Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +77 -0
- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- added_tokens.json +5 -0
- checkpoint-100/README.md +21 -0
- checkpoint-100/adapter_config.json +28 -0
- checkpoint-100/adapter_model.bin +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +635 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-150/README.md +21 -0
- checkpoint-150/adapter_config.json +28 -0
- checkpoint-150/adapter_model.bin +3 -0
- checkpoint-150/optimizer.pt +3 -0
- checkpoint-150/rng_state.pth +3 -0
- checkpoint-150/scheduler.pt +3 -0
- checkpoint-150/trainer_state.json +943 -0
- checkpoint-150/training_args.bin +3 -0
- checkpoint-200/README.md +21 -0
- checkpoint-200/adapter_config.json +28 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +1251 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-250/README.md +21 -0
- checkpoint-250/adapter_config.json +28 -0
- checkpoint-250/adapter_model.bin +3 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/trainer_state.json +1559 -0
- checkpoint-250/training_args.bin +3 -0
- checkpoint-300/README.md +21 -0
- checkpoint-300/adapter_config.json +28 -0
- checkpoint-300/adapter_model.bin +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/trainer_state.json +1867 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-350/README.md +21 -0
- checkpoint-350/adapter_config.json +28 -0
- checkpoint-350/adapter_model.bin +3 -0
- checkpoint-350/optimizer.pt +3 -0
- checkpoint-350/rng_state.pth +3 -0
- checkpoint-350/scheduler.pt +3 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: lora-out
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
13 |
+
# lora-out
|
14 |
+
|
15 |
+
This model was trained from scratch on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.6736
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0002
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 4
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 4
|
41 |
+
- total_train_batch_size: 16
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_steps: 10
|
45 |
+
- num_epochs: 3
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 1.6421 | 0.16 | 50 | 1.6217 |
|
52 |
+
| 1.6288 | 0.31 | 100 | 1.6144 |
|
53 |
+
| 1.5725 | 0.47 | 150 | 1.6102 |
|
54 |
+
| 1.5582 | 0.62 | 200 | 1.6065 |
|
55 |
+
| 1.6055 | 0.78 | 250 | 1.6051 |
|
56 |
+
| 1.5733 | 0.93 | 300 | 1.6023 |
|
57 |
+
| 1.4885 | 1.09 | 350 | 1.6130 |
|
58 |
+
| 1.484 | 1.24 | 400 | 1.6169 |
|
59 |
+
| 1.4354 | 1.4 | 450 | 1.6194 |
|
60 |
+
| 1.4427 | 1.56 | 500 | 1.6187 |
|
61 |
+
| 1.4687 | 1.71 | 550 | 1.6178 |
|
62 |
+
| 1.461 | 1.87 | 600 | 1.6174 |
|
63 |
+
| 1.327 | 2.02 | 650 | 1.6341 |
|
64 |
+
| 1.3015 | 2.18 | 700 | 1.6665 |
|
65 |
+
| 1.3328 | 2.33 | 750 | 1.6714 |
|
66 |
+
| 1.3453 | 2.49 | 800 | 1.6718 |
|
67 |
+
| 1.3458 | 2.64 | 850 | 1.6725 |
|
68 |
+
| 1.3016 | 2.8 | 900 | 1.6737 |
|
69 |
+
| 1.3018 | 2.95 | 950 | 1.6736 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.34.0.dev0
|
75 |
+
- Pytorch 2.0.1+cu118
|
76 |
+
- Datasets 2.14.5
|
77 |
+
- Tokenizers 0.14.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:219facdff16b696735f1a84fdd92a0cbac9e197db9eef71c8ce3344d57718790
|
3 |
+
size 84046925
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-100/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15b988ab295a843da4e545e17f172c76e0f1bfa3a9dd9edf198aef5f67b77510
|
3 |
+
size 84046925
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d7a2c502708a4001a524b14e53231dd6709ac7558468e509fa4048cd3f6e77c
|
3 |
+
size 168039109
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b33e2e1c1d173dea2a01ae0984bce42a42fb5bc88b8e940e3d611fa0910ef6b
|
3 |
+
size 14575
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c403caea7cd1ca879cd128b86652676d56ca84332ed1fd33c5182cf98e7a10
|
3 |
+
size 627
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,635 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6143836975097656,
|
3 |
+
"best_model_checkpoint": "./lora-out/checkpoint-100",
|
4 |
+
"epoch": 0.3110419906687403,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 1.7924,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4e-05,
|
20 |
+
"loss": 1.8083,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 6e-05,
|
26 |
+
"loss": 1.8177,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 8e-05,
|
32 |
+
"loss": 1.7595,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 0.0001,
|
38 |
+
"loss": 1.6598,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 0.00012,
|
44 |
+
"loss": 1.6919,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.00014,
|
50 |
+
"loss": 1.6706,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.00016,
|
56 |
+
"loss": 1.6879,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.03,
|
61 |
+
"learning_rate": 0.00018,
|
62 |
+
"loss": 1.7051,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.7022,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.000199999456645141,
|
74 |
+
"loss": 1.6809,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.04,
|
79 |
+
"learning_rate": 0.00019999782658646859,
|
80 |
+
"loss": 1.6098,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.04,
|
85 |
+
"learning_rate": 0.0001999951098416968,
|
86 |
+
"loss": 1.7014,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 0.00019999130644034888,
|
92 |
+
"loss": 1.5885,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05,
|
97 |
+
"learning_rate": 0.00019998641642375657,
|
98 |
+
"loss": 1.6243,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.05,
|
103 |
+
"learning_rate": 0.00019998043984506027,
|
104 |
+
"loss": 1.6484,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.05,
|
109 |
+
"learning_rate": 0.00019997337676920803,
|
110 |
+
"loss": 1.6093,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.06,
|
115 |
+
"learning_rate": 0.00019996522727295496,
|
116 |
+
"loss": 1.6173,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.06,
|
121 |
+
"learning_rate": 0.00019995599144486247,
|
122 |
+
"loss": 1.646,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.06,
|
127 |
+
"learning_rate": 0.00019994566938529712,
|
128 |
+
"loss": 1.6469,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07,
|
133 |
+
"learning_rate": 0.00019993426120642983,
|
134 |
+
"loss": 1.6564,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07,
|
139 |
+
"learning_rate": 0.00019992176703223432,
|
140 |
+
"loss": 1.5901,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.07,
|
145 |
+
"learning_rate": 0.000199908186998486,
|
146 |
+
"loss": 1.664,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.07,
|
151 |
+
"learning_rate": 0.00019989352125276047,
|
152 |
+
"loss": 1.6275,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.08,
|
157 |
+
"learning_rate": 0.00019987776995443178,
|
158 |
+
"loss": 1.5839,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.08,
|
163 |
+
"learning_rate": 0.00019986093327467076,
|
164 |
+
"loss": 1.5611,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.08,
|
169 |
+
"learning_rate": 0.00019984301139644334,
|
170 |
+
"loss": 1.669,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.09,
|
175 |
+
"learning_rate": 0.0001998240045145083,
|
176 |
+
"loss": 1.5641,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09,
|
181 |
+
"learning_rate": 0.00019980391283541522,
|
182 |
+
"loss": 1.6023,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.09,
|
187 |
+
"learning_rate": 0.00019978273657750238,
|
188 |
+
"loss": 1.6309,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.1,
|
193 |
+
"learning_rate": 0.0001997604759708942,
|
194 |
+
"loss": 1.6353,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.1,
|
199 |
+
"learning_rate": 0.00019973713125749884,
|
200 |
+
"loss": 1.6328,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.1,
|
205 |
+
"learning_rate": 0.00019971270269100564,
|
206 |
+
"loss": 1.5683,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.11,
|
211 |
+
"learning_rate": 0.00019968719053688213,
|
212 |
+
"loss": 1.6217,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.11,
|
217 |
+
"learning_rate": 0.0001996605950723714,
|
218 |
+
"loss": 1.5734,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11,
|
223 |
+
"learning_rate": 0.00019963291658648896,
|
224 |
+
"loss": 1.6162,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.12,
|
229 |
+
"learning_rate": 0.00019960415538001957,
|
230 |
+
"loss": 1.5922,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.12,
|
235 |
+
"learning_rate": 0.0001995743117655141,
|
236 |
+
"loss": 1.5806,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.12,
|
241 |
+
"learning_rate": 0.000199543386067286,
|
242 |
+
"loss": 1.5938,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.12,
|
247 |
+
"learning_rate": 0.00019951137862140778,
|
248 |
+
"loss": 1.6386,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.13,
|
253 |
+
"learning_rate": 0.00019947828977570756,
|
254 |
+
"loss": 1.6476,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.13,
|
259 |
+
"learning_rate": 0.00019944411988976496,
|
260 |
+
"loss": 1.6557,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13,
|
265 |
+
"learning_rate": 0.00019940886933490749,
|
266 |
+
"loss": 1.5836,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.14,
|
271 |
+
"learning_rate": 0.00019937253849420635,
|
272 |
+
"loss": 1.6421,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.14,
|
277 |
+
"learning_rate": 0.0001993351277624723,
|
278 |
+
"loss": 1.629,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.14,
|
283 |
+
"learning_rate": 0.00019929663754625145,
|
284 |
+
"loss": 1.6392,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.15,
|
289 |
+
"learning_rate": 0.00019925706826382064,
|
290 |
+
"loss": 1.5677,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.15,
|
295 |
+
"learning_rate": 0.00019921642034518317,
|
296 |
+
"loss": 1.6144,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.15,
|
301 |
+
"learning_rate": 0.00019917469423206389,
|
302 |
+
"loss": 1.6068,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.16,
|
307 |
+
"learning_rate": 0.00019913189037790456,
|
308 |
+
"loss": 1.6421,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.16,
|
313 |
+
"eval_loss": 1.621693730354309,
|
314 |
+
"eval_runtime": 233.7603,
|
315 |
+
"eval_samples_per_second": 16.354,
|
316 |
+
"eval_steps_per_second": 4.09,
|
317 |
+
"step": 50
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16,
|
321 |
+
"learning_rate": 0.0001990880092478588,
|
322 |
+
"loss": 1.6172,
|
323 |
+
"step": 51
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.16,
|
327 |
+
"learning_rate": 0.0001990430513187871,
|
328 |
+
"loss": 1.6095,
|
329 |
+
"step": 52
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.16,
|
333 |
+
"learning_rate": 0.00019899701707925166,
|
334 |
+
"loss": 1.5967,
|
335 |
+
"step": 53
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.17,
|
339 |
+
"learning_rate": 0.00019894990702951106,
|
340 |
+
"loss": 1.617,
|
341 |
+
"step": 54
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.17,
|
345 |
+
"learning_rate": 0.00019890172168151473,
|
346 |
+
"loss": 1.5932,
|
347 |
+
"step": 55
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.17,
|
351 |
+
"learning_rate": 0.0001988524615588976,
|
352 |
+
"loss": 1.6548,
|
353 |
+
"step": 56
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.18,
|
357 |
+
"learning_rate": 0.00019880212719697413,
|
358 |
+
"loss": 1.6033,
|
359 |
+
"step": 57
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.18,
|
363 |
+
"learning_rate": 0.00019875071914273278,
|
364 |
+
"loss": 1.6063,
|
365 |
+
"step": 58
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.18,
|
369 |
+
"learning_rate": 0.00019869823795482986,
|
370 |
+
"loss": 1.6107,
|
371 |
+
"step": 59
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.19,
|
375 |
+
"learning_rate": 0.00019864468420358354,
|
376 |
+
"loss": 1.5758,
|
377 |
+
"step": 60
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.19,
|
381 |
+
"learning_rate": 0.00019859005847096763,
|
382 |
+
"loss": 1.5723,
|
383 |
+
"step": 61
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.19,
|
387 |
+
"learning_rate": 0.00019853436135060527,
|
388 |
+
"loss": 1.542,
|
389 |
+
"step": 62
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.2,
|
393 |
+
"learning_rate": 0.00019847759344776252,
|
394 |
+
"loss": 1.5611,
|
395 |
+
"step": 63
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.2,
|
399 |
+
"learning_rate": 0.00019841975537934162,
|
400 |
+
"loss": 1.6157,
|
401 |
+
"step": 64
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2,
|
405 |
+
"learning_rate": 0.00019836084777387458,
|
406 |
+
"loss": 1.5589,
|
407 |
+
"step": 65
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.21,
|
411 |
+
"learning_rate": 0.00019830087127151598,
|
412 |
+
"loss": 1.6077,
|
413 |
+
"step": 66
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.21,
|
417 |
+
"learning_rate": 0.00019823982652403634,
|
418 |
+
"loss": 1.5473,
|
419 |
+
"step": 67
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.21,
|
423 |
+
"learning_rate": 0.00019817771419481487,
|
424 |
+
"loss": 1.6265,
|
425 |
+
"step": 68
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.21,
|
429 |
+
"learning_rate": 0.0001981145349588323,
|
430 |
+
"loss": 1.6074,
|
431 |
+
"step": 69
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.22,
