Upload folder using huggingface_hub
Browse files- README.md +75 -0
- all_results.json +22 -0
- config.json +29 -0
- eval_results.json +16 -0
- generation_config.json +12 -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 +298 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- train_results.json +9 -0
- trainer_state.json +1588 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: llama3
|
4 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
5 |
+
tags:
|
6 |
+
- alignment-handbook
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- simonycl/Meta-Llama-3-8B-Instruct_metamath-Meta-Llama-3-8B-Instruct-annotate-judge-5
|
10 |
+
model-index:
|
11 |
+
- name: llama-3-8b-instruct-metamath-agg-judge
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# llama-3-8b-instruct-metamath-agg-judge
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the simonycl/Meta-Llama-3-8B-Instruct_metamath-Meta-Llama-3-8B-Instruct-annotate-judge-5 dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.7013
|
23 |
+
- Rewards/chosen: -4.0945
|
24 |
+
- Rewards/rejected: -5.8632
|
25 |
+
- Rewards/accuracies: 0.7060
|
26 |
+
- Rewards/margins: 1.7687
|
27 |
+
- Logps/rejected: -705.5204
|
28 |
+
- Logps/chosen: -502.4185
|
29 |
+
- Logits/rejected: -0.8140
|
30 |
+
- Logits/chosen: -1.0704
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 5e-07
|
50 |
+
- train_batch_size: 1
|
51 |
+
- eval_batch_size: 2
|
52 |
+
- seed: 42
|
53 |
+
- distributed_type: multi-GPU
|
54 |
+
- num_devices: 4
|
55 |
+
- gradient_accumulation_steps: 32
|
56 |
+
- total_train_batch_size: 128
|
57 |
+
- total_eval_batch_size: 8
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: cosine
|
60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 1
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
66 |
+
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
67 |
+
| 0.2753 | 0.7882 | 400 | 0.7013 | -4.0945 | -5.8632 | 0.7060 | 1.7687 | -705.5204 | -502.4185 | -0.8140 | -1.0704 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.44.2
|
73 |
+
- Pytorch 2.4.0+cu121
|
74 |
+
- Datasets 2.21.0
|
75 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990762978015888,
|
3 |
+
"eval_logits/chosen": -1.0541683435440063,
|
4 |
+
"eval_logits/rejected": -0.8055270910263062,
|
5 |
+
"eval_logps/chosen": -522.3192749023438,
|
6 |
+
"eval_logps/rejected": -728.829833984375,
|
7 |
+
"eval_loss": 0.7119433283805847,
|
8 |
+
"eval_rewards/accuracies": 0.7080000042915344,
|
9 |
+
"eval_rewards/chosen": -4.293468475341797,
|
10 |
+
"eval_rewards/margins": 1.8028156757354736,
|
11 |
+
"eval_rewards/rejected": -6.096283435821533,
|
12 |
+
"eval_runtime": 191.3844,
|
13 |
+
"eval_samples": 1999,
|
14 |
+
"eval_samples_per_second": 10.445,
|
15 |
+
"eval_steps_per_second": 1.306,
|
16 |
+
"total_flos": 0.0,
|
17 |
+
"train_loss": 0.3691282767280789,
|
18 |
+
"train_runtime": 28319.5283,
|
19 |
+
"train_samples": 64953,
|
20 |
+
"train_samples_per_second": 2.294,
|
21 |
+
"train_steps_per_second": 0.018
|
22 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 500000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.44.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 128256
|
29 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990762978015888,
|
3 |
+
"eval_logits/chosen": -1.0541683435440063,
|
4 |
+
"eval_logits/rejected": -0.8055270910263062,
|
5 |
+
"eval_logps/chosen": -522.3192749023438,
|
6 |
+
"eval_logps/rejected": -728.829833984375,
|
7 |
+
"eval_loss": 0.7119433283805847,
|
8 |
+
"eval_rewards/accuracies": 0.7080000042915344,
|
9 |
+
"eval_rewards/chosen": -4.293468475341797,
|
10 |
+
"eval_rewards/margins": 1.8028156757354736,
|
11 |
+
"eval_rewards/rejected": -6.096283435821533,
|
12 |
+
"eval_runtime": 191.3844,
|
13 |
+
"eval_samples": 1999,
|
14 |
+
"eval_samples_per_second": 10.445,
|
15 |
+
"eval_steps_per_second": 1.306
|
16 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"max_length": 4096,
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.44.2"
|
12 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5af39f67d8c36ee2ffd1845f50deab7f67429510bfedd1c1b2632c408cfa1bdb
|
3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b631ebd1ce3f0b3b46308e39a8856203a024eaa1b6ccc93f4363532dfa2445
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50868b7c6a4d494f813bf31fcb0c497c93f39f17847391ff620db2dea4ab83c9
|
3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40eb5af599118dcf1b4e53e8b8559c6ff7cb8f24cb652e15661f03ff4bf9eb94
|
3 |
+
size 1168138808
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 16060522496
|
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.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
296 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
297 |
+
}
|
298 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|reserved_special_token_2|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_3|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|reserved_special_token_4|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|reserved_special_token_5|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_6|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_7|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_8|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_9|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_10|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_11|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_12|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_13|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_14|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_15|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_16|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_17|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_18|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_19|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_20|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_21|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_22|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_23|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_24|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_25|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_26|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_27|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_28|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_29|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_30|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_31|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_32|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_33|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_34|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_35|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_36|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_37|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_38|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_39|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_40|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_41|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_42|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_43|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_44|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_45|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_46|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_47|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_48|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_49|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_50|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_51|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_52|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_53|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_54|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_55|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_56|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_57|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_58|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_59|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_60|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_61|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_62|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_63|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_64|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_65|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_66|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_67|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_68|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_69|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_70|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_71|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_72|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_73|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_74|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_75|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_76|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_77|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_78|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_79|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_80|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_81|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_82|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_83|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_84|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_85|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_86|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_87|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_88|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_89|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_90|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_91|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_92|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_93|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_94|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_95|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_96|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_97|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_98|