359 |
+
"learning_rate": 9.976801044672607e-07,
|
360 |
+
"logits/chosen": -0.4481334686279297,
|
361 |
+
"logits/rejected": -0.45388296246528625,
|
362 |
+
"logps/chosen": -0.7301231622695923,
|
363 |
+
"logps/rejected": -0.6901272535324097,
|
364 |
+
"loss": 1.8305,
|
365 |
+
"rewards/accuracies": 0.4140625,
|
366 |
+
"rewards/chosen": -1.7253180742263794,
|
367 |
+
"rewards/margins": 0.09998967498540878,
|
368 |
+
"rewards/rejected": -1.825307846069336,
|
369 |
+
"step": 24
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.13712718546451835,
|
373 |
+
"grad_norm": 16.624964926964527,
|
374 |
+
"learning_rate": 9.966604879945656e-07,
|
375 |
+
"logits/chosen": -0.5069385170936584,
|
376 |
+
"logits/rejected": -0.5200111865997314,
|
377 |
+
"logps/chosen": -0.721697211265564,
|
378 |
+
"logps/rejected": -0.7383979558944702,
|
379 |
+
"loss": 1.9472,
|
380 |
+
"rewards/accuracies": 0.3828125,
|
381 |
+
"rewards/chosen": -1.8459948301315308,
|
382 |
+
"rewards/margins": -0.04175184667110443,
|
383 |
+
"rewards/rejected": -1.8042429685592651,
|
384 |
+
"step": 25
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.14261227288309908,
|
388 |
+
"grad_norm": 8.144004658411824,
|
389 |
+
"learning_rate": 9.954563824255877e-07,
|
390 |
+
"logits/chosen": -0.4636583924293518,
|
391 |
+
"logits/rejected": -0.4762532711029053,
|
392 |
+
"logps/chosen": -0.6404789686203003,
|
393 |
+
"logps/rejected": -0.7015948295593262,
|
394 |
+
"loss": 1.8902,
|
395 |
+
"rewards/accuracies": 0.4140625,
|
396 |
+
"rewards/chosen": -1.7539873123168945,
|
397 |
+
"rewards/margins": -0.15278980135917664,
|
398 |
+
"rewards/rejected": -1.601197361946106,
|
399 |
+
"step": 26
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.1480973603016798,
|
403 |
+
"grad_norm": 9.860499037174334,
|
404 |
+
"learning_rate": 9.94068235036391e-07,
|
405 |
+
"logits/chosen": -0.4618387818336487,
|
406 |
+
"logits/rejected": -0.47574925422668457,
|
407 |
+
"logps/chosen": -0.6812009811401367,
|
408 |
+
"logps/rejected": -0.7617368698120117,
|
409 |
+
"loss": 1.9858,
|
410 |
+
"rewards/accuracies": 0.3046875,
|
411 |
+
"rewards/chosen": -1.9043422937393188,
|
412 |
+
"rewards/margins": -0.20133966207504272,
|
413 |
+
"rewards/rejected": -1.7030025720596313,
|
414 |
+
"step": 27
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.15358244772026053,
|
418 |
+
"grad_norm": 10.039428944668376,
|
419 |
+
"learning_rate": 9.924965614670628e-07,
|
420 |
+
"logits/chosen": -0.5124188661575317,
|
421 |
+
"logits/rejected": -0.4997189939022064,
|
422 |
+
"logps/chosen": -0.755838930606842,
|
423 |
+
"logps/rejected": -0.7807177901268005,
|
424 |
+
"loss": 1.9039,
|
425 |
+
"rewards/accuracies": 0.3828125,
|
426 |
+
"rewards/chosen": -1.9517943859100342,
|
427 |
+
"rewards/margins": -0.06219691038131714,
|
428 |
+
"rewards/rejected": -1.8895972967147827,
|
429 |
+
"step": 28
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.15906753513884128,
|
433 |
+
"grad_norm": 10.666772071989447,
|
434 |
+
"learning_rate": 9.90741945530174e-07,
|
435 |
+
"logits/chosen": -0.5431128740310669,
|
436 |
+
"logits/rejected": -0.5210611820220947,
|
437 |
+
"logps/chosen": -0.9286273121833801,
|
438 |
+
"logps/rejected": -0.9671891927719116,
|
439 |
+
"loss": 2.0302,
|
440 |
+
"rewards/accuracies": 0.28125,
|
441 |
+
"rewards/chosen": -2.417973041534424,
|
442 |
+
"rewards/margins": -0.0964045524597168,
|
443 |
+
"rewards/rejected": -2.321568250656128,
|
444 |
+
"step": 29
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.164552622557422,
|
448 |
+
"grad_norm": 8.160421166678184,
|
449 |
+
"learning_rate": 9.888050389939172e-07,
|
450 |
+
"logits/chosen": -0.5067495107650757,
|
451 |
+
"logits/rejected": -0.4774128198623657,
|
452 |
+
"logps/chosen": -0.7992498874664307,
|
453 |
+
"logps/rejected": -0.8549879789352417,
|
454 |
+
"loss": 1.9332,
|
455 |
+
"rewards/accuracies": 0.421875,
|
456 |
+
"rewards/chosen": -2.13746976852417,
|
457 |
+
"rewards/margins": -0.13934528827667236,
|
458 |
+
"rewards/rejected": -1.9981244802474976,
|
459 |
+
"step": 30
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.17003770997600273,
|
463 |
+
"grad_norm": 10.514382125623976,
|
464 |
+
"learning_rate": 9.866865613400006e-07,
|
465 |
+
"logits/chosen": -0.5173575282096863,
|
466 |
+
"logits/rejected": -0.4771508574485779,
|
467 |
+
"logps/chosen": -0.8561153411865234,
|
468 |
+
"logps/rejected": -0.9025238156318665,
|
469 |
+
"loss": 1.9123,
|
470 |
+
"rewards/accuracies": 0.3671875,
|
471 |
+
"rewards/chosen": -2.256309747695923,
|
472 |
+
"rewards/margins": -0.11602123826742172,
|
473 |
+
"rewards/rejected": -2.1402883529663086,
|
474 |
+
"step": 31
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.17552279739458349,
|
478 |
+
"grad_norm": 6.797061723595508,
|
479 |
+
"learning_rate": 9.843872994963912e-07,
|
480 |
+
"logits/chosen": -0.6115865707397461,
|
481 |
+
"logits/rejected": -0.5253005027770996,
|
482 |
+
"logps/chosen": -0.8001683950424194,
|
483 |
+
"logps/rejected": -0.8365844488143921,
|
484 |
+
"loss": 1.9177,
|
485 |
+
"rewards/accuracies": 0.3515625,
|
486 |
+
"rewards/chosen": -2.091461181640625,
|
487 |
+
"rewards/margins": -0.09104003012180328,
|
488 |
+
"rewards/rejected": -2.0004210472106934,
|
489 |
+
"step": 32
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.1810078848131642,
|
493 |
+
"grad_norm": 10.986752360147651,
|
494 |
+
"learning_rate": 9.819081075450013e-07,
|
495 |
+
"logits/chosen": -0.5589928030967712,
|
496 |
+
"logits/rejected": -0.5537349581718445,
|
497 |
+
"logps/chosen": -0.9822956323623657,
|
498 |
+
"logps/rejected": -0.8852106332778931,
|
499 |
+
"loss": 1.7645,
|
500 |
+
"rewards/accuracies": 0.4921875,
|
501 |
+
"rewards/chosen": -2.213026523590088,
|
502 |
+
"rewards/margins": 0.2427126169204712,
|
503 |
+
"rewards/rejected": -2.4557392597198486,
|
504 |
+
"step": 33
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.18649297223174494,
|
508 |
+
"grad_norm": 7.9793683352025395,
|
509 |
+
"learning_rate": 9.792499064044342e-07,
|
510 |
+
"logits/chosen": -0.6396060585975647,
|
511 |
+
"logits/rejected": -0.557750940322876,
|
512 |
+
"logps/chosen": -0.8982308506965637,
|
513 |
+
"logps/rejected": -0.9113630056381226,
|
514 |
+
"loss": 1.8363,
|
515 |
+
"rewards/accuracies": 0.375,
|
516 |
+
"rewards/chosen": -2.2784078121185303,
|
517 |
+
"rewards/margins": -0.03283056244254112,
|
518 |
+
"rewards/rejected": -2.245576858520508,
|
519 |
+
"step": 34
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.1919780596503257,
|
523 |
+
"grad_norm": 6.791520764999855,
|
524 |
+
"learning_rate": 9.764136834878985e-07,
|
525 |
+
"logits/chosen": -0.6534283757209778,
|
526 |
+
"logits/rejected": -0.6032913327217102,
|
527 |
+
"logps/chosen": -0.8987076282501221,
|
528 |
+
"logps/rejected": -0.9370582699775696,
|
529 |
+
"loss": 1.8242,
|
530 |
+
"rewards/accuracies": 0.40625,
|
531 |
+
"rewards/chosen": -2.3426456451416016,
|
532 |
+
"rewards/margins": -0.095876544713974,
|
533 |
+
"rewards/rejected": -2.2467689514160156,
|
534 |
+
"step": 35
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.19746314706890641,
|
538 |
+
"grad_norm": 7.022459099441044,
|
539 |
+
"learning_rate": 9.734004923364256e-07,
|
540 |
+
"logits/chosen": -0.6581586003303528,
|
541 |
+
"logits/rejected": -0.6092681884765625,
|
542 |
+
"logps/chosen": -0.960416316986084,
|
543 |
+
"logps/rejected": -0.9933475852012634,
|
544 |
+
"loss": 1.8998,
|
545 |
+
"rewards/accuracies": 0.390625,
|
546 |
+
"rewards/chosen": -2.4833688735961914,
|
547 |
+
"rewards/margins": -0.08232799917459488,
|
548 |
+
"rewards/rejected": -2.401041030883789,
|
549 |
+
"step": 36
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.20294823448748714,
|
553 |
+
"grad_norm": 7.996309219752066,
|
554 |
+
"learning_rate": 9.702114522275216e-07,
|
555 |
+
"logits/chosen": -0.6663313508033752,
|
556 |
+
"logits/rejected": -0.6023609638214111,
|
557 |
+
"logps/chosen": -0.9479801058769226,
|
558 |
+
"logps/rejected": -0.998908281326294,
|
559 |
+
"loss": 1.8343,
|
560 |
+
"rewards/accuracies": 0.40625,
|
561 |
+
"rewards/chosen": -2.4972708225250244,
|
562 |
+
"rewards/margins": -0.1273205429315567,
|
563 |
+
"rewards/rejected": -2.369950294494629,
|
564 |
+
"step": 37
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.20843332190606786,
|
568 |
+
"grad_norm": 6.699323358307292,
|
569 |
+
"learning_rate": 9.66847747759402e-07,
|
570 |
+
"logits/chosen": -0.622665286064148,
|
571 |
+
"logits/rejected": -0.5349312424659729,
|
572 |
+
"logps/chosen": -1.041911244392395,
|
573 |
+
"logps/rejected": -0.9843886494636536,
|
574 |
+
"loss": 1.6697,
|
575 |
+
"rewards/accuracies": 0.4921875,
|
576 |
+
"rewards/chosen": -2.4609715938568115,
|
577 |
+
"rewards/margins": 0.14380690455436707,
|
578 |
+
"rewards/rejected": -2.604778289794922,
|
579 |
+
"step": 38
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.21391840932464862,
|
583 |
+
"grad_norm": 6.682266326866778,
|
584 |
+
"learning_rate": 9.63310628410961e-07,
|
585 |
+
"logits/chosen": -0.6338837742805481,
|
586 |
+
"logits/rejected": -0.5423075556755066,
|
587 |
+
"logps/chosen": -1.0179288387298584,
|
588 |
+
"logps/rejected": -0.967695951461792,
|
589 |
+
"loss": 1.8336,
|
590 |
+
"rewards/accuracies": 0.359375,
|
591 |
+
"rewards/chosen": -2.4192402362823486,
|
592 |
+
"rewards/margins": 0.1255817860364914,
|
593 |
+
"rewards/rejected": -2.5448219776153564,
|
594 |
+
"step": 39
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.21940349674322934,
|
598 |
+
"grad_norm": 8.105951134201701,
|
599 |
+
"learning_rate": 9.596014080776421e-07,
|
600 |
+
"logits/chosen": -0.6672332286834717,
|
601 |
+
"logits/rejected": -0.6281388998031616,
|
602 |
+
"logps/chosen": -1.0504218339920044,
|
603 |
+
"logps/rejected": -1.0622175931930542,
|
604 |
+
"loss": 1.8315,
|
605 |
+
"rewards/accuracies": 0.40625,
|
606 |
+
"rewards/chosen": -2.6555442810058594,
|
607 |
+
"rewards/margins": -0.029489843174815178,
|
608 |
+
"rewards/rejected": -2.626054525375366,
|
609 |
+
"step": 40
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.22488858416181007,
|
613 |
+
"grad_norm": 13.378049805845984,
|
614 |
+
"learning_rate": 9.55721464583379e-07,
|
615 |
+
"logits/chosen": -0.7849185466766357,
|
616 |
+
"logits/rejected": -0.6884415745735168,
|
617 |
+
"logps/chosen": -1.0642319917678833,
|
618 |
+
"logps/rejected": -1.05228853225708,
|
619 |
+
"loss": 1.7842,
|
620 |
+
"rewards/accuracies": 0.4140625,
|
621 |
+
"rewards/chosen": -2.6307215690612793,
|
622 |
+
"rewards/margins": 0.02985840104520321,
|
623 |
+
"rewards/rejected": -2.6605796813964844,
|
624 |
+
"step": 41
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.23037367158039082,
|
628 |
+
"grad_norm": 9.064118287711297,
|
629 |
+
"learning_rate": 9.516722391687902e-07,
|
630 |
+
"logits/chosen": -0.6929774284362793,
|
631 |
+
"logits/rejected": -0.6579635739326477,
|
632 |
+
"logps/chosen": -1.1520164012908936,
|
633 |
+
"logps/rejected": -1.1617083549499512,
|
634 |
+
"loss": 1.9825,
|
635 |
+
"rewards/accuracies": 0.3203125,
|
636 |
+
"rewards/chosen": -2.904270887374878,
|
637 |
+
"rewards/margins": -0.02423013746738434,
|
638 |
+
"rewards/rejected": -2.8800406455993652,
|
639 |
+
"step": 42
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.23585875899897155,
|
643 |
+
"grad_norm": 7.541139303599616,
|
644 |
+
"learning_rate": 9.474552359558165e-07,
|
645 |
+
"logits/chosen": -0.7736871242523193,
|
646 |
+
"logits/rejected": -0.6667463183403015,
|
647 |
+
"logps/chosen": -1.1246612071990967,
|
648 |
+
"logps/rejected": -1.06680428981781,
|
649 |
+
"loss": 1.6144,
|
650 |
+
"rewards/accuracies": 0.4453125,
|
651 |
+
"rewards/chosen": -2.667010545730591,
|
652 |
+
"rewards/margins": 0.1446424126625061,
|
653 |
+
"rewards/rejected": -2.811652898788452,
|
654 |
+
"step": 43
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.24134384641755227,
|
658 |
+
"grad_norm": 9.736710769671427,
|
659 |
+
"learning_rate": 9.430720213890029e-07,
|
660 |
+
"logits/chosen": -0.7818886041641235,
|
661 |
+
"logits/rejected": -0.7196276187896729,
|
662 |
+
"logps/chosen": -1.2841920852661133,