|
435 |
+
"learning_rate": 0.00019805028950266348,
|
436 |
+
"loss": 1.6195,
|
437 |
+
"step": 70
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.22,
|
441 |
+
"learning_rate": 0.00019798497852447006,
|
442 |
+
"loss": 1.5876,
|
443 |
+
"step": 71
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.22,
|
447 |
+
"learning_rate": 0.0001979186027339928,
|
448 |
+
"loss": 1.5978,
|
449 |
+
"step": 72
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.23,
|
453 |
+
"learning_rate": 0.00019785116285254381,
|
454 |
+
"loss": 1.533,
|
455 |
+
"step": 73
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.23,
|
459 |
+
"learning_rate": 0.00019778265961299888,
|
460 |
+
"loss": 1.5888,
|
461 |
+
"step": 74
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.23,
|
465 |
+
"learning_rate": 0.0001977130937597894,
|
466 |
+
"loss": 1.6211,
|
467 |
+
"step": 75
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.24,
|
471 |
+
"learning_rate": 0.00019764246604889415,
|
472 |
+
"loss": 1.6091,
|
473 |
+
"step": 76
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.24,
|
477 |
+
"learning_rate": 0.00019757077724783147,
|
478 |
+
"loss": 1.6012,
|
479 |
+
"step": 77
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.24,
|
483 |
+
"learning_rate": 0.0001974980281356504,
|
484 |
+
"loss": 1.6401,
|
485 |
+
"step": 78
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.25,
|
489 |
+
"learning_rate": 0.0001974242195029227,
|
490 |
+
"loss": 1.6111,
|
491 |
+
"step": 79
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.25,
|
495 |
+
"learning_rate": 0.00019734935215173392,
|
496 |
+
"loss": 1.6208,
|
497 |
+
"step": 80
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.25,
|
501 |
+
"learning_rate": 0.00019727342689567482,
|
502 |
+
"loss": 1.6038,
|
503 |
+
"step": 81
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.26,
|
507 |
+
"learning_rate": 0.00019719644455983256,
|
508 |
+
"loss": 1.5915,
|
509 |
+
"step": 82
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.26,
|
513 |
+
"learning_rate": 0.0001971184059807817,
|
514 |
+
"loss": 1.5872,
|
515 |
+
"step": 83
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.26,
|
519 |
+
"learning_rate": 0.000197039312006575,
|
520 |
+
"loss": 1.5984,
|
521 |
+
"step": 84
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.26,
|
525 |
+
"learning_rate": 0.0001969591634967344,
|
526 |
+
"loss": 1.5996,
|
527 |
+
"step": 85
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.27,
|
531 |
+
"learning_rate": 0.00019687796132224152,
|
532 |
+
"loss": 1.6056,
|
533 |
+
"step": 86
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.27,
|
537 |
+
"learning_rate": 0.0001967957063655283,
|
538 |
+
"loss": 1.6099,
|
539 |
+
"step": 87
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.27,
|
543 |
+
"learning_rate": 0.0001967123995204674,
|
544 |
+
"loss": 1.6295,
|
545 |
+
"step": 88
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.28,
|
549 |
+
"learning_rate": 0.00019662804169236225,
|
550 |
+
"loss": 1.5482,
|
551 |
+
"step": 89
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.28,
|
555 |
+
"learning_rate": 0.00019654263379793773,
|
556 |
+
"loss": 1.5781,
|
557 |
+
"step": 90
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.28,
|
561 |
+
"learning_rate": 0.00019645617676532963,
|
562 |
+
"loss": 1.5954,
|
563 |
+
"step": 91
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.29,
|
567 |
+
"learning_rate": 0.000196368671534075,
|
568 |
+
"loss": 1.619,
|
569 |
+
"step": 92
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.29,
|
573 |
+
"learning_rate": 0.0001962801190551016,
|
574 |
+
"loss": 1.6153,
|
575 |
+
"step": 93
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.29,
|
579 |
+
"learning_rate": 0.0001961905202907179,
|
580 |
+
"loss": 1.6008,
|
581 |
+
"step": 94
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.3,
|
585 |
+
"learning_rate": 0.00019609987621460232,
|
586 |
+
"loss": 1.5891,
|
587 |
+
"step": 95
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.3,
|
591 |
+
"learning_rate": 0.0001960081878117929,
|
592 |
+
"loss": 1.6438,
|
593 |
+
"step": 96
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.3,
|
597 |
+
"learning_rate": 0.0001959154560786764,
|
598 |
+
"loss": 1.5576,
|
599 |
+
"step": 97
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.3,
|
603 |
+
"learning_rate": 0.00019582168202297758,
|
604 |
+
"loss": 1.646,
|
605 |
+
"step": 98
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.31,
|
609 |
+
"learning_rate": 0.00019572686666374822,
|
610 |
+
"loss": 1.6269,
|
611 |
+
"step": 99
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.31,
|
615 |
+
"learning_rate": 0.00019563101103135602,
|
616 |
+
"loss": 1.6288,
|
617 |
+
"step": 100
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.31,
|
621 |
+
"eval_loss": 1.6143836975097656,
|
622 |
+
"eval_runtime": 233.6412,
|
623 |
+
"eval_samples_per_second": 16.363,
|
624 |
+
"eval_steps_per_second": 4.092,
|
625 |
+
"step": 100
|
626 |
+
}
|
627 |
+
],
|
628 |
+
"logging_steps": 1,
|
629 |
+
"max_steps": 963,
|
630 |
+
"num_train_epochs": 3,
|
631 |
+
"save_steps": 50,
|
632 |
+
"total_flos": 2.804271657517056e+17,
|
633 |
+
"trial_name": null,
|
634 |
+
"trial_params": null
|
635 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f61cafb89242b653e455003b5517e685ecccfa6180af5fb7d0bfb35b4fc77a4
|
3 |
+
size 4475
|
checkpoint-150/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-150/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-150/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a8dc95d466eddcfa8f6d8c0d5ccbea2ab6e546948aa9f5852746421f82e77c0
|
3 |
+
size 84046925
|
checkpoint-150/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5972252f94afdaa16250d0a4a3efb52fef281f559cc7aab7a784266e5c32b047
|
3 |
+
size 168039109
|
checkpoint-150/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90a6fa23e9d23da035b3cd7f01ac4e5c74cc8369e9fff9529d9aa0c1fed279ac
|
3 |
+
size 14575
|
checkpoint-150/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce3e98547f3323418da3efa641653d361277560a755469afb6b5a3bc118996a
|
3 |
+
size 627
|
checkpoint-150/trainer_state.json
ADDED
@@ -0,0 +1,943 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6101970672607422,
|
3 |
+
"best_model_checkpoint": "./lora-out/checkpoint-150",
|
4 |
+
"epoch": 0.4665629860031104,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 150,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 1.7924,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4e-05,
|
20 |
+
"loss": 1.8083,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 6e-05,
|
26 |
+
"loss": 1.8177,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 8e-05,
|
32 |
+
"loss": 1.7595,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 0.0001,
|
38 |
+
"loss": 1.6598,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 0.00012,
|
44 |
+
"loss": 1.6919,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.00014,
|
50 |
+
"loss": 1.6706,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.00016,
|
56 |
+
"loss": 1.6879,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.03,
|
61 |
+
"learning_rate": 0.00018,
|
62 |
+
"loss": 1.7051,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.7022,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.000199999456645141,
|
74 |
+
"loss": 1.6809,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.04,
|
79 |
+
"learning_rate": 0.00019999782658646859,
|
80 |
+
"loss": 1.6098,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.04,
|
85 |
+
"learning_rate": 0.0001999951098416968,
|
86 |
+
"loss": 1.7014,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 0.00019999130644034888,
|
92 |
+
"loss": 1.5885,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05,
|
97 |
+
"learning_rate": 0.00019998641642375657,
|
98 |
+
"loss": 1.6243,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.05,
|
103 |
+
"learning_rate": 0.00019998043984506027,
|
104 |
+
"loss": 1.6484,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.05,
|
109 |
+
"learning_rate": 0.00019997337676920803,
|
110 |
+
"loss": 1.6093,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.06,
|
115 |
+
"learning_rate": 0.00019996522727295496,
|
116 |
+
"loss": 1.6173,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.06,
|
121 |
+
"learning_rate": 0.00019995599144486247,
|
122 |
+
"loss": 1.646,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.06,
|
127 |
+
"learning_rate": 0.00019994566938529712,
|
128 |
+
"loss": 1.6469,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07,
|
133 |
+
"learning_rate": 0.00019993426120642983,
|
134 |
+
"loss": 1.6564,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07,
|
139 |
+
"learning_rate": 0.00019992176703223432,
|
140 |
+
"loss": 1.5901,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.07,
|
145 |
+
"learning_rate": 0.000199908186998486,
|
146 |
+
"loss": 1.664,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.07,
|
151 |
+
"learning_rate": 0.00019989352125276047,
|
152 |
+
"loss": 1.6275,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.08,
|
157 |
+
"learning_rate": 0.00019987776995443178,
|
158 |
+
"loss": 1.5839,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.08,
|
163 |
+
"learning_rate": 0.00019986093327467076,
|
164 |
+
"loss": 1.5611,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.08,
|
169 |
+
"learning_rate": 0.00019984301139644334,
|
170 |
+
"loss": 1.669,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.09,
|
175 |
+
"learning_rate": 0.0001998240045145083,
|
176 |
+
"loss": 1.5641,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09,
|
181 |
+
"learning_rate": 0.00019980391283541522,
|
182 |
+
"loss": 1.6023,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.09,
|
187 |
+
"learning_rate": 0.00019978273657750238,
|
188 |
+
"loss": 1.6309,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.1,
|
193 |
+
"learning_rate": 0.0001997604759708942,
|
194 |
+
"loss": 1.6353,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.1,
|
199 |
+
"learning_rate": 0.00019973713125749884,
|
200 |
+
"loss": 1.6328,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.1,
|
205 |
+
"learning_rate": 0.00019971270269100564,
|
206 |
+
"loss": 1.5683,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.11,
|
211 |
+
"learning_rate": 0.00019968719053688213,
|
212 |
+
"loss": 1.6217,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.11,
|
217 |
+
"learning_rate": 0.0001996605950723714,
|
218 |
+
"loss": 1.5734,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11,
|
223 |
+
"learning_rate": 0.00019963291658648896,
|
224 |
+
"loss": 1.6162,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.12,
|
229 |
+
"learning_rate": 0.00019960415538001957,
|
230 |
+
"loss": 1.5922,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.12,
|
235 |
+
"learning_rate": 0.0001995743117655141,
|
236 |
+
"loss": 1.5806,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.12,
|
241 |
+
"learning_rate": 0.000199543386067286,
|
242 |
+
"loss": 1.5938,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.12,
|
247 |
+
"learning_rate": 0.00019951137862140778,
|
248 |
+
"loss": 1.6386,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.13,
|
253 |
+
"learning_rate": 0.00019947828977570756,
|
254 |
+
"loss": 1.6476,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.13,
|
259 |
+
"learning_rate": 0.00019944411988976496,
|
260 |
+
"loss": 1.6557,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13,
|
265 |
+
"learning_rate": 0.00019940886933490749,
|
266 |
+
"loss": 1.5836,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.14,
|
271 |
+
"learning_rate": 0.00019937253849420635,
|
272 |
+
"loss": 1.6421,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.14,
|
277 |
+
"learning_rate": 0.0001993351277624723,
|
278 |
+
"loss": 1.629,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.14,
|
283 |
+
"learning_rate": 0.00019929663754625145,
|
284 |
+
"loss": 1.6392,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.15,
|
289 |
+
"learning_rate": 0.00019925706826382064,
|
290 |
+
"loss": 1.5677,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.15,
|
295 |
+
"learning_rate": 0.00019921642034518317,
|
296 |
+
"loss": 1.6144,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.15,
|
301 |
+
"learning_rate": 0.00019917469423206389,
|
302 |
+
"loss": 1.6068,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.16,
|
307 |
+
"learning_rate": 0.00019913189037790456,
|
308 |
+
"loss": 1.6421,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.16,
|
313 |
+
"eval_loss": 1.621693730354309,
|
314 |
+
"eval_runtime": 233.7603,
|
315 |
+
"eval_samples_per_second": 16.354,
|
316 |
+
"eval_steps_per_second": 4.09,
|
317 |
+
"step": 50
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16,
|
321 |
+
"learning_rate": 0.0001990880092478588,
|
322 |
+
"loss": 1.6172,
|
323 |
+
"step": 51
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.16,
|
327 |
+
"learning_rate": 0.0001990430513187871,
|
328 |
+
"loss": 1.6095,
|
329 |
+
"step": 52
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.16,
|
333 |
+
"learning_rate": 0.00019899701707925166,
|
334 |
+
"loss": 1.5967,
|
335 |
+
"step": 53
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.17,
|
339 |
+
"learning_rate": 0.00019894990702951106,
|
340 |
+
"loss": 1.617,
|
341 |
+