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_99|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_100|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_101|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_102|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_103|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_104|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_105|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_106|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_107|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_108|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_109|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_110|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_111|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_112|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_113|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_114|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_115|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_116|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_117|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_118|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_119|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_120|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_121|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_122|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_123|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_124|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_125|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_126|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_127|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_128|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_129|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_130|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_131|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_132|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_133|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_134|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_135|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_136|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_137|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_138|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_139|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_140|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_141|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_142|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_143|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_144|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_145|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_146|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_147|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_148|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_149|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_150|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_151|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_152|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_153|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_154|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_155|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_156|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_157|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_158|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_159|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_160|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_161|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_162|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_163|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_164|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_165|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_166|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_167|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_168|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_169|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_170|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_171|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_172|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_173|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_174|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_175|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_176|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_177|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_178|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_179|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_180|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_181|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_182|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_183|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_184|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_185|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_186|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_187|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_188|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_189|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_190|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_191|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_192|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_193|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_194|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_195|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_196|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_197|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_198|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_199|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_200|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_201|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_202|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_203|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_204|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_205|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_206|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_207|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_208|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_209|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_210|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_211|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_212|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_213|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_214|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_215|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_216|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_217|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_218|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_219|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_220|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_221|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_222|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_223|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_224|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_225|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_226|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_227|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_228|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_229|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_230|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_231|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_232|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_233|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_234|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_235|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_236|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_237|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_238|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_239|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_240|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_241|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_242|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_243|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_244|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_245|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_246|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_247|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_248|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_249|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_250|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 2048,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990762978015888,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.3691282767280789,
|
5 |
+
"train_runtime": 28319.5283,
|
6 |
+
"train_samples": 64953,
|
7 |
+
"train_samples_per_second": 2.294,
|
8 |
+
"train_steps_per_second": 0.018
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9990762978015888,
|
5 |
+
"eval_steps": 400,
|
6 |
+
"global_step": 507,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.001970564689943962,
|
13 |
+
"grad_norm": 3.539861305637653,
|
14 |
+
"learning_rate": 9.803921568627451e-09,
|
15 |
+
"logits/chosen": -0.03196336328983307,
|
16 |
+
"logits/rejected": -0.15967734158039093,
|
17 |
+
"logps/chosen": -99.96153259277344,
|
18 |
+
"logps/rejected": -93.94828033447266,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.00985282344971981,
|
28 |
+
"grad_norm": 3.74004975366523,
|
29 |
+
"learning_rate": 4.901960784313725e-08,
|
30 |
+
"logits/chosen": -0.042198292911052704,
|
31 |
+
"logits/rejected": -0.34676456451416016,
|
32 |
+
"logps/chosen": -112.20402526855469,
|
33 |
+
"logps/rejected": -101.837646484375,
|
34 |
+
"loss": 0.6932,
|
35 |
+
"rewards/accuracies": 0.421875,
|
36 |
+
"rewards/chosen": 0.0011955354129895568,
|
37 |
+
"rewards/margins": 0.0004524323157966137,
|
38 |
+
"rewards/rejected": 0.0007431029807776213,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01970564689943962,
|
43 |
+
"grad_norm": 3.5769285168326417,
|
44 |
+
"learning_rate": 9.80392156862745e-08,
|
45 |
+