|
663 |
+
"logps/rejected": -1.2012193202972412,
|
664 |
+
"loss": 1.648,
|
665 |
+
"rewards/accuracies": 0.4453125,
|
666 |
+
"rewards/chosen": -3.0030481815338135,
|
667 |
+
"rewards/margins": 0.2074318528175354,
|
668 |
+
"rewards/rejected": -3.210480213165283,
|
669 |
+
"step": 44
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.24682893383613302,
|
673 |
+
"grad_norm": 21.756241022877973,
|
674 |
+
"learning_rate": 9.385242236536259e-07,
|
675 |
+
"logits/chosen": -0.8642858266830444,
|
676 |
+
"logits/rejected": -0.816374659538269,
|
677 |
+
"logps/chosen": -1.3722171783447266,
|
678 |
+
"logps/rejected": -1.34407639503479,
|
679 |
+
"loss": 1.9336,
|
680 |
+
"rewards/accuracies": 0.46875,
|
681 |
+
"rewards/chosen": -3.3601903915405273,
|
682 |
+
"rewards/margins": 0.07035252451896667,
|
683 |
+
"rewards/rejected": -3.4305431842803955,
|
684 |
+
"step": 45
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.25231402125471375,
|
688 |
+
"grad_norm": 32.5907546315537,
|
689 |
+
"learning_rate": 9.338135320708911e-07,
|
690 |
+
"logits/chosen": -0.7350670695304871,
|
691 |
+
"logits/rejected": -0.6843174695968628,
|
692 |
+
"logps/chosen": -1.6099109649658203,
|
693 |
+
"logps/rejected": -1.380704641342163,
|
694 |
+
"loss": 1.4913,
|
695 |
+
"rewards/accuracies": 0.5234375,
|
696 |
+
"rewards/chosen": -3.4517619609832764,
|
697 |
+
"rewards/margins": 0.5730158686637878,
|
698 |
+
"rewards/rejected": -4.024777889251709,
|
699 |
+
"step": 46
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.2577991086732945,
|
703 |
+
"grad_norm": 69.74307826075179,
|
704 |
+
"learning_rate": 9.289416964704185e-07,
|
705 |
+
"logits/chosen": -0.6261876821517944,
|
706 |
+
"logits/rejected": -0.5953123569488525,
|
707 |
+
"logps/chosen": -2.0205883979797363,
|
708 |
+
"logps/rejected": -1.7966296672821045,
|
709 |
+
"loss": 1.4505,
|
710 |
+
"rewards/accuracies": 0.6171875,
|
711 |
+
"rewards/chosen": -4.491574287414551,
|
712 |
+
"rewards/margins": 0.5598966479301453,
|
713 |
+
"rewards/rejected": -5.05147123336792,
|
714 |
+
"step": 47
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.2632841960918752,
|
718 |
+
"grad_norm": 111.71156009374812,
|
719 |
+
"learning_rate": 9.239105265402525e-07,
|
720 |
+
"logits/chosen": -0.6214447021484375,
|
721 |
+
"logits/rejected": -0.6121379137039185,
|
722 |
+
"logps/chosen": -4.529265880584717,
|
723 |
+
"logps/rejected": -4.061288356781006,
|
724 |
+
"loss": 1.5693,
|
725 |
+
"rewards/accuracies": 0.671875,
|
726 |
+
"rewards/chosen": -10.15322208404541,
|
727 |
+
"rewards/margins": 1.1699434518814087,
|
728 |
+
"rewards/rejected": -11.323163032531738,
|
729 |
+
"step": 48
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.2687692835104559,
|
733 |
+
"grad_norm": 106.00540500477615,
|
734 |
+
"learning_rate": 9.187218911546361e-07,
|
735 |
+
"logits/chosen": -0.6318798661231995,
|
736 |
+
"logits/rejected": -0.6299155950546265,
|
737 |
+
"logps/chosen": -6.402857780456543,
|
738 |
+
"logps/rejected": -5.515579700469971,
|
739 |
+
"loss": 1.4994,
|
740 |
+
"rewards/accuracies": 0.75,
|
741 |
+
"rewards/chosen": -13.788949966430664,
|
742 |
+
"rewards/margins": 2.218195676803589,
|
743 |
+
"rewards/rejected": -16.007144927978516,
|
744 |
+
"step": 49
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.2742543709290367,
|
748 |
+
"grad_norm": 100.18405633526882,
|
749 |
+
"learning_rate": 9.133777176798012e-07,
|
750 |
+
"logits/chosen": -0.5955071449279785,
|
751 |
+
"logits/rejected": -0.587684690952301,
|
752 |
+
"logps/chosen": -6.099169731140137,
|
753 |
+
"logps/rejected": -5.420334339141846,
|
754 |
+
"loss": 1.686,
|
755 |
+
"rewards/accuracies": 0.640625,
|
756 |
+
"rewards/chosen": -13.550837516784668,
|
757 |
+
"rewards/margins": 1.6970889568328857,
|
758 |
+
"rewards/rejected": -15.2479248046875,
|
759 |
+
"step": 50
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.27973945834761743,
|
763 |
+
"grad_norm": 58.20603276880462,
|
764 |
+
"learning_rate": 9.078799912580303e-07,
|
765 |
+
"logits/chosen": -0.4950883388519287,
|
766 |
+
"logits/rejected": -0.47393253445625305,
|
767 |
+
"logps/chosen": -3.7327165603637695,
|
768 |
+
"logps/rejected": -2.9755775928497314,
|
769 |
+
"loss": 1.1265,
|
770 |
+
"rewards/accuracies": 0.7265625,
|
771 |
+
"rewards/chosen": -7.438943386077881,
|
772 |
+
"rewards/margins": 1.892848014831543,
|
773 |
+
"rewards/rejected": -9.331791877746582,
|
774 |
+
"step": 51
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.28522454576619816,
|
778 |
+
"grad_norm": 34.976161133474584,
|
779 |
+
"learning_rate": 9.022307540702576e-07,
|
780 |
+
"logits/chosen": -0.595772385597229,
|
781 |
+
"logits/rejected": -0.5804386138916016,
|
782 |
+
"logps/chosen": -3.406771659851074,
|
783 |
+
"logps/rejected": -2.477839469909668,
|
784 |
+
"loss": 1.0881,
|
785 |
+
"rewards/accuracies": 0.7578125,
|
786 |
+
"rewards/chosen": -6.1945977210998535,
|
787 |
+
"rewards/margins": 2.322330951690674,
|
788 |
+
"rewards/rejected": -8.516929626464844,
|
789 |
+
"step": 52
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.2907096331847789,
|
793 |
+
"grad_norm": 51.69206884243948,
|
794 |
+
"learning_rate": 8.964321045774806e-07,
|
795 |
+
"logits/chosen": -0.5769085884094238,
|
796 |
+
"logits/rejected": -0.5628898739814758,
|
797 |
+
"logps/chosen": -3.4867472648620605,
|
798 |
+
"logps/rejected": -2.7880890369415283,
|
799 |
+
"loss": 1.2003,
|
800 |
+
"rewards/accuracies": 0.734375,
|
801 |
+
"rewards/chosen": -6.970221996307373,
|
802 |
+
"rewards/margins": 1.7466471195220947,
|
803 |
+
"rewards/rejected": -8.716869354248047,
|
804 |
+
"step": 53
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.2961947206033596,
|
808 |
+
"grad_norm": 71.37167688264066,
|
809 |
+
"learning_rate": 8.904861967412701e-07,
|
810 |
+
"logits/chosen": -0.6889777183532715,
|
811 |
+
"logits/rejected": -0.6549051403999329,
|
812 |
+
"logps/chosen": -2.727174997329712,
|
813 |
+
"logps/rejected": -2.3221614360809326,
|
814 |
+
"loss": 1.4033,
|
815 |
+
"rewards/accuracies": 0.6640625,
|
816 |
+
"rewards/chosen": -5.805403709411621,
|
817 |
+
"rewards/margins": 1.0125339031219482,
|
818 |
+
"rewards/rejected": -6.817937850952148,
|
819 |
+
"step": 54
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.30167980802194033,
|
823 |
+
"grad_norm": 47.86988316740339,
|
824 |
+
"learning_rate": 8.843952392236593e-07,
|
825 |
+
"logits/chosen": -0.7492246031761169,
|
826 |
+
"logits/rejected": -0.6207780838012695,
|
827 |
+
"logps/chosen": -3.1855251789093018,
|
828 |
+
"logps/rejected": -2.70566987991333,
|
829 |
+
"loss": 1.3969,
|
830 |
+
"rewards/accuracies": 0.8125,
|
831 |
+
"rewards/chosen": -6.764174461364746,
|
832 |
+
"rewards/margins": 1.1996381282806396,
|
833 |
+
"rewards/rejected": -7.963812351226807,
|
834 |
+
"step": 55
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.30716489544052106,
|
838 |
+
"grad_norm": 78.52357858963444,
|
839 |
+
"learning_rate": 8.781614945667168e-07,
|
840 |
+
"logits/chosen": -0.7661877274513245,
|
841 |
+
"logits/rejected": -0.6237936615943909,
|
842 |
+
"logps/chosen": -3.6718194484710693,
|
843 |
+
"logps/rejected": -2.841695547103882,
|
844 |
+
"loss": 1.2378,
|
845 |
+
"rewards/accuracies": 0.765625,
|
846 |
+
"rewards/chosen": -7.104238033294678,
|
847 |
+
"rewards/margins": 2.075310230255127,
|
848 |
+
"rewards/rejected": -9.179548263549805,
|
849 |
+
"step": 56
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.31264998285910184,
|
853 |
+
"grad_norm": 71.4152133884341,
|
854 |
+
"learning_rate": 8.717872783521047e-07,
|
855 |
+
"logits/chosen": -0.800015389919281,
|
856 |
+
"logits/rejected": -0.7331135272979736,
|
857 |
+
"logps/chosen": -3.140065908432007,
|
858 |
+
"logps/rejected": -2.2423806190490723,
|
859 |
+
"loss": 1.0947,
|
860 |
+
"rewards/accuracies": 0.8125,
|
861 |
+
"rewards/chosen": -5.605951309204102,
|
862 |
+
"rewards/margins": 2.244213104248047,
|
863 |
+
"rewards/rejected": -7.850164890289307,
|
864 |
+
"step": 57
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.31813507027768256,
|
868 |
+
"grad_norm": 42.30260390013795,
|
869 |
+
"learning_rate": 8.652749583409339e-07,
|
870 |
+
"logits/chosen": -0.9033212661743164,
|
871 |
+
"logits/rejected": -0.7837256193161011,
|
872 |
+
"logps/chosen": -3.608813524246216,
|
873 |
+
"logps/rejected": -2.8119547367095947,
|
874 |
+
"loss": 1.0673,
|
875 |
+
"rewards/accuracies": 0.78125,
|
876 |
+
"rewards/chosen": -7.0298871994018555,
|
877 |
+
"rewards/margins": 1.99214768409729,
|
878 |
+
"rewards/rejected": -9.02203369140625,
|
879 |
+
"step": 58
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.3236201576962633,
|
883 |
+
"grad_norm": 72.45091367067401,
|
884 |
+
"learning_rate": 8.586269535942385e-07,
|
885 |
+
"logits/chosen": -0.9157741069793701,
|
886 |
+
"logits/rejected": -0.8138267993927002,
|
887 |
+
"logps/chosen": -4.422084808349609,
|
888 |
+
"logps/rejected": -3.3933629989624023,
|
889 |
+
"loss": 1.0082,
|
890 |
+
"rewards/accuracies": 0.8359375,
|
891 |
+
"rewards/chosen": -8.483407974243164,
|
892 |
+
"rewards/margins": 2.5718040466308594,
|
893 |
+
"rewards/rejected": -11.055212020874023,
|
894 |
+
"step": 59
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.329105245114844,
|
898 |
+
"grad_norm": 67.2038247219744,
|
899 |
+
"learning_rate": 8.518457335743924e-07,
|
900 |
+
"logits/chosen": -1.0231534242630005,
|
901 |
+
"logits/rejected": -0.8920707106590271,
|
902 |
+
"logps/chosen": -6.588432312011719,
|
903 |
+
"logps/rejected": -4.968594551086426,
|
904 |
+
"loss": 1.2004,
|
905 |
+
"rewards/accuracies": 0.7734375,
|
906 |
+
"rewards/chosen": -12.42148494720459,
|
907 |
+
"rewards/margins": 4.049595832824707,
|
908 |
+
"rewards/rejected": -16.471080780029297,
|
909 |
+
"step": 60
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.33459033253342474,
|
913 |
+
"grad_norm": 71.2725286215776,
|
914 |
+
"learning_rate": 8.449338172278058e-07,
|
915 |
+
"logits/chosen": -1.0856202840805054,
|
916 |
+
"logits/rejected": -1.001308798789978,
|
917 |
+
"logps/chosen": -7.01667594909668,
|
918 |
+
"logps/rejected": -5.5445075035095215,
|
919 |
+
"loss": 1.07,
|
920 |
+
"rewards/accuracies": 0.78125,
|
921 |
+
"rewards/chosen": -13.861268043518066,
|
922 |
+
"rewards/margins": 3.680420398712158,
|
923 |
+
"rewards/rejected": -17.541690826416016,
|
924 |
+
"step": 61
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.34007541995200546,
|
928 |
+
"grad_norm": 83.45605345714169,
|
929 |
+
"learning_rate": 8.378937720492383e-07,
|
930 |
+
"logits/chosen": -0.9825168251991272,
|
931 |
+
"logits/rejected": -0.8393011093139648,
|
932 |
+
"logps/chosen": -6.87870979309082,
|
933 |
+
"logps/rejected": -5.226398468017578,
|
934 |
+
"loss": 1.1342,
|
935 |
+
"rewards/accuracies": 0.7578125,
|
936 |
+
"rewards/chosen": -13.065997123718262,
|
937 |
+
"rewards/margins": 4.130776882171631,
|
938 |
+
"rewards/rejected": -17.196773529052734,
|
939 |
+
"step": 62
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.34556050737058625,
|
943 |
+
"grad_norm": 47.538952621401116,
|
944 |
+
"learning_rate": 8.307282131280804e-07,
|
945 |
+
"logits/chosen": -1.073388695716858,
|
946 |
+
"logits/rejected": -0.8648728728294373,
|
947 |
+
"logps/chosen": -5.328536033630371,
|
948 |
+
"logps/rejected": -3.9907565116882324,
|
949 |
+
"loss": 0.9218,
|
950 |
+
"rewards/accuracies": 0.8203125,
|
951 |
+
"rewards/chosen": -9.976890563964844,
|
952 |
+
"rewards/margins": 3.344449520111084,
|
953 |
+
"rewards/rejected": -13.321340560913086,
|
954 |
+
"step": 63
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.35104559478916697,
|
958 |
+
"grad_norm": 69.97786008191355,
|
959 |
+
"learning_rate": 8.23439802176954e-07,
|
960 |
+
"logits/chosen": -1.045760989189148,
|
961 |
+
"logits/rejected": -0.8985159993171692,
|
962 |
+
"logps/chosen": -4.391729831695557,
|
963 |
+
"logps/rejected": -2.979081869125366,
|
964 |
+
"loss": 1.0545,
|
965 |
+
"rewards/accuracies": 0.796875,
|
966 |
+
"rewards/chosen": -7.447704315185547,
|
967 |
+
"rewards/margins": 3.531620502471924,
|
968 |
+
"rewards/rejected": -10.979324340820312,