"step": 54
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.17,
|
345 |
+
"learning_rate": 0.00019890172168151473,
|
346 |
+
"loss": 1.5932,
|
347 |
+
"step": 55
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.17,
|
351 |
+
"learning_rate": 0.0001988524615588976,
|
352 |
+
"loss": 1.6548,
|
353 |
+
"step": 56
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.18,
|
357 |
+
"learning_rate": 0.00019880212719697413,
|
358 |
+
"loss": 1.6033,
|
359 |
+
"step": 57
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.18,
|
363 |
+
"learning_rate": 0.00019875071914273278,
|
364 |
+
"loss": 1.6063,
|
365 |
+
"step": 58
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.18,
|
369 |
+
"learning_rate": 0.00019869823795482986,
|
370 |
+
"loss": 1.6107,
|
371 |
+
"step": 59
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.19,
|
375 |
+
"learning_rate": 0.00019864468420358354,
|
376 |
+
"loss": 1.5758,
|
377 |
+
"step": 60
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.19,
|
381 |
+
"learning_rate": 0.00019859005847096763,
|
382 |
+
"loss": 1.5723,
|
383 |
+
"step": 61
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.19,
|
387 |
+
"learning_rate": 0.00019853436135060527,
|
388 |
+
"loss": 1.542,
|
389 |
+
"step": 62
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.2,
|
393 |
+
"learning_rate": 0.00019847759344776252,
|
394 |
+
"loss": 1.5611,
|
395 |
+
"step": 63
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.2,
|
399 |
+
"learning_rate": 0.00019841975537934162,
|
400 |
+
"loss": 1.6157,
|
401 |
+
"step": 64
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2,
|
405 |
+
"learning_rate": 0.00019836084777387458,
|
406 |
+
"loss": 1.5589,
|
407 |
+
"step": 65
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.21,
|
411 |
+
"learning_rate": 0.00019830087127151598,
|
412 |
+
"loss": 1.6077,
|
413 |
+
"step": 66
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.21,
|
417 |
+
"learning_rate": 0.00019823982652403634,
|
418 |
+
"loss": 1.5473,
|
419 |
+
"step": 67
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.21,
|
423 |
+
"learning_rate": 0.00019817771419481487,
|
424 |
+
"loss": 1.6265,
|
425 |
+
"step": 68
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.21,
|
429 |
+
"learning_rate": 0.0001981145349588323,
|
430 |
+
"loss": 1.6074,
|
431 |
+
"step": 69
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.22,
|
435 |
+
"learning_rate": 0.00019805028950266348,
|
436 |
+
"loss": 1.6195,
|
437 |
+
"step": 70
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.22,
|
441 |
+
"learning_rate": 0.00019798497852447006,
|
442 |
+
"loss": 1.5876,
|
443 |
+
"step": 71
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.22,
|
447 |
+
"learning_rate": 0.0001979186027339928,
|
448 |
+
"loss": 1.5978,
|
449 |
+
"step": 72
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.23,
|
453 |
+
"learning_rate": 0.00019785116285254381,
|
454 |
+
"loss": 1.533,
|
455 |
+
"step": 73
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.23,
|
459 |
+
"learning_rate": 0.00019778265961299888,
|
460 |
+
"loss": 1.5888,
|
461 |
+
"step": 74
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.23,
|
465 |
+
"learning_rate": 0.0001977130937597894,
|
466 |
+
"loss": 1.6211,
|
467 |
+
"step": 75
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.24,
|
471 |
+
"learning_rate": 0.00019764246604889415,
|
472 |
+
"loss": 1.6091,
|
473 |
+
"step": 76
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.24,
|
477 |
+
"learning_rate": 0.00019757077724783147,
|
478 |
+
"loss": 1.6012,
|
479 |
+
"step": 77
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.24,
|
483 |
+
"learning_rate": 0.0001974980281356504,
|
484 |
+
"loss": 1.6401,
|
485 |
+
"step": 78
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.25,
|
489 |
+
"learning_rate": 0.0001974242195029227,
|
490 |
+
"loss": 1.6111,
|
491 |
+
"step": 79
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.25,
|
495 |
+
"learning_rate": 0.00019734935215173392,
|
496 |
+
"loss": 1.6208,
|
497 |
+
"step": 80
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.25,
|
501 |
+
"learning_rate": 0.00019727342689567482,
|
502 |
+
"loss": 1.6038,
|
503 |
+
"step": 81
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.26,
|
507 |
+
"learning_rate": 0.00019719644455983256,
|
508 |
+
"loss": 1.5915,
|
509 |
+
"step": 82
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.26,
|
513 |
+
"learning_rate": 0.0001971184059807817,
|
514 |
+
"loss": 1.5872,
|
515 |
+
"step": 83
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.26,
|
519 |
+
"learning_rate": 0.000197039312006575,
|
520 |
+
"loss": 1.5984,
|
521 |
+
"step": 84
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.26,
|
525 |
+
"learning_rate": 0.0001969591634967344,
|
526 |
+
"loss": 1.5996,
|
527 |
+
"step": 85
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.27,
|
531 |
+
"learning_rate": 0.00019687796132224152,
|
532 |
+
"loss": 1.6056,
|
533 |
+
"step": 86
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.27,
|
537 |
+
"learning_rate": 0.0001967957063655283,
|
538 |
+
"loss": 1.6099,
|
539 |
+
"step": 87
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.27,
|
543 |
+
"learning_rate": 0.0001967123995204674,
|
544 |
+
"loss": 1.6295,
|
545 |
+
"step": 88
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.28,
|
549 |
+
"learning_rate": 0.00019662804169236225,
|
550 |
+
"loss": 1.5482,
|
551 |
+
"step": 89
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.28,
|
555 |
+
"learning_rate": 0.00019654263379793773,
|
556 |
+
"loss": 1.5781,
|
557 |
+
"step": 90
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.28,
|
561 |
+
"learning_rate": 0.00019645617676532963,
|
562 |
+
"loss": 1.5954,
|
563 |
+
"step": 91
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.29,
|
567 |
+
"learning_rate": 0.000196368671534075,
|
568 |
+
"loss": 1.619,
|
569 |
+
"step": 92
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.29,
|
573 |
+
"learning_rate": 0.0001962801190551016,
|
574 |
+
"loss": 1.6153,
|
575 |
+
"step": 93
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.29,
|
579 |
+
"learning_rate": 0.0001961905202907179,
|
580 |
+
"loss": 1.6008,
|
581 |
+
"step": 94
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.3,
|
585 |
+
"learning_rate": 0.00019609987621460232,
|
586 |
+
"loss": 1.5891,
|
587 |
+
"step": 95
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.3,
|
591 |
+
"learning_rate": 0.0001960081878117929,
|
592 |
+
"loss": 1.6438,
|
593 |
+
"step": 96
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.3,
|
597 |
+
"learning_rate": 0.0001959154560786764,
|
598 |
+
"loss": 1.5576,
|
599 |
+
"step": 97
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.3,
|
603 |
+
"learning_rate": 0.00019582168202297758,
|
604 |
+
"loss": 1.646,
|
605 |
+
"step": 98
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.31,
|
609 |
+
"learning_rate": 0.00019572686666374822,
|
610 |
+
"loss": 1.6269,
|
611 |
+
"step": 99
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.31,
|
615 |
+
"learning_rate": 0.00019563101103135602,
|
616 |
+
"loss": 1.6288,
|
617 |
+
"step": 100
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.31,
|
621 |
+
"eval_loss": 1.6143836975097656,
|
622 |
+
"eval_runtime": 233.6412,
|
623 |
+
"eval_samples_per_second": 16.363,
|
624 |
+
"eval_steps_per_second": 4.092,
|
625 |
+
"step": 100
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.31,
|
629 |
+
"learning_rate": 0.00019553411616747348,
|
630 |
+
"loss": 1.5667,
|
631 |
+
"step": 101
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.32,
|
635 |
+
"learning_rate": 0.00019543618312506647,
|
636 |
+
"loss": 1.6221,
|
637 |
+
"step": 102
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.32,
|
641 |
+
"learning_rate": 0.0001953372129683829,
|
642 |
+
"loss": 1.5992,
|
643 |
+
"step": 103
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.32,
|
647 |
+
"learning_rate": 0.0001952372067729411,
|
648 |
+
"loss": 1.6138,
|
649 |
+
"step": 104
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.33,
|
653 |
+
"learning_rate": 0.00019513616562551807,
|
654 |
+
"loss": 1.51,
|
655 |
+
"step": 105
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33,
|
659 |
+
"learning_rate": 0.00019503409062413782,
|
660 |
+
"loss": 1.6227,
|
661 |
+
"step": 106
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.33,
|
665 |
+
"learning_rate": 0.00019493098287805927,
|
666 |
+
"loss": 1.6014,
|
667 |
+
"step": 107
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.34,
|
671 |
+
"learning_rate": 0.00019482684350776434,
|
672 |
+
"loss": 1.625,
|
673 |
+
"step": 108
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.34,
|
677 |
+
"learning_rate": 0.0001947216736449457,
|
678 |
+
"loss": 1.6109,
|
679 |
+
"step": 109
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.34,
|
683 |
+
"learning_rate": 0.0001946154744324945,
|
684 |
+
"loss": 1.62,
|
685 |
+
"step": 110
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.35,
|
689 |
+
"learning_rate": 0.00019450824702448778,
|
690 |
+
"loss": 1.5878,
|
691 |
+
"step": 111
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.35,
|
695 |
+
"learning_rate": 0.0001943999925861763,
|
696 |
+
"loss": 1.6264,
|
697 |
+
"step": 112
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.35,
|
701 |
+
"learning_rate": 0.00019429071229397157,
|
702 |
+
"loss": 1.6186,
|
703 |
+
"step": 113
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.35,
|
707 |
+
"learning_rate": 0.0001941804073354331,
|
708 |
+
"loss": 1.6363,
|
709 |
+
"step": 114
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.36,
|
713 |
+
"learning_rate": 0.00019406907890925562,
|
714 |
+
"loss": 1.5341,
|
715 |
+
"step": 115
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.36,
|
719 |
+
"learning_rate": 0.00019395672822525593,
|
720 |
+
"loss": 1.5986,
|
721 |
+
"step": 116
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.36,
|
725 |
+
"learning_rate": 0.00019384335650435985,
|
726 |
+
"loss": 1.6181,
|
727 |
+
"step": 117
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.37,
|
731 |
+
"learning_rate": 0.0001937289649785889,
|
732 |
+
"loss": 1.6118,
|
733 |
+
"step": 118
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.37,
|
737 |
+
"learning_rate": 0.0001936135548910469,
|
738 |
+
"loss": 1.6404,
|
739 |
+
"step": 119
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.37,
|
743 |
+
"learning_rate": 0.00019349712749590649,
|
744 |
+
"loss": 1.583,
|
745 |
+
"step": 120
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.38,
|
749 |
+
"learning_rate": 0.00019337968405839547,
|
750 |
+
"loss": 1.5827,
|
751 |
+
"step": 121
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.38,
|
755 |
+
"learning_rate": 0.00019326122585478308,
|
756 |
+
"loss": 1.6392,
|
757 |
+
"step": 122
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.38,
|
761 |
+
"learning_rate": 0.00019314175417236616,
|
762 |
+
"loss": 1.5861,
|
763 |
+
"step": 123
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.39,
|
767 |
+
"learning_rate": 0.00019302127030945508,
|
768 |
+
"loss": 1.5738,
|
769 |
+
"step": 124
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.39,
|
773 |
+
"learning_rate": 0.0001928997755753597,
|
774 |
+
"loss": 1.5915,
|
775 |
+
"step": 125
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.39,
|
779 |
+
"learning_rate": 0.00019277727129037508,
|
780 |
+
"loss": 1.617,
|
781 |
+
"step": 126
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4,
|
785 |
+
"learning_rate": 0.0001926537587857672,
|
786 |
+
"loss": 1.5582,
|
787 |
+
"step": 127
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.4,
|
791 |
+
"learning_rate": 0.00019252923940375844,
|
792 |
+
"loss": 1.6294,
|
793 |
+
"step": 128
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.4,
|
797 |
+
"learning_rate": 0.00019240371449751306,
|
798 |
+
"loss": 1.6087,
|
799 |
+
"step": 129
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.4,
|
803 |
+
"learning_rate": 0.00019227718543112236,
|
804 |
+
"loss": 1.5749,
|
805 |
+
"step": 130
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.41,
|
809 |
+
"learning_rate": 0.00019214965357959005,
|
810 |
+
"loss": 1.6041,
|
811 |
+
"step": 131
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.41,
|
815 |
+
"learning_rate": 0.00019202112032881715,
|
816 |
+
"loss": 1.6106,
|
817 |
+
"step": 132
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.41,
|
821 |
+
"learning_rate": 0.00019189158707558695,
|
822 |
+
"loss": 1.5553,
|
823 |
+
"step": 133
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.42,
|
827 |
+
"learning_rate": 0.00019176105522754995,
|
828 |
+
"loss": 1.5638,
|
829 |
+
"step": 134
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.42,
|
833 |
+
"learning_rate": 0.0001916295262032084,
|
834 |
+
"loss": 1.5921,
|
835 |
+
"step": 135
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.42,
|
839 |
+
"learning_rate": 0.00019149700143190096,
|
840 |
+
"loss": 1.5837,
|
841 |
+
"step": 136
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.43,
|
845 |
+
"learning_rate": 0.00019136348235378726,
|
846 |
+
"loss": 1.6341,
|
847 |
+
"step": 137
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.43,
|
851 |
+
"learning_rate": 0.00019122897041983205,
|
852 |
+
"loss": 1.5678,
|
853 |
+
"step": 138
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.43,