"logits/chosen": -0.16411139070987701,
|
46 |
+
"logits/rejected": -0.29173845052719116,
|
47 |
+
"logps/chosen": -94.1719741821289,
|
48 |
+
"logps/rejected": -96.02313232421875,
|
49 |
+
"loss": 0.6933,
|
50 |
+
"rewards/accuracies": 0.4375,
|
51 |
+
"rewards/chosen": 4.2173640395049006e-05,
|
52 |
+
"rewards/margins": -0.001043520518578589,
|
53 |
+
"rewards/rejected": 0.001085694064386189,
|
54 |
+
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.02955847034915943,
|
58 |
+
"grad_norm": 3.3653465070579673,
|
59 |
+
"learning_rate": 1.4705882352941175e-07,
|
60 |
+
"logits/chosen": -0.07717452943325043,
|
61 |
+
"logits/rejected": -0.3865337371826172,
|
62 |
+
"logps/chosen": -100.953125,
|
63 |
+
"logps/rejected": -92.61229705810547,
|
64 |
+
"loss": 0.6931,
|
65 |
+
"rewards/accuracies": 0.512499988079071,
|
66 |
+
"rewards/chosen": -0.00025451680994592607,
|
67 |
+
"rewards/margins": -0.0001873960136435926,
|
68 |
+
"rewards/rejected": -6.712078902637586e-05,
|
69 |
+
"step": 15
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03941129379887924,
|
73 |
+
"grad_norm": 3.373649973394512,
|
74 |
+
"learning_rate": 1.96078431372549e-07,
|
75 |
+
"logits/chosen": -0.0971444696187973,
|
76 |
+
"logits/rejected": -0.35578858852386475,
|
77 |
+
"logps/chosen": -106.3487319946289,
|
78 |
+
"logps/rejected": -102.8326416015625,
|
79 |
+
"loss": 0.6929,
|
80 |
+
"rewards/accuracies": 0.48750001192092896,
|
81 |
+
"rewards/chosen": -0.0003346280718687922,
|
82 |
+
"rewards/margins": 0.0001382694172207266,
|
83 |
+
"rewards/rejected": -0.00047289757640101016,
|
84 |
+
"step": 20
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.049264117248599054,
|
88 |
+
"grad_norm": 3.224755352064536,
|
89 |
+
"learning_rate": 2.4509803921568627e-07,
|
90 |
+
"logits/chosen": -0.10794611275196075,
|
91 |
+
"logits/rejected": -0.29162880778312683,
|
92 |
+
"logps/chosen": -99.07095336914062,
|
93 |
+
"logps/rejected": -95.20055389404297,
|
94 |
+
"loss": 0.6927,
|
95 |
+
"rewards/accuracies": 0.6187499761581421,
|
96 |
+
"rewards/chosen": 0.00042314338497817516,
|
97 |
+
"rewards/margins": 0.0012360246619209647,
|
98 |
+
"rewards/rejected": -0.0008128813351504505,
|
99 |
+
"step": 25
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.05911694069831886,
|
103 |
+
"grad_norm": 3.444342352448875,
|
104 |
+
"learning_rate": 2.941176470588235e-07,
|
105 |
+
"logits/chosen": -0.12300117313861847,
|
106 |
+
"logits/rejected": -0.27830368280410767,
|
107 |
+
"logps/chosen": -105.83805847167969,
|
108 |
+
"logps/rejected": -104.1891860961914,
|
109 |
+
"loss": 0.6914,
|
110 |
+
"rewards/accuracies": 0.75,
|
111 |
+
"rewards/chosen": 0.002045437227934599,
|
112 |
+
"rewards/margins": 0.004656647797673941,
|
113 |
+
"rewards/rejected": -0.002611211035400629,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.06896976414803867,
|
118 |
+
"grad_norm": 3.5299163808469496,
|
119 |
+
"learning_rate": 3.431372549019608e-07,
|
120 |
+
"logits/chosen": -0.03614411875605583,
|
121 |
+
"logits/rejected": -0.3109976053237915,
|
122 |
+
"logps/chosen": -99.59745788574219,
|
123 |
+
"logps/rejected": -98.72537231445312,
|
124 |
+
"loss": 0.6903,
|
125 |
+
"rewards/accuracies": 0.6875,
|
126 |
+
"rewards/chosen": 0.000885780609678477,
|
127 |
+
"rewards/margins": 0.0061457473784685135,
|
128 |
+
"rewards/rejected": -0.005259966477751732,
|
129 |
+
"step": 35
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07882258759775848,
|
133 |
+
"grad_norm": 3.9275316344127242,
|
134 |
+
"learning_rate": 3.92156862745098e-07,
|
135 |
+
"logits/chosen": -0.08717192709445953,
|
136 |
+
"logits/rejected": -0.30741095542907715,
|
137 |
+
"logps/chosen": -99.77064514160156,
|
138 |
+
"logps/rejected": -96.07014465332031,
|
139 |
+
"loss": 0.6882,
|
140 |
+
"rewards/accuracies": 0.6312500238418579,
|
141 |
+
"rewards/chosen": -0.0018755150958895683,
|
142 |
+
"rewards/margins": 0.007984376512467861,
|
143 |
+
"rewards/rejected": -0.00985989160835743,
|
144 |
+
"step": 40
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.0886754110474783,
|
148 |
+
"grad_norm": 3.5883285534109493,
|
149 |
+
"learning_rate": 4.4117647058823526e-07,
|
150 |
+
"logits/chosen": -0.032524555921554565,
|
151 |
+
"logits/rejected": -0.3046508729457855,
|
152 |
+
"logps/chosen": -96.41732788085938,
|
153 |
+
"logps/rejected": -95.6390380859375,
|
154 |
+
"loss": 0.6842,
|
155 |
+
"rewards/accuracies": 0.762499988079071,
|
156 |
+
"rewards/chosen": -0.005956724286079407,
|
157 |
+
"rewards/margins": 0.01741139218211174,
|
158 |
+
"rewards/rejected": -0.023368116468191147,
|
159 |
+
"step": 45
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.09852823449719811,
|
163 |
+
"grad_norm": 3.3794927211727392,
|
164 |
+
"learning_rate": 4.901960784313725e-07,
|
165 |
+
"logits/chosen": -0.12240082025527954,
|
166 |
+
"logits/rejected": -0.28499796986579895,
|
167 |
+
"logps/chosen": -106.6746597290039,
|
168 |
+
"logps/rejected": -104.4252700805664,
|
169 |
+
"loss": 0.6811,
|
170 |
+
"rewards/accuracies": 0.731249988079071,
|
171 |
+
"rewards/chosen": -0.017990436404943466,
|
172 |
+
"rewards/margins": 0.024439355358481407,
|
173 |
+
"rewards/rejected": -0.042429789900779724,
|
174 |
+
"step": 50
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.10838105794691791,
|
178 |
+
"grad_norm": 3.8844805866458234,
|
179 |
+
"learning_rate": 4.999050767562379e-07,
|
180 |
+
"logits/chosen": -0.06140371039509773,
|
181 |
+
"logits/rejected": -0.36449694633483887,
|
182 |
+
"logps/chosen": -112.74903869628906,
|
183 |
+
"logps/rejected": -107.06253814697266,
|
184 |
+
"loss": 0.6729,
|
185 |
+
"rewards/accuracies": 0.706250011920929,
|
186 |
+
"rewards/chosen": -0.048891425132751465,
|
187 |
+
"rewards/margins": 0.04517052322626114,
|
188 |
+
"rewards/rejected": -0.0940619483590126,
|
189 |
+
"step": 55
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.11823388139663772,
|
193 |
+
"grad_norm": 4.246075688346676,
|
194 |
+
"learning_rate": 4.99519574616467e-07,
|
195 |
+
"logits/chosen": -0.08420858532190323,
|
196 |
+
"logits/rejected": -0.2296031415462494,
|
197 |
+
"logps/chosen": -106.52708435058594,
|
198 |
+
"logps/rejected": -114.71268463134766,
|
199 |
+
"loss": 0.6598,
|
200 |
+
"rewards/accuracies": 0.7562500238418579,
|
201 |
+
"rewards/chosen": -0.0871507003903389,
|
202 |
+
"rewards/margins": 0.07720854133367538,
|
203 |
+
"rewards/rejected": -0.16435924172401428,
|
204 |
+
"step": 60
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.12808670484635754,
|
208 |
+
"grad_norm": 4.078056870628684,
|
209 |
+
"learning_rate": 4.988380179235842e-07,
|
210 |
+
"logits/chosen": -0.04726668819785118,
|
211 |
+
"logits/rejected": -0.2177656590938568,
|
212 |
+
"logps/chosen": -117.36442565917969,
|
213 |
+
"logps/rejected": -122.31159973144531,
|
214 |
+
"loss": 0.6488,
|
215 |
+
"rewards/accuracies": 0.737500011920929,
|
216 |
+
"rewards/chosen": -0.15060417354106903,
|
217 |
+
"rewards/margins": 0.0838489979505539,
|
218 |
+
"rewards/rejected": -0.23445317149162292,
|
219 |
+
"step": 65
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.13793952829607734,
|
223 |
+
"grad_norm": 3.820719733352528,
|
224 |
+
"learning_rate": 4.978612153434526e-07,
|
225 |
+
"logits/chosen": -0.05979006737470627,
|
226 |
+
"logits/rejected": -0.19735023379325867,
|
227 |
+
"logps/chosen": -124.60560607910156,
|
228 |
+
"logps/rejected": -155.1808624267578,
|
229 |
+
"loss": 0.6318,
|
230 |
+
"rewards/accuracies": 0.75,
|
231 |
+
"rewards/chosen": -0.2229953557252884,
|
232 |
+
"rewards/margins": 0.31397417187690735,
|
233 |
+
"rewards/rejected": -0.5369695425033569,
|
234 |
+
"step": 70
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.14779235174579716,
|
238 |
+
"grad_norm": 5.031693747430946,
|
239 |
+
"learning_rate": 4.965903258506806e-07,
|
240 |
+
"logits/chosen": -0.059552647173404694,
|
241 |
+
"logits/rejected": -0.19415248930454254,
|
242 |
+
"logps/chosen": -136.63735961914062,
|
243 |
+
"logps/rejected": -191.6803741455078,
|
244 |
+
"loss": 0.6086,
|
245 |
+
"rewards/accuracies": 0.7749999761581421,
|
246 |
+
"rewards/chosen": -0.35170239210128784,
|
247 |
+
"rewards/margins": 0.49619174003601074,
|
248 |
+
"rewards/rejected": -0.8478941917419434,
|
249 |
+
"step": 75
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.15764517519551696,
|
253 |
+
"grad_norm": 5.160412651014448,
|
254 |
+
"learning_rate": 4.950268573535011e-07,
|
255 |
+
"logits/chosen": -0.0038110867608338594,
|
256 |
+
"logits/rejected": -0.15630409121513367,
|
257 |
+
"logps/chosen": -147.3404083251953,
|
258 |
+
"logps/rejected": -173.90728759765625,
|
259 |
+
"loss": 0.5967,
|
260 |
+
"rewards/accuracies": 0.737500011920929,
|
261 |
+
"rewards/chosen": -0.4520920217037201,
|
262 |
+
"rewards/margins": 0.27063217759132385,
|
263 |
+
"rewards/rejected": -0.7227243185043335,
|
264 |
+
"step": 80
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.16749799864523676,
|
268 |
+
"grad_norm": 6.145536461291785,
|
269 |
+
"learning_rate": 4.93172664904641e-07,
|
270 |
+
"logits/chosen": 0.01297803781926632,
|
271 |
+
"logits/rejected": -0.1908242255449295,
|
272 |
+
"logps/chosen": -167.2682647705078,
|
273 |
+
"logps/rejected": -198.43177795410156,
|
274 |
+
"loss": 0.5701,
|
275 |
+
"rewards/accuracies": 0.7437499761581421,
|
276 |
+
"rewards/chosen": -0.589021623134613,
|
277 |
+
"rewards/margins": 0.3708820641040802,
|
278 |
+
"rewards/rejected": -0.9599035978317261,
|
279 |
+
"step": 85
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.1773508220949566,
|
283 |
+
"grad_norm": 60.6627948159201,
|
284 |
+
"learning_rate": 4.910299485003033e-07,
|
285 |
+
"logits/chosen": -0.007486692164093256,
|
286 |
+
"logits/rejected": -0.18025372922420502,
|
287 |
+
"logps/chosen": -183.25140380859375,
|
288 |
+
"logps/rejected": -288.912109375,
|
289 |
+
"loss": 0.5755,
|
290 |
+
"rewards/accuracies": 0.71875,
|
291 |
+
"rewards/chosen": -0.8218961954116821,
|
292 |
+
"rewards/margins": 1.0762311220169067,
|
293 |
+
"rewards/rejected": -1.8981273174285889,
|
294 |
+
"step": 90
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.1872036455446764,
|
298 |
+
"grad_norm": 6.619891594866407,
|
299 |
+
"learning_rate": 4.886012504698769e-07,
|
300 |
+
"logits/chosen": -0.00334315188229084,
|
301 |
+
"logits/rejected": -0.3066111207008362,
|
302 |
+
"logps/chosen": -222.06753540039062,
|
303 |
+