|
969 |
+
"step": 64
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.3565306822077477,
|
973 |
+
"grad_norm": 57.99100276656143,
|
974 |
+
"learning_rate": 8.160312465429952e-07,
|
975 |
+
"logits/chosen": -1.059841513633728,
|
976 |
+
"logits/rejected": -0.9158331155776978,
|
977 |
+
"logps/chosen": -4.3702073097229,
|
978 |
+
"logps/rejected": -2.9328854084014893,
|
979 |
+
"loss": 0.8092,
|
980 |
+
"rewards/accuracies": 0.828125,
|
981 |
+
"rewards/chosen": -7.332213401794434,
|
982 |
+
"rewards/margins": 3.5933048725128174,
|
983 |
+
"rewards/rejected": -10.925518035888672,
|
984 |
+
"step": 65
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.3620157696263284,
|
988 |
+
"grad_norm": 32.78666266298242,
|
989 |
+
"learning_rate": 8.085052982021847e-07,
|
990 |
+
"logits/chosen": -1.128019094467163,
|
991 |
+
"logits/rejected": -0.9226801991462708,
|
992 |
+
"logps/chosen": -3.9989237785339355,
|
993 |
+
"logps/rejected": -2.929816246032715,
|
994 |
+
"loss": 1.0525,
|
995 |
+
"rewards/accuracies": 0.7734375,
|
996 |
+
"rewards/chosen": -7.324541091918945,
|
997 |
+
"rewards/margins": 2.6727685928344727,
|
998 |
+
"rewards/rejected": -9.997309684753418,
|
999 |
+
"step": 66
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.36750085704490915,
|
1003 |
+
"grad_norm": 50.293055849490955,
|
1004 |
+
"learning_rate": 8.008647527371022e-07,
|
1005 |
+
"logits/chosen": -1.4013196229934692,
|
1006 |
+
"logits/rejected": -1.138377070426941,
|
1007 |
+
"logps/chosen": -4.476810932159424,
|
1008 |
+
"logps/rejected": -3.069303512573242,
|
1009 |
+
"loss": 0.8161,
|
1010 |
+
"rewards/accuracies": 0.84375,
|
1011 |
+
"rewards/chosen": -7.6732587814331055,
|
1012 |
+
"rewards/margins": 3.518767833709717,
|
1013 |
+
"rewards/rejected": -11.19202709197998,
|
1014 |
+
"step": 67
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.37298594446348987,
|
1018 |
+
"grad_norm": 50.48347857053289,
|
1019 |
+
"learning_rate": 7.931124482984801e-07,
|
1020 |
+
"logits/chosen": -1.4336833953857422,
|
1021 |
+
"logits/rejected": -1.2769416570663452,
|
1022 |
+
"logps/chosen": -4.982694625854492,
|
1023 |
+
"logps/rejected": -3.5518202781677246,
|
1024 |
+
"loss": 1.0579,
|
1025 |
+
"rewards/accuracies": 0.765625,
|
1026 |
+
"rewards/chosen": -8.87955093383789,
|
1027 |
+
"rewards/margins": 3.5771865844726562,
|
1028 |
+
"rewards/rejected": -12.45673656463623,
|
1029 |
+
"step": 68
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.3784710318820706,
|
1033 |
+
"grad_norm": 41.95073141945747,
|
1034 |
+
"learning_rate": 7.85251264550948e-07,
|
1035 |
+
"logits/chosen": -1.5961790084838867,
|
1036 |
+
"logits/rejected": -1.3946001529693604,
|
1037 |
+
"logps/chosen": -5.758039951324463,
|
1038 |
+
"logps/rejected": -4.470717906951904,
|
1039 |
+
"loss": 1.3453,
|
1040 |
+
"rewards/accuracies": 0.7265625,
|
1041 |
+
"rewards/chosen": -11.176795959472656,
|
1042 |
+
"rewards/margins": 3.218303680419922,
|
1043 |
+
"rewards/rejected": -14.395099639892578,
|
1044 |
+
"step": 69
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.3839561193006514,
|
1048 |
+
"grad_norm": 52.202423339982246,
|
1049 |
+
"learning_rate": 7.772841216033532e-07,
|
1050 |
+
"logits/chosen": -1.6466355323791504,
|
1051 |
+
"logits/rejected": -1.4171117544174194,
|
1052 |
+
"logps/chosen": -6.761007308959961,
|
1053 |
+
"logps/rejected": -5.078183650970459,
|
1054 |
+
"loss": 1.2675,
|
1055 |
+
"rewards/accuracies": 0.7890625,
|
1056 |
+
"rewards/chosen": -12.69545841217041,
|
1057 |
+
"rewards/margins": 4.207059860229492,
|
1058 |
+
"rewards/rejected": -16.90251922607422,
|
1059 |
+
"step": 70
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.3894412067192321,
|
1063 |
+
"grad_norm": 33.978850229748005,
|
1064 |
+
"learning_rate": 7.69213978924061e-07,
|
1065 |
+
"logits/chosen": -1.544925332069397,
|
1066 |
+
"logits/rejected": -1.2573606967926025,
|
1067 |
+
"logps/chosen": -6.336057662963867,
|
1068 |
+
"logps/rejected": -4.741216659545898,
|
1069 |
+
"loss": 1.096,
|
1070 |
+
"rewards/accuracies": 0.828125,
|
1071 |
+
"rewards/chosen": -11.85304069519043,
|
1072 |
+
"rewards/margins": 3.987103223800659,
|
1073 |
+
"rewards/rejected": -15.840145111083984,
|
1074 |
+
"step": 71
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.39492629413781283,
|
1078 |
+
"grad_norm": 96.09934849635745,
|
1079 |
+
"learning_rate": 7.610438342416319e-07,
|
1080 |
+
"logits/chosen": -1.4953880310058594,
|
1081 |
+
"logits/rejected": -1.2785418033599854,
|
1082 |
+
"logps/chosen": -6.89131498336792,
|
1083 |
+
"logps/rejected": -5.383131980895996,
|
1084 |
+
"loss": 1.0171,
|
1085 |
+
"rewards/accuracies": 0.8046875,
|
1086 |
+
"rewards/chosen": -13.457829475402832,
|
1087 |
+
"rewards/margins": 3.7704575061798096,
|
1088 |
+
"rewards/rejected": -17.228288650512695,
|
1089 |
+
"step": 72
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.40041138155639355,
|
1093 |
+
"grad_norm": 27.422261234951808,
|
1094 |
+
"learning_rate": 7.527767224312882e-07,
|
1095 |
+
"logits/chosen": -1.322948932647705,
|
1096 |
+
"logits/rejected": -1.1441978216171265,
|
1097 |
+
"logps/chosen": -6.809509754180908,
|
1098 |
+
"logps/rejected": -4.989666938781738,
|
1099 |
+
"loss": 0.6614,
|
1100 |
+
"rewards/accuracies": 0.8515625,
|
1101 |
+
"rewards/chosen": -12.47416877746582,
|
1102 |
+
"rewards/margins": 4.549604415893555,
|
1103 |
+
"rewards/rejected": -17.023773193359375,
|
1104 |
+
"step": 73
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.4058964689749743,
|
1108 |
+
"grad_norm": 80.95278759548928,
|
1109 |
+
"learning_rate": 7.444157143875819e-07,
|
1110 |
+
"logits/chosen": -1.216729760169983,
|
1111 |
+
"logits/rejected": -1.057979941368103,
|
1112 |
+
"logps/chosen": -6.466203689575195,
|
1113 |
+
"logps/rejected": -5.076437950134277,
|
1114 |
+
"loss": 0.9105,
|
1115 |
+
"rewards/accuracies": 0.8359375,
|
1116 |
+
"rewards/chosen": -12.691095352172852,
|
1117 |
+
"rewards/margins": 3.474414110183716,
|
1118 |
+
"rewards/rejected": -16.165510177612305,
|
1119 |
+
"step": 74
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.411381556393555,
|
1123 |
+
"grad_norm": 72.36852993655451,
|
1124 |
+
"learning_rate": 7.359639158836827e-07,
|
1125 |
+
"logits/chosen": -1.1118669509887695,
|
1126 |
+
"logits/rejected": -1.0416420698165894,
|
1127 |
+
"logps/chosen": -7.078163146972656,
|
1128 |
+
"logps/rejected": -5.48430871963501,
|
1129 |
+
"loss": 1.0358,
|
1130 |
+
"rewards/accuracies": 0.75,
|
1131 |
+
"rewards/chosen": -13.710769653320312,
|
1132 |
+
"rewards/margins": 3.9846386909484863,
|
1133 |
+
"rewards/rejected": -17.695409774780273,
|
1134 |
+
"step": 75
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.41686664381213573,
|
1138 |
+
"grad_norm": 66.4908598237263,
|
1139 |
+
"learning_rate": 7.274244664177097e-07,
|
1140 |
+
"logits/chosen": -1.041873812675476,
|
1141 |
+
"logits/rejected": -0.9867510199546814,
|
1142 |
+
"logps/chosen": -6.261934280395508,
|
1143 |
+
"logps/rejected": -4.695401668548584,
|
1144 |
+
"loss": 0.9974,
|
1145 |
+
"rewards/accuracies": 0.8046875,
|
1146 |
+
"rewards/chosen": -11.738503456115723,
|
1147 |
+
"rewards/margins": 3.9163331985473633,
|
1148 |
+
"rewards/rejected": -15.654836654663086,
|
1149 |
+
"step": 76
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.4223517312307165,
|
1153 |
+
"grad_norm": 49.259846719809424,
|
1154 |
+
"learning_rate": 7.188005380465364e-07,
|
1155 |
+
"logits/chosen": -1.1777944564819336,
|
1156 |
+
"logits/rejected": -1.0354324579238892,
|
1157 |
+
"logps/chosen": -6.061973571777344,
|
1158 |
+
"logps/rejected": -4.546577453613281,
|
1159 |
+
"loss": 0.8174,
|
1160 |
+
"rewards/accuracies": 0.8046875,
|
1161 |
+
"rewards/chosen": -11.36644458770752,
|
1162 |
+
"rewards/margins": 3.7884879112243652,
|
1163 |
+
"rewards/rejected": -15.154932975769043,
|
1164 |
+
"step": 77
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.42783681864929723,
|
1168 |
+
"grad_norm": 29.6260649209974,
|
1169 |
+
"learning_rate": 7.100953342075009e-07,
|
1170 |
+
"logits/chosen": -1.2290102243423462,
|
1171 |
+
"logits/rejected": -1.110871434211731,
|
1172 |
+
"logps/chosen": -5.283913612365723,
|
1173 |
+
"logps/rejected": -3.9515509605407715,
|
1174 |
+
"loss": 0.8695,
|
1175 |
+
"rewards/accuracies": 0.8203125,
|
1176 |
+
"rewards/chosen": -9.878876686096191,
|
1177 |
+
"rewards/margins": 3.33090877532959,
|
1178 |
+
"rewards/rejected": -13.209785461425781,
|
1179 |
+
"step": 78
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.43332190606787796,
|
1183 |
+
"grad_norm": 32.05872824883326,
|
1184 |
+
"learning_rate": 7.013120885284598e-07,
|
1185 |
+
"logits/chosen": -1.3086589574813843,
|
1186 |
+
"logits/rejected": -1.1846544742584229,
|
1187 |
+
"logps/chosen": -5.159869194030762,
|
1188 |
+
"logps/rejected": -3.5984580516815186,
|
1189 |
+
"loss": 0.7876,
|
1190 |
+
"rewards/accuracies": 0.8359375,
|
1191 |
+
"rewards/chosen": -8.996145248413086,
|
1192 |
+
"rewards/margins": 3.9035279750823975,
|
1193 |
+
"rewards/rejected": -12.899672508239746,
|
1194 |
+
"step": 79
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.4388069934864587,
|
1198 |
+
"grad_norm": 40.42205251951496,
|
1199 |
+
"learning_rate": 6.924540636266272e-07,
|
1200 |
+
"logits/chosen": -1.3288094997406006,
|
1201 |
+
"logits/rejected": -1.2276866436004639,
|
1202 |
+
"logps/chosen": -5.131710529327393,
|
1203 |
+
"logps/rejected": -3.831780433654785,
|
1204 |
+
"loss": 0.9434,
|
1205 |
+
"rewards/accuracies": 0.859375,
|
1206 |
+
"rewards/chosen": -9.579451560974121,
|
1207 |
+
"rewards/margins": 3.2498245239257812,
|
1208 |
+
"rewards/rejected": -12.829277038574219,
|
1209 |
+
"step": 80
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.4442920809050394,
|
1213 |
+
"grad_norm": 36.25388918144398,
|
1214 |
+
"learning_rate": 6.83524549896646e-07,
|
1215 |
+
"logits/chosen": -1.163621187210083,
|
1216 |
+
"logits/rejected": -1.1168286800384521,
|
1217 |
+
"logps/chosen": -5.016862392425537,
|
1218 |
+
"logps/rejected": -3.682563066482544,
|
1219 |
+
"loss": 0.8759,
|
1220 |
+
"rewards/accuracies": 0.8046875,
|
1221 |
+
"rewards/chosen": -9.206408500671387,
|
1222 |
+
"rewards/margins": 3.3357465267181396,
|
1223 |
+
"rewards/rejected": -12.542155265808105,
|
1224 |
+
"step": 81
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.44977716832362014,
|
1228 |
+
"grad_norm": 25.153488392194294,
|
1229 |
+
"learning_rate": 6.745268642883404e-07,
|
1230 |
+
"logits/chosen": -1.2277235984802246,
|
1231 |
+
"logits/rejected": -1.0471045970916748,
|
1232 |
+
"logps/chosen": -5.926680088043213,
|
1233 |
+
"logps/rejected": -4.389726161956787,
|
1234 |
+
"loss": 0.6727,
|
1235 |
+
"rewards/accuracies": 0.875,
|
1236 |
+
"rewards/chosen": -10.974315643310547,
|
1237 |
+
"rewards/margins": 3.8423848152160645,
|
1238 |
+
"rewards/rejected": -14.816699981689453,
|
1239 |
+
"step": 82
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.4552622557422009,
|
1243 |
+
"grad_norm": 22.152291434451502,
|
1244 |
+
"learning_rate": 6.654643490746041e-07,
|
1245 |
+
"logits/chosen": -1.2063225507736206,
|
1246 |
+
"logits/rejected": -1.0923081636428833,
|
1247 |
+
"logps/chosen": -6.3293843269348145,
|
1248 |
+
"logps/rejected": -4.906074047088623,
|
1249 |
+
"loss": 0.8406,
|
1250 |
+
"rewards/accuracies": 0.875,
|
1251 |
+
"rewards/chosen": -12.26518440246582,
|
1252 |
+
"rewards/margins": 3.558277130126953,
|
1253 |
+
"rewards/rejected": -15.823461532592773,
|
1254 |
+
"step": 83
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.46074734316078164,
|
1258 |
+
"grad_norm": 29.47429990683989,
|
1259 |
+
"learning_rate": 6.563403706098832e-07,
|
1260 |
+
"logits/chosen": -1.2531236410140991,
|
1261 |
+
"logits/rejected": -1.1536014080047607,
|
1262 |
+
"logps/chosen": -7.200500965118408,
|
1263 |
+
"logps/rejected": -5.6704511642456055,
|
1264 |
+
"loss": 0.844,
|
1265 |
+
"rewards/accuracies": 0.78125,
|
1266 |
+
"rewards/chosen": -14.176128387451172,
|
1267 |
+
"rewards/margins": 3.8251240253448486,
|
1268 |
+
"rewards/rejected": -18.001251220703125,
|
1269 |
+
"step": 84