|
857 |
+
"learning_rate": 0.00019109346709178963,
|
858 |
+
"loss": 1.6137,
|
859 |
+
"step": 139
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.44,
|
863 |
+
"learning_rate": 0.0001909569738421878,
|
864 |
+
"loss": 1.6324,
|
865 |
+
"step": 140
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.44,
|
869 |
+
"learning_rate": 0.00019081949215431194,
|
870 |
+
"loss": 1.612,
|
871 |
+
"step": 141
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.44,
|
875 |
+
"learning_rate": 0.00019068102352218897,
|
876 |
+
"loss": 1.5908,
|
877 |
+
"step": 142
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.44,
|
881 |
+
"learning_rate": 0.00019054156945057097,
|
882 |
+
"loss": 1.6087,
|
883 |
+
"step": 143
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.45,
|
887 |
+
"learning_rate": 0.00019040113145491887,
|
888 |
+
"loss": 1.5613,
|
889 |
+
"step": 144
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.45,
|
893 |
+
"learning_rate": 0.000190259711061386,
|
894 |
+
"loss": 1.6072,
|
895 |
+
"step": 145
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.45,
|
899 |
+
"learning_rate": 0.00019011730980680156,
|
900 |
+
"loss": 1.5722,
|
901 |
+
"step": 146
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.46,
|
905 |
+
"learning_rate": 0.0001899739292386538,
|
906 |
+
"loss": 1.5961,
|
907 |
+
"step": 147
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.46,
|
911 |
+
"learning_rate": 0.00018982957091507325,
|
912 |
+
"loss": 1.5409,
|
913 |
+
"step": 148
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.46,
|
917 |
+
"learning_rate": 0.0001896842364048159,
|
918 |
+
"loss": 1.6557,
|
919 |
+
"step": 149
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.47,
|
923 |
+
"learning_rate": 0.000189537927287246,
|
924 |
+
"loss": 1.5725,
|
925 |
+
"step": 150
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 0.47,
|
929 |
+
"eval_loss": 1.6101970672607422,
|
930 |
+
"eval_runtime": 233.5313,
|
931 |
+
"eval_samples_per_second": 16.37,
|
932 |
+
"eval_steps_per_second": 4.094,
|
933 |
+
"step": 150
|
934 |
+
}
|
935 |
+
],
|
936 |
+
"logging_steps": 1,
|
937 |
+
"max_steps": 963,
|
938 |
+
"num_train_epochs": 3,
|
939 |
+
"save_steps": 50,
|
940 |
+
"total_flos": 4.206407486275584e+17,
|
941 |
+
"trial_name": null,
|
942 |
+
"trial_params": null
|
943 |
+
}
|
checkpoint-150/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f61cafb89242b653e455003b5517e685ecccfa6180af5fb7d0bfb35b4fc77a4
|
3 |
+
size 4475
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a22955168eaee3fb137ff861f71f50175e92e749a4651883a21a62d89a683d29
|
3 |
+
size 84046925
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60fecaee34f97b4a56b90bda6df1c46f987fd91ba3dac957aae197ea931cd966
|
3 |
+
size 168039109
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af60ac7a22907ef419c05b0c85df6ad791a63738c92e1690745698d449673a5f
|
3 |
+
size 14575
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:591a15d1a18d8da2c87f78ca1e99fd842dc60d1eb3d13c069154f369561b36af
|
3 |
+
size 627
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,1251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6065257787704468,
|
3 |
+
"best_model_checkpoint": "./lora-out/checkpoint-200",
|
4 |
+
"epoch": 0.6220839813374806,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 1.7924,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4e-05,
|
20 |
+
"loss": 1.8083,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 6e-05,
|
26 |
+
"loss": 1.8177,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 8e-05,
|
32 |
+
"loss": 1.7595,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 0.0001,
|
38 |
+
"loss": 1.6598,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 0.00012,
|
44 |
+
"loss": 1.6919,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.00014,
|
50 |
+
"loss": 1.6706,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.00016,
|
56 |
+
"loss": 1.6879,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.03,
|
61 |
+
"learning_rate": 0.00018,
|
62 |
+
"loss": 1.7051,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.7022,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.000199999456645141,
|
74 |
+
"loss": 1.6809,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.04,
|
79 |
+
"learning_rate": 0.00019999782658646859,
|
80 |
+
"loss": 1.6098,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.04,
|
85 |
+
"learning_rate": 0.0001999951098416968,
|
86 |
+
"loss": 1.7014,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 0.00019999130644034888,
|
92 |
+
"loss": 1.5885,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05,
|
97 |
+
"learning_rate": 0.00019998641642375657,
|
98 |
+
"loss": 1.6243,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.05,
|
103 |
+
"learning_rate": 0.00019998043984506027,
|
104 |
+
"loss": 1.6484,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.05,
|
109 |
+
"learning_rate": 0.00019997337676920803,
|
110 |
+
"loss": 1.6093,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.06,
|
115 |
+
"learning_rate": 0.00019996522727295496,
|
116 |
+
"loss": 1.6173,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.06,
|
121 |
+
"learning_rate": 0.00019995599144486247,
|
122 |
+
"loss": 1.646,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.06,
|
127 |
+
"learning_rate": 0.00019994566938529712,
|
128 |
+
"loss": 1.6469,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07,
|
133 |
+
"learning_rate": 0.00019993426120642983,
|
134 |
+
"loss": 1.6564,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07,
|
139 |
+
"learning_rate": 0.00019992176703223432,
|
140 |
+
"loss": 1.5901,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.07,
|
145 |
+
"learning_rate": 0.000199908186998486,
|
146 |
+
"loss": 1.664,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.07,
|
151 |
+
"learning_rate": 0.00019989352125276047,
|
152 |
+
"loss": 1.6275,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.08,
|
157 |
+
"learning_rate": 0.00019987776995443178,
|
158 |
+
"loss": 1.5839,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.08,
|
163 |
+
"learning_rate": 0.00019986093327467076,
|
164 |
+
"loss": 1.5611,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.08,
|
169 |
+
"learning_rate": 0.00019984301139644334,
|
170 |
+
"loss": 1.669,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.09,
|
175 |
+
"learning_rate": 0.0001998240045145083,
|
176 |
+
"loss": 1.5641,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09,
|
181 |
+
"learning_rate": 0.00019980391283541522,
|
182 |
+
"loss": 1.6023,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.09,
|
187 |
+
"learning_rate": 0.00019978273657750238,
|
188 |
+
"loss": 1.6309,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.1,
|
193 |
+
"learning_rate": 0.0001997604759708942,
|
194 |
+
"loss": 1.6353,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.1,
|
199 |
+
"learning_rate": 0.00019973713125749884,
|
200 |
+
"loss": 1.6328,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.1,
|
205 |
+
"learning_rate": 0.00019971270269100564,
|
206 |
+
"loss": 1.5683,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.11,
|
211 |
+
"learning_rate": 0.00019968719053688213,
|
212 |
+
"loss": 1.6217,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.11,
|
217 |
+
"learning_rate": 0.0001996605950723714,
|
218 |
+
"loss": 1.5734,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11,
|
223 |
+
"learning_rate": 0.00019963291658648896,
|
224 |
+
"loss": 1.6162,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.12,
|
229 |
+
"learning_rate": 0.00019960415538001957,
|
230 |
+
"loss": 1.5922,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.12,
|
235 |
+
"learning_rate": 0.0001995743117655141,
|
236 |
+
"loss": 1.5806,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.12,
|
241 |
+
"learning_rate": 0.000199543386067286,
|
242 |
+
"loss": 1.5938,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.12,
|
247 |
+
"learning_rate": 0.00019951137862140778,
|
248 |
+
"loss": 1.6386,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.13,
|
253 |
+
"learning_rate": 0.00019947828977570756,
|
254 |
+
"loss": 1.6476,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.13,
|
259 |
+
"learning_rate": 0.00019944411988976496,
|
260 |
+
"loss": 1.6557,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13,
|
265 |
+
"learning_rate": 0.00019940886933490749,
|
266 |
+
"loss": 1.5836,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.14,
|
271 |
+
"learning_rate": 0.00019937253849420635,
|
272 |
+
"loss": 1.6421,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.14,
|
277 |
+
"learning_rate": 0.0001993351277624723,
|
278 |
+
"loss": 1.629,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.14,
|
283 |
+
"learning_rate": 0.00019929663754625145,
|
284 |
+
"loss": 1.6392,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.15,
|
289 |
+
"learning_rate": 0.00019925706826382064,
|
290 |
+
"loss": 1.5677,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.15,
|
295 |
+
"learning_rate": 0.00019921642034518317,
|
296 |
+
"loss": 1.6144,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.15,
|
301 |
+
"learning_rate": 0.00019917469423206389,
|
302 |
+
"loss": 1.6068,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.16,
|
307 |
+
"learning_rate": 0.00019913189037790456,
|
308 |
+
"loss": 1.6421,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.16,
|
313 |
+
"eval_loss": 1.621693730354309,
|
314 |
+
"eval_runtime": 233.7603,
|
315 |
+
"eval_samples_per_second": 16.354,
|
316 |
+
"eval_steps_per_second": 4.09,
|
317 |
+
"step": 50
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16,
|
321 |
+
"learning_rate": 0.0001990880092478588,
|
322 |
+
"loss": 1.6172,
|
323 |
+
"step": 51
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.16,
|
327 |
+
"learning_rate": 0.0001990430513187871,
|
328 |
+
"loss": 1.6095,
|
329 |
+
"step": 52
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.16,
|
333 |
+
"learning_rate": 0.00019899701707925166,
|
334 |
+
"loss": 1.5967,
|
335 |
+
"step": 53
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.17,
|
339 |
+
"learning_rate": 0.00019894990702951106,
|
340 |
+
"loss": 1.617,
|
341 |
+
"step": 54
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.17,
|
345 |
+
"learning_rate": 0.00019890172168151473,
|
346 |
+
"loss": 1.5932,
|
347 |
+
"step": 55
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.17,
|
351 |
+
"learning_rate": 0.0001988524615588976,
|
352 |
+
"loss": 1.6548,
|
353 |
+
"step": 56
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.18,
|
357 |
+
"learning_rate": 0.00019880212719697413,
|
358 |
+
"loss": 1.6033,
|
359 |
+
"step": 57
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.18,
|
363 |
+
"learning_rate": 0.00019875071914273278,
|
364 |
+
"loss": 1.6063,
|
365 |
+
"step": 58
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.18,
|
369 |
+
"learning_rate": 0.00019869823795482986,
|
370 |
+
"loss": 1.6107,
|
371 |
+
"step": 59
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.19,
|
375 |
+
"learning_rate": 0.00019864468420358354,
|
376 |
+
"loss": 1.5758,
|
377 |
+
"step": 60
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.19,
|
381 |
+
"learning_rate": 0.00019859005847096763,
|
382 |
+
"loss": 1.5723,
|
383 |
+
"step": 61
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.19,
|
387 |
+
"learning_rate": 0.00019853436135060527,
|
388 |
+
"loss": 1.542,
|
389 |
+
"step": 62
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.2,
|
393 |
+
"learning_rate": 0.00019847759344776252,
|
394 |
+
"loss": 1.5611,
|
395 |
+
"step": 63
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.2,
|
399 |
+
"learning_rate": 0.00019841975537934162,
|
400 |
+
"loss": 1.6157,
|
401 |
+
"step": 64
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2,
|
405 |
+
"learning_rate": 0.00019836084777387458,
|
406 |
+
"loss": 1.5589,
|
407 |
+
"step": 65
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.21,
|
411 |
+
"learning_rate": 0.00019830087127151598,
|
412 |
+
"loss": 1.6077,
|
413 |
+
"step": 66
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.21,
|
417 |
+
"learning_rate": 0.00019823982652403634,
|
418 |
+
"loss": 1.5473,
|
419 |
+
"step": 67
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.21,
|
423 |
+
"learning_rate": 0.00019817771419481487,
|
424 |
+
"loss": 1.6265,
|
425 |
+
"step": 68
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.21,
|
429 |
+
"learning_rate": 0.0001981145349588323,
|
430 |
+
"loss": 1.6074,
|
431 |
+
"step": 69
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.22,
|
435 |
+
"learning_rate": 0.00019805028950266348,
|
436 |
+
"loss": 1.6195,
|
437 |
+
"step": 70
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.22,
|
441 |
+
"learning_rate": 0.00019798497852447006,
|
442 |
+
"loss": 1.5876,
|
443 |
+
"step": 71
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.22,
|
447 |
+
"learning_rate": 0.0001979186027339928,
|
448 |
+
"loss": 1.5978,
|
449 |
+
"step": 72
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.23,
|
453 |
+
"learning_rate": 0.00019785116285254381,
|
454 |
+
"loss": 1.533,
|
455 |
+
"step": 73
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.23,
|
459 |
+
"learning_rate": 0.00019778265961299888,
|
460 |
+
"loss": 1.5888,
|
461 |
+
"step": 74