"logps/rejected": -272.4456481933594,
|
304 |
+
"loss": 0.5397,
|
305 |
+
"rewards/accuracies": 0.737500011920929,
|
306 |
+
"rewards/chosen": -1.1969377994537354,
|
307 |
+
"rewards/margins": 0.5773923397064209,
|
308 |
+
"rewards/rejected": -1.7743301391601562,
|
309 |
+
"step": 95
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.19705646899439622,
|
313 |
+
"grad_norm": 6.740434195327616,
|
314 |
+
"learning_rate": 4.858894524594652e-07,
|
315 |
+
"logits/chosen": -0.1177954450249672,
|
316 |
+
"logits/rejected": -0.3193029761314392,
|
317 |
+
"logps/chosen": -216.84396362304688,
|
318 |
+
"logps/rejected": -431.8846740722656,
|
319 |
+
"loss": 0.5071,
|
320 |
+
"rewards/accuracies": 0.800000011920929,
|
321 |
+
"rewards/chosen": -1.120563268661499,
|
322 |
+
"rewards/margins": 2.212986707687378,
|
323 |
+
"rewards/rejected": -3.333550214767456,
|
324 |
+
"step": 100
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.20690929244411602,
|
328 |
+
"grad_norm": 7.617693374089276,
|
329 |
+
"learning_rate": 4.828977720128198e-07,
|
330 |
+
"logits/chosen": -0.1505376100540161,
|
331 |
+
"logits/rejected": -0.3399549126625061,
|
332 |
+
"logps/chosen": -235.60617065429688,
|
333 |
+
"logps/rejected": -358.7390441894531,
|
334 |
+
"loss": 0.497,
|
335 |
+
"rewards/accuracies": 0.706250011920929,
|
336 |
+
"rewards/chosen": -1.3088951110839844,
|
337 |
+
"rewards/margins": 1.3302855491638184,
|
338 |
+
"rewards/rejected": -2.639180898666382,
|
339 |
+
"step": 105
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.21676211589383582,
|
343 |
+
"grad_norm": 7.105788785064987,
|
344 |
+
"learning_rate": 4.796297587537285e-07,
|
345 |
+
"logits/chosen": -0.1506040096282959,
|
346 |
+
"logits/rejected": -0.3250656723976135,
|
347 |
+
"logps/chosen": -257.82464599609375,
|
348 |
+
"logps/rejected": -416.75958251953125,
|
349 |
+
"loss": 0.4453,
|
350 |
+
"rewards/accuracies": 0.800000011920929,
|
351 |
+
"rewards/chosen": -1.5325710773468018,
|
352 |
+
"rewards/margins": 1.6099077463150024,
|
353 |
+
"rewards/rejected": -3.1424789428710938,
|
354 |
+
"step": 110
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.22661493934355564,
|
358 |
+
"grad_norm": 8.60769452133117,
|
359 |
+
"learning_rate": 4.760892901743944e-07,
|
360 |
+
"logits/chosen": -0.13159573078155518,
|
361 |
+
"logits/rejected": -0.3428110182285309,
|
362 |
+
"logps/chosen": -300.0444030761719,
|
363 |
+
"logps/rejected": -514.811279296875,
|
364 |
+
"loss": 0.4607,
|
365 |
+
"rewards/accuracies": 0.8187500238418579,
|
366 |
+
"rewards/chosen": -1.9326972961425781,
|
367 |
+
"rewards/margins": 2.217697858810425,
|
368 |
+
"rewards/rejected": -4.150395393371582,
|
369 |
+
"step": 115
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.23646776279327544,
|
373 |
+
"grad_norm": 10.209138794878942,
|
374 |
+
"learning_rate": 4.7228056703479626e-07,
|
375 |
+
"logits/chosen": -0.16759036481380463,
|
376 |
+
"logits/rejected": -0.3990747332572937,
|
377 |
+
"logps/chosen": -299.72705078125,
|
378 |
+
"logps/rejected": -433.87823486328125,
|
379 |
+
"loss": 0.4381,
|
380 |
+
"rewards/accuracies": 0.78125,
|
381 |
+
"rewards/chosen": -1.9569202661514282,
|
382 |
+
"rewards/margins": 1.37308669090271,
|
383 |
+
"rewards/rejected": -3.3300068378448486,
|
384 |
+
"step": 120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.24632058624299527,
|
388 |
+
"grad_norm": 28.609743111268017,
|
389 |
+
"learning_rate": 4.6820810837849535e-07,
|
390 |
+
"logits/chosen": -0.20535437762737274,
|
391 |
+
"logits/rejected": -0.4542999267578125,
|
392 |
+
"logps/chosen": -307.52362060546875,
|
393 |
+
"logps/rejected": -520.55322265625,
|
394 |
+
"loss": 0.4403,
|
395 |
+
"rewards/accuracies": 0.8187500238418579,
|
396 |
+
"rewards/chosen": -2.0457329750061035,
|
397 |
+
"rewards/margins": 2.181645393371582,
|
398 |
+
"rewards/rejected": -4.227377891540527,
|
399 |
+
"step": 125
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.25617340969271507,
|
403 |
+
"grad_norm": 11.650217681846684,
|
404 |
+
"learning_rate": 4.63876746170797e-07,
|
405 |
+
"logits/chosen": -0.23113389313220978,
|
406 |
+
"logits/rejected": -0.47989240288734436,
|
407 |
+
"logps/chosen": -344.0136413574219,
|
408 |
+
"logps/rejected": -512.1621704101562,
|
409 |
+
"loss": 0.474,
|
410 |
+
"rewards/accuracies": 0.8062499761581421,
|
411 |
+
"rewards/chosen": -2.392538547515869,
|
412 |
+
"rewards/margins": 1.7528173923492432,
|
413 |
+
"rewards/rejected": -4.145355701446533,
|
414 |
+
"step": 130
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.2660262331424349,
|
418 |
+
"grad_norm": 12.280394789341818,
|
419 |
+
"learning_rate": 4.592916195656321e-07,
|
420 |
+
"logits/chosen": -0.2849624454975128,
|
421 |
+
"logits/rejected": -0.4641537070274353,
|
422 |
+
"logps/chosen": -360.0565490722656,
|
423 |
+
"logps/rejected": -593.3041381835938,
|
424 |
+
"loss": 0.4143,
|
425 |
+
"rewards/accuracies": 0.862500011920929,
|
426 |
+
"rewards/chosen": -2.587618112564087,
|
427 |
+
"rewards/margins": 2.348435401916504,
|
428 |
+
"rewards/rejected": -4.936053276062012,
|
429 |
+
"step": 135
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.27587905659215467,
|
433 |
+
"grad_norm": 11.781977035196428,
|
434 |
+
"learning_rate": 4.544581688079602e-07,
|
435 |
+
"logits/chosen": -0.27669793367385864,
|
436 |
+
"logits/rejected": -0.4249224066734314,
|
437 |
+
"logps/chosen": -346.13238525390625,
|
438 |
+
"logps/rejected": -542.8922119140625,
|
439 |
+
"loss": 0.3764,
|
440 |
+
"rewards/accuracies": 0.8062499761581421,
|
441 |
+
"rewards/chosen": -2.43330454826355,
|
442 |
+
"rewards/margins": 1.9707410335540771,
|
443 |
+
"rewards/rejected": -4.404046058654785,
|
444 |
+
"step": 140
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.2857318800418745,
|
448 |
+
"grad_norm": 12.725521218797944,
|
449 |
+
"learning_rate": 4.493821287789272e-07,
|
450 |
+
"logits/chosen": -0.29486262798309326,
|
451 |
+
"logits/rejected": -0.45644649863243103,
|
452 |
+
"logps/chosen": -350.2372131347656,
|
453 |
+
"logps/rejected": -533.0991821289062,
|
454 |
+
"loss": 0.3874,
|
455 |
+
"rewards/accuracies": 0.8500000238418579,
|
456 |
+
"rewards/chosen": -2.510737657546997,
|
457 |
+
"rewards/margins": 1.8067106008529663,
|
458 |
+
"rewards/rejected": -4.317447662353516,
|
459 |
+
"step": 145
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.2955847034915943,
|
463 |
+
"grad_norm": 10.47948759187309,
|
464 |
+
"learning_rate": 4.4406952219143934e-07,
|
465 |
+
"logits/chosen": -0.20662228763103485,
|
466 |
+
"logits/rejected": -0.47787055373191833,
|
467 |
+
"logps/chosen": -331.3938903808594,
|
468 |
+
"logps/rejected": -496.76922607421875,
|
469 |
+
"loss": 0.3901,
|
470 |
+
"rewards/accuracies": 0.824999988079071,
|
471 |
+
"rewards/chosen": -2.2830259799957275,
|
472 |
+
"rewards/margins": 1.7167097330093384,
|
473 |
+
"rewards/rejected": -3.9997353553771973,
|
474 |
+
"step": 150
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.3054375269413141,
|
478 |
+
"grad_norm": 9.243554014229469,
|
479 |
+
"learning_rate": 4.38526652444224e-07,
|
480 |
+
"logits/chosen": -0.23520083725452423,
|
481 |
+
"logits/rejected": -0.45836538076400757,
|
482 |
+
"logps/chosen": -338.83935546875,
|
483 |
+
"logps/rejected": -600.7113037109375,
|
484 |
+
"loss": 0.3776,
|
485 |
+
"rewards/accuracies": 0.862500011920929,
|
486 |
+
"rewards/chosen": -2.335677146911621,
|
487 |
+
"rewards/margins": 2.6365208625793457,
|
488 |
+
"rewards/rejected": -4.972198009490967,
|
489 |
+
"step": 155
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.3152903503910339,
|
493 |
+
"grad_norm": 16.302237845544973,
|
494 |
+
"learning_rate": 4.3276009614285824e-07,
|
495 |
+
"logits/chosen": -0.27397865056991577,
|
496 |
+
"logits/rejected": -0.4509497582912445,
|
497 |
+
"logps/chosen": -340.3817443847656,
|
498 |
+
"logps/rejected": -519.3179321289062,
|
499 |
+
"loss": 0.373,
|
500 |
+
"rewards/accuracies": 0.824999988079071,
|
501 |
+
"rewards/chosen": -2.389813184738159,
|
502 |
+
"rewards/margins": 1.820207953453064,
|
503 |
+
"rewards/rejected": -4.210021018981934,
|
504 |
+
"step": 160
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.32514317384075375,
|
508 |
+
"grad_norm": 12.790316412360088,
|
509 |
+
"learning_rate": 4.2677669529663686e-07,
|
510 |
+
"logits/chosen": -0.3117635250091553,
|
511 |
+
"logits/rejected": -0.5069926977157593,
|
512 |
+
"logps/chosen": -408.1647033691406,
|
513 |
+
"logps/rejected": -684.1016845703125,
|
514 |
+
"loss": 0.3554,
|
515 |
+
"rewards/accuracies": 0.862500011920929,
|
516 |
+
"rewards/chosen": -2.9762721061706543,
|
517 |
+
"rewards/margins": 2.816100597381592,
|
518 |
+
"rewards/rejected": -5.792372703552246,
|
519 |
+
"step": 165
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.3349959972904735,
|
523 |
+
"grad_norm": 12.163515409448873,
|
524 |
+
"learning_rate": 4.2058354920054043e-07,
|
525 |
+
"logits/chosen": -0.32501062750816345,
|
526 |
+
"logits/rejected": -0.4444299340248108,
|
527 |
+
"logps/chosen": -392.1680603027344,
|
528 |
+
"logps/rejected": -582.3343505859375,
|
529 |
+
"loss": 0.3309,
|
530 |
+
"rewards/accuracies": 0.8125,
|
531 |
+
"rewards/chosen": -2.916874885559082,
|
532 |
+
"rewards/margins": 1.9237887859344482,
|
533 |
+
"rewards/rejected": -4.840663909912109,
|
534 |
+
"step": 170
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.34484882074019335,
|
538 |
+
"grad_norm": 16.509396763840595,
|
539 |
+
"learning_rate": 4.141880060119336e-07,
|
540 |
+
"logits/chosen": -0.30287298560142517,
|
541 |
+
"logits/rejected": -0.5002428293228149,
|
542 |
+
"logps/chosen": -392.53900146484375,
|
543 |
+
"logps/rejected": -621.8858642578125,
|
544 |
+
"loss": 0.3799,
|
545 |
+
"rewards/accuracies": 0.8500000238418579,
|
546 |
+
"rewards/chosen": -2.818398952484131,
|
547 |
+
"rewards/margins": 2.3253607749938965,
|
548 |
+
"rewards/rejected": -5.143759250640869,
|
549 |
+
"step": 175
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.3547016441899132,
|
553 |
+
"grad_norm": 19.861599589919685,
|
554 |
+
"learning_rate": 4.0759765403198877e-07,
|
555 |
+
"logits/chosen": -0.2992296814918518,
|
556 |
+
"logits/rejected": -0.46128687262535095,
|
557 |
+
"logps/chosen": -369.04058837890625,
|
558 |
+
"logps/rejected": -594.5716552734375,
|
559 |
+
"loss": 0.3318,
|
560 |
+
"rewards/accuracies": 0.8687499761581421,
|
561 |