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.46623243057936237,
|
1273 |
+
"grad_norm": 39.720494087331325,
|
1274 |
+
"learning_rate": 6.47158318079712e-07,
|
1275 |
+
"logits/chosen": -1.2474052906036377,
|
1276 |
+
"logits/rejected": -1.1939733028411865,
|
1277 |
+
"logps/chosen": -7.995599746704102,
|
1278 |
+
"logps/rejected": -6.105539321899414,
|
1279 |
+
"loss": 0.9392,
|
1280 |
+
"rewards/accuracies": 0.8046875,
|
1281 |
+
"rewards/chosen": -15.263847351074219,
|
1282 |
+
"rewards/margins": 4.725150108337402,
|
1283 |
+
"rewards/rejected": -19.988998413085938,
|
1284 |
+
"step": 85
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.4717175179979431,
|
1288 |
+
"grad_norm": 26.901425160757288,
|
1289 |
+
"learning_rate": 6.379216022417695e-07,
|
1290 |
+
"logits/chosen": -1.2418212890625,
|
1291 |
+
"logits/rejected": -1.1997092962265015,
|
1292 |
+
"logps/chosen": -8.617918014526367,
|
1293 |
+
"logps/rejected": -6.57258415222168,
|
1294 |
+
"loss": 0.6221,
|
1295 |
+
"rewards/accuracies": 0.9140625,
|
1296 |
+
"rewards/chosen": -16.431461334228516,
|
1297 |
+
"rewards/margins": 5.113334655761719,
|
1298 |
+
"rewards/rejected": -21.544795989990234,
|
1299 |
+
"step": 86
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.4772026054165238,
|
1303 |
+
"grad_norm": 58.114713536632436,
|
1304 |
+
"learning_rate": 6.286336541589223e-07,
|
1305 |
+
"logits/chosen": -1.2740073204040527,
|
1306 |
+
"logits/rejected": -1.2163861989974976,
|
1307 |
+
"logps/chosen": -8.867392539978027,
|
1308 |
+
"logps/rejected": -7.1280741691589355,
|
1309 |
+
"loss": 0.9602,
|
1310 |
+
"rewards/accuracies": 0.8125,
|
1311 |
+
"rewards/chosen": -17.820186614990234,
|
1312 |
+
"rewards/margins": 4.348294734954834,
|
1313 |
+
"rewards/rejected": -22.168481826782227,
|
1314 |
+
"step": 87
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.48268769283510454,
|
1318 |
+
"grad_norm": 33.361524717086475,
|
1319 |
+
"learning_rate": 6.192979239247242e-07,
|
1320 |
+
"logits/chosen": -1.1057997941970825,
|
1321 |
+
"logits/rejected": -1.0285227298736572,
|
1322 |
+
"logps/chosen": -8.445158004760742,
|
1323 |
+
"logps/rejected": -6.86185359954834,
|
1324 |
+
"loss": 0.8718,
|
1325 |
+
"rewards/accuracies": 0.796875,
|
1326 |
+
"rewards/chosen": -17.154632568359375,
|
1327 |
+
"rewards/margins": 3.9582619667053223,
|
1328 |
+
"rewards/rejected": -21.112895965576172,
|
1329 |
+
"step": 88
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.48817278025368527,
|
1333 |
+
"grad_norm": 51.84635707806423,
|
1334 |
+
"learning_rate": 6.099178793818478e-07,
|
1335 |
+
"logits/chosen": -1.1163854598999023,
|
1336 |
+
"logits/rejected": -1.0613051652908325,
|
1337 |
+
"logps/chosen": -9.026713371276855,
|
1338 |
+
"logps/rejected": -7.194836616516113,
|
1339 |
+
"loss": 0.8724,
|
1340 |
+
"rewards/accuracies": 0.8359375,
|
1341 |
+
"rewards/chosen": -17.987092971801758,
|
1342 |
+
"rewards/margins": 4.5796895027160645,
|
1343 |
+
"rewards/rejected": -22.566783905029297,
|
1344 |
+
"step": 89
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 0.49365786767226605,
|
1348 |
+
"grad_norm": 35.13623148031408,
|
1349 |
+
"learning_rate": 6.004970048339225e-07,
|
1350 |
+
"logits/chosen": -0.9862219095230103,
|
1351 |
+
"logits/rejected": -0.868794858455658,
|
1352 |
+
"logps/chosen": -7.408356666564941,
|
1353 |
+
"logps/rejected": -5.994558334350586,
|
1354 |
+
"loss": 0.9605,
|
1355 |
+
"rewards/accuracies": 0.796875,
|
1356 |
+
"rewards/chosen": -14.986395835876465,
|
1357 |
+
"rewards/margins": 3.5344960689544678,
|
1358 |
+
"rewards/rejected": -18.520891189575195,
|
1359 |
+
"step": 90
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.4991429550908468,
|
1363 |
+
"grad_norm": 30.15074112906336,
|
1364 |
+
"learning_rate": 5.910387997512573e-07,
|
1365 |
+
"logits/chosen": -0.9399983286857605,
|
1366 |
+
"logits/rejected": -0.8564634919166565,
|
1367 |
+
"logps/chosen": -7.057155609130859,
|
1368 |
+
"logps/rejected": -5.3340325355529785,
|
1369 |
+
"loss": 0.7882,
|
1370 |
+
"rewards/accuracies": 0.859375,
|
1371 |
+
"rewards/chosen": -13.3350830078125,
|
1372 |
+
"rewards/margins": 4.307806968688965,
|
1373 |
+
"rewards/rejected": -17.64288902282715,
|
1374 |
+
"step": 91
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.5046280425094275,
|
1378 |
+
"grad_norm": 38.88195575984379,
|
1379 |
+
"learning_rate": 5.815467774709313e-07,
|
1380 |
+
"logits/chosen": -0.9454355835914612,
|
1381 |
+
"logits/rejected": -0.9133027791976929,
|
1382 |
+
"logps/chosen": -6.99016809463501,
|
1383 |
+
"logps/rejected": -5.265021324157715,
|
1384 |
+
"loss": 0.8483,
|
1385 |
+
"rewards/accuracies": 0.8359375,
|
1386 |
+
"rewards/chosen": -13.162553787231445,
|
1387 |
+
"rewards/margins": 4.3128662109375,
|
1388 |
+
"rewards/rejected": -17.475419998168945,
|
1389 |
+
"step": 92
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.5101131299280083,
|
1393 |
+
"grad_norm": 30.158868667054477,
|
1394 |
+
"learning_rate": 5.720244638917323e-07,
|
1395 |
+
"logits/chosen": -0.965910792350769,
|
1396 |
+
"logits/rejected": -0.8706585168838501,
|
1397 |
+
"logps/chosen": -6.497648239135742,
|
1398 |
+
"logps/rejected": -4.859541416168213,
|
1399 |
+
"loss": 0.8819,
|
1400 |
+
"rewards/accuracies": 0.8203125,
|
1401 |
+
"rewards/chosen": -12.148852348327637,
|
1402 |
+
"rewards/margins": 4.095267295837402,
|
1403 |
+
"rewards/rejected": -16.24411964416504,
|
1404 |
+
"step": 93
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.515598217346589,
|
1408 |
+
"grad_norm": 53.363507967860116,
|
1409 |
+
"learning_rate": 5.624753961644281e-07,
|
1410 |
+
"logits/chosen": -1.0084278583526611,
|
1411 |
+
"logits/rejected": -0.9723138213157654,
|
1412 |
+
"logps/chosen": -5.623072624206543,
|
1413 |
+
"logps/rejected": -4.460352420806885,
|
1414 |
+
"loss": 1.0174,
|
1415 |
+
"rewards/accuracies": 0.796875,
|
1416 |
+
"rewards/chosen": -11.150880813598633,
|
1417 |
+
"rewards/margins": 2.9068009853363037,
|
1418 |
+
"rewards/rejected": -14.057682037353516,
|
1419 |
+
"step": 94
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.5210833047651697,
|
1423 |
+
"grad_norm": 23.23631443491041,
|
1424 |
+
"learning_rate": 5.529031213778614e-07,
|
1425 |
+
"logits/chosen": -1.0280265808105469,
|
1426 |
+
"logits/rejected": -0.9905204772949219,
|
1427 |
+
"logps/chosen": -5.483713150024414,
|
1428 |
+
"logps/rejected": -4.167681694030762,
|
1429 |
+
"loss": 0.98,
|
1430 |
+
"rewards/accuracies": 0.7890625,
|
1431 |
+
"rewards/chosen": -10.419203758239746,
|
1432 |
+
"rewards/margins": 3.290079355239868,
|
1433 |
+
"rewards/rejected": -13.709283828735352,
|
1434 |
+
"step": 95
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.5265683921837504,
|
1438 |
+
"grad_norm": 37.123060878167124,
|
1439 |
+
"learning_rate": 5.433111952413494e-07,
|
1440 |
+
"logits/chosen": -1.088523507118225,
|
1441 |
+
"logits/rejected": -0.998890221118927,
|
1442 |
+
"logps/chosen": -5.065528869628906,
|
1443 |
+
"logps/rejected": -3.6324613094329834,
|
1444 |
+
"loss": 0.8177,
|
1445 |
+
"rewards/accuracies": 0.8125,
|
1446 |
+
"rewards/chosen": -9.081153869628906,
|
1447 |
+
"rewards/margins": 3.582667112350464,
|
1448 |
+
"rewards/rejected": -12.663820266723633,
|
1449 |
+
"step": 96
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.5320534796023312,
|
1453 |
+
"grad_norm": 25.260662494721746,
|
1454 |
+
"learning_rate": 5.33703180763884e-07,
|
1455 |
+
"logits/chosen": -1.0532890558242798,
|
1456 |
+
"logits/rejected": -0.9741649031639099,
|
1457 |
+
"logps/chosen": -5.729362964630127,
|
1458 |
+
"logps/rejected": -4.276680946350098,
|
1459 |
+
"loss": 0.7902,
|
1460 |
+
"rewards/accuracies": 0.8671875,
|
1461 |
+
"rewards/chosen": -10.691701889038086,
|
1462 |
+
"rewards/margins": 3.631704568862915,
|
1463 |
+
"rewards/rejected": -14.323406219482422,
|
1464 |
+
"step": 97
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 0.5375385670209119,
|
1468 |
+
"grad_norm": 46.96307372174284,
|
1469 |
+
"learning_rate": 5.240826469306186e-07,
|
1470 |
+
"logits/chosen": -1.0120959281921387,
|
1471 |
+
"logits/rejected": -0.9785177707672119,
|
1472 |
+
"logps/chosen": -6.013980865478516,
|
1473 |
+
"logps/rejected": -4.12684965133667,
|
1474 |
+
"loss": 0.5899,
|
1475 |
+
"rewards/accuracies": 0.9140625,
|
1476 |
+
"rewards/chosen": -10.317124366760254,
|
1477 |
+
"rewards/margins": 4.71782922744751,
|
1478 |
+
"rewards/rejected": -15.034952163696289,
|
1479 |
+
"step": 98
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.5430236544394926,
|
1483 |
+
"grad_norm": 24.414358778835954,
|
1484 |
+
"learning_rate": 5.144531673771363e-07,
|
1485 |
+
"logits/chosen": -1.002170205116272,
|
1486 |
+
"logits/rejected": -0.9993859529495239,
|
1487 |
+
"logps/chosen": -6.949717044830322,
|
1488 |
+
"logps/rejected": -5.171581745147705,
|
1489 |
+
"loss": 0.8516,
|
1490 |
+
"rewards/accuracies": 0.796875,
|
1491 |
+
"rewards/chosen": -12.928955078125,
|
1492 |
+
"rewards/margins": 4.445338726043701,
|
1493 |
+
"rewards/rejected": -17.37429428100586,
|
1494 |
+
"step": 99
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.5485087418580734,
|
1498 |
+
"grad_norm": 25.008431407505398,
|
1499 |
+
"learning_rate": 5.048183190619903e-07,
|
1500 |
+
"logits/chosen": -0.9874565005302429,
|
1501 |
+
"logits/rejected": -0.9811626672744751,
|
1502 |
+
"logps/chosen": -6.921389102935791,
|
1503 |
+
"logps/rejected": -5.277797698974609,
|
1504 |
+
"loss": 0.8378,
|
1505 |
+
"rewards/accuracies": 0.828125,
|
1506 |
+
"rewards/chosen": -13.19449520111084,
|
1507 |
+
"rewards/margins": 4.108977317810059,
|
1508 |
+
"rewards/rejected": -17.3034725189209,
|
1509 |
+
"step": 100
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.5539938292766541,
|
1513 |
+
"grad_norm": 27.960086992805927,
|
1514 |
+
"learning_rate": 4.951816809380097e-07,
|
1515 |
+
"logits/chosen": -1.0021039247512817,
|
1516 |
+
"logits/rejected": -0.9522125124931335,
|
1517 |
+
"logps/chosen": -7.083625793457031,
|
1518 |
+
"logps/rejected": -5.62723445892334,
|
1519 |
+
"loss": 0.669,
|
1520 |
+
"rewards/accuracies": 0.8828125,
|
1521 |
+
"rewards/chosen": -14.068085670471191,
|
1522 |
+
"rewards/margins": 3.6409800052642822,
|
1523 |
+
"rewards/rejected": -17.709064483642578,
|
1524 |
+
"step": 101
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.5594789166952349,
|
1528 |
+
"grad_norm": 30.679626728308502,
|
1529 |
+
"learning_rate": 4.855468326228638e-07,
|
1530 |
+
"logits/chosen": -1.0606987476348877,
|
1531 |
+
"logits/rejected": -1.041282296180725,
|
1532 |
+
"logps/chosen": -7.568184852600098,
|
1533 |
+
"logps/rejected": -6.082253456115723,
|
1534 |
+
"loss": 0.8745,
|
1535 |
+
"rewards/accuracies": 0.8046875,
|
1536 |
+
"rewards/chosen": -15.205633163452148,
|
1537 |
+
"rewards/margins": 3.714829206466675,
|
1538 |
+
"rewards/rejected": -18.92046356201172,
|
1539 |
+
"step": 102
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.5649640041138155,
|
1543 |
+
"grad_norm": 27.494401307007365,
|
1544 |
+
"learning_rate": 4.7591735306938134e-07,
|
1545 |
+
"logits/chosen": -1.0469098091125488,
|
1546 |
+
"logits/rejected": -0.9781535267829895,
|
1547 |
+
"logps/chosen": -7.355569839477539,
|
1548 |
+
"logps/rejected": -6.020066261291504,
|
1549 |
+
"loss": 0.7655,
|
1550 |
+
"rewards/accuracies": 0.8515625,
|
1551 |
+
"rewards/chosen": -15.050165176391602,
|
1552 |
+
"rewards/margins": 3.3387598991394043,
|
1553 |
+
"rewards/rejected": -18.388925552368164,
|
1554 |
+
"step": 103
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.5704490915323963,
|
1558 |
+
"grad_norm": 37.8050143114576,
|
1559 |
+
"learning_rate": 4.6629681923611603e-07,
|
1560 |
+
"logits/chosen": -1.049713373184204,
|
1561 |
+
"logits/rejected": -1.0141334533691406,
|
1562 |
+
"logps/chosen": -7.472883224487305,
|
1563 |
+
"logps/rejected": -6.059725284576416,
|
1564 |
+
"loss": 0.9818,
|
1565 |
+
"rewards/accuracies": 0.796875,
|
1566 |
+
"rewards/chosen": -15.149312973022461,
|
1567 |
+
"rewards/margins": 3.5328941345214844,
|
1568 |
+
"rewards/rejected": -18.682207107543945,
|
1569 |
+
"step": 104