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.23,
|
465 |
+
"learning_rate": 0.0001977130937597894,
|
466 |
+
"loss": 1.6211,
|
467 |
+
"step": 75
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.24,
|
471 |
+
"learning_rate": 0.00019764246604889415,
|
472 |
+
"loss": 1.6091,
|
473 |
+
"step": 76
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.24,
|
477 |
+
"learning_rate": 0.00019757077724783147,
|
478 |
+
"loss": 1.6012,
|
479 |
+
"step": 77
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.24,
|
483 |
+
"learning_rate": 0.0001974980281356504,
|
484 |
+
"loss": 1.6401,
|
485 |
+
"step": 78
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.25,
|
489 |
+
"learning_rate": 0.0001974242195029227,
|
490 |
+
"loss": 1.6111,
|
491 |
+
"step": 79
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.25,
|
495 |
+
"learning_rate": 0.00019734935215173392,
|
496 |
+
"loss": 1.6208,
|
497 |
+
"step": 80
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.25,
|
501 |
+
"learning_rate": 0.00019727342689567482,
|
502 |
+
"loss": 1.6038,
|
503 |
+
"step": 81
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.26,
|
507 |
+
"learning_rate": 0.00019719644455983256,
|
508 |
+
"loss": 1.5915,
|
509 |
+
"step": 82
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.26,
|
513 |
+
"learning_rate": 0.0001971184059807817,
|
514 |
+
"loss": 1.5872,
|
515 |
+
"step": 83
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.26,
|
519 |
+
"learning_rate": 0.000197039312006575,
|
520 |
+
"loss": 1.5984,
|
521 |
+
"step": 84
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.26,
|
525 |
+
"learning_rate": 0.0001969591634967344,
|
526 |
+
"loss": 1.5996,
|
527 |
+
"step": 85
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.27,
|
531 |
+
"learning_rate": 0.00019687796132224152,
|
532 |
+
"loss": 1.6056,
|
533 |
+
"step": 86
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.27,
|
537 |
+
"learning_rate": 0.0001967957063655283,
|
538 |
+
"loss": 1.6099,
|
539 |
+
"step": 87
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.27,
|
543 |
+
"learning_rate": 0.0001967123995204674,
|
544 |
+
"loss": 1.6295,
|
545 |
+
"step": 88
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.28,
|
549 |
+
"learning_rate": 0.00019662804169236225,
|
550 |
+
"loss": 1.5482,
|
551 |
+
"step": 89
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.28,
|
555 |
+
"learning_rate": 0.00019654263379793773,
|
556 |
+
"loss": 1.5781,
|
557 |
+
"step": 90
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.28,
|
561 |
+
"learning_rate": 0.00019645617676532963,
|
562 |
+
"loss": 1.5954,
|
563 |
+
"step": 91
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.29,
|
567 |
+
"learning_rate": 0.000196368671534075,
|
568 |
+
"loss": 1.619,
|
569 |
+
"step": 92
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.29,
|
573 |
+
"learning_rate": 0.0001962801190551016,
|
574 |
+
"loss": 1.6153,
|
575 |
+
"step": 93
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.29,
|
579 |
+
"learning_rate": 0.0001961905202907179,
|
580 |
+
"loss": 1.6008,
|
581 |
+
"step": 94
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.3,
|
585 |
+
"learning_rate": 0.00019609987621460232,
|
586 |
+
"loss": 1.5891,
|
587 |
+
"step": 95
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.3,
|
591 |
+
"learning_rate": 0.0001960081878117929,
|
592 |
+
"loss": 1.6438,
|
593 |
+
"step": 96
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.3,
|
597 |
+
"learning_rate": 0.0001959154560786764,
|
598 |
+
"loss": 1.5576,
|
599 |
+
"step": 97
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.3,
|
603 |
+
"learning_rate": 0.00019582168202297758,
|
604 |
+
"loss": 1.646,
|
605 |
+
"step": 98
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.31,
|
609 |
+
"learning_rate": 0.00019572686666374822,
|
610 |
+
"loss": 1.6269,
|
611 |
+
"step": 99
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.31,
|
615 |
+
"learning_rate": 0.00019563101103135602,
|
616 |
+
"loss": 1.6288,
|
617 |
+
"step": 100
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.31,
|
621 |
+
"eval_loss": 1.6143836975097656,
|
622 |
+
"eval_runtime": 233.6412,
|
623 |
+
"eval_samples_per_second": 16.363,
|
624 |
+
"eval_steps_per_second": 4.092,
|
625 |
+
"step": 100
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.31,
|
629 |
+
"learning_rate": 0.00019553411616747348,
|
630 |
+
"loss": 1.5667,
|
631 |
+
"step": 101
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.32,
|
635 |
+
"learning_rate": 0.00019543618312506647,
|
636 |
+
"loss": 1.6221,
|
637 |
+
"step": 102
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.32,
|
641 |
+
"learning_rate": 0.0001953372129683829,
|
642 |
+
"loss": 1.5992,
|
643 |
+
"step": 103
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.32,
|
647 |
+
"learning_rate": 0.0001952372067729411,
|
648 |
+
"loss": 1.6138,
|
649 |
+
"step": 104
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.33,
|
653 |
+
"learning_rate": 0.00019513616562551807,
|
654 |
+
"loss": 1.51,
|
655 |
+
"step": 105
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33,
|
659 |
+
"learning_rate": 0.00019503409062413782,
|
660 |
+
"loss": 1.6227,
|
661 |
+
"step": 106
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.33,
|
665 |
+
"learning_rate": 0.00019493098287805927,
|
666 |
+
"loss": 1.6014,
|
667 |
+
"step": 107
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.34,
|
671 |
+
"learning_rate": 0.00019482684350776434,
|
672 |
+
"loss": 1.625,
|
673 |
+
"step": 108
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.34,
|
677 |
+
"learning_rate": 0.0001947216736449457,
|
678 |
+
"loss": 1.6109,
|
679 |
+
"step": 109
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.34,
|
683 |
+
"learning_rate": 0.0001946154744324945,
|
684 |
+
"loss": 1.62,
|
685 |
+
"step": 110
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.35,
|
689 |
+
"learning_rate": 0.00019450824702448778,
|
690 |
+
"loss": 1.5878,
|
691 |
+
"step": 111
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.35,
|
695 |
+
"learning_rate": 0.0001943999925861763,
|
696 |
+
"loss": 1.6264,
|
697 |
+
"step": 112
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.35,
|
701 |
+
"learning_rate": 0.00019429071229397157,
|
702 |
+
"loss": 1.6186,
|
703 |
+
"step": 113
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.35,
|
707 |
+
"learning_rate": 0.0001941804073354331,
|
708 |
+
"loss": 1.6363,
|
709 |
+
"step": 114
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.36,
|
713 |
+
"learning_rate": 0.00019406907890925562,
|
714 |
+
"loss": 1.5341,
|
715 |
+
"step": 115
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.36,
|
719 |
+
"learning_rate": 0.00019395672822525593,
|
720 |
+
"loss": 1.5986,
|
721 |
+
"step": 116
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.36,
|
725 |
+
"learning_rate": 0.00019384335650435985,
|
726 |
+
"loss": 1.6181,
|
727 |
+
"step": 117
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.37,
|
731 |
+
"learning_rate": 0.0001937289649785889,
|
732 |
+
"loss": 1.6118,
|
733 |
+
"step": 118
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.37,
|
737 |
+
"learning_rate": 0.0001936135548910469,
|
738 |
+
"loss": 1.6404,
|
739 |
+
"step": 119
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.37,
|
743 |
+
"learning_rate": 0.00019349712749590649,
|
744 |
+
"loss": 1.583,
|
745 |
+
"step": 120
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.38,
|
749 |
+
"learning_rate": 0.00019337968405839547,
|
750 |
+
"loss": 1.5827,
|
751 |
+
"step": 121
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.38,
|
755 |
+
"learning_rate": 0.00019326122585478308,
|
756 |
+
"loss": 1.6392,
|
757 |
+
"step": 122
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.38,
|
761 |
+
"learning_rate": 0.00019314175417236616,
|
762 |
+
"loss": 1.5861,
|
763 |
+
"step": 123
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.39,
|
767 |
+
"learning_rate": 0.00019302127030945508,
|
768 |
+
"loss": 1.5738,
|
769 |
+
"step": 124
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.39,
|
773 |
+
"learning_rate": 0.0001928997755753597,
|
774 |
+
"loss": 1.5915,
|
775 |
+
"step": 125
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.39,
|
779 |
+
"learning_rate": 0.00019277727129037508,
|
780 |
+
"loss": 1.617,
|
781 |
+
"step": 126
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4,
|
785 |
+
"learning_rate": 0.0001926537587857672,
|
786 |
+
"loss": 1.5582,
|
787 |
+
"step": 127
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.4,
|
791 |
+
"learning_rate": 0.00019252923940375844,
|
792 |
+
"loss": 1.6294,
|
793 |
+
"step": 128
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.4,
|
797 |
+
"learning_rate": 0.00019240371449751306,
|
798 |
+
"loss": 1.6087,
|
799 |
+
"step": 129
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.4,
|
803 |
+
"learning_rate": 0.00019227718543112236,
|
804 |
+
"loss": 1.5749,
|
805 |
+
"step": 130
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.41,
|
809 |
+
"learning_rate": 0.00019214965357959005,
|
810 |
+
"loss": 1.6041,
|
811 |
+
"step": 131
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.41,
|
815 |
+
"learning_rate": 0.00019202112032881715,
|
816 |
+
"loss": 1.6106,
|
817 |
+
"step": 132
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.41,
|
821 |
+
"learning_rate": 0.00019189158707558695,
|
822 |
+
"loss": 1.5553,
|
823 |
+
"step": 133
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.42,
|
827 |
+
"learning_rate": 0.00019176105522754995,
|
828 |
+
"loss": 1.5638,
|
829 |
+
"step": 134
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.42,
|
833 |
+
"learning_rate": 0.0001916295262032084,
|
834 |
+
"loss": 1.5921,
|
835 |
+
"step": 135
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.42,
|
839 |
+
"learning_rate": 0.00019149700143190096,
|
840 |
+
"loss": 1.5837,
|
841 |
+
"step": 136
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.43,
|
845 |
+
"learning_rate": 0.00019136348235378726,
|
846 |
+
"loss": 1.6341,
|
847 |
+
"step": 137
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.43,
|
851 |
+
"learning_rate": 0.00019122897041983205,
|
852 |
+
"loss": 1.5678,
|
853 |
+
"step": 138
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.43,
|
857 |
+
"learning_rate": 0.00019109346709178963,
|
858 |
+
"loss": 1.6137,
|
859 |
+
"step": 139
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.44,
|
863 |
+
"learning_rate": 0.0001909569738421878,
|
864 |
+
"loss": 1.6324,
|
865 |
+
"step": 140
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.44,
|
869 |
+
"learning_rate": 0.00019081949215431194,
|
870 |
+
"loss": 1.612,
|
871 |
+
"step": 141
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.44,
|
875 |
+
"learning_rate": 0.00019068102352218897,
|
876 |
+
"loss": 1.5908,
|
877 |
+
"step": 142
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.44,
|
881 |
+
"learning_rate": 0.00019054156945057097,
|
882 |
+
"loss": 1.6087,
|
883 |
+
"step": 143
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.45,
|
887 |
+
"learning_rate": 0.00019040113145491887,
|
888 |
+
"loss": 1.5613,
|
889 |
+
"step": 144
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.45,
|
893 |
+
"learning_rate": 0.000190259711061386,
|
894 |
+
"loss": 1.6072,
|
895 |
+
"step": 145
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.45,
|
899 |
+
"learning_rate": 0.00019011730980680156,
|
900 |
+
"loss": 1.5722,
|
901 |
+
"step": 146
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.46,
|
905 |
+
"learning_rate": 0.0001899739292386538,
|
906 |
+
"loss": 1.5961,
|
907 |
+
"step": 147
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.46,
|
911 |
+
"learning_rate": 0.00018982957091507325,
|
912 |
+
"loss": 1.5409,
|
913 |
+
"step": 148
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.46,
|
917 |
+
"learning_rate": 0.0001896842364048159,
|
918 |
+
"loss": 1.6557,
|
919 |
+
"step": 149
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.47,
|
923 |
+
"learning_rate": 0.000189537927287246,
|
924 |
+
"loss": 1.5725,
|
925 |
+
"step": 150
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 0.47,
|
929 |
+
"eval_loss": 1.6101970672607422,
|
930 |
+
"eval_runtime": 233.5313,
|
931 |
+
"eval_samples_per_second": 16.37,
|
932 |
+
"eval_steps_per_second": 4.094,
|
933 |
+
"step": 150
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.47,
|
937 |
+
"learning_rate": 0.00018939064515231888,
|
938 |
+
"loss": 1.5949,
|
939 |
+
"step": 151
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.47,
|
943 |
+
"learning_rate": 0.0001892423916005639,
|
944 |
+
"loss": 1.6191,
|
945 |
+
"step": 152
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.48,
|
949 |
+
"learning_rate": 0.00018909316824306674,
|
950 |
+
"loss": 1.5487,
|
951 |
+
"step": 153
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.48,
|
955 |
+
"learning_rate": 0.00018894297670145216,
|
956 |
+
"loss": 1.5104,
|
957 |
+
"step": 154
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.48,
|
961 |
+
"learning_rate": 0.00018879181860786623,
|
962 |
+
"loss": 1.6392,
|
963 |
+
"step": 155
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.49,
|
967 |
+
"learning_rate": 0.00018863969560495866,
|
968 |
+
"loss": 1.5932,
|
969 |
+
"step": 156
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.49,
|
973 |
+
"learning_rate": 0.00018848660934586491,
|
974 |
+