+
"rewards/chosen": -2.6274733543395996,
|
562 |
+
"rewards/margins": 2.262349843978882,
|
563 |
+
"rewards/rejected": -4.889822959899902,
|
564 |
+
"step": 180
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.364554467639633,
|
568 |
+
"grad_norm": 20.974452355570566,
|
569 |
+
"learning_rate": 4.008203127021797e-07,
|
570 |
+
"logits/chosen": -0.25085026025772095,
|
571 |
+
"logits/rejected": -0.46279406547546387,
|
572 |
+
"logps/chosen": -358.7597351074219,
|
573 |
+
"logps/rejected": -571.667724609375,
|
574 |
+
"loss": 0.3218,
|
575 |
+
"rewards/accuracies": 0.8812500238418579,
|
576 |
+
"rewards/chosen": -2.5963218212127686,
|
577 |
+
"rewards/margins": 2.143275022506714,
|
578 |
+
"rewards/rejected": -4.739596843719482,
|
579 |
+
"step": 185
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.3744072910893528,
|
583 |
+
"grad_norm": 14.073373162388602,
|
584 |
+
"learning_rate": 3.9386402332652754e-07,
|
585 |
+
"logits/chosen": -0.23608064651489258,
|
586 |
+
"logits/rejected": -0.5011879205703735,
|
587 |
+
"logps/chosen": -423.06573486328125,
|
588 |
+
"logps/rejected": -701.5946044921875,
|
589 |
+
"loss": 0.3171,
|
590 |
+
"rewards/accuracies": 0.8999999761581421,
|
591 |
+
"rewards/chosen": -3.2071080207824707,
|
592 |
+
"rewards/margins": 2.7721924781799316,
|
593 |
+
"rewards/rejected": -5.979300498962402,
|
594 |
+
"step": 190
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.3842601145390726,
|
598 |
+
"grad_norm": 22.462855346029198,
|
599 |
+
"learning_rate": 3.867370395306068e-07,
|
600 |
+
"logits/chosen": -0.21024306118488312,
|
601 |
+
"logits/rejected": -0.48892831802368164,
|
602 |
+
"logps/chosen": -421.2330627441406,
|
603 |
+
"logps/rejected": -660.6759643554688,
|
604 |
+
"loss": 0.3264,
|
605 |
+
"rewards/accuracies": 0.8374999761581421,
|
606 |
+
"rewards/chosen": -3.2450497150421143,
|
607 |
+
"rewards/margins": 2.429110527038574,
|
608 |
+
"rewards/rejected": -5.674160003662109,
|
609 |
+
"step": 195
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.39411293798879243,
|
613 |
+
"grad_norm": 12.932519297904385,
|
614 |
+
"learning_rate": 3.794478174686328e-07,
|
615 |
+
"logits/chosen": -0.29106825590133667,
|
616 |
+
"logits/rejected": -0.4926213324069977,
|
617 |
+
"logps/chosen": -411.04840087890625,
|
618 |
+
"logps/rejected": -645.6761474609375,
|
619 |
+
"loss": 0.344,
|
620 |
+
"rewards/accuracies": 0.8125,
|
621 |
+
"rewards/chosen": -3.0619587898254395,
|
622 |
+
"rewards/margins": 2.4115443229675293,
|
623 |
+
"rewards/rejected": -5.473503112792969,
|
624 |
+
"step": 200
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.4039657614385122,
|
628 |
+
"grad_norm": 12.885808088365131,
|
629 |
+
"learning_rate": 3.720050057902495e-07,
|
630 |
+
"logits/chosen": -0.28087863326072693,
|
631 |
+
"logits/rejected": -0.5519760847091675,
|
632 |
+
"logps/chosen": -393.69659423828125,
|
633 |
+
"logps/rejected": -613.2288208007812,
|
634 |
+
"loss": 0.3363,
|
635 |
+
"rewards/accuracies": 0.8500000238418579,
|
636 |
+
"rewards/chosen": -2.869983196258545,
|
637 |
+
"rewards/margins": 2.265076160430908,
|
638 |
+
"rewards/rejected": -5.135059356689453,
|
639 |
+
"step": 205
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.41381858488823203,
|
643 |
+
"grad_norm": 16.468484087079414,
|
644 |
+
"learning_rate": 3.644174353789204e-07,
|
645 |
+
"logits/chosen": -0.3173820376396179,
|
646 |
+
"logits/rejected": -0.41476958990097046,
|
647 |
+
"logps/chosen": -439.092529296875,
|
648 |
+
"logps/rejected": -734.161865234375,
|
649 |
+
"loss": 0.2861,
|
650 |
+
"rewards/accuracies": 0.84375,
|
651 |
+
"rewards/chosen": -3.3481502532958984,
|
652 |
+
"rewards/margins": 2.985670566558838,
|
653 |
+
"rewards/rejected": -6.3338212966918945,
|
654 |
+
"step": 210
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.42367140833795186,
|
658 |
+
"grad_norm": 22.743564527030898,
|
659 |
+
"learning_rate": 3.566941088741009e-07,
|
660 |
+
"logits/chosen": -0.32451528310775757,
|
661 |
+
"logits/rejected": -0.4603727459907532,
|
662 |
+
"logps/chosen": -506.1102600097656,
|
663 |
+
"logps/rejected": -843.5612182617188,
|
664 |
+
"loss": 0.3019,
|
665 |
+
"rewards/accuracies": 0.875,
|
666 |
+
"rewards/chosen": -4.0731306076049805,
|
667 |
+
"rewards/margins": 3.3347747325897217,
|
668 |
+
"rewards/rejected": -7.407905578613281,
|
669 |
+
"step": 215
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.43352423178767163,
|
673 |
+
"grad_norm": 13.898026449525894,
|
674 |
+
"learning_rate": 3.488441899896217e-07,
|
675 |
+
"logits/chosen": -0.36527490615844727,
|
676 |
+
"logits/rejected": -0.5059664845466614,
|
677 |
+
"logps/chosen": -498.8099670410156,
|
678 |
+
"logps/rejected": -819.1517333984375,
|
679 |
+
"loss": 0.2831,
|
680 |
+
"rewards/accuracies": 0.8687499761581421,
|
681 |
+
"rewards/chosen": -3.9226620197296143,
|
682 |
+
"rewards/margins": 3.1661388874053955,
|
683 |
+
"rewards/rejected": -7.088801383972168,
|
684 |
+
"step": 220
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.44337705523739146,
|
688 |
+
"grad_norm": 13.52248766735538,
|
689 |
+
"learning_rate": 3.408769926409574e-07,
|
690 |
+
"logits/chosen": -0.2923319637775421,
|
691 |
+
"logits/rejected": -0.5522831082344055,
|
692 |
+
"logps/chosen": -440.209716796875,
|
693 |
+
"logps/rejected": -757.4591064453125,
|
694 |
+
"loss": 0.2934,
|
695 |
+
"rewards/accuracies": 0.9125000238418579,
|
696 |
+
"rewards/chosen": -3.353994369506836,
|
697 |
+
"rewards/margins": 3.2045319080352783,
|
698 |
+
"rewards/rejected": -6.558526039123535,
|
699 |
+
"step": 225
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.4532298786871113,
|
703 |
+
"grad_norm": 25.763440445028106,
|
704 |
+
"learning_rate": 3.3280196989428263e-07,
|
705 |
+
"logits/chosen": -0.28175559639930725,
|
706 |
+
"logits/rejected": -0.5395274758338928,
|
707 |
+
"logps/chosen": -408.2548828125,
|
708 |
+
"logps/rejected": -689.34326171875,
|
709 |
+
"loss": 0.3182,
|
710 |
+
"rewards/accuracies": 0.8500000238418579,
|
711 |
+
"rewards/chosen": -3.0639290809631348,
|
712 |
+
"rewards/margins": 2.8385584354400635,
|
713 |
+
"rewards/rejected": -5.902487754821777,
|
714 |
+
"step": 230
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.46308270213683106,
|
718 |
+
"grad_norm": 25.454226685247495,
|
719 |
+
"learning_rate": 3.2462870275042367e-07,
|
720 |
+
"logits/chosen": -0.3556864261627197,
|
721 |
+
"logits/rejected": -0.5125774145126343,
|
722 |
+
"logps/chosen": -393.869140625,
|
723 |
+
"logps/rejected": -721.3883666992188,
|
724 |
+
"loss": 0.2842,
|
725 |
+
"rewards/accuracies": 0.862500011920929,
|
726 |
+
"rewards/chosen": -2.9227001667022705,
|
727 |
+
"rewards/margins": 3.2367324829101562,
|
728 |
+
"rewards/rejected": -6.159432888031006,
|
729 |
+
"step": 235
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.4729355255865509,
|
733 |
+
"grad_norm": 17.441738861595127,
|
734 |
+
"learning_rate": 3.1636688877701806e-07,
|
735 |
+
"logits/chosen": -0.2837878167629242,
|
736 |
+
"logits/rejected": -0.4791291654109955,
|
737 |
+
"logps/chosen": -416.69989013671875,
|
738 |
+
"logps/rejected": -730.2517700195312,
|
739 |
+
"loss": 0.2738,
|
740 |
+
"rewards/accuracies": 0.893750011920929,
|
741 |
+
"rewards/chosen": -3.118884563446045,
|
742 |
+
"rewards/margins": 3.163923978805542,
|
743 |
+
"rewards/rejected": -6.282808303833008,
|
744 |
+
"step": 240
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.4827883490362707,
|
748 |
+
"grad_norm": 15.400566409989613,
|
749 |
+
"learning_rate": 3.080263306023669e-07,
|
750 |
+
"logits/chosen": -0.30386677384376526,
|
751 |
+
"logits/rejected": -0.5350344777107239,
|
752 |
+
"logps/chosen": -433.35760498046875,
|
753 |
+
"logps/rejected": -742.5108642578125,
|
754 |
+
"loss": 0.2983,
|
755 |
+
"rewards/accuracies": 0.875,
|
756 |
+
"rewards/chosen": -3.27720308303833,
|
757 |
+
"rewards/margins": 3.1466774940490723,
|
758 |
+
"rewards/rejected": -6.423880100250244,
|
759 |
+
"step": 245
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.49264117248599054,
|
763 |
+
"grad_norm": 13.243347184925653,
|
764 |
+
"learning_rate": 2.996169242846328e-07,
|
765 |
+
"logits/chosen": -0.2507760524749756,
|
766 |
+
"logits/rejected": -0.5307763814926147,
|
767 |
+
"logps/chosen": -420.93218994140625,
|
768 |
+
"logps/rejected": -727.508056640625,
|
769 |
+
"loss": 0.2864,
|
770 |
+
"rewards/accuracies": 0.887499988079071,
|
771 |
+
"rewards/chosen": -3.2063565254211426,
|
772 |
+
"rewards/margins": 3.135401725769043,
|
773 |
+
"rewards/rejected": -6.3417582511901855,
|
774 |
+
"step": 250
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.5024939959357103,
|
778 |
+
"grad_norm": 15.905893971492043,
|
779 |
+
"learning_rate": 2.911486475701835e-07,
|
780 |
+
"logits/chosen": -0.3323180675506592,
|
781 |
+
"logits/rejected": -0.500321090221405,
|
782 |
+
"logps/chosen": -417.96533203125,
|
783 |
+
"logps/rejected": -669.329345703125,
|
784 |
+
"loss": 0.3038,
|
785 |
+
"rewards/accuracies": 0.8687499761581421,
|
786 |
+
"rewards/chosen": -3.0756640434265137,
|
787 |
+
"rewards/margins": 2.5683434009552,
|
788 |
+
"rewards/rejected": -5.644008159637451,
|
789 |
+
"step": 255
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.5123468193854301,
|
793 |
+
"grad_norm": 15.678554296764496,
|
794 |
+
"learning_rate": 2.826315480550129e-07,
|
795 |
+
"logits/chosen": -0.2549038529396057,
|
796 |
+
"logits/rejected": -0.5205506682395935,
|
797 |
+
"logps/chosen": -397.9513244628906,
|
798 |
+
"logps/rejected": -706.6505126953125,
|
799 |
+
"loss": 0.2709,
|
800 |
+
"rewards/accuracies": 0.862500011920929,
|
801 |
+
"rewards/chosen": -2.9337005615234375,
|
802 |
+
"rewards/margins": 3.1359124183654785,
|
803 |
+
"rewards/rejected": -6.069613456726074,
|
804 |
+
"step": 260
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.52219964283515,
|
808 |
+
"grad_norm": 13.183965337617314,
|
809 |
+
"learning_rate": 2.740757312632854e-07,
|
810 |
+
"logits/chosen": -0.3502804636955261,
|
811 |
+
"logits/rejected": -0.47828468680381775,
|
812 |
+
"logps/chosen": -458.28009033203125,
|
813 |
+
"logps/rejected": -756.2743530273438,
|
814 |
+
"loss": 0.3101,
|
815 |
+
"rewards/accuracies": 0.8374999761581421,
|
816 |
+
"rewards/chosen": -3.547351837158203,
|
817 |
+
"rewards/margins": 3.0040035247802734,
|
818 |
+
"rewards/rejected": -6.551354885101318,
|
819 |
+