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.575934178950977,
|
1573 |
+
"grad_norm": 24.845125832684612,
|
1574 |
+
"learning_rate": 4.5668880475865067e-07,
|
1575 |
+
"logits/chosen": -1.0235170125961304,
|
1576 |
+
"logits/rejected": -0.9582427144050598,
|
1577 |
+
"logps/chosen": -7.626412391662598,
|
1578 |
+
"logps/rejected": -6.162938594818115,
|
1579 |
+
"loss": 0.7142,
|
1580 |
+
"rewards/accuracies": 0.8515625,
|
1581 |
+
"rewards/chosen": -15.407346725463867,
|
1582 |
+
"rewards/margins": 3.658684730529785,
|
1583 |
+
"rewards/rejected": -19.066030502319336,
|
1584 |
+
"step": 105
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.5814192663695578,
|
1588 |
+
"grad_norm": 24.20853718541258,
|
1589 |
+
"learning_rate": 4.4709687862213864e-07,
|
1590 |
+
"logits/chosen": -0.9750124216079712,
|
1591 |
+
"logits/rejected": -0.9425258636474609,
|
1592 |
+
"logps/chosen": -7.844966411590576,
|
1593 |
+
"logps/rejected": -6.051673412322998,
|
1594 |
+
"loss": 0.624,
|
1595 |
+
"rewards/accuracies": 0.8671875,
|
1596 |
+
"rewards/chosen": -15.129182815551758,
|
1597 |
+
"rewards/margins": 4.4832329750061035,
|
1598 |
+
"rewards/rejected": -19.612417221069336,
|
1599 |
+
"step": 106
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.5869043537881385,
|
1603 |
+
"grad_norm": 27.32408594646776,
|
1604 |
+
"learning_rate": 4.3752460383557194e-07,
|
1605 |
+
"logits/chosen": -0.9948883056640625,
|
1606 |
+
"logits/rejected": -0.8997665643692017,
|
1607 |
+
"logps/chosen": -7.177610397338867,
|
1608 |
+
"logps/rejected": -5.7914228439331055,
|
1609 |
+
"loss": 0.779,
|
1610 |
+
"rewards/accuracies": 0.8515625,
|
1611 |
+
"rewards/chosen": -14.478557586669922,
|
1612 |
+
"rewards/margins": 3.465468406677246,
|
1613 |
+
"rewards/rejected": -17.94402503967285,
|
1614 |
+
"step": 107
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.5923894412067192,
|
1618 |
+
"grad_norm": 25.295159101372597,
|
1619 |
+
"learning_rate": 4.2797553610826797e-07,
|
1620 |
+
"logits/chosen": -0.9283576011657715,
|
1621 |
+
"logits/rejected": -0.8969117403030396,
|
1622 |
+
"logps/chosen": -7.38961935043335,
|
1623 |
+
"logps/rejected": -6.016010284423828,
|
1624 |
+
"loss": 0.8094,
|
1625 |
+
"rewards/accuracies": 0.8359375,
|
1626 |
+
"rewards/chosen": -15.04002571105957,
|
1627 |
+
"rewards/margins": 3.434022903442383,
|
1628 |
+
"rewards/rejected": -18.474048614501953,
|
1629 |
+
"step": 108
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.5978745286253,
|
1633 |
+
"grad_norm": 34.809554467100526,
|
1634 |
+
"learning_rate": 4.184532225290686e-07,
|
1635 |
+
"logits/chosen": -0.8853582739830017,
|
1636 |
+
"logits/rejected": -0.8778493404388428,
|
1637 |
+
"logps/chosen": -7.672779560089111,
|
1638 |
+
"logps/rejected": -5.923637390136719,
|
1639 |
+
"loss": 0.6594,
|
1640 |
+
"rewards/accuracies": 0.84375,
|
1641 |
+
"rewards/chosen": -14.809093475341797,
|
1642 |
+
"rewards/margins": 4.372855186462402,
|
1643 |
+
"rewards/rejected": -19.181949615478516,
|
1644 |
+
"step": 109
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 0.6033596160438807,
|
1648 |
+
"grad_norm": 37.595761539961494,
|
1649 |
+
"learning_rate": 4.089612002487428e-07,
|
1650 |
+
"logits/chosen": -0.9878619909286499,
|
1651 |
+
"logits/rejected": -0.9121577739715576,
|
1652 |
+
"logps/chosen": -7.86918830871582,
|
1653 |
+
"logps/rejected": -6.307096481323242,
|
1654 |
+
"loss": 0.9853,
|
1655 |
+
"rewards/accuracies": 0.7734375,
|
1656 |
+
"rewards/chosen": -15.767744064331055,
|
1657 |
+
"rewards/margins": 3.905228614807129,
|
1658 |
+
"rewards/rejected": -19.672971725463867,
|
1659 |
+
"step": 110
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.6088447034624614,
|
1663 |
+
"grad_norm": 19.136373017418645,
|
1664 |
+
"learning_rate": 3.995029951660776e-07,
|
1665 |
+
"logits/chosen": -0.938258945941925,
|
1666 |
+
"logits/rejected": -0.9154999256134033,
|
1667 |
+
"logps/chosen": -7.287668704986572,
|
1668 |
+
"logps/rejected": -5.683687210083008,
|
1669 |
+
"loss": 0.6273,
|
1670 |
+
"rewards/accuracies": 0.875,
|
1671 |
+
"rewards/chosen": -14.20921802520752,
|
1672 |
+
"rewards/margins": 4.009955406188965,
|
1673 |
+
"rewards/rejected": -18.21917152404785,
|
1674 |
+
"step": 111
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 0.6143297908810421,
|
1678 |
+
"grad_norm": 41.38729707458279,
|
1679 |
+
"learning_rate": 3.9008212061815207e-07,
|
1680 |
+
"logits/chosen": -0.9403737783432007,
|
1681 |
+
"logits/rejected": -0.8944230079650879,
|
1682 |
+
"logps/chosen": -7.414663314819336,
|
1683 |
+
"logps/rejected": -5.728695869445801,
|
1684 |
+
"loss": 0.5671,
|
1685 |
+
"rewards/accuracies": 0.875,
|
1686 |
+
"rewards/chosen": -14.32174015045166,
|
1687 |
+
"rewards/margins": 4.214918613433838,
|
1688 |
+
"rewards/rejected": -18.536659240722656,
|
1689 |
+
"step": 112
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.6198148782996229,
|
1693 |
+
"grad_norm": 24.324325222505287,
|
1694 |
+
"learning_rate": 3.8070207607527585e-07,
|
1695 |
+
"logits/chosen": -0.9715641736984253,
|
1696 |
+
"logits/rejected": -0.9244170784950256,
|
1697 |
+
"logps/chosen": -6.609511852264404,
|
1698 |
+
"logps/rejected": -5.317971229553223,
|
1699 |
+
"loss": 1.0423,
|
1700 |
+
"rewards/accuracies": 0.8203125,
|
1701 |
+
"rewards/chosen": -13.294927597045898,
|
1702 |
+
"rewards/margins": 3.228851795196533,
|
1703 |
+
"rewards/rejected": -16.523780822753906,
|
1704 |
+
"step": 113
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.6252999657182037,
|
1708 |
+
"grad_norm": 25.97873694518042,
|
1709 |
+
"learning_rate": 3.7136634584107783e-07,
|
1710 |
+
"logits/chosen": -1.0553674697875977,
|
1711 |
+
"logits/rejected": -0.9997435808181763,
|
1712 |
+
"logps/chosen": -7.505800247192383,
|
1713 |
+
"logps/rejected": -5.754428863525391,
|
1714 |
+
"loss": 0.7409,
|
1715 |
+
"rewards/accuracies": 0.84375,
|
1716 |
+
"rewards/chosen": -14.386072158813477,
|
1717 |
+
"rewards/margins": 4.378428936004639,
|
1718 |
+
"rewards/rejected": -18.764501571655273,
|
1719 |
+
"step": 114
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.6307850531367843,
|
1723 |
+
"grad_norm": 33.98592167333287,
|
1724 |
+
"learning_rate": 3.6207839775823047e-07,
|
1725 |
+
"logits/chosen": -0.9378336071968079,
|
1726 |
+
"logits/rejected": -0.9261949062347412,
|
1727 |
+
"logps/chosen": -6.874807357788086,
|
1728 |
+
"logps/rejected": -5.083373546600342,
|
1729 |
+
"loss": 0.8674,
|
1730 |
+
"rewards/accuracies": 0.8359375,
|
1731 |
+
"rewards/chosen": -12.708434104919434,
|
1732 |
+
"rewards/margins": 4.478583335876465,
|
1733 |
+
"rewards/rejected": -17.1870174407959,
|
1734 |
+
"step": 115
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.6362701405553651,
|
1738 |
+
"grad_norm": 27.335955275549072,
|
1739 |
+
"learning_rate": 3.5284168192028805e-07,
|
1740 |
+
"logits/chosen": -0.9258574843406677,
|
1741 |
+
"logits/rejected": -0.8993632793426514,
|
1742 |
+
"logps/chosen": -6.7075514793396,
|
1743 |
+
"logps/rejected": -5.005417346954346,
|
1744 |
+
"loss": 0.6846,
|
1745 |
+
"rewards/accuracies": 0.890625,
|
1746 |
+
"rewards/chosen": -12.513543128967285,
|
1747 |
+
"rewards/margins": 4.255335330963135,
|
1748 |
+
"rewards/rejected": -16.768878936767578,
|
1749 |
+
"step": 116
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.6417552279739458,
|
1753 |
+
"grad_norm": 36.43999913709104,
|
1754 |
+
"learning_rate": 3.4365962939011693e-07,
|
1755 |
+
"logits/chosen": -0.9867472648620605,
|
1756 |
+
"logits/rejected": -0.9383954405784607,
|
1757 |
+
"logps/chosen": -6.8381452560424805,
|
1758 |
+
"logps/rejected": -5.291529178619385,
|
1759 |
+
"loss": 0.9343,
|
1760 |
+
"rewards/accuracies": 0.8046875,
|
1761 |
+
"rewards/chosen": -13.228822708129883,
|
1762 |
+
"rewards/margins": 3.86653995513916,
|
1763 |
+
"rewards/rejected": -17.09536361694336,
|
1764 |
+
"step": 117
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 0.6472403153925266,
|
1768 |
+
"grad_norm": 43.410283610352316,
|
1769 |
+
"learning_rate": 3.345356509253958e-07,
|
1770 |
+
"logits/chosen": -0.9349948167800903,
|
1771 |
+
"logits/rejected": -0.8691989183425903,
|
1772 |
+
"logps/chosen": -6.570774555206299,
|
1773 |
+
"logps/rejected": -4.859616279602051,
|
1774 |
+
"loss": 0.6338,
|
1775 |
+
"rewards/accuracies": 0.90625,
|
1776 |
+
"rewards/chosen": -12.149040222167969,
|
1777 |
+
"rewards/margins": 4.277895927429199,
|
1778 |
+
"rewards/rejected": -16.42693519592285,
|
1779 |
+
"step": 118
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.6527254028111072,
|
1783 |
+
"grad_norm": 30.13014793522752,
|
1784 |
+
"learning_rate": 3.2547313571165967e-07,
|
1785 |
+
"logits/chosen": -0.9361096024513245,
|
1786 |
+
"logits/rejected": -0.9115648865699768,
|
1787 |
+
"logps/chosen": -6.824566841125488,
|
1788 |
+
"logps/rejected": -5.03220272064209,
|
1789 |
+
"loss": 0.7826,
|
1790 |
+
"rewards/accuracies": 0.859375,
|
1791 |
+
"rewards/chosen": -12.580507278442383,
|
1792 |
+
"rewards/margins": 4.480910778045654,
|
1793 |
+
"rewards/rejected": -17.061420440673828,
|
1794 |
+
"step": 119
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.658210490229688,
|
1798 |
+
"grad_norm": 33.220837044211905,
|
1799 |
+
"learning_rate": 3.1647545010335395e-07,
|
1800 |
+
"logits/chosen": -0.9235398173332214,
|
1801 |
+
"logits/rejected": -0.8107198476791382,
|
1802 |
+
"logps/chosen": -6.378120422363281,
|
1803 |
+
"logps/rejected": -4.839158058166504,
|
1804 |
+
"loss": 0.6904,
|
1805 |
+
"rewards/accuracies": 0.84375,
|
1806 |
+
"rewards/chosen": -12.097895622253418,
|
1807 |
+
"rewards/margins": 3.847404956817627,
|
1808 |
+
"rewards/rejected": -15.945301055908203,
|
1809 |
+
"step": 120
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.6636955776482688,
|
1813 |
+
"grad_norm": 50.56573612879948,
|
1814 |
+
"learning_rate": 3.075459363733727e-07,
|
1815 |
+
"logits/chosen": -0.8829526901245117,
|
1816 |
+
"logits/rejected": -0.8535292744636536,
|
1817 |
+
"logps/chosen": -6.172534465789795,
|
1818 |
+
"logps/rejected": -4.939080715179443,
|
1819 |
+
"loss": 0.9172,
|
1820 |
+
"rewards/accuracies": 0.7578125,
|
1821 |
+
"rewards/chosen": -12.347702026367188,
|
1822 |
+
"rewards/margins": 3.0836341381073,
|
1823 |
+
"rewards/rejected": -15.431337356567383,
|
1824 |
+
"step": 121
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.6691806650668495,
|
1828 |
+
"grad_norm": 31.870637933820483,
|
1829 |
+
"learning_rate": 2.9868791147154025e-07,
|
1830 |
+
"logits/chosen": -0.9092215895652771,
|
1831 |
+
"logits/rejected": -0.8585975170135498,
|
1832 |
+
"logps/chosen": -6.820605278015137,
|
1833 |
+
"logps/rejected": -5.349386215209961,
|
1834 |
+
"loss": 0.868,
|
1835 |
+
"rewards/accuracies": 0.8125,
|
1836 |
+
"rewards/chosen": -13.373466491699219,
|
1837 |
+
"rewards/margins": 3.678046226501465,
|
1838 |
+
"rewards/rejected": -17.051511764526367,
|
1839 |
+
"step": 122
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.6746657524854303,
|
1843 |
+
"grad_norm": 28.176132333643206,
|
1844 |
+
"learning_rate": 2.8990466579249917e-07,
|
1845 |
+
"logits/chosen": -0.8528233766555786,
|
1846 |
+
"logits/rejected": -0.7868634462356567,
|
1847 |
+
"logps/chosen": -6.514227867126465,
|
1848 |
+
"logps/rejected": -4.8763251304626465,
|
1849 |
+
"loss": 0.659,
|
1850 |
+
"rewards/accuracies": 0.84375,
|
1851 |
+
"rewards/chosen": -12.190811157226562,
|
1852 |
+
"rewards/margins": 4.094757556915283,
|
1853 |
+
"rewards/rejected": -16.28557014465332,
|
1854 |
+
"step": 123
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 0.6801508399040109,
|
1858 |
+
"grad_norm": 38.990501071087174,
|
1859 |
+
"learning_rate": 2.811994619534637e-07,
|
1860 |
+
"logits/chosen": -0.9431190490722656,
|
1861 |
+
"logits/rejected": -0.9019297957420349,
|
1862 |
+
"logps/chosen": -7.381836891174316,
|
1863 |
+
"logps/rejected": -5.60933780670166,
|
1864 |
+
"loss": 0.6562,
|
1865 |
+
"rewards/accuracies": 0.875,
|
1866 |
+
"rewards/chosen": -14.023344993591309,
|
1867 |
+
"rewards/margins": 4.431247711181641,
|
1868 |
+
"rewards/rejected": -18.454591751098633,
|
1869 |
+
"step": 124