"loss": 1.6213,
|
975 |
+
"step": 157
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.49,
|
979 |
+
"learning_rate": 0.0001883325614941882,
|
980 |
+
"loss": 1.5515,
|
981 |
+
"step": 158
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.49,
|
985 |
+
"learning_rate": 0.00018817755372398155,
|
986 |
+
"loss": 1.6166,
|
987 |
+
"step": 159
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.5,
|
991 |
+
"learning_rate": 0.00018802158771972943,
|
992 |
+
"loss": 1.6552,
|
993 |
+
"step": 160
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.5,
|
997 |
+
"learning_rate": 0.00018786466517632956,
|
998 |
+
"loss": 1.6378,
|
999 |
+
"step": 161
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5,
|
1003 |
+
"learning_rate": 0.00018770678779907448,
|
1004 |
+
"loss": 1.5176,
|
1005 |
+
"step": 162
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.51,
|
1009 |
+
"learning_rate": 0.00018754795730363302,
|
1010 |
+
"loss": 1.5793,
|
1011 |
+
"step": 163
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.51,
|
1015 |
+
"learning_rate": 0.00018738817541603156,
|
1016 |
+
"loss": 1.6616,
|
1017 |
+
"step": 164
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.51,
|
1021 |
+
"learning_rate": 0.00018722744387263544,
|
1022 |
+
"loss": 1.6055,
|
1023 |
+
"step": 165
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.52,
|
1027 |
+
"learning_rate": 0.00018706576442012994,
|
1028 |
+
"loss": 1.6204,
|
1029 |
+
"step": 166
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.52,
|
1033 |
+
"learning_rate": 0.00018690313881550137,
|
1034 |
+
"loss": 1.5952,
|
1035 |
+
"step": 167
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.52,
|
1039 |
+
"learning_rate": 0.00018673956882601803,
|
1040 |
+
"loss": 1.6271,
|
1041 |
+
"step": 168
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.53,
|
1045 |
+
"learning_rate": 0.00018657505622921082,
|
1046 |
+
"loss": 1.538,
|
1047 |
+
"step": 169
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.53,
|
1051 |
+
"learning_rate": 0.00018640960281285417,
|
1052 |
+
"loss": 1.5874,
|
1053 |
+
"step": 170
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.53,
|
1057 |
+
"learning_rate": 0.0001862432103749464,
|
1058 |
+
"loss": 1.5694,
|
1059 |
+
"step": 171
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.53,
|
1063 |
+
"learning_rate": 0.00018607588072369033,
|
1064 |
+
"loss": 1.583,
|
1065 |
+
"step": 172
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.54,
|
1069 |
+
"learning_rate": 0.00018590761567747354,
|
1070 |
+
"loss": 1.5961,
|
1071 |
+
"step": 173
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.54,
|
1075 |
+
"learning_rate": 0.00018573841706484866,
|
1076 |
+
"loss": 1.582,
|
1077 |
+
"step": 174
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.54,
|
1081 |
+
"learning_rate": 0.0001855682867245134,
|
1082 |
+
"loss": 1.6427,
|
1083 |
+
"step": 175
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.55,
|
1087 |
+
"learning_rate": 0.00018539722650529075,
|
1088 |
+
"loss": 1.604,
|
1089 |
+
"step": 176
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.55,
|
1093 |
+
"learning_rate": 0.00018522523826610868,
|
1094 |
+
"loss": 1.577,
|
1095 |
+
"step": 177
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.55,
|
1099 |
+
"learning_rate": 0.00018505232387598018,
|
1100 |
+
"loss": 1.6339,
|
1101 |
+
"step": 178
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.56,
|
1105 |
+
"learning_rate": 0.00018487848521398265,
|
1106 |
+
"loss": 1.5993,
|
1107 |
+
"step": 179
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.56,
|
1111 |
+
"learning_rate": 0.0001847037241692378,
|
1112 |
+
"loss": 1.6286,
|
1113 |
+
"step": 180
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.56,
|
1117 |
+
"learning_rate": 0.00018452804264089084,
|
1118 |
+
"loss": 1.5963,
|
1119 |
+
"step": 181
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.57,
|
1123 |
+
"learning_rate": 0.00018435144253809,
|
1124 |
+
"loss": 1.5856,
|
1125 |
+
"step": 182
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.57,
|
1129 |
+
"learning_rate": 0.00018417392577996578,
|
1130 |
+
"loss": 1.5787,
|
1131 |
+
"step": 183
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.57,
|
1135 |
+
"learning_rate": 0.00018399549429561006,
|
1136 |
+
"loss": 1.5876,
|
1137 |
+
"step": 184
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.58,
|
1141 |
+
"learning_rate": 0.00018381615002405509,
|
1142 |
+
"loss": 1.5565,
|
1143 |
+
"step": 185
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.58,
|
1147 |
+
"learning_rate": 0.00018363589491425248,
|
1148 |
+
"loss": 1.5897,
|
1149 |
+
"step": 186
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.58,
|
1153 |
+
"learning_rate": 0.0001834547309250521,
|
1154 |
+
"loss": 1.5951,
|
1155 |
+
"step": 187
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.58,
|
1159 |
+
"learning_rate": 0.00018327266002518056,
|
1160 |
+
"loss": 1.5447,
|
1161 |
+
"step": 188
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.59,
|
1165 |
+
"learning_rate": 0.00018308968419322003,
|
1166 |
+
"loss": 1.6087,
|
1167 |
+
"step": 189
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.59,
|
1171 |
+
"learning_rate": 0.00018290580541758668,
|
1172 |
+
"loss": 1.5946,
|
1173 |
+
"step": 190
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.59,
|
1177 |
+
"learning_rate": 0.00018272102569650905,
|
1178 |
+
"loss": 1.6148,
|
1179 |
+
"step": 191
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6,
|
1183 |
+
"learning_rate": 0.00018253534703800627,
|
1184 |
+
"loss": 1.649,
|
1185 |
+
"step": 192
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.6,
|
1189 |
+
"learning_rate": 0.0001823487714598664,
|
1190 |
+
"loss": 1.6312,
|
1191 |
+
"step": 193
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.6,
|
1195 |
+
"learning_rate": 0.0001821613009896244,
|
1196 |
+
"loss": 1.5858,
|
1197 |
+
"step": 194
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.61,
|
1201 |
+
"learning_rate": 0.00018197293766454003,
|
1202 |
+
"loss": 1.5925,
|
1203 |
+
"step": 195
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.61,
|
1207 |
+
"learning_rate": 0.0001817836835315759,
|
1208 |
+
"loss": 1.5604,
|
1209 |
+
"step": 196
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.61,
|
1213 |
+
"learning_rate": 0.00018159354064737506,
|
1214 |
+
"loss": 1.6125,
|
1215 |
+
"step": 197
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.62,
|
1219 |
+
"learning_rate": 0.0001814025110782387,
|
1220 |
+
"loss": 1.5954,
|
1221 |
+
"step": 198
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.62,
|
1225 |
+
"learning_rate": 0.00018121059690010368,
|
1226 |
+
"loss": 1.5937,
|
1227 |
+
"step": 199
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.62,
|
1231 |
+
"learning_rate": 0.00018101780019852008,
|
1232 |
+
"loss": 1.5582,
|
1233 |
+
"step": 200
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.62,
|
1237 |
+
"eval_loss": 1.6065257787704468,
|
1238 |
+
"eval_runtime": 233.7919,
|
1239 |
+
"eval_samples_per_second": 16.352,
|
1240 |
+
"eval_steps_per_second": 4.089,
|
1241 |
+
"step": 200
|
1242 |
+
}
|
1243 |
+
],
|
1244 |
+
"logging_steps": 1,
|
1245 |
+
"max_steps": 963,
|
1246 |
+
"num_train_epochs": 3,
|
1247 |
+
"save_steps": 50,
|
1248 |
+
"total_flos": 5.608543315034112e+17,
|
1249 |
+
"trial_name": null,
|
1250 |
+
"trial_params": null
|
1251 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f61cafb89242b653e455003b5517e685ecccfa6180af5fb7d0bfb35b4fc77a4
|
3 |
+
size 4475
|
checkpoint-250/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-250/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-250/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8f2be5e57601e9471651b0e8821845228d7a8b73ebbaea4df07cd4de3b3ac0d
|
3 |
+
size 84046925
|
checkpoint-250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce35862ebc0e21a86a1e6281a6822907917216d33e0560244de74624d72d7204
|
3 |
+
size 168039109
|
checkpoint-250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6223a05bbaac028fbfc88016641eb39c4bc95a13c0658c4f8611997cc29c5e41
|
3 |
+
size 14575
|
checkpoint-250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a922f36e3287f78e28f040c3193d729dfc63546fcf6eb66508241f493732d059
|
3 |
+
size 627
|
checkpoint-250/trainer_state.json
ADDED
@@ -0,0 +1,1559 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.60513174533844,
|
3 |
+
"best_model_checkpoint": "./lora-out/checkpoint-250",
|
4 |
+
"epoch": 0.7776049766718507,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 1.7924,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4e-05,
|
20 |
+
"loss": 1.8083,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 6e-05,
|
26 |
+
"loss": 1.8177,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 8e-05,
|
32 |
+
"loss": 1.7595,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 0.0001,
|
38 |
+
"loss": 1.6598,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 0.00012,
|
44 |
+
"loss": 1.6919,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.00014,
|
50 |
+
"loss": 1.6706,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.00016,
|
56 |
+
"loss": 1.6879,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.03,
|
61 |
+
"learning_rate": 0.00018,
|
62 |
+
"loss": 1.7051,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.7022,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.000199999456645141,
|
74 |
+
"loss": 1.6809,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.04,
|
79 |
+
"learning_rate": 0.00019999782658646859,
|
80 |
+
"loss": 1.6098,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.04,
|
85 |
+
"learning_rate": 0.0001999951098416968,
|
86 |
+
"loss": 1.7014,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 0.00019999130644034888,
|
92 |
+
"loss": 1.5885,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05,
|
97 |
+
"learning_rate": 0.00019998641642375657,
|
98 |
+
"loss": 1.6243,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.05,
|
103 |
+
"learning_rate": 0.00019998043984506027,
|
104 |
+
"loss": 1.6484,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.05,
|
109 |
+
"learning_rate": 0.00019997337676920803,
|
110 |
+
"loss": 1.6093,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.06,
|
115 |
+
"learning_rate": 0.00019996522727295496,
|
116 |
+
"loss": 1.6173,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.06,
|
121 |
+
"learning_rate": 0.00019995599144486247,
|
122 |
+
"loss": 1.646,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.06,
|
127 |
+
"learning_rate": 0.00019994566938529712,
|
128 |
+
"loss": 1.6469,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07,
|
133 |
+
"learning_rate": 0.00019993426120642983,
|
134 |
+
"loss": 1.6564,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07,
|
139 |
+
"learning_rate": 0.00019992176703223432,
|
140 |
+
"loss": 1.5901,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.07,
|
145 |
+
"learning_rate": 0.000199908186998486,
|
146 |
+
"loss": 1.664,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.07,
|
151 |
+
"learning_rate": 0.00019989352125276047,
|
152 |
+
"loss": 1.6275,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.08,
|
157 |
+
"learning_rate": 0.00019987776995443178,
|
158 |
+
"loss": 1.5839,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.08,
|
163 |
+
"learning_rate": 0.00019986093327467076,
|
164 |
+
"loss": 1.5611,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.08,
|
169 |
+
"learning_rate": 0.00019984301139644334,
|
170 |
+
"loss": 1.669,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.09,
|
175 |
+
"learning_rate": 0.0001998240045145083,
|
176 |
+
"loss": 1.5641,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09,
|
181 |
+
"learning_rate": 0.00019980391283541522,
|
182 |
+
"loss": 1.6023,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.09,
|
187 |
+
"learning_rate": 0.00019978273657750238,
|
188 |
+
"loss": 1.6309,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.1,
|
193 |
+
"learning_rate": 0.0001997604759708942,
|
194 |
+
"loss": 1.6353,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.1,
|
199 |
+
"learning_rate": 0.00019973713125749884,
|
200 |
+
"loss": 1.6328,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.1,
|
205 |
+
"learning_rate": 0.00019971270269100564,
|
206 |
+
"loss": 1.5683,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.11,
|
211 |
+
"learning_rate": 0.00019968719053688213,
|
212 |
+
"loss": 1.6217,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.11,
|
217 |
+
"learning_rate": 0.0001996605950723714,
|
218 |
+
"loss": 1.5734,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11,
|
223 |
+
"learning_rate": 0.00019963291658648896,
|
224 |
+
"loss": 1.6162,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.12,
|
229 |
+
"learning_rate": 0.00019960415538001957,
|
230 |
+
"loss": 1.5922,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.12,
|
235 |
+
"learning_rate": 0.0001995743117655141,
|
236 |
+
"loss": 1.5806,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.12,
|
241 |
+
"learning_rate": 0.000199543386067286,
|
242 |
+
"loss": 1.5938,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.12,
|
247 |
+
"learning_rate": 0.00019951137862140778,
|
248 |
+
"loss": 1.6386,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.13,
|
253 |
+
"learning_rate": 0.00019947828977570756,
|
254 |
+