"step": 265
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.5320524662848698,
|
823 |
+
"grad_norm": 14.251066041226494,
|
824 |
+
"learning_rate": 2.654913486571487e-07,
|
825 |
+
"logits/chosen": -0.29742032289505005,
|
826 |
+
"logits/rejected": -0.512765109539032,
|
827 |
+
"logps/chosen": -433.20281982421875,
|
828 |
+
"logps/rejected": -742.1527099609375,
|
829 |
+
"loss": 0.269,
|
830 |
+
"rewards/accuracies": 0.893750011920929,
|
831 |
+
"rewards/chosen": -3.3142356872558594,
|
832 |
+
"rewards/margins": 3.1091339588165283,
|
833 |
+
"rewards/rejected": -6.423369407653809,
|
834 |
+
"step": 270
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.5419052897345896,
|
838 |
+
"grad_norm": 15.970456495692506,
|
839 |
+
"learning_rate": 2.5688858559204053e-07,
|
840 |
+
"logits/chosen": -0.29328054189682007,
|
841 |
+
"logits/rejected": -0.5653128027915955,
|
842 |
+
"logps/chosen": -457.0283203125,
|
843 |
+
"logps/rejected": -802.5032958984375,
|
844 |
+
"loss": 0.2619,
|
845 |
+
"rewards/accuracies": 0.8999999761581421,
|
846 |
+
"rewards/chosen": -3.5228774547576904,
|
847 |
+
"rewards/margins": 3.504716396331787,
|
848 |
+
"rewards/rejected": -7.027594566345215,
|
849 |
+
"step": 275
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.5517581131843093,
|
853 |
+
"grad_norm": 30.315717109626856,
|
854 |
+
"learning_rate": 2.4827764923178246e-07,
|
855 |
+
"logits/chosen": -0.2728544771671295,
|
856 |
+
"logits/rejected": -0.5340480208396912,
|
857 |
+
"logps/chosen": -508.76715087890625,
|
858 |
+
"logps/rejected": -814.9278564453125,
|
859 |
+
"loss": 0.3282,
|
860 |
+
"rewards/accuracies": 0.8812500238418579,
|
861 |
+
"rewards/chosen": -4.023861408233643,
|
862 |
+
"rewards/margins": 3.080327272415161,
|
863 |
+
"rewards/rejected": -7.104189395904541,
|
864 |
+
"step": 280
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.5616109366340292,
|
868 |
+
"grad_norm": 12.181715177068432,
|
869 |
+
"learning_rate": 2.3966875643779667e-07,
|
870 |
+
"logits/chosen": -0.39192137122154236,
|
871 |
+
"logits/rejected": -0.48601895570755005,
|
872 |
+
"logps/chosen": -509.3650817871094,
|
873 |
+
"logps/rejected": -919.6329956054688,
|
874 |
+
"loss": 0.2728,
|
875 |
+
"rewards/accuracies": 0.8999999761581421,
|
876 |
+
"rewards/chosen": -4.043977737426758,
|
877 |
+
"rewards/margins": 4.052145957946777,
|
878 |
+
"rewards/rejected": -8.096123695373535,
|
879 |
+
"step": 285
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.571463760083749,
|
883 |
+
"grad_norm": 22.18619533848792,
|
884 |
+
"learning_rate": 2.3107212164681774e-07,
|
885 |
+
"logits/chosen": -0.2627003788948059,
|
886 |
+
"logits/rejected": -0.512112557888031,
|
887 |
+
"logps/chosen": -514.5509033203125,
|
888 |
+
"logps/rejected": -777.1829833984375,
|
889 |
+
"loss": 0.286,
|
890 |
+
"rewards/accuracies": 0.8500000238418579,
|
891 |
+
"rewards/chosen": -4.147472381591797,
|
892 |
+
"rewards/margins": 2.6902387142181396,
|
893 |
+
"rewards/rejected": -6.837711334228516,
|
894 |
+
"step": 290
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.5813165835334688,
|
898 |
+
"grad_norm": 20.397352654188396,
|
899 |
+
"learning_rate": 2.2249794475148019e-07,
|
900 |
+
"logits/chosen": -0.2886350750923157,
|
901 |
+
"logits/rejected": -0.533146858215332,
|
902 |
+
"logps/chosen": -465.264892578125,
|
903 |
+
"logps/rejected": -807.4385986328125,
|
904 |
+
"loss": 0.2676,
|
905 |
+
"rewards/accuracies": 0.887499988079071,
|
906 |
+
"rewards/chosen": -3.6474337577819824,
|
907 |
+
"rewards/margins": 3.4217605590820312,
|
908 |
+
"rewards/rejected": -7.0691938400268555,
|
909 |
+
"step": 295
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.5911694069831886,
|
913 |
+
"grad_norm": 12.525676548560202,
|
914 |
+
"learning_rate": 2.1395639899816332e-07,
|
915 |
+
"logits/chosen": -0.35506710410118103,
|
916 |
+
"logits/rejected": -0.4460170865058899,
|
917 |
+
"logps/chosen": -424.7347106933594,
|
918 |
+
"logps/rejected": -713.3164672851562,
|
919 |
+
"loss": 0.2296,
|
920 |
+
"rewards/accuracies": 0.8999999761581421,
|
921 |
+
"rewards/chosen": -3.2564120292663574,
|
922 |
+
"rewards/margins": 2.842578411102295,
|
923 |
+
"rewards/rejected": -6.098990440368652,
|
924 |
+
"step": 300
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.6010222304329085,
|
928 |
+
"grad_norm": 16.20564210489265,
|
929 |
+
"learning_rate": 2.0545761891645177e-07,
|
930 |
+
"logits/chosen": -0.2978189289569855,
|
931 |
+
"logits/rejected": -0.5122548937797546,
|
932 |
+
"logps/chosen": -471.35693359375,
|
933 |
+
"logps/rejected": -824.7840576171875,
|
934 |
+
"loss": 0.2482,
|
935 |
+
"rewards/accuracies": 0.925000011920929,
|
936 |
+
"rewards/chosen": -3.6659018993377686,
|
937 |
+
"rewards/margins": 3.483975887298584,
|
938 |
+
"rewards/rejected": -7.14987850189209,
|
939 |
+
"step": 305
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.6108750538826282,
|
943 |
+
"grad_norm": 16.59602026766405,
|
944 |
+
"learning_rate": 1.9701168829453305e-07,
|
945 |
+
"logits/chosen": -0.2841472625732422,
|
946 |
+
"logits/rejected": -0.49612703919410706,
|
947 |
+
"logps/chosen": -475.79559326171875,
|
948 |
+
"logps/rejected": -832.6185302734375,
|
949 |
+
"loss": 0.2832,
|
950 |
+
"rewards/accuracies": 0.8812500238418579,
|
951 |
+
"rewards/chosen": -3.748015880584717,
|
952 |
+
"rewards/margins": 3.5668914318084717,
|
953 |
+
"rewards/rejected": -7.314908027648926,
|
954 |
+
"step": 310
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.620727877332348,
|
958 |
+
"grad_norm": 14.834560333592078,
|
959 |
+
"learning_rate": 1.886286282148002e-07,
|
960 |
+
"logits/chosen": -0.2684577405452728,
|
961 |
+
"logits/rejected": -0.5325924158096313,
|
962 |
+
"logps/chosen": -491.4776306152344,
|
963 |
+
"logps/rejected": -837.3449096679688,
|
964 |
+
"loss": 0.2599,
|
965 |
+
"rewards/accuracies": 0.862500011920929,
|
966 |
+
"rewards/chosen": -3.8538050651550293,
|
967 |
+
"rewards/margins": 3.5408568382263184,
|
968 |
+
"rewards/rejected": -7.394662380218506,
|
969 |
+
"step": 315
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.6305807007820678,
|
973 |
+
"grad_norm": 11.160506827485138,
|
974 |
+
"learning_rate": 1.8031838516385422e-07,
|
975 |
+
"logits/chosen": -0.2939426898956299,
|
976 |
+
"logits/rejected": -0.4827597141265869,
|
977 |
+
"logps/chosen": -524.61865234375,
|
978 |
+
"logps/rejected": -873.7683715820312,
|
979 |
+
"loss": 0.294,
|
980 |
+
"rewards/accuracies": 0.856249988079071,
|
981 |
+
"rewards/chosen": -4.23654842376709,
|
982 |
+
"rewards/margins": 3.4801859855651855,
|
983 |
+
"rewards/rejected": -7.716734409332275,
|
984 |
+
"step": 320
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.6404335242317877,
|
988 |
+
"grad_norm": 25.16794488629472,
|
989 |
+
"learning_rate": 1.7209081923101472e-07,
|
990 |
+
"logits/chosen": -0.37951114773750305,
|
991 |
+
"logits/rejected": -0.5442458391189575,
|
992 |
+
"logps/chosen": -484.8412170410156,
|
993 |
+
"logps/rejected": -843.31494140625,
|
994 |
+
"loss": 0.2438,
|
995 |
+
"rewards/accuracies": 0.84375,
|
996 |
+
"rewards/chosen": -3.8335394859313965,
|
997 |
+
"rewards/margins": 3.537074565887451,
|
998 |
+
"rewards/rejected": -7.370614528656006,
|
999 |
+
"step": 325
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.6502863476815075,
|
1003 |
+
"grad_norm": 15.675332902369199,
|
1004 |
+
"learning_rate": 1.639556924093404e-07,
|
1005 |
+
"logits/chosen": -0.31534910202026367,
|
1006 |
+
"logits/rejected": -0.6055206656455994,
|
1007 |
+
"logps/chosen": -469.186767578125,
|
1008 |
+
"logps/rejected": -785.3204345703125,
|
1009 |
+
"loss": 0.2862,
|
1010 |
+
"rewards/accuracies": 0.8999999761581421,
|
1011 |
+
"rewards/chosen": -3.6316142082214355,
|
1012 |
+
"rewards/margins": 3.245419979095459,
|
1013 |
+
"rewards/rejected": -6.8770341873168945,
|
1014 |
+
"step": 330
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.6601391711312273,
|
1018 |
+
"grad_norm": 12.550466940425805,
|
1019 |
+
"learning_rate": 1.5592265701304114e-07,
|
1020 |
+
"logits/chosen": -0.309912770986557,
|
1021 |
+
"logits/rejected": -0.580001950263977,
|
1022 |
+
"logps/chosen": -455.7469177246094,
|
1023 |
+
"logps/rejected": -795.7465209960938,
|
1024 |
+
"loss": 0.2543,
|
1025 |
+
"rewards/accuracies": 0.893750011920929,
|
1026 |
+
"rewards/chosen": -3.550823211669922,
|
1027 |
+
"rewards/margins": 3.412391185760498,
|
1028 |
+
"rewards/rejected": -6.9632134437561035,
|
1029 |
+
"step": 335
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.669991994580947,
|
1033 |
+
"grad_norm": 14.379670239758621,
|
1034 |
+
"learning_rate": 1.4800124422502334e-07,
|
1035 |
+
"logits/chosen": -0.3434782028198242,
|
1036 |
+
"logits/rejected": -0.5037192106246948,
|
1037 |
+
"logps/chosen": -427.98486328125,
|
1038 |
+
"logps/rejected": -760.0518798828125,
|
1039 |
+
"loss": 0.2582,
|
1040 |
+
"rewards/accuracies": 0.893750011920929,
|
1041 |
+
"rewards/chosen": -3.309481143951416,
|
1042 |
+
"rewards/margins": 3.3087706565856934,
|
1043 |
+
"rewards/rejected": -6.618251800537109,
|
1044 |
+
"step": 340
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.6798448180306669,
|
1048 |
+
"grad_norm": 16.948885121756778,
|
1049 |
+
"learning_rate": 1.4020085278815743e-07,
|
1050 |
+
"logits/chosen": -0.3305511176586151,
|
1051 |
+
"logits/rejected": -0.510036289691925,
|
1052 |
+
"logps/chosen": -473.0335998535156,
|
1053 |
+
"logps/rejected": -838.19970703125,
|
1054 |
+
"loss": 0.2595,
|
1055 |
+
"rewards/accuracies": 0.8500000238418579,
|
1056 |
+
"rewards/chosen": -3.7052788734436035,
|
1057 |
+
"rewards/margins": 3.6906940937042236,
|
1058 |
+
"rewards/rejected": -7.39597225189209,
|
1059 |
+
"step": 345
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.6896976414803867,
|
1063 |
+
"grad_norm": 13.672982554566653,
|
1064 |
+
"learning_rate": 1.3253073785368545e-07,
|
1065 |
+
"logits/chosen": -0.3359353244304657,
|
1066 |
+
"logits/rejected": -0.599565863609314,
|
1067 |
+
"logps/chosen": -450.7706604003906,
|
1068 |
+
"logps/rejected": -766.9132080078125,
|
1069 |
+
"loss": 0.2378,
|
1070 |
+
"rewards/accuracies": 0.875,
|
1071 |
+
"rewards/chosen": -3.4409427642822266,
|
1072 |
+
"rewards/margins": 3.247152328491211,
|
1073 |
+
"rewards/rejected": -6.6880950927734375,
|
1074 |
+
"step": 350
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.6995504649301065,
|