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.6856359273225917,
|
1873 |
+
"grad_norm": 23.287789798850373,
|
1874 |
+
"learning_rate": 2.725755335822903e-07,
|
1875 |
+
"logits/chosen": -0.9163570404052734,
|
1876 |
+
"logits/rejected": -0.8643731474876404,
|
1877 |
+
"logps/chosen": -7.203619003295898,
|
1878 |
+
"logps/rejected": -5.303135395050049,
|
1879 |
+
"loss": 0.5385,
|
1880 |
+
"rewards/accuracies": 0.921875,
|
1881 |
+
"rewards/chosen": -13.25783920288086,
|
1882 |
+
"rewards/margins": 4.7512078285217285,
|
1883 |
+
"rewards/rejected": -18.00904655456543,
|
1884 |
+
"step": 125
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.6911210147411725,
|
1888 |
+
"grad_norm": 29.532793849548835,
|
1889 |
+
"learning_rate": 2.640360841163174e-07,
|
1890 |
+
"logits/chosen": -0.87614506483078,
|
1891 |
+
"logits/rejected": -0.8524197340011597,
|
1892 |
+
"logps/chosen": -6.783047676086426,
|
1893 |
+
"logps/rejected": -5.092715263366699,
|
1894 |
+
"loss": 0.6031,
|
1895 |
+
"rewards/accuracies": 0.875,
|
1896 |
+
"rewards/chosen": -12.731788635253906,
|
1897 |
+
"rewards/margins": 4.225830078125,
|
1898 |
+
"rewards/rejected": -16.957618713378906,
|
1899 |
+
"step": 126
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.6966061021597532,
|
1903 |
+
"grad_norm": 30.505873793824883,
|
1904 |
+
"learning_rate": 2.5558428561241816e-07,
|
1905 |
+
"logits/chosen": -0.947504997253418,
|
1906 |
+
"logits/rejected": -0.8782521486282349,
|
1907 |
+
"logps/chosen": -6.791367530822754,
|
1908 |
+
"logps/rejected": -5.176680564880371,
|
1909 |
+
"loss": 0.6676,
|
1910 |
+
"rewards/accuracies": 0.859375,
|
1911 |
+
"rewards/chosen": -12.941701889038086,
|
1912 |
+
"rewards/margins": 4.036717414855957,
|
1913 |
+
"rewards/rejected": -16.97842025756836,
|
1914 |
+
"step": 127
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.7020911895783339,
|
1918 |
+
"grad_norm": 39.92525272801302,
|
1919 |
+
"learning_rate": 2.472232775687119e-07,
|
1920 |
+
"logits/chosen": -0.8722752332687378,
|
1921 |
+
"logits/rejected": -0.856322705745697,
|
1922 |
+
"logps/chosen": -7.144659042358398,
|
1923 |
+
"logps/rejected": -5.182129859924316,
|
1924 |
+
"loss": 0.7803,
|
1925 |
+
"rewards/accuracies": 0.828125,
|
1926 |
+
"rewards/chosen": -12.955324172973633,
|
1927 |
+
"rewards/margins": 4.906323432922363,
|
1928 |
+
"rewards/rejected": -17.86164665222168,
|
1929 |
+
"step": 128
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.7075762769969146,
|
1933 |
+
"grad_norm": 35.65648286534799,
|
1934 |
+
"learning_rate": 2.3895616575836806e-07,
|
1935 |
+
"logits/chosen": -0.8648374676704407,
|
1936 |
+
"logits/rejected": -0.8587543964385986,
|
1937 |
+
"logps/chosen": -7.462764263153076,
|
1938 |
+
"logps/rejected": -5.415197372436523,
|
1939 |
+
"loss": 0.5901,
|
1940 |
+
"rewards/accuracies": 0.875,
|
1941 |
+
"rewards/chosen": -13.537995338439941,
|
1942 |
+
"rewards/margins": 5.1189165115356445,
|
1943 |
+
"rewards/rejected": -18.656909942626953,
|
1944 |
+
"step": 129
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 0.7130613644154954,
|
1948 |
+
"grad_norm": 36.897396094592246,
|
1949 |
+
"learning_rate": 2.3078602107593897e-07,
|
1950 |
+
"logits/chosen": -0.9551251530647278,
|
1951 |
+
"logits/rejected": -0.9301334619522095,
|
1952 |
+
"logps/chosen": -7.187896251678467,
|
1953 |
+
"logps/rejected": -5.676419258117676,
|
1954 |
+
"loss": 0.7432,
|
1955 |
+
"rewards/accuracies": 0.8515625,
|
1956 |
+
"rewards/chosen": -14.191046714782715,
|
1957 |
+
"rewards/margins": 3.7786920070648193,
|
1958 |
+
"rewards/rejected": -17.96973991394043,
|
1959 |
+
"step": 130
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.7185464518340761,
|
1963 |
+
"grad_norm": 23.791455410978802,
|
1964 |
+
"learning_rate": 2.2271587839664668e-07,
|
1965 |
+
"logits/chosen": -0.8816163539886475,
|
1966 |
+
"logits/rejected": -0.8654621839523315,
|
1967 |
+
"logps/chosen": -7.688798427581787,
|
1968 |
+
"logps/rejected": -5.900554180145264,
|
1969 |
+
"loss": 0.7962,
|
1970 |
+
"rewards/accuracies": 0.828125,
|
1971 |
+
"rewards/chosen": -14.751386642456055,
|
1972 |
+
"rewards/margins": 4.470608711242676,
|
1973 |
+
"rewards/rejected": -19.221996307373047,
|
1974 |
+
"step": 131
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 0.7240315392526568,
|
1978 |
+
"grad_norm": 25.229342149520836,
|
1979 |
+
"learning_rate": 2.1474873544905203e-07,
|
1980 |
+
"logits/chosen": -0.9233815670013428,
|
1981 |
+
"logits/rejected": -0.8769809007644653,
|
1982 |
+
"logps/chosen": -7.945870876312256,
|
1983 |
+
"logps/rejected": -6.068084239959717,
|
1984 |
+
"loss": 0.7871,
|
1985 |
+
"rewards/accuracies": 0.859375,
|
1986 |
+
"rewards/chosen": -15.170208930969238,
|
1987 |
+
"rewards/margins": 4.694468975067139,
|
1988 |
+
"rewards/rejected": -19.86467933654785,
|
1989 |
+
"step": 132
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 0.7295166266712376,
|
1993 |
+
"grad_norm": 24.072357862431296,
|
1994 |
+
"learning_rate": 2.0688755170151994e-07,
|
1995 |
+
"logits/chosen": -0.9093427062034607,
|
1996 |
+
"logits/rejected": -0.8254431486129761,
|
1997 |
+
"logps/chosen": -7.6159138679504395,
|
1998 |
+
"logps/rejected": -6.035447597503662,
|
1999 |
+
"loss": 0.7131,
|
2000 |
+
"rewards/accuracies": 0.8671875,
|
2001 |
+
"rewards/chosen": -15.08862018585205,
|
2002 |
+
"rewards/margins": 3.951165199279785,
|
2003 |
+
"rewards/rejected": -19.039783477783203,
|
2004 |
+
"step": 133
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.7350017140898183,
|
2008 |
+
"grad_norm": 27.574889812468303,
|
2009 |
+
"learning_rate": 1.991352472628978e-07,
|
2010 |
+
"logits/chosen": -0.9855005741119385,
|
2011 |
+
"logits/rejected": -0.8852315545082092,
|
2012 |
+
"logps/chosen": -8.272013664245605,
|
2013 |
+
"logps/rejected": -6.531748294830322,
|
2014 |
+
"loss": 0.5673,
|
2015 |
+
"rewards/accuracies": 0.8828125,
|
2016 |
+
"rewards/chosen": -16.329370498657227,
|
2017 |
+
"rewards/margins": 4.350663661956787,
|
2018 |
+
"rewards/rejected": -20.68003273010254,
|
2019 |
+
"step": 134
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.7404868015083991,
|
2023 |
+
"grad_norm": 38.0684454587543,
|
2024 |
+
"learning_rate": 1.9149470179781529e-07,
|
2025 |
+
"logits/chosen": -0.8634744882583618,
|
2026 |
+
"logits/rejected": -0.8510404825210571,
|
2027 |
+
"logps/chosen": -8.125703811645508,
|
2028 |
+
"logps/rejected": -6.487473011016846,
|
2029 |
+
"loss": 0.9743,
|
2030 |
+
"rewards/accuracies": 0.8125,
|
2031 |
+
"rewards/chosen": -16.21868324279785,
|
2032 |
+
"rewards/margins": 4.095577239990234,
|
2033 |
+
"rewards/rejected": -20.314258575439453,
|
2034 |
+
"step": 135
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 0.7459718889269797,
|
2038 |
+
"grad_norm": 48.36799803983576,
|
2039 |
+
"learning_rate": 1.8396875345700496e-07,
|
2040 |
+
"logits/chosen": -0.9214343428611755,
|
2041 |
+
"logits/rejected": -0.8962255120277405,
|
2042 |
+
"logps/chosen": -8.190770149230957,
|
2043 |
+
"logps/rejected": -6.314955711364746,
|
2044 |
+
"loss": 0.5596,
|
2045 |
+
"rewards/accuracies": 0.8984375,
|
2046 |
+
"rewards/chosen": -15.78738784790039,
|
2047 |
+
"rewards/margins": 4.689537048339844,
|
2048 |
+
"rewards/rejected": -20.476924896240234,
|
2049 |
+
"step": 136
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.7514569763455605,
|
2053 |
+
"grad_norm": 44.16548053204111,
|
2054 |
+
"learning_rate": 1.76560197823046e-07,
|
2055 |
+
"logits/chosen": -0.919052004814148,
|
2056 |
+
"logits/rejected": -0.8849231600761414,
|
2057 |
+
"logps/chosen": -8.452275276184082,
|
2058 |
+
"logps/rejected": -6.598462104797363,
|
2059 |
+
"loss": 0.7156,
|
2060 |
+
"rewards/accuracies": 0.875,
|
2061 |
+
"rewards/chosen": -16.496156692504883,
|
2062 |
+
"rewards/margins": 4.634530544281006,
|
2063 |
+
"rewards/rejected": -21.130685806274414,
|
2064 |
+
"step": 137
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 0.7569420637641412,
|
2068 |
+
"grad_norm": 21.109729731146004,
|
2069 |
+
"learning_rate": 1.6927178687191952e-07,
|
2070 |
+
"logits/chosen": -0.9427747130393982,
|
2071 |
+
"logits/rejected": -0.8983960151672363,
|
2072 |
+
"logps/chosen": -8.133773803710938,
|
2073 |
+
"logps/rejected": -6.293461322784424,
|
2074 |
+
"loss": 0.5443,
|
2075 |
+
"rewards/accuracies": 0.875,
|
2076 |
+
"rewards/chosen": -15.733654022216797,
|
2077 |
+
"rewards/margins": 4.600779056549072,
|
2078 |
+
"rewards/rejected": -20.334434509277344,
|
2079 |
+
"step": 138
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 0.762427151182722,
|
2083 |
+
"grad_norm": 24.71923168446529,
|
2084 |
+
"learning_rate": 1.6210622795076167e-07,
|
2085 |
+
"logits/chosen": -0.9024847149848938,
|
2086 |
+
"logits/rejected": -0.8320090770721436,
|
2087 |
+
"logps/chosen": -7.866386413574219,
|
2088 |
+
"logps/rejected": -5.999449729919434,
|
2089 |
+
"loss": 0.7399,
|
2090 |
+
"rewards/accuracies": 0.8359375,
|
2091 |
+
"rewards/chosen": -14.998624801635742,
|
2092 |
+
"rewards/margins": 4.6673407554626465,
|
2093 |
+
"rewards/rejected": -19.665966033935547,
|
2094 |
+
"step": 139
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 0.7679122386013028,
|
2098 |
+
"grad_norm": 28.05368903550952,
|
2099 |
+
"learning_rate": 1.5506618277219408e-07,
|
2100 |
+
"logits/chosen": -0.9084888100624084,
|
2101 |
+
"logits/rejected": -0.8153257966041565,
|
2102 |
+
"logps/chosen": -8.255277633666992,
|
2103 |
+
"logps/rejected": -6.376511096954346,
|
2104 |
+
"loss": 0.6289,
|
2105 |
+
"rewards/accuracies": 0.859375,
|
2106 |
+
"rewards/chosen": -15.941277503967285,
|
2107 |
+
"rewards/margins": 4.696916580200195,
|
2108 |
+
"rewards/rejected": -20.638193130493164,
|
2109 |
+
"step": 140
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.7733973260198834,
|
2113 |
+
"grad_norm": 25.708532161588263,
|
2114 |
+
"learning_rate": 1.481542664256075e-07,
|
2115 |
+
"logits/chosen": -0.8618345856666565,
|
2116 |
+
"logits/rejected": -0.7895917892456055,
|
2117 |
+
"logps/chosen": -7.592902660369873,
|
2118 |
+
"logps/rejected": -5.800815582275391,
|
2119 |
+
"loss": 0.623,
|
2120 |
+
"rewards/accuracies": 0.8671875,
|
2121 |
+
"rewards/chosen": -14.50204086303711,
|
2122 |
+
"rewards/margins": 4.480217933654785,
|
2123 |
+
"rewards/rejected": -18.982257843017578,
|
2124 |
+
"step": 141
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 0.7788824134384642,
|
2128 |
+
"grad_norm": 24.709393184243222,
|
2129 |
+
"learning_rate": 1.413730464057616e-07,
|
2130 |
+
"logits/chosen": -0.8121160268783569,
|
2131 |
+
"logits/rejected": -0.7455395460128784,
|
2132 |
+
"logps/chosen": -7.604070663452148,
|
2133 |
+
"logps/rejected": -5.874716281890869,
|
2134 |
+
"loss": 0.6692,
|
2135 |
+
"rewards/accuracies": 0.8359375,
|
2136 |
+
"rewards/chosen": -14.68679141998291,
|
2137 |
+
"rewards/margins": 4.323384761810303,
|
2138 |
+
"rewards/rejected": -19.010177612304688,
|
2139 |
+
"step": 142
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.7843675008570449,
|
2143 |
+
"grad_norm": 38.97698904003614,
|
2144 |
+
"learning_rate": 1.3472504165906612e-07,
|
2145 |
+
"logits/chosen": -0.8006829619407654,
|
2146 |
+
"logits/rejected": -0.7394671440124512,
|
2147 |
+
"logps/chosen": -7.116863250732422,
|
2148 |
+
"logps/rejected": -5.581884384155273,
|
2149 |
+
"loss": 0.6601,
|
2150 |
+
"rewards/accuracies": 0.890625,
|
2151 |
+
"rewards/chosen": -13.954710960388184,
|
2152 |
+
"rewards/margins": 3.837446928024292,
|
2153 |
+
"rewards/rejected": -17.792160034179688,
|
2154 |
+
"step": 143
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 0.7898525882756257,
|
2158 |
+
"grad_norm": 29.640146576501934,
|
2159 |
+
"learning_rate": 1.2821272164789543e-07,
|
2160 |
+
"logits/chosen": -0.8447168469429016,
|
2161 |
+
"logits/rejected": -0.7728930115699768,
|
2162 |
+
"logps/chosen": -7.501246452331543,
|
2163 |
+
"logps/rejected": -5.655298709869385,
|
2164 |
+
"loss": 0.564,
|
2165 |
+
"rewards/accuracies": 0.890625,
|
2166 |
+
"rewards/chosen": -14.138248443603516,
|
2167 |
+
"rewards/margins": 4.6148681640625,
|
2168 |
+
"rewards/rejected": -18.753116607666016,
|
2169 |
+
"step": 144