"loss": 1.6476,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.13,
|
259 |
+
"learning_rate": 0.00019944411988976496,
|
260 |
+
"loss": 1.6557,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13,
|
265 |
+
"learning_rate": 0.00019940886933490749,
|
266 |
+
"loss": 1.5836,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.14,
|
271 |
+
"learning_rate": 0.00019937253849420635,
|
272 |
+
"loss": 1.6421,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.14,
|
277 |
+
"learning_rate": 0.0001993351277624723,
|
278 |
+
"loss": 1.629,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.14,
|
283 |
+
"learning_rate": 0.00019929663754625145,
|
284 |
+
"loss": 1.6392,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.15,
|
289 |
+
"learning_rate": 0.00019925706826382064,
|
290 |
+
"loss": 1.5677,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.15,
|
295 |
+
"learning_rate": 0.00019921642034518317,
|
296 |
+
"loss": 1.6144,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.15,
|
301 |
+
"learning_rate": 0.00019917469423206389,
|
302 |
+
"loss": 1.6068,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.16,
|
307 |
+
"learning_rate": 0.00019913189037790456,
|
308 |
+
"loss": 1.6421,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.16,
|
313 |
+
"eval_loss": 1.621693730354309,
|
314 |
+
"eval_runtime": 233.7603,
|
315 |
+
"eval_samples_per_second": 16.354,
|
316 |
+
"eval_steps_per_second": 4.09,
|
317 |
+
"step": 50
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16,
|
321 |
+
"learning_rate": 0.0001990880092478588,
|
322 |
+
"loss": 1.6172,
|
323 |
+
"step": 51
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.16,
|
327 |
+
"learning_rate": 0.0001990430513187871,
|
328 |
+
"loss": 1.6095,
|
329 |
+
"step": 52
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.16,
|
333 |
+
"learning_rate": 0.00019899701707925166,
|
334 |
+
"loss": 1.5967,
|
335 |
+
"step": 53
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.17,
|
339 |
+
"learning_rate": 0.00019894990702951106,
|
340 |
+
"loss": 1.617,
|
341 |
+
"step": 54
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.17,
|
345 |
+
"learning_rate": 0.00019890172168151473,
|
346 |
+
"loss": 1.5932,
|
347 |
+
"step": 55
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.17,
|
351 |
+
"learning_rate": 0.0001988524615588976,
|
352 |
+
"loss": 1.6548,
|
353 |
+
"step": 56
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.18,
|
357 |
+
"learning_rate": 0.00019880212719697413,
|
358 |
+
"loss": 1.6033,
|
359 |
+
"step": 57
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.18,
|
363 |
+
"learning_rate": 0.00019875071914273278,
|
364 |
+
"loss": 1.6063,
|
365 |
+
"step": 58
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.18,
|
369 |
+
"learning_rate": 0.00019869823795482986,
|
370 |
+
"loss": 1.6107,
|
371 |
+
"step": 59
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.19,
|
375 |
+
"learning_rate": 0.00019864468420358354,
|
376 |
+
"loss": 1.5758,
|
377 |
+
"step": 60
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.19,
|
381 |
+
"learning_rate": 0.00019859005847096763,
|
382 |
+
"loss": 1.5723,
|
383 |
+
"step": 61
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.19,
|
387 |
+
"learning_rate": 0.00019853436135060527,
|
388 |
+
"loss": 1.542,
|
389 |
+
"step": 62
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.2,
|
393 |
+
"learning_rate": 0.00019847759344776252,
|
394 |
+
"loss": 1.5611,
|
395 |
+
"step": 63
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.2,
|
399 |
+
"learning_rate": 0.00019841975537934162,
|
400 |
+
"loss": 1.6157,
|
401 |
+
"step": 64
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2,
|
405 |
+
"learning_rate": 0.00019836084777387458,
|
406 |
+
"loss": 1.5589,
|
407 |
+
"step": 65
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.21,
|
411 |
+
"learning_rate": 0.00019830087127151598,
|
412 |
+
"loss": 1.6077,
|
413 |
+
"step": 66
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.21,
|
417 |
+
"learning_rate": 0.00019823982652403634,
|
418 |
+
"loss": 1.5473,
|
419 |
+
"step": 67
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.21,
|
423 |
+
"learning_rate": 0.00019817771419481487,
|
424 |
+
"loss": 1.6265,
|
425 |
+
"step": 68
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.21,
|
429 |
+
"learning_rate": 0.0001981145349588323,
|
430 |
+
"loss": 1.6074,
|
431 |
+
"step": 69
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.22,
|
435 |
+
"learning_rate": 0.00019805028950266348,
|
436 |
+
"loss": 1.6195,
|
437 |
+
"step": 70
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.22,
|
441 |
+
"learning_rate": 0.00019798497852447006,
|
442 |
+
"loss": 1.5876,
|
443 |
+
"step": 71
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.22,
|
447 |
+
"learning_rate": 0.0001979186027339928,
|
448 |
+
"loss": 1.5978,
|
449 |
+
"step": 72
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.23,
|
453 |
+
"learning_rate": 0.00019785116285254381,
|
454 |
+
"loss": 1.533,
|
455 |
+
"step": 73
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.23,
|
459 |
+
"learning_rate": 0.00019778265961299888,
|
460 |
+
"loss": 1.5888,
|
461 |
+
"step": 74
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.23,
|
465 |
+
"learning_rate": 0.0001977130937597894,
|
466 |
+
"loss": 1.6211,
|
467 |
+
"step": 75
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.24,
|
471 |
+
"learning_rate": 0.00019764246604889415,
|
472 |
+
"loss": 1.6091,
|
473 |
+
"step": 76
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.24,
|
477 |
+
"learning_rate": 0.00019757077724783147,
|
478 |
+
"loss": 1.6012,
|
479 |
+
"step": 77
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.24,
|
483 |
+
"learning_rate": 0.0001974980281356504,
|
484 |
+
"loss": 1.6401,
|
485 |
+
"step": 78
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.25,
|
489 |
+
"learning_rate": 0.0001974242195029227,
|
490 |
+
"loss": 1.6111,
|
491 |
+
"step": 79
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.25,
|
495 |
+
"learning_rate": 0.00019734935215173392,
|
496 |
+
"loss": 1.6208,
|
497 |
+
"step": 80
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.25,
|
501 |
+
"learning_rate": 0.00019727342689567482,
|
502 |
+
"loss": 1.6038,
|
503 |
+
"step": 81
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.26,
|
507 |
+
"learning_rate": 0.00019719644455983256,
|
508 |
+
"loss": 1.5915,
|
509 |
+
"step": 82
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.26,
|
513 |
+
"learning_rate": 0.0001971184059807817,
|
514 |
+
"loss": 1.5872,
|
515 |
+
"step": 83
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.26,
|
519 |
+
"learning_rate": 0.000197039312006575,
|
520 |
+
"loss": 1.5984,
|
521 |
+
"step": 84
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.26,
|
525 |
+
"learning_rate": 0.0001969591634967344,
|
526 |
+
"loss": 1.5996,
|
527 |
+
"step": 85
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.27,
|
531 |
+
"learning_rate": 0.00019687796132224152,
|
532 |
+
"loss": 1.6056,
|
533 |
+
"step": 86
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.27,
|
537 |
+
"learning_rate": 0.0001967957063655283,
|
538 |
+
"loss": 1.6099,
|
539 |
+
"step": 87
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.27,
|
543 |
+
"learning_rate": 0.0001967123995204674,
|
544 |
+
"loss": 1.6295,
|
545 |
+
"step": 88
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.28,
|
549 |
+
"learning_rate": 0.00019662804169236225,
|
550 |
+
"loss": 1.5482,
|
551 |
+
"step": 89
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.28,
|
555 |
+
"learning_rate": 0.00019654263379793773,
|
556 |
+
"loss": 1.5781,
|
557 |
+
"step": 90
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.28,
|
561 |
+
"learning_rate": 0.00019645617676532963,
|
562 |
+
"loss": 1.5954,
|
563 |
+
"step": 91
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.29,
|
567 |
+
"learning_rate": 0.000196368671534075,
|
568 |
+
"loss": 1.619,
|
569 |
+
"step": 92
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.29,
|
573 |
+
"learning_rate": 0.0001962801190551016,
|
574 |
+
"loss": 1.6153,
|
575 |
+
"step": 93
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.29,
|
579 |
+
"learning_rate": 0.0001961905202907179,
|
580 |
+
"loss": 1.6008,
|
581 |
+
"step": 94
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.3,
|
585 |
+
"learning_rate": 0.00019609987621460232,
|
586 |
+
"loss": 1.5891,
|
587 |
+
"step": 95
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.3,
|
591 |
+
"learning_rate": 0.0001960081878117929,
|
592 |
+
"loss": 1.6438,
|
593 |
+
"step": 96
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.3,
|
597 |
+
"learning_rate": 0.0001959154560786764,
|
598 |
+
"loss": 1.5576,
|
599 |
+
"step": 97
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.3,
|
603 |
+
"learning_rate": 0.00019582168202297758,
|
604 |
+
"loss": 1.646,
|
605 |
+
"step": 98
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.31,
|
609 |
+
"learning_rate": 0.00019572686666374822,
|
610 |
+
"loss": 1.6269,
|
611 |
+
"step": 99
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.31,
|
615 |
+
"learning_rate": 0.00019563101103135602,
|
616 |
+
"loss": 1.6288,
|
617 |
+
"step": 100
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.31,
|
621 |
+
"eval_loss": 1.6143836975097656,
|
622 |
+
"eval_runtime": 233.6412,
|
623 |
+
"eval_samples_per_second": 16.363,
|
624 |
+
"eval_steps_per_second": 4.092,
|
625 |
+
"step": 100
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.31,
|
629 |
+
"learning_rate": 0.00019553411616747348,
|
630 |
+
"loss": 1.5667,
|
631 |
+
"step": 101
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.32,
|
635 |
+
"learning_rate": 0.00019543618312506647,
|
636 |
+
"loss": 1.6221,
|
637 |
+
"step": 102
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.32,
|
641 |
+
"learning_rate": 0.0001953372129683829,
|
642 |
+
"loss": 1.5992,
|
643 |
+
"step": 103
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.32,
|
647 |
+
"learning_rate": 0.0001952372067729411,
|
648 |
+
"loss": 1.6138,
|
649 |
+
"step": 104
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.33,
|
653 |
+
"learning_rate": 0.00019513616562551807,
|
654 |
+
"loss": 1.51,
|
655 |
+
"step": 105
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33,
|
659 |
+
"learning_rate": 0.00019503409062413782,
|
660 |
+
"loss": 1.6227,
|
661 |
+
"step": 106
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.33,
|
665 |
+
"learning_rate": 0.00019493098287805927,
|
666 |
+
"loss": 1.6014,
|
667 |
+
"step": 107
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.34,
|
671 |
+
"learning_rate": 0.00019482684350776434,
|
672 |
+
"loss": 1.625,
|
673 |
+
"step": 108
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.34,
|
677 |
+
"learning_rate": 0.0001947216736449457,
|
678 |
+
"loss": 1.6109,
|
679 |
+
"step": 109
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.34,
|
683 |
+
"learning_rate": 0.0001946154744324945,
|
684 |
+
"loss": 1.62,
|
685 |
+
"step": 110
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.35,
|
689 |
+
"learning_rate": 0.00019450824702448778,
|
690 |
+
"loss": 1.5878,
|
691 |
+
"step": 111
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.35,
|
695 |
+
"learning_rate": 0.0001943999925861763,
|
696 |
+
"loss": 1.6264,
|
697 |
+
"step": 112
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.35,
|
701 |
+
"learning_rate": 0.00019429071229397157,
|
702 |
+
"loss": 1.6186,
|
703 |
+
"step": 113
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.35,
|
707 |
+
"learning_rate": 0.0001941804073354331,
|
708 |
+
"loss": 1.6363,
|
709 |
+
"step": 114
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.36,
|
713 |
+
"learning_rate": 0.00019406907890925562,
|
714 |
+
"loss": 1.5341,
|
715 |
+
"step": 115
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.36,
|
719 |
+
"learning_rate": 0.00019395672822525593,
|
720 |
+
"loss": 1.5986,
|
721 |
+
"step": 116
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.36,
|
725 |
+
"learning_rate": 0.00019384335650435985,
|
726 |
+
"loss": 1.6181,
|
727 |
+
"step": 117
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.37,
|
731 |
+
"learning_rate": 0.0001937289649785889,
|
732 |
+
"loss": 1.6118,
|
733 |
+
"step": 118
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.37,
|
737 |
+
"learning_rate": 0.0001936135548910469,
|
738 |
+
"loss": 1.6404,
|
739 |
+
"step": 119
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.37,
|
743 |
+
"learning_rate": 0.00019349712749590649,
|
744 |
+
"loss": 1.583,
|
745 |
+
"step": 120
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.38,
|
749 |
+
"learning_rate": 0.00019337968405839547,
|
750 |
+
"loss": 1.5827,
|
751 |
+
"step": 121
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.38,
|
755 |
+
"learning_rate": 0.00019326122585478308,
|
756 |
+
"loss": 1.6392,
|
757 |
+
"step": 122
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.38,
|
761 |
+
"learning_rate": 0.00019314175417236616,
|
762 |
+
"loss": 1.5861,
|
763 |
+
"step": 123
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.39,
|
767 |
+
"learning_rate": 0.00019302127030945508,
|
768 |
+
"loss": 1.5738,
|
769 |
+
"step": 124
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.39,
|
773 |
+
"learning_rate": 0.0001928997755753597,
|
774 |
+
"loss": 1.5915,
|
775 |
+
"step": 125