1078 |
+
"grad_norm": 17.198800285063513,
|
1079 |
+
"learning_rate": 1.2500000000000005e-07,
|
1080 |
+
"logits/chosen": -0.3707168996334076,
|
1081 |
+
"logits/rejected": -0.5359587669372559,
|
1082 |
+
"logps/chosen": -492.1787109375,
|
1083 |
+
"logps/rejected": -895.4451904296875,
|
1084 |
+
"loss": 0.266,
|
1085 |
+
"rewards/accuracies": 0.875,
|
1086 |
+
"rewards/chosen": -3.8479511737823486,
|
1087 |
+
"rewards/margins": 4.02894926071167,
|
1088 |
+
"rewards/rejected": -7.876900672912598,
|
1089 |
+
"step": 355
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.7094032883798264,
|
1093 |
+
"grad_norm": 19.550687307980805,
|
1094 |
+
"learning_rate": 1.1761757443482285e-07,
|
1095 |
+
"logits/chosen": -0.2943348288536072,
|
1096 |
+
"logits/rejected": -0.6027869582176208,
|
1097 |
+
"logps/chosen": -481.8168029785156,
|
1098 |
+
"logps/rejected": -860.5421142578125,
|
1099 |
+
"loss": 0.2475,
|
1100 |
+
"rewards/accuracies": 0.8999999761581421,
|
1101 |
+
"rewards/chosen": -3.7917988300323486,
|
1102 |
+
"rewards/margins": 3.795625686645508,
|
1103 |
+
"rewards/rejected": -7.587424278259277,
|
1104 |
+
"step": 360
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.7192561118295462,
|
1108 |
+
"grad_norm": 19.931316668144966,
|
1109 |
+
"learning_rate": 1.1039222039359644e-07,
|
1110 |
+
"logits/chosen": -0.32548245787620544,
|
1111 |
+
"logits/rejected": -0.5251120328903198,
|
1112 |
+
"logps/chosen": -466.42352294921875,
|
1113 |
+
"logps/rejected": -837.3107299804688,
|
1114 |
+
"loss": 0.2503,
|
1115 |
+
"rewards/accuracies": 0.8999999761581421,
|
1116 |
+
"rewards/chosen": -3.647482395172119,
|
1117 |
+
"rewards/margins": 3.7225258350372314,
|
1118 |
+
"rewards/rejected": -7.370007514953613,
|
1119 |
+
"step": 365
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.729108935279266,
|
1123 |
+
"grad_norm": 27.992034585729865,
|
1124 |
+
"learning_rate": 1.0333251074666608e-07,
|
1125 |
+
"logits/chosen": -0.26019373536109924,
|
1126 |
+
"logits/rejected": -0.5685330629348755,
|
1127 |
+
"logps/chosen": -508.7705078125,
|
1128 |
+
"logps/rejected": -834.8313598632812,
|
1129 |
+
"loss": 0.3009,
|
1130 |
+
"rewards/accuracies": 0.8500000238418579,
|
1131 |
+
"rewards/chosen": -4.032122611999512,
|
1132 |
+
"rewards/margins": 3.357773542404175,
|
1133 |
+
"rewards/rejected": -7.389896392822266,
|
1134 |
+
"step": 370
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.7389617587289857,
|
1138 |
+
"grad_norm": 11.391526012410443,
|
1139 |
+
"learning_rate": 9.644682182758304e-08,
|
1140 |
+
"logits/chosen": -0.36888641119003296,
|
1141 |
+
"logits/rejected": -0.544438362121582,
|
1142 |
+
"logps/chosen": -501.13922119140625,
|
1143 |
+
"logps/rejected": -866.8273315429688,
|
1144 |
+
"loss": 0.267,
|
1145 |
+
"rewards/accuracies": 0.8500000238418579,
|
1146 |
+
"rewards/chosen": -4.018528938293457,
|
1147 |
+
"rewards/margins": 3.660531997680664,
|
1148 |
+
"rewards/rejected": -7.679060459136963,
|
1149 |
+
"step": 375
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.7488145821787056,
|
1153 |
+
"grad_norm": 15.381753957706216,
|
1154 |
+
"learning_rate": 8.974332349459992e-08,
|
1155 |
+
"logits/chosen": -0.3592904210090637,
|
1156 |
+
"logits/rejected": -0.5230213403701782,
|
1157 |
+
"logps/chosen": -498.76397705078125,
|
1158 |
+
"logps/rejected": -873.2203369140625,
|
1159 |
+
"loss": 0.2913,
|
1160 |
+
"rewards/accuracies": 0.856249988079071,
|
1161 |
+
"rewards/chosen": -3.937748432159424,
|
1162 |
+
"rewards/margins": 3.7432987689971924,
|
1163 |
+
"rewards/rejected": -7.681046962738037,
|
1164 |
+
"step": 380
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.7586674056284254,
|
1168 |
+
"grad_norm": 12.706615805349994,
|
1169 |
+
"learning_rate": 8.322996943714672e-08,
|
1170 |
+
"logits/chosen": -0.3497922718524933,
|
1171 |
+
"logits/rejected": -0.5577541589736938,
|
1172 |
+
"logps/chosen": -512.2010498046875,
|
1173 |
+
"logps/rejected": -885.4027099609375,
|
1174 |
+
"loss": 0.2356,
|
1175 |
+
"rewards/accuracies": 0.8999999761581421,
|
1176 |
+
"rewards/chosen": -4.10722017288208,
|
1177 |
+
"rewards/margins": 3.7454257011413574,
|
1178 |
+
"rewards/rejected": -7.8526458740234375,
|
1179 |
+
"step": 385
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.7685202290781452,
|
1183 |
+
"grad_norm": 14.360275587084523,
|
1184 |
+
"learning_rate": 7.691448773879256e-08,
|
1185 |
+
"logits/chosen": -0.3780885934829712,
|
1186 |
+
"logits/rejected": -0.5432588458061218,
|
1187 |
+
"logps/chosen": -449.843505859375,
|
1188 |
+
"logps/rejected": -840.5940551757812,
|
1189 |
+
"loss": 0.2795,
|
1190 |
+
"rewards/accuracies": 0.875,
|
1191 |
+
"rewards/chosen": -3.502520799636841,
|
1192 |
+
"rewards/margins": 3.937730073928833,
|
1193 |
+
"rewards/rejected": -7.440250396728516,
|
1194 |
+
"step": 390
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.778373052527865,
|
1198 |
+
"grad_norm": 15.407447239164402,
|
1199 |
+
"learning_rate": 7.080437170788722e-08,
|
1200 |
+
"logits/chosen": -0.38400599360466003,
|
1201 |
+
"logits/rejected": -0.5888391733169556,
|
1202 |
+
"logps/chosen": -466.9847717285156,
|
1203 |
+
"logps/rejected": -768.0460205078125,
|
1204 |
+
"loss": 0.2824,
|
1205 |
+
"rewards/accuracies": 0.862500011920929,
|
1206 |
+
"rewards/chosen": -3.600980281829834,
|
1207 |
+
"rewards/margins": 3.0612690448760986,
|
1208 |
+
"rewards/rejected": -6.6622490882873535,
|
1209 |
+
"step": 395
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.7882258759775849,
|
1213 |
+
"grad_norm": 11.960557567104859,
|
1214 |
+
"learning_rate": 6.490687098676332e-08,
|
1215 |
+
"logits/chosen": -0.4111432433128357,
|
1216 |
+
"logits/rejected": -0.6113660335540771,
|
1217 |
+
"logps/chosen": -448.69500732421875,
|
1218 |
+
"logps/rejected": -851.4993896484375,
|
1219 |
+
"loss": 0.2753,
|
1220 |
+
"rewards/accuracies": 0.8812500238418579,
|
1221 |
+
"rewards/chosen": -3.424553394317627,
|
1222 |
+
"rewards/margins": 4.026993751525879,
|
1223 |
+
"rewards/rejected": -7.451546669006348,
|
1224 |
+
"step": 400
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.7882258759775849,
|
1228 |
+
"eval_logits/chosen": -1.0704303979873657,
|
1229 |
+
"eval_logits/rejected": -0.814034640789032,
|
1230 |
+
"eval_logps/chosen": -502.4184875488281,
|
1231 |
+
"eval_logps/rejected": -705.5203857421875,
|
1232 |
+
"eval_loss": 0.7013445496559143,
|
1233 |
+
"eval_rewards/accuracies": 0.7059999704360962,
|
1234 |
+
"eval_rewards/chosen": -4.094460487365723,
|
1235 |
+
"eval_rewards/margins": 1.768728494644165,
|
1236 |
+
"eval_rewards/rejected": -5.863188743591309,
|
1237 |
+
"eval_runtime": 197.0588,
|
1238 |
+
"eval_samples_per_second": 10.144,
|
1239 |
+
"eval_steps_per_second": 1.269,
|
1240 |
+
"step": 400
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 0.7980786994273046,
|
1244 |
+
"grad_norm": 16.569681590429596,
|
1245 |
+
"learning_rate": 5.9228982950048414e-08,
|
1246 |
+
"logits/chosen": -0.3508976995944977,
|
1247 |
+
"logits/rejected": -0.6730154752731323,
|
1248 |
+
"logps/chosen": -446.61688232421875,
|
1249 |
+
"logps/rejected": -841.1275634765625,
|
1250 |
+
"loss": 0.2751,
|
1251 |
+
"rewards/accuracies": 0.90625,
|
1252 |
+
"rewards/chosen": -3.3948426246643066,
|
1253 |
+
"rewards/margins": 4.001449108123779,
|
1254 |
+
"rewards/rejected": -7.396292209625244,
|
1255 |
+
"step": 405
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.8079315228770244,
|
1259 |
+
"grad_norm": 30.74667877593499,
|
1260 |
+
"learning_rate": 5.3777444402291345e-08,
|
1261 |
+
"logits/chosen": -0.44255560636520386,
|
1262 |
+
"logits/rejected": -0.5289443135261536,
|
1263 |
+
"logps/chosen": -484.78363037109375,
|
1264 |
+
"logps/rejected": -847.515625,
|
1265 |
+
"loss": 0.2925,
|
1266 |
+
"rewards/accuracies": 0.8125,
|
1267 |
+
"rewards/chosen": -3.900998592376709,
|
1268 |
+
"rewards/margins": 3.6134960651397705,
|
1269 |
+
"rewards/rejected": -7.5144944190979,
|
1270 |
+
"step": 410
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.8177843463267442,
|
1274 |
+
"grad_norm": 23.687222476192307,
|
1275 |
+
"learning_rate": 4.855872358475546e-08,
|
1276 |
+
"logits/chosen": -0.3782200217247009,
|
1277 |
+
"logits/rejected": -0.6156097650527954,
|
1278 |
+
"logps/chosen": -456.51220703125,
|
1279 |
+
"logps/rejected": -778.0684814453125,
|
1280 |
+
"loss": 0.266,
|
1281 |
+
"rewards/accuracies": 0.824999988079071,
|
1282 |
+
"rewards/chosen": -3.4957103729248047,
|
1283 |
+
"rewards/margins": 3.254422664642334,
|
1284 |
+
"rewards/rejected": -6.750133514404297,
|
1285 |
+
"step": 415
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.8276371697764641,
|
1289 |
+
"grad_norm": 19.649935116061837,
|
1290 |
+
"learning_rate": 4.357901250086107e-08,
|
1291 |
+
"logits/chosen": -0.42209166288375854,
|
1292 |
+
"logits/rejected": -0.5967798233032227,
|
1293 |
+
"logps/chosen": -440.5074157714844,
|
1294 |
+
"logps/rejected": -706.137451171875,
|
1295 |
+
"loss": 0.2765,
|
1296 |
+
"rewards/accuracies": 0.8187500238418579,
|
1297 |
+
"rewards/chosen": -3.3461577892303467,
|
1298 |
+
"rewards/margins": 2.7582011222839355,
|
1299 |
+
"rewards/rejected": -6.104359149932861,
|
1300 |
+
"step": 420
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.8374899932261839,
|
1304 |
+
"grad_norm": 20.031137924167396,
|
1305 |
+
"learning_rate": 3.884421956938377e-08,
|
1306 |
+
"logits/chosen": -0.3795103430747986,
|
1307 |
+
"logits/rejected": -0.5693720579147339,
|
1308 |
+
"logps/chosen": -415.31976318359375,
|
1309 |
+
"logps/rejected": -812.3355712890625,
|
1310 |
+
"loss": 0.2851,
|
1311 |
+
"rewards/accuracies": 0.8687499761581421,
|
1312 |
+
"rewards/chosen": -3.1916797161102295,
|
1313 |
+
"rewards/margins": 3.95634126663208,
|
1314 |
+
"rewards/rejected": -7.1480207443237305,
|
1315 |
+
"step": 425
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 0.8473428166759037,
|
1319 |
+
"grad_norm": 13.471904858040782,
|
1320 |
+
"learning_rate": 3.435996261412591e-08,
|
1321 |
+
"logits/chosen": -0.37054741382598877,
|
1322 |
+
"logits/rejected": -0.5658844113349915,
|
1323 |
+
"logps/chosen": -443.5189514160156,
|
1324 |
+
"logps/rejected": -789.6598510742188,
|
1325 |
+
"loss": 0.2174,
|
1326 |
+
"rewards/accuracies": 0.8999999761581421,
|
1327 |
+
"rewards/chosen": -3.431079864501953,
|
1328 |
+
"rewards/margins": 3.494525909423828,
|
1329 |
+