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 0.7953376756942063,
|
2173 |
+
"grad_norm": 22.947844708118026,
|
2174 |
+
"learning_rate": 1.2183850543328312e-07,
|
2175 |
+
"logits/chosen": -0.8897333741188049,
|
2176 |
+
"logits/rejected": -0.8205296397209167,
|
2177 |
+
"logps/chosen": -7.398487091064453,
|
2178 |
+
"logps/rejected": -5.790860652923584,
|
2179 |
+
"loss": 0.7226,
|
2180 |
+
"rewards/accuracies": 0.8515625,
|
2181 |
+
"rewards/chosen": -14.477151870727539,
|
2182 |
+
"rewards/margins": 4.019064426422119,
|
2183 |
+
"rewards/rejected": -18.4962158203125,
|
2184 |
+
"step": 145
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 0.8008227631127871,
|
2188 |
+
"grad_norm": 27.798903132552176,
|
2189 |
+
"learning_rate": 1.1560476077634069e-07,
|
2190 |
+
"logits/chosen": -0.7919908761978149,
|
2191 |
+
"logits/rejected": -0.8394799828529358,
|
2192 |
+
"logps/chosen": -7.839868068695068,
|
2193 |
+
"logps/rejected": -5.743566036224365,
|
2194 |
+
"loss": 0.544,
|
2195 |
+
"rewards/accuracies": 0.875,
|
2196 |
+
"rewards/chosen": -14.358914375305176,
|
2197 |
+
"rewards/margins": 5.240755081176758,
|
2198 |
+
"rewards/rejected": -19.59967041015625,
|
2199 |
+
"step": 146
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.8063078505313679,
|
2203 |
+
"grad_norm": 29.92809246962988,
|
2204 |
+
"learning_rate": 1.0951380325872977e-07,
|
2205 |
+
"logits/chosen": -0.8169230818748474,
|
2206 |
+
"logits/rejected": -0.7812893986701965,
|
2207 |
+
"logps/chosen": -7.359820365905762,
|
2208 |
+
"logps/rejected": -5.6241607666015625,
|
2209 |
+
"loss": 0.7967,
|
2210 |
+
"rewards/accuracies": 0.828125,
|
2211 |
+
"rewards/chosen": -14.060400009155273,
|
2212 |
+
"rewards/margins": 4.3391499519348145,
|
2213 |
+
"rewards/rejected": -18.39954948425293,
|
2214 |
+
"step": 147
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.8117929379499486,
|
2218 |
+
"grad_norm": 27.792210529581745,
|
2219 |
+
"learning_rate": 1.0356789542251936e-07,
|
2220 |
+
"logits/chosen": -0.8669033050537109,
|
2221 |
+
"logits/rejected": -0.8605407476425171,
|
2222 |
+
"logps/chosen": -8.198552131652832,
|
2223 |
+
"logps/rejected": -6.282137393951416,
|
2224 |
+
"loss": 0.8025,
|
2225 |
+
"rewards/accuracies": 0.84375,
|
2226 |
+
"rewards/chosen": -15.705344200134277,
|
2227 |
+
"rewards/margins": 4.791035175323486,
|
2228 |
+
"rewards/rejected": -20.496379852294922,
|
2229 |
+
"step": 148
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.8172780253685293,
|
2233 |
+
"grad_norm": 28.277349818001756,
|
2234 |
+
"learning_rate": 9.776924592974256e-08,
|
2235 |
+
"logits/chosen": -0.8328518867492676,
|
2236 |
+
"logits/rejected": -0.8236594796180725,
|
2237 |
+
"logps/chosen": -7.214673042297363,
|
2238 |
+
"logps/rejected": -5.481906414031982,
|
2239 |
+
"loss": 0.7674,
|
2240 |
+
"rewards/accuracies": 0.8515625,
|
2241 |
+
"rewards/chosen": -13.704765319824219,
|
2242 |
+
"rewards/margins": 4.331914901733398,
|
2243 |
+
"rewards/rejected": -18.03668212890625,
|
2244 |
+
"step": 149
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 0.82276311278711,
|
2248 |
+
"grad_norm": 29.007836684575707,
|
2249 |
+
"learning_rate": 9.212000874196952e-08,
|
2250 |
+
"logits/chosen": -0.8581669330596924,
|
2251 |
+
"logits/rejected": -0.8325639367103577,
|
2252 |
+
"logps/chosen": -7.351170539855957,
|
2253 |
+
"logps/rejected": -5.474079608917236,
|
2254 |
+
"loss": 0.6909,
|
2255 |
+
"rewards/accuracies": 0.8671875,
|
2256 |
+
"rewards/chosen": -13.685198783874512,
|
2257 |
+
"rewards/margins": 4.692727088928223,
|
2258 |
+
"rewards/rejected": -18.377925872802734,
|
2259 |
+
"step": 150
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 0.8282482002056908,
|
2263 |
+
"grad_norm": 43.71571457854729,
|
2264 |
+
"learning_rate": 8.662228232019875e-08,
|
2265 |
+
"logits/chosen": -0.8501139879226685,
|
2266 |
+
"logits/rejected": -0.8618481755256653,
|
2267 |
+
"logps/chosen": -7.359824180603027,
|
2268 |
+
"logps/rejected": -5.42210054397583,
|
2269 |
+
"loss": 0.7332,
|
2270 |
+
"rewards/accuracies": 0.8359375,
|
2271 |
+
"rewards/chosen": -13.555251121520996,
|
2272 |
+
"rewards/margins": 4.844309329986572,
|
2273 |
+
"rewards/rejected": -18.399559020996094,
|
2274 |
+
"step": 151
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 0.8337332876242715,
|
2278 |
+
"grad_norm": 46.33073864540601,
|
2279 |
+
"learning_rate": 8.127810884536402e-08,
|
2280 |
+
"logits/chosen": -0.853046715259552,
|
2281 |
+
"logits/rejected": -0.8423393964767456,
|
2282 |
+
"logps/chosen": -6.985077857971191,
|
2283 |
+
"logps/rejected": -5.142387390136719,
|
2284 |
+
"loss": 0.6407,
|
2285 |
+
"rewards/accuracies": 0.875,
|
2286 |
+
"rewards/chosen": -12.855968475341797,
|
2287 |
+
"rewards/margins": 4.606726169586182,
|
2288 |
+
"rewards/rejected": -17.462696075439453,
|
2289 |
+
"step": 152
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 0.8392183750428522,
|
2293 |
+
"grad_norm": 42.89209343669169,
|
2294 |
+
"learning_rate": 7.608947345974759e-08,
|
2295 |
+
"logits/chosen": -0.920865535736084,
|
2296 |
+
"logits/rejected": -0.8836889266967773,
|
2297 |
+
"logps/chosen": -7.042182445526123,
|
2298 |
+
"logps/rejected": -5.48915958404541,
|
2299 |
+
"loss": 0.8117,
|
2300 |
+
"rewards/accuracies": 0.8359375,
|
2301 |
+
"rewards/chosen": -13.722898483276367,
|
2302 |
+
"rewards/margins": 3.882556915283203,
|
2303 |
+
"rewards/rejected": -17.605453491210938,
|
2304 |
+
"step": 153
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 0.844703462461433,
|
2308 |
+
"grad_norm": 37.7037024205324,
|
2309 |
+
"learning_rate": 7.105830352958142e-08,
|
2310 |
+
"logits/chosen": -0.9472789764404297,
|
2311 |
+
"logits/rejected": -0.9106646180152893,
|
2312 |
+
"logps/chosen": -7.459850311279297,
|
2313 |
+
"logps/rejected": -5.479578971862793,
|
2314 |
+
"loss": 0.6658,
|
2315 |
+
"rewards/accuracies": 0.8671875,
|
2316 |
+
"rewards/chosen": -13.698948860168457,
|
2317 |
+
"rewards/margins": 4.950677871704102,
|
2318 |
+
"rewards/rejected": -18.649625778198242,
|
2319 |
+
"step": 154
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.8501885498800137,
|
2323 |
+
"grad_norm": 24.0763873064064,
|
2324 |
+
"learning_rate": 6.618646792910893e-08,
|
2325 |
+
"logits/chosen": -0.8774456977844238,
|
2326 |
+
"logits/rejected": -0.7841386795043945,
|
2327 |
+
"logps/chosen": -6.863981246948242,
|
2328 |
+
"logps/rejected": -5.015853404998779,
|
2329 |
+
"loss": 0.5643,
|
2330 |
+
"rewards/accuracies": 0.8984375,
|
2331 |
+
"rewards/chosen": -12.539634704589844,
|
2332 |
+
"rewards/margins": 4.620318412780762,
|
2333 |
+
"rewards/rejected": -17.15995216369629,
|
2334 |
+
"step": 155
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.8556736372985945,
|
2338 |
+
"grad_norm": 32.66084265444344,
|
2339 |
+
"learning_rate": 6.147577634637413e-08,
|
2340 |
+
"logits/chosen": -0.9129813313484192,
|
2341 |
+
"logits/rejected": -0.8859033584594727,
|
2342 |
+
"logps/chosen": -7.296760082244873,
|
2343 |
+
"logps/rejected": -5.64870548248291,
|
2344 |
+
"loss": 0.7727,
|
2345 |
+
"rewards/accuracies": 0.8359375,
|
2346 |
+
"rewards/chosen": -14.121763229370117,
|
2347 |
+
"rewards/margins": 4.120136737823486,
|
2348 |
+
"rewards/rejected": -18.241899490356445,
|
2349 |
+
"step": 156
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.8611587247171751,
|
2353 |
+
"grad_norm": 23.94997399437051,
|
2354 |
+
"learning_rate": 5.692797861099718e-08,
|
2355 |
+
"logits/chosen": -0.8945199847221375,
|
2356 |
+
"logits/rejected": -0.8570997714996338,
|
2357 |
+
"logps/chosen": -6.75827693939209,
|
2358 |
+
"logps/rejected": -5.06813907623291,
|
2359 |
+
"loss": 0.5738,
|
2360 |
+
"rewards/accuracies": 0.875,
|
2361 |
+
"rewards/chosen": -12.670347213745117,
|
2362 |
+
"rewards/margins": 4.22534704208374,
|
2363 |
+
"rewards/rejected": -16.895692825317383,
|
2364 |
+
"step": 157
|
2365 |
+
},
|
2366 |
+
{
|
2367 |
+
"epoch": 0.8666438121357559,
|
2368 |
+
"grad_norm": 24.150699682280717,
|
2369 |
+
"learning_rate": 5.25447640441834e-08,
|
2370 |
+
"logits/chosen": -0.954617977142334,
|
2371 |
+
"logits/rejected": -0.8557642102241516,
|
2372 |
+
"logps/chosen": -7.347589492797852,
|
2373 |
+
"logps/rejected": -5.5732340812683105,
|
2374 |
+
"loss": 0.6284,
|
2375 |
+
"rewards/accuracies": 0.8671875,
|
2376 |
+
"rewards/chosen": -13.933087348937988,
|
2377 |
+
"rewards/margins": 4.435887813568115,
|
2378 |
+
"rewards/rejected": -18.368972778320312,
|
2379 |
+
"step": 158
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 0.8721288995543367,
|
2383 |
+
"grad_norm": 36.75533433702862,
|
2384 |
+
"learning_rate": 4.832776083120982e-08,
|
2385 |
+
"logits/chosen": -0.9205527305603027,
|
2386 |
+
"logits/rejected": -0.8304504752159119,
|
2387 |
+
"logps/chosen": -7.045970439910889,
|
2388 |
+
"logps/rejected": -5.256443023681641,
|
2389 |
+
"loss": 0.6382,
|
2390 |
+
"rewards/accuracies": 0.8828125,
|
2391 |
+
"rewards/chosen": -13.141106605529785,
|
2392 |
+
"rewards/margins": 4.473819732666016,
|
2393 |
+
"rewards/rejected": -17.614925384521484,
|
2394 |
+
"step": 159
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 0.8776139869729174,
|
2398 |
+
"grad_norm": 31.994585110678578,
|
2399 |
+
"learning_rate": 4.427853541662091e-08,
|
2400 |
+
"logits/chosen": -0.9841543436050415,
|
2401 |
+
"logits/rejected": -0.8539234399795532,
|
2402 |
+
"logps/chosen": -7.1274094581604,
|
2403 |
+
"logps/rejected": -5.204132080078125,
|
2404 |
+
"loss": 0.6011,
|
2405 |
+
"rewards/accuracies": 0.875,
|
2406 |
+
"rewards/chosen": -13.010330200195312,
|
2407 |
+
"rewards/margins": 4.808194160461426,
|
2408 |
+
"rewards/rejected": -17.818523406982422,
|
2409 |
+
"step": 160
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 0.8830990743914982,
|
2413 |
+
"grad_norm": 28.795886036839306,
|
2414 |
+
"learning_rate": 4.039859192235778e-08,
|
2415 |
+
"logits/chosen": -0.9625253677368164,
|
2416 |
+
"logits/rejected": -0.9089056849479675,
|
2417 |
+
"logps/chosen": -7.486809253692627,
|
2418 |
+
"logps/rejected": -5.702870845794678,
|
2419 |
+
"loss": 0.8583,
|
2420 |
+
"rewards/accuracies": 0.8203125,
|
2421 |
+
"rewards/chosen": -14.257177352905273,
|
2422 |
+
"rewards/margins": 4.459846496582031,
|
2423 |
+
"rewards/rejected": -18.717023849487305,
|
2424 |
+
"step": 161
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 0.8885841618100788,
|
2428 |
+
"grad_norm": 26.44205968756603,
|
2429 |
+
"learning_rate": 3.668937158903901e-08,
|
2430 |
+
"logits/chosen": -0.9169929027557373,
|
2431 |
+
"logits/rejected": -0.8381502628326416,
|
2432 |
+
"logps/chosen": -7.5406494140625,
|
2433 |
+
"logps/rejected": -5.6013288497924805,
|
2434 |
+
"loss": 0.5664,
|
2435 |
+
"rewards/accuracies": 0.8984375,
|
2436 |
+
"rewards/chosen": -14.003321647644043,
|
2437 |
+
"rewards/margins": 4.848302364349365,
|
2438 |
+
"rewards/rejected": -18.85162353515625,
|
2439 |
+
"step": 162
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 0.8940692492286596,
|
2443 |
+
"grad_norm": 27.304950853911894,
|
2444 |
+
"learning_rate": 3.3152252240598086e-08,
|
2445 |
+
"logits/chosen": -0.9413248896598816,
|
2446 |
+
"logits/rejected": -0.8493109941482544,
|
2447 |
+
"logps/chosen": -7.453137397766113,
|
2448 |
+
"logps/rejected": -5.501208782196045,
|
2449 |
+
"loss": 0.5001,
|
2450 |
+
"rewards/accuracies": 0.90625,
|
2451 |
+
"rewards/chosen": -13.753022193908691,
|
2452 |
+
"rewards/margins": 4.87982177734375,
|
2453 |
+
"rewards/rejected": -18.632844924926758,
|
2454 |
+
"step": 163
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 0.8995543366472403,
|
2458 |
+
"grad_norm": 20.074530093573202,
|
2459 |
+
"learning_rate": 2.978854777247841e-08,
|
2460 |
+
"logits/chosen": -0.9120803475379944,
|
2461 |
+
"logits/rejected": -0.8509462475776672,
|
2462 |
+
"logps/chosen": -7.397423267364502,
|
2463 |
+
"logps/rejected": -5.588208198547363,
|
2464 |
+
"loss": 0.6246,
|
2465 |
+
"rewards/accuracies": 0.875,
|
2466 |
+
"rewards/chosen": -13.97052001953125,
|
2467 |
+
"rewards/margins": 4.523037433624268,
|
2468 |
+
"rewards/rejected": -18.49355697631836,
|
2469 |
+
"step": 164
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 0.905039424065821,
|
2473 |
+
"grad_norm": 26.09353600189251,
|
2474 |
+
"learning_rate": 2.6599507663574384e-08,
|
2475 |
+
"logits/chosen": -0.952299952507019,
|
2476 |
+
"logits/rejected": -0.8652746677398682,
|
2477 |
+
"logps/chosen": -7.684518814086914,
|
2478 |
+
"logps/rejected": -5.83120584487915,
|
2479 |
+
"loss": 0.5817,
|
2480 |
+
"rewards/accuracies": 0.890625,
|
2481 |
+
"rewards/chosen": -14.57801628112793,
|
2482 |
+
"rewards/margins": 4.633281707763672,
|
2483 |
+
"rewards/rejected": -19.21129608154297,
|
2484 |
+
"step": 165
|
2485 |
+
},
|
2486 |
+
{
|
2487 |
+
"epoch": 0.9105245114844018,
|
2488 |
+
"grad_norm": 38.37398443400821,
|
2489 |
+
"learning_rate": 2.358631651210141e-08,
|
2490 |
+
"logits/chosen": -0.8585479259490967,
|
2491 |
+
"logits/rejected": -0.8270218372344971,
|
2492 |
+
"logps/chosen": -7.32467794418335,
|
2493 |
+
"logps/rejected": -5.463205337524414,
|
2494 |
+
"loss": 0.5111,
|
2495 |
+
"rewards/accuracies": 0.8828125,
|
2496 |
+
"rewards/chosen": -13.658012390136719,
|
2497 |
+
"rewards/margins": 4.653683185577393,
|
2498 |
+
"rewards/rejected": -18.311695098876953,
|
2499 |
+
"step": 166
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 0.9160095989029825,
|
2503 |
+
"grad_norm": 17.666453011965785,
|
2504 |
+
"learning_rate": 2.0750093595565733e-08,
|
2505 |
+
"logits/chosen": -0.8858319520950317,
|
2506 |
+
"logits/rejected": -0.8542614579200745,
|
2507 |
+
"logps/chosen": -7.348204612731934,
|
2508 |
+
"logps/rejected": -5.504924774169922,
|
2509 |
+
"loss": 0.6247,
|
2510 |
+
"rewards/accuracies": 0.8671875,
|
2511 |
+
"rewards/chosen": -13.762311935424805,
|
2512 |
+
"rewards/margins": 4.608198165893555,
|
2513 |
+
"rewards/rejected": -18.37051010131836,
|
2514 |
+
"step": 167
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 0.9214946863215633,
|
2518 |
+
"grad_norm": 19.09191014386972,
|
2519 |
+
"learning_rate": 1.8091892454998593e-08,
|
2520 |
+
"logits/chosen": -0.8447603583335876,
|
2521 |
+
"logits/rejected": -0.8495924472808838,
|
2522 |
+
"logps/chosen": -7.054547309875488,
|
2523 |
+
"logps/rejected": -5.083424091339111,
|
2524 |
+
"loss": 0.6335,
|
2525 |
+
"rewards/accuracies": 0.8828125,
|
2526 |
+
"rewards/chosen": -12.708559036254883,
|
2527 |
+
"rewards/margins": 4.927809238433838,
|
2528 |
+
"rewards/rejected": -17.636367797851562,
|
2529 |
+
"step": 168
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.926979773740144,
|
2533 |
+
"grad_norm": 38.37416244304177,
|
2534 |
+
"learning_rate": 1.5612700503608967e-08,
|
2535 |
+
"logits/chosen": -0.95904541015625,
|
2536 |
+
"logits/rejected": -0.874359130859375,
|
2537 |
+
"logps/chosen": -8.061529159545898,
|
2538 |
+
"logps/rejected": -6.1823248863220215,
|
2539 |
+
"loss": 0.79,
|
2540 |
+
"rewards/accuracies": 0.8359375,
|
2541 |
+
"rewards/chosen": -15.455812454223633,
|
2542 |
+
"rewards/margins": 4.698009967803955,
|
2543 |
+
"rewards/rejected": -20.153823852539062,
|
2544 |
+
"step": 169
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 0.9324648611587247,
|
2548 |
+
"grad_norm": 20.52317809637831,
|
2549 |
+
"learning_rate": 1.3313438659999399e-08,
|
2550 |
+
"logits/chosen": -0.8840410113334656,
|
2551 |
+
"logits/rejected": -0.8565166592597961,
|
2552 |
+
"logps/chosen": -7.426989555358887,
|
2553 |
+
"logps/rejected": -5.389143943786621,
|
2554 |
+
"loss": 0.6073,
|
2555 |
+
"rewards/accuracies": 0.8671875,
|
2556 |
+
"rewards/chosen": -13.472861289978027,
|
2557 |
+
"rewards/margins": 5.094613552093506,
|
2558 |
+
"rewards/rejected": -18.567476272583008,
|
2559 |
+
"step": 170
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 0.9379499485773054,
|
2563 |
+
"grad_norm": 28.898112504649927,
|
2564 |
+
"learning_rate": 1.119496100608297e-08,
|
2565 |
+
"logits/chosen": -0.902927815914154,
|
2566 |
+
"logits/rejected": -0.8713952302932739,
|
2567 |
+
"logps/chosen": -7.5428547859191895,
|
2568 |
+
"logps/rejected": -5.551333904266357,
|
2569 |
+
"loss": 0.6478,
|
2570 |
+
"rewards/accuracies": 0.8984375,
|
2571 |
+
"rewards/chosen": -13.878334045410156,
|
2572 |
+
"rewards/margins": 4.978802680969238,
|
2573 |
+
"rewards/rejected": -18.857135772705078,
|
2574 |
+
"step": 171
|
2575 |
+
},
|
2576 |
+
{
|
2577 |
+
"epoch": 0.9434350359958862,
|
2578 |
+
"grad_norm": 30.615659518253594,
|
2579 |
+
"learning_rate": 9.258054469825972e-09,
|
2580 |
+
"logits/chosen": -0.9755229949951172,
|
2581 |
+
"logits/rejected": -0.8522156476974487,
|
2582 |
+
"logps/chosen": -7.569779396057129,
|
2583 |
+
"logps/rejected": -5.832912445068359,
|
2584 |
+
"loss": 0.4678,
|
2585 |
+
"rewards/accuracies": 0.921875,
|
2586 |
+
"rewards/chosen": -14.582280158996582,
|
2587 |
+
"rewards/margins": 4.34216833114624,
|
2588 |
+
"rewards/rejected": -18.924448013305664,
|
2589 |
+
"step": 172
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 0.948920123414467,
|
2593 |
+
"grad_norm": 24.650975590320186,
|
2594 |
+
"learning_rate": 7.503438532937168e-09,
|
2595 |
+
"logits/chosen": -0.8953875303268433,
|
2596 |
+
"logits/rejected": -0.8538772463798523,
|
2597 |
+
"logps/chosen": -7.302203178405762,
|
2598 |
+
"logps/rejected": -5.746313095092773,
|
2599 |
+
"loss": 0.8124,
|
2600 |
+
"rewards/accuracies": 0.8515625,
|
2601 |
+
"rewards/chosen": -14.365781784057617,
|
2602 |
+
"rewards/margins": 3.8897247314453125,
|
2603 |
+
"rewards/rejected": -18.255508422851562,
|
2604 |
+
"step": 173
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 0.9544052108330476,
|
2608 |
+
"grad_norm": 22.56008245408754,
|
2609 |
+
"learning_rate": 5.931764963608865e-09,
|
2610 |
+
"logits/chosen": -0.8796699047088623,
|
2611 |
+
"logits/rejected": -0.8065083026885986,
|
2612 |
+
"logps/chosen": -7.606590270996094,
|
2613 |
+
"logps/rejected": -5.541936874389648,
|
2614 |
+
"loss": 0.5972,
|
2615 |
+
"rewards/accuracies": 0.875,
|
2616 |
+
"rewards/chosen": -13.854841232299805,
|
2617 |
+
"rewards/margins": 5.1616339683532715,
|
2618 |
+
"rewards/rejected": -19.016477584838867,
|
2619 |
+
"step": 174
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 0.9598902982516284,
|
2623 |
+
"grad_norm": 27.265075122995274,
|
2624 |
+
"learning_rate": 4.543617574412184e-09,
|
2625 |
+
"logits/chosen": -0.9127550721168518,
|
2626 |
+
"logits/rejected": -0.8750625848770142,
|
2627 |
+
"logps/chosen": -7.915278434753418,
|
2628 |
+
"logps/rejected": -6.025564670562744,
|
2629 |
+
"loss": 0.8845,
|
2630 |
+
"rewards/accuracies": 0.8046875,
|
2631 |
+
"rewards/chosen": -15.063911437988281,
|
2632 |
+
"rewards/margins": 4.724285125732422,
|
2633 |
+
"rewards/rejected": -19.788196563720703,
|
2634 |
+
"step": 175
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 0.9653753856702091,
|
2638 |
+
"grad_norm": 28.882962456249174,
|
2639 |
+
"learning_rate": 3.3395120054343086e-09,
|
2640 |
+
"logits/chosen": -0.9111831188201904,
|
2641 |
+
"logits/rejected": -0.8427572250366211,
|
2642 |
+
"logps/chosen": -7.206770420074463,
|
2643 |
+
"logps/rejected": -5.539353847503662,
|
2644 |
+
"loss": 0.7588,
|
2645 |
+
"rewards/accuracies": 0.8203125,
|
2646 |
+
"rewards/chosen": -13.848384857177734,
|
2647 |
+
"rewards/margins": 4.168540000915527,
|
2648 |
+
"rewards/rejected": -18.016923904418945,
|
2649 |
+
"step": 176
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 0.9708604730887899,
|
2653 |
+
"grad_norm": 31.271655213972466,
|
2654 |
+
"learning_rate": 2.3198955327393686e-09,
|
2655 |
+
"logits/chosen": -0.9476001262664795,
|
2656 |
+
"logits/rejected": -0.8903546333312988,
|
2657 |
+
"logps/chosen": -7.501628875732422,
|
2658 |
+
"logps/rejected": -5.69838809967041,
|
2659 |
+
"loss": 0.603,
|
2660 |
+
"rewards/accuracies": 0.875,
|
2661 |
+
"rewards/chosen": -14.245970726013184,
|
2662 |
+
"rewards/margins": 4.508101463317871,
|
2663 |
+
"rewards/rejected": -18.754070281982422,
|
2664 |
+
"step": 177
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 0.9763455605073705,
|
2668 |
+
"grad_norm": 27.6286427872623,
|
2669 |
+
"learning_rate": 1.4851469022233997e-09,
|
2670 |
+
"logits/chosen": -0.9050301313400269,
|
2671 |
+
"logits/rejected": -0.8429163694381714,
|
2672 |
+
"logps/chosen": -7.289128303527832,
|
2673 |
+
"logps/rejected": -5.459531784057617,
|
2674 |
+
"loss": 0.478,
|
2675 |
+
"rewards/accuracies": 0.921875,
|
2676 |
+
"rewards/chosen": -13.648829460144043,
|
2677 |
+
"rewards/margins": 4.5739922523498535,
|
2678 |
+
"rewards/rejected": -18.222822189331055,
|
2679 |
+
"step": 178
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 0.9818306479259513,
|
2683 |
+
"grad_norm": 33.536490419312095,
|
2684 |
+
"learning_rate": 8.35576188926046e-10,
|
2685 |
+
"logits/chosen": -0.8602910041809082,
|
2686 |
+
"logits/rejected": -0.8685486912727356,
|
2687 |
+
"logps/chosen": -7.6485795974731445,
|
2688 |
+
"logps/rejected": -5.617213249206543,
|
2689 |
+
"loss": 0.5532,
|
2690 |
+
"rewards/accuracies": 0.8984375,
|
2691 |
+
"rewards/chosen": -14.043033599853516,
|
2692 |
+
"rewards/margins": 5.078416347503662,
|
2693 |
+
"rewards/rejected": -19.12145233154297,
|
2694 |
+
"step": 179
|
2695 |
+
},
|
2696 |
+
{
|
2697 |
+
"epoch": 0.9873157353445321,
|
2698 |
+
"grad_norm": 36.03602197080609,
|
2699 |
+
"learning_rate": 3.71424681850141e-10,
|
2700 |
+
"logits/chosen": -0.9029905200004578,
|
2701 |
+
"logits/rejected": -0.8996679186820984,
|
2702 |
+
"logps/chosen": -7.467672348022461,
|
2703 |
+
"logps/rejected": -5.66632080078125,
|
2704 |
+
"loss": 0.692,
|
2705 |
+
"rewards/accuracies": 0.84375,
|
2706 |
+
"rewards/chosen": -14.165802001953125,
|
2707 |
+
"rewards/margins": 4.503378391265869,
|
2708 |
+
"rewards/rejected": -18.66918182373047,
|
2709 |
+
"step": 180
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 0.9928008227631128,
|
2713 |
+
"grad_norm": 30.463376086047504,
|
2714 |
+
"learning_rate": 9.286479433257e-11,
|
2715 |
+
"logits/chosen": -0.9386723041534424,
|
2716 |
+
"logits/rejected": -0.8105076551437378,
|
2717 |
+
"logps/chosen": -7.705523490905762,
|
2718 |
+
"logps/rejected": -5.895651817321777,
|
2719 |
+
"loss": 0.6545,
|
2720 |
+
"rewards/accuracies": 0.84375,
|
2721 |
+
"rewards/chosen": -14.739130020141602,
|
2722 |
+
"rewards/margins": 4.524680137634277,
|
2723 |
+
"rewards/rejected": -19.263809204101562,
|
2724 |
+
"step": 181
|
2725 |
+
},
|
2726 |
+
{
|
2727 |
+
"epoch": 0.9982859101816935,
|
2728 |
+
"grad_norm": 27.85120971616897,
|
2729 |
+
"learning_rate": 0.0,
|
2730 |
+
"logits/chosen": -0.8981151580810547,
|
2731 |
+
"logits/rejected": -0.8777621388435364,
|
2732 |
+
"logps/chosen": -8.53371524810791,
|
2733 |
+
"logps/rejected": -5.803772449493408,
|
2734 |
+
"loss": 0.3779,
|
2735 |
+
"rewards/accuracies": 0.953125,
|
2736 |
+
"rewards/chosen": -14.509430885314941,
|
2737 |
+
"rewards/margins": 6.824857234954834,
|
2738 |
+
"rewards/rejected": -21.33428955078125,
|
2739 |
+
"step": 182
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.9982859101816935,
|
2743 |
+
"step": 182,
|
2744 |
+
"total_flos": 58779245903872.0,
|
2745 |
+
"train_loss": 1.1193010831599708,
|
2746 |
+
"train_runtime": 13670.339,
|
2747 |
+
"train_samples_per_second": 1.707,
|
2748 |
+
"train_steps_per_second": 0.013
|
2749 |
+
}
|
2750 |
+
],
|
2751 |
+
"logging_steps": 1,
|
2752 |
+
"max_steps": 182,
|
2753 |
+
"num_input_tokens_seen": 0,
|
2754 |
+
"num_train_epochs": 1,
|
2755 |
+
"save_steps": 182,
|
2756 |
+
"stateful_callbacks": {
|
2757 |
+
"TrainerControl": {
|
2758 |
+
"args": {
|
2759 |
+
"should_epoch_stop": false,
|
2760 |
+
"should_evaluate": false,
|
2761 |
+
"should_log": false,
|
2762 |
+
"should_save": true,
|
2763 |
+
"should_training_stop": true
|
2764 |
+
},
|
2765 |
+
"attributes": {}
|
2766 |
+
}
|
2767 |
+
},
|
2768 |
+
"total_flos": 58779245903872.0,
|
2769 |
+
"train_batch_size": 1,
|
2770 |
+
"trial_name": null,
|
2771 |
+
"trial_params": null
|
2772 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4143040e12d17e7ce35ebd0bfd82f6da325a56498f0606da029c43ea7027edb
|
3 |
+
size 7288
|
training_loss.png
ADDED
training_rewards_accuracies.png
ADDED
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|