"rewards/rejected": -6.925606727600098,
|
1330 |
+
"step": 430
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.8571956401256235,
|
1334 |
+
"grad_norm": 41.43328285681965,
|
1335 |
+
"learning_rate": 3.013156219837776e-08,
|
1336 |
+
"logits/chosen": -0.42507949471473694,
|
1337 |
+
"logits/rejected": -0.6270584464073181,
|
1338 |
+
"logps/chosen": -437.37841796875,
|
1339 |
+
"logps/rejected": -766.0833129882812,
|
1340 |
+
"loss": 0.2904,
|
1341 |
+
"rewards/accuracies": 0.8999999761581421,
|
1342 |
+
"rewards/chosen": -3.347297191619873,
|
1343 |
+
"rewards/margins": 3.312955856323242,
|
1344 |
+
"rewards/rejected": -6.660252571105957,
|
1345 |
+
"step": 435
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 0.8670484635753433,
|
1349 |
+
"grad_norm": 14.214226148262764,
|
1350 |
+
"learning_rate": 2.6164035312078447e-08,
|
1351 |
+
"logits/chosen": -0.35758644342422485,
|
1352 |
+
"logits/rejected": -0.5952532291412354,
|
1353 |
+
"logps/chosen": -442.4962463378906,
|
1354 |
+
"logps/rejected": -813.2142944335938,
|
1355 |
+
"loss": 0.2391,
|
1356 |
+
"rewards/accuracies": 0.925000011920929,
|
1357 |
+
"rewards/chosen": -3.3745460510253906,
|
1358 |
+
"rewards/margins": 3.7038657665252686,
|
1359 |
+
"rewards/rejected": -7.0784125328063965,
|
1360 |
+
"step": 440
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.8769012870250631,
|
1364 |
+
"grad_norm": 12.722193098483684,
|
1365 |
+
"learning_rate": 2.2462089419165776e-08,
|
1366 |
+
"logits/chosen": -0.3699408173561096,
|
1367 |
+
"logits/rejected": -0.6010391116142273,
|
1368 |
+
"logps/chosen": -450.82745361328125,
|
1369 |
+
"logps/rejected": -841.6207885742188,
|
1370 |
+
"loss": 0.2671,
|
1371 |
+
"rewards/accuracies": 0.9125000238418579,
|
1372 |
+
"rewards/chosen": -3.4586853981018066,
|
1373 |
+
"rewards/margins": 3.931617259979248,
|
1374 |
+
"rewards/rejected": -7.3903021812438965,
|
1375 |
+
"step": 445
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.8867541104747829,
|
1379 |
+
"grad_norm": 34.89251514032782,
|
1380 |
+
"learning_rate": 1.9030116872178314e-08,
|
1381 |
+
"logits/chosen": -0.42120829224586487,
|
1382 |
+
"logits/rejected": -0.5930547118186951,
|
1383 |
+
"logps/chosen": -482.32049560546875,
|
1384 |
+
"logps/rejected": -877.3797607421875,
|
1385 |
+
"loss": 0.2528,
|
1386 |
+
"rewards/accuracies": 0.887499988079071,
|
1387 |
+
"rewards/chosen": -3.762233018875122,
|
1388 |
+
"rewards/margins": 3.9991488456726074,
|
1389 |
+
"rewards/rejected": -7.761382102966309,
|
1390 |
+
"step": 450
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.8966069339245027,
|
1394 |
+
"grad_norm": 11.63474736568058,
|
1395 |
+
"learning_rate": 1.5872189700736337e-08,
|
1396 |
+
"logits/chosen": -0.3359231948852539,
|
1397 |
+
"logits/rejected": -0.580034613609314,
|
1398 |
+
"logps/chosen": -476.1517028808594,
|
1399 |
+
"logps/rejected": -840.4141845703125,
|
1400 |
+
"loss": 0.2568,
|
1401 |
+
"rewards/accuracies": 0.893750011920929,
|
1402 |
+
"rewards/chosen": -3.7410130500793457,
|
1403 |
+
"rewards/margins": 3.678678512573242,
|
1404 |
+
"rewards/rejected": -7.419691562652588,
|
1405 |
+
"step": 455
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 0.9064597573742226,
|
1409 |
+
"grad_norm": 17.200657346282192,
|
1410 |
+
"learning_rate": 1.2992054780085692e-08,
|
1411 |
+
"logits/chosen": -0.42435139417648315,
|
1412 |
+
"logits/rejected": -0.5707032084465027,
|
1413 |
+
"logps/chosen": -480.90673828125,
|
1414 |
+
"logps/rejected": -864.6921997070312,
|
1415 |
+
"loss": 0.2681,
|
1416 |
+
"rewards/accuracies": 0.862500011920929,
|
1417 |
+
"rewards/chosen": -3.753577470779419,
|
1418 |
+
"rewards/margins": 3.8412506580352783,
|
1419 |
+
"rewards/rejected": -7.594828128814697,
|
1420 |
+
"step": 460
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.9163125808239424,
|
1424 |
+
"grad_norm": 15.168319053661703,
|
1425 |
+
"learning_rate": 1.0393129385436823e-08,
|
1426 |
+
"logits/chosen": -0.41962409019470215,
|
1427 |
+
"logits/rejected": -0.5582268238067627,
|
1428 |
+
"logps/chosen": -480.22650146484375,
|
1429 |
+
"logps/rejected": -835.0930786132812,
|
1430 |
+
"loss": 0.2639,
|
1431 |
+
"rewards/accuracies": 0.862500011920929,
|
1432 |
+
"rewards/chosen": -3.7359073162078857,
|
1433 |
+
"rewards/margins": 3.5815021991729736,
|
1434 |
+
"rewards/rejected": -7.317408561706543,
|
1435 |
+
"step": 465
|
1436 |
+
},
|
1437 |
+
{
|
1438 |
+
"epoch": 0.9261654042736621,
|
1439 |
+
"grad_norm": 14.145988270109239,
|
1440 |
+
"learning_rate": 8.078497137373242e-09,
|
1441 |
+
"logits/chosen": -0.3046739399433136,
|
1442 |
+
"logits/rejected": -0.6777099967002869,
|
1443 |
+
"logps/chosen": -452.22406005859375,
|
1444 |
+
"logps/rejected": -792.261474609375,
|
1445 |
+
"loss": 0.2466,
|
1446 |
+
"rewards/accuracies": 0.893750011920929,
|
1447 |
+
"rewards/chosen": -3.451488494873047,
|
1448 |
+
"rewards/margins": 3.4896602630615234,
|
1449 |
+
"rewards/rejected": -6.941148281097412,
|
1450 |
+
"step": 470
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 0.936018227723382,
|
1454 |
+
"grad_norm": 17.26395488122693,
|
1455 |
+
"learning_rate": 6.0509043431410945e-09,
|
1456 |
+
"logits/chosen": -0.47448891401290894,
|
1457 |
+
"logits/rejected": -0.5780371427536011,
|
1458 |
+
"logps/chosen": -473.33148193359375,
|
1459 |
+
"logps/rejected": -845.0810546875,
|
1460 |
+
"loss": 0.2735,
|
1461 |
+
"rewards/accuracies": 0.8999999761581421,
|
1462 |
+
"rewards/chosen": -3.652672290802002,
|
1463 |
+
"rewards/margins": 3.7301712036132812,
|
1464 |
+
"rewards/rejected": -7.382843971252441,
|
1465 |
+
"step": 475
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.9458710511731018,
|
1469 |
+
"grad_norm": 13.502447902766075,
|
1470 |
+
"learning_rate": 4.312756738160145e-09,
|
1471 |
+
"logits/chosen": -0.4307557940483093,
|
1472 |
+
"logits/rejected": -0.609841525554657,
|
1473 |
+
"logps/chosen": -455.236572265625,
|
1474 |
+
"logps/rejected": -856.6760864257812,
|
1475 |
+
"loss": 0.2483,
|
1476 |
+
"rewards/accuracies": 0.925000011920929,
|
1477 |
+
"rewards/chosen": -3.540134906768799,
|
1478 |
+
"rewards/margins": 3.9815449714660645,
|
1479 |
+
"rewards/rejected": -7.521679878234863,
|
1480 |
+
"step": 480
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.9557238746228216,
|
1484 |
+
"grad_norm": 14.00663655974014,
|
1485 |
+
"learning_rate": 2.8661166316229223e-09,
|
1486 |
+
"logits/chosen": -0.34750238060951233,
|
1487 |
+
"logits/rejected": -0.5667217969894409,
|
1488 |
+
"logps/chosen": -460.013671875,
|
1489 |
+
"logps/rejected": -754.5597534179688,
|
1490 |
+
"loss": 0.2729,
|
1491 |
+
"rewards/accuracies": 0.856249988079071,
|
1492 |
+
"rewards/chosen": -3.5511062145233154,
|
1493 |
+
"rewards/margins": 2.9699506759643555,
|
1494 |
+
"rewards/rejected": -6.52105712890625,
|
1495 |
+
"step": 485
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.9655766980725414,
|
1499 |
+
"grad_norm": 14.399934375372629,
|
1500 |
+
"learning_rate": 1.7127004595681727e-09,
|
1501 |
+
"logits/chosen": -0.37273770570755005,
|
1502 |
+
"logits/rejected": -0.6115278005599976,
|
1503 |
+
"logps/chosen": -470.6495056152344,
|
1504 |
+
"logps/rejected": -818.9450073242188,
|
1505 |
+
"loss": 0.2724,
|
1506 |
+
"rewards/accuracies": 0.90625,
|
1507 |
+
"rewards/chosen": -3.666602611541748,
|
1508 |
+
"rewards/margins": 3.5529751777648926,
|
1509 |
+
"rewards/rejected": -7.219576835632324,
|
1510 |
+
"step": 490
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 0.9754295215222613,
|
1514 |
+
"grad_norm": 13.760376876126982,
|
1515 |
+
"learning_rate": 8.538767483325383e-10,
|
1516 |
+
"logits/chosen": -0.3895708918571472,
|
1517 |
+
"logits/rejected": -0.6080259084701538,
|
1518 |
+
"logps/chosen": -463.2498474121094,
|
1519 |
+
"logps/rejected": -805.6424560546875,
|
1520 |
+
"loss": 0.2489,
|
1521 |
+
"rewards/accuracies": 0.8812500238418579,
|
1522 |
+
"rewards/chosen": -3.570629119873047,
|
1523 |
+
"rewards/margins": 3.4926178455352783,
|
1524 |
+
"rewards/rejected": -7.063246726989746,
|
1525 |
+
"step": 495
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 0.9852823449719811,
|
1529 |
+
"grad_norm": 23.653347787632313,
|
1530 |
+
"learning_rate": 2.9066449079634404e-10,
|
1531 |
+
"logits/chosen": -0.37257179617881775,
|
1532 |
+
"logits/rejected": -0.5408270955085754,
|
1533 |
+
"logps/chosen": -501.0938415527344,
|
1534 |
+
"logps/rejected": -795.1988525390625,
|
1535 |
+
"loss": 0.2689,
|
1536 |
+
"rewards/accuracies": 0.8500000238418579,
|
1537 |
+
"rewards/chosen": -3.9710209369659424,
|
1538 |
+
"rewards/margins": 2.9601473808288574,
|
1539 |
+
"rewards/rejected": -6.931168556213379,
|
1540 |
+
"step": 500
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 0.9951351684217008,
|
1544 |
+
"grad_norm": 14.616427588956885,
|
1545 |
+
"learning_rate": 2.3731937350224273e-11,
|
1546 |
+
"logits/chosen": -0.4466114044189453,
|
1547 |
+
"logits/rejected": -0.6212998032569885,
|
1548 |
+
"logps/chosen": -427.31536865234375,
|
1549 |
+
"logps/rejected": -899.2130126953125,
|
1550 |
+
"loss": 0.268,
|
1551 |
+
"rewards/accuracies": 0.8687499761581421,
|
1552 |
+
"rewards/chosen": -3.2273106575012207,
|
1553 |
+
"rewards/margins": 4.719491481781006,
|
1554 |
+
"rewards/rejected": -7.946801662445068,
|
1555 |
+
"step": 505
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.9990762978015888,
|
1559 |
+
"step": 507,
|
1560 |
+
"total_flos": 0.0,
|
1561 |
+
"train_loss": 0.3691282767280789,
|
1562 |
+
"train_runtime": 28319.5283,
|
1563 |
+
"train_samples_per_second": 2.294,
|
1564 |
+
"train_steps_per_second": 0.018
|
1565 |
+
}
|
1566 |
+
],
|
1567 |
+
"logging_steps": 5,
|
1568 |
+
"max_steps": 507,
|
1569 |
+
"num_input_tokens_seen": 0,
|
1570 |
+
"num_train_epochs": 1,
|
1571 |
+
"save_steps": 1000000,
|
1572 |
+
"stateful_callbacks": {
|
1573 |
+
"TrainerControl": {
|
1574 |
+
"args": {
|
1575 |
+
"should_epoch_stop": false,
|
1576 |
+
"should_evaluate": false,
|
1577 |
+
"should_log": false,
|
1578 |
+
"should_save": true,
|
1579 |
+
"should_training_stop": true
|
1580 |
+
},
|
1581 |
+
"attributes": {}
|
1582 |
+
}
|
1583 |
+
},
|
1584 |
+
"total_flos": 0.0,
|
1585 |
+
"train_batch_size": 1,
|
1586 |
+
"trial_name": null,
|
1587 |
+
"trial_params": null
|
1588 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb92d3e3a81f64a59318c9916a353d0da79967aa8c8b3c20e43e72b9d9c1c711
|
3 |
+
size 7608
|