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.39,
|
779 |
+
"learning_rate": 0.00019277727129037508,
|
780 |
+
"loss": 1.617,
|
781 |
+
"step": 126
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4,
|
785 |
+
"learning_rate": 0.0001926537587857672,
|
786 |
+
"loss": 1.5582,
|
787 |
+
"step": 127
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.4,
|
791 |
+
"learning_rate": 0.00019252923940375844,
|
792 |
+
"loss": 1.6294,
|
793 |
+
"step": 128
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.4,
|
797 |
+
"learning_rate": 0.00019240371449751306,
|
798 |
+
"loss": 1.6087,
|
799 |
+
"step": 129
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.4,
|
803 |
+
"learning_rate": 0.00019227718543112236,
|
804 |
+
"loss": 1.5749,
|
805 |
+
"step": 130
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.41,
|
809 |
+
"learning_rate": 0.00019214965357959005,
|
810 |
+
"loss": 1.6041,
|
811 |
+
"step": 131
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.41,
|
815 |
+
"learning_rate": 0.00019202112032881715,
|
816 |
+
"loss": 1.6106,
|
817 |
+
"step": 132
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.41,
|
821 |
+
"learning_rate": 0.00019189158707558695,
|
822 |
+
"loss": 1.5553,
|
823 |
+
"step": 133
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.42,
|
827 |
+
"learning_rate": 0.00019176105522754995,
|
828 |
+
"loss": 1.5638,
|
829 |
+
"step": 134
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.42,
|
833 |
+
"learning_rate": 0.0001916295262032084,
|
834 |
+
"loss": 1.5921,
|
835 |
+
"step": 135
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.42,
|
839 |
+
"learning_rate": 0.00019149700143190096,
|
840 |
+
"loss": 1.5837,
|
841 |
+
"step": 136
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.43,
|
845 |
+
"learning_rate": 0.00019136348235378726,
|
846 |
+
"loss": 1.6341,
|
847 |
+
"step": 137
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.43,
|
851 |
+
"learning_rate": 0.00019122897041983205,
|
852 |
+
"loss": 1.5678,
|
853 |
+
"step": 138
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.43,
|
857 |
+
"learning_rate": 0.00019109346709178963,
|
858 |
+
"loss": 1.6137,
|
859 |
+
"step": 139
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.44,
|
863 |
+
"learning_rate": 0.0001909569738421878,
|
864 |
+
"loss": 1.6324,
|
865 |
+
"step": 140
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.44,
|
869 |
+
"learning_rate": 0.00019081949215431194,
|
870 |
+
"loss": 1.612,
|
871 |
+
"step": 141
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.44,
|
875 |
+
"learning_rate": 0.00019068102352218897,
|
876 |
+
"loss": 1.5908,
|
877 |
+
"step": 142
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.44,
|
881 |
+
"learning_rate": 0.00019054156945057097,
|
882 |
+
"loss": 1.6087,
|
883 |
+
"step": 143
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.45,
|
887 |
+
"learning_rate": 0.00019040113145491887,
|
888 |
+
"loss": 1.5613,
|
889 |
+
"step": 144
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.45,
|
893 |
+
"learning_rate": 0.000190259711061386,
|
894 |
+
"loss": 1.6072,
|
895 |
+
"step": 145
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.45,
|
899 |
+
"learning_rate": 0.00019011730980680156,
|
900 |
+
"loss": 1.5722,
|
901 |
+
"step": 146
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.46,
|
905 |
+
"learning_rate": 0.0001899739292386538,
|
906 |
+
"loss": 1.5961,
|
907 |
+
"step": 147
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.46,
|
911 |
+
"learning_rate": 0.00018982957091507325,
|
912 |
+
"loss": 1.5409,
|
913 |
+
"step": 148
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.46,
|
917 |
+
"learning_rate": 0.0001896842364048159,
|
918 |
+
"loss": 1.6557,
|
919 |
+
"step": 149
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.47,
|
923 |
+
"learning_rate": 0.000189537927287246,
|
924 |
+
"loss": 1.5725,
|
925 |
+
"step": 150
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 0.47,
|
929 |
+
"eval_loss": 1.6101970672607422,
|
930 |
+
"eval_runtime": 233.5313,
|
931 |
+
"eval_samples_per_second": 16.37,
|
932 |
+
"eval_steps_per_second": 4.094,
|
933 |
+
"step": 150
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.47,
|
937 |
+
"learning_rate": 0.00018939064515231888,
|
938 |
+
"loss": 1.5949,
|
939 |
+
"step": 151
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.47,
|
943 |
+
"learning_rate": 0.0001892423916005639,
|
944 |
+
"loss": 1.6191,
|
945 |
+
"step": 152
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.48,
|
949 |
+
"learning_rate": 0.00018909316824306674,
|
950 |
+
"loss": 1.5487,
|
951 |
+
"step": 153
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.48,
|
955 |
+
"learning_rate": 0.00018894297670145216,
|
956 |
+
"loss": 1.5104,
|
957 |
+
"step": 154
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.48,
|
961 |
+
"learning_rate": 0.00018879181860786623,
|
962 |
+
"loss": 1.6392,
|
963 |
+
"step": 155
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.49,
|
967 |
+
"learning_rate": 0.00018863969560495866,
|
968 |
+
"loss": 1.5932,
|
969 |
+
"step": 156
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.49,
|
973 |
+
"learning_rate": 0.00018848660934586491,
|
974 |
+
"loss": 1.6213,
|
975 |
+
"step": 157
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.49,
|
979 |
+
"learning_rate": 0.0001883325614941882,
|
980 |
+
"loss": 1.5515,
|
981 |
+
"step": 158
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.49,
|
985 |
+
"learning_rate": 0.00018817755372398155,
|
986 |
+
"loss": 1.6166,
|
987 |
+
"step": 159
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.5,
|
991 |
+
"learning_rate": 0.00018802158771972943,
|
992 |
+
"loss": 1.6552,
|
993 |
+
"step": 160
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.5,
|
997 |
+
"learning_rate": 0.00018786466517632956,
|
998 |
+
"loss": 1.6378,
|
999 |
+
"step": 161
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5,
|
1003 |
+
"learning_rate": 0.00018770678779907448,
|
1004 |
+
"loss": 1.5176,
|
1005 |
+
"step": 162
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.51,
|
1009 |
+
"learning_rate": 0.00018754795730363302,
|
1010 |
+
"loss": 1.5793,
|
1011 |
+
"step": 163
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.51,
|
1015 |
+
"learning_rate": 0.00018738817541603156,
|
1016 |
+
"loss": 1.6616,
|
1017 |
+
"step": 164
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.51,
|
1021 |
+
"learning_rate": 0.00018722744387263544,
|
1022 |
+
"loss": 1.6055,
|
1023 |
+
"step": 165
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.52,
|
1027 |
+
"learning_rate": 0.00018706576442012994,
|
1028 |
+
"loss": 1.6204,
|
1029 |
+
"step": 166
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.52,
|
1033 |
+
"learning_rate": 0.00018690313881550137,
|
1034 |
+
"loss": 1.5952,
|
1035 |
+
"step": 167
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.52,
|
1039 |
+
"learning_rate": 0.00018673956882601803,
|
1040 |
+
"loss": 1.6271,
|
1041 |
+
"step": 168
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.53,
|
1045 |
+
"learning_rate": 0.00018657505622921082,
|
1046 |
+
"loss": 1.538,
|
1047 |
+
"step": 169
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.53,
|
1051 |
+
"learning_rate": 0.00018640960281285417,
|
1052 |
+
"loss": 1.5874,
|
1053 |
+
"step": 170
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.53,
|
1057 |
+
"learning_rate": 0.0001862432103749464,
|
1058 |
+
"loss": 1.5694,
|
1059 |
+
"step": 171
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.53,
|
1063 |
+
"learning_rate": 0.00018607588072369033,
|
1064 |
+
"loss": 1.583,
|
1065 |
+
"step": 172
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.54,
|
1069 |
+
"learning_rate": 0.00018590761567747354,
|
1070 |
+
"loss": 1.5961,
|
1071 |
+
"step": 173
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.54,
|
1075 |
+
"learning_rate": 0.00018573841706484866,
|
1076 |
+
"loss": 1.582,
|
1077 |
+
"step": 174
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.54,
|
1081 |
+
"learning_rate": 0.0001855682867245134,
|
1082 |
+
"loss": 1.6427,
|
1083 |
+
"step": 175
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.55,
|
1087 |
+
"learning_rate": 0.00018539722650529075,
|
1088 |
+
"loss": 1.604,
|
1089 |
+
"step": 176
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.55,
|
1093 |
+
"learning_rate": 0.00018522523826610868,
|
1094 |
+
"loss": 1.577,
|
1095 |
+
"step": 177
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.55,
|
1099 |
+
"learning_rate": 0.00018505232387598018,
|
1100 |
+
"loss": 1.6339,
|
1101 |
+
"step": 178
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.56,
|
1105 |
+
"learning_rate": 0.00018487848521398265,
|
1106 |
+
"loss": 1.5993,
|
1107 |
+
"step": 179
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.56,
|
1111 |
+
"learning_rate": 0.0001847037241692378,
|
1112 |
+
"loss": 1.6286,
|
1113 |
+
"step": 180
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.56,
|
1117 |
+
"learning_rate": 0.00018452804264089084,
|
1118 |
+
"loss": 1.5963,
|
1119 |
+
"step": 181
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.57,
|
1123 |
+
"learning_rate": 0.00018435144253809,
|
1124 |
+
"loss": 1.5856,
|
1125 |
+
"step": 182
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.57,
|
1129 |
+
"learning_rate": 0.00018417392577996578,
|
1130 |
+
"loss": 1.5787,
|
1131 |
+
"step": 183
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.57,
|
1135 |
+
"learning_rate": 0.00018399549429561006,
|
1136 |
+
"loss": 1.5876,
|
1137 |
+
"step": 184
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.58,
|
1141 |
+
"learning_rate": 0.00018381615002405509,
|
1142 |
+
"loss": 1.5565,
|
1143 |
+
"step": 185
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.58,
|
1147 |
+
"learning_rate": 0.00018363589491425248,
|
1148 |
+
"loss": 1.5897,
|
1149 |
+
"step": 186
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.58,
|
1153 |
+
"learning_rate": 0.0001834547309250521,
|
1154 |
+
"loss": 1.5951,
|
1155 |
+
"step": 187
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.58,
|
1159 |
+
"learning_rate": 0.00018327266002518056,
|
1160 |
+
"loss": 1.5447,
|
1161 |
+
"step": 188
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.59,
|
1165 |
+
"learning_rate": 0.00018308968419322003,
|
1166 |
+
"loss": 1.6087,
|
1167 |
+
"step": 189
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.59,
|
1171 |
+
"learning_rate": 0.00018290580541758668,
|
1172 |
+
"loss": 1.5946,
|
1173 |
+
"step": 190
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.59,
|
1177 |
+
"learning_rate": 0.00018272102569650905,
|
1178 |
+
"loss": 1.6148,
|
1179 |
+
"step": 191
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6,
|
1183 |
+
"learning_rate": 0.00018253534703800627,
|
1184 |
+
"loss": 1.649,
|
1185 |
+
"step": 192
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.6,
|
1189 |
+
"learning_rate": 0.0001823487714598664,
|
1190 |
+
"loss": 1.6312,
|
1191 |
+
"step": 193
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.6,
|
1195 |
+
"learning_rate": 0.0001821613009896244,
|
1196 |
+
"loss": 1.5858,
|
1197 |
+
"step": 194
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.61,
|
1201 |
+
"learning_rate": 0.00018197293766454003,
|
1202 |
+
"loss": 1.5925,
|
1203 |
+
"step": 195
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.61,
|
1207 |
+
"learning_rate": 0.0001817836835315759,
|
1208 |
+
"loss": 1.5604,
|
1209 |
+
"step": 196
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.61,
|
1213 |
+
"learning_rate": 0.00018159354064737506,
|
1214 |
+
"loss": 1.6125,
|
1215 |
+
"step": 197
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.62,
|
1219 |
+
"learning_rate": 0.0001814025110782387,
|
1220 |
+
"loss": 1.5954,
|
1221 |
+
"step": 198
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.62,
|
1225 |
+
"learning_rate": 0.00018121059690010368,
|
1226 |
+
"loss": 1.5937,
|
1227 |
+
"step": 199
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.62,
|
1231 |
+
"learning_rate": 0.00018101780019852008,
|
1232 |
+
"loss": 1.5582,
|
1233 |
+
"step": 200
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.62,
|
1237 |
+
"eval_loss": 1.6065257787704468,
|
1238 |
+
"eval_runtime": 233.7919,
|
1239 |
+
"eval_samples_per_second": 16.352,
|
1240 |
+
"eval_steps_per_second": 4.089,
|
1241 |
+
"step": 200
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.63,
|
1245 |
+
"learning_rate": 0.00018082412306862837,
|
1246 |
+
"loss": 1.5628,
|
1247 |
+
"step": 201
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 0.63,
|
1251 |
+
"learning_rate": 0.00018062956761513675,
|
1252 |
+
"loss": 1.5735,
|
1253 |
+
"step": 202
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 0.63,
|
1257 |
+
"learning_rate": 0.00018043413595229818,
|
1258 |
+
"loss": 1.6011,
|
1259 |
+
"step": 203
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 0.63,
|
1263 |
+
"learning_rate": 0.00018023783020388763,
|
1264 |
+
"loss": 1.5434,
|
1265 |
+
"step": 204
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 0.64,
|
1269 |
+
"learning_rate": 0.00018004065250317868,
|
1270 |
+
"loss": 1.5533,
|
1271 |
+
"step": 205
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.64,
|
1275 |
+
"learning_rate": 0.00017984260499292058,
|
1276 |
+
"loss": 1.6074,
|
1277 |
+
"step": 206
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.64,
|
1281 |
+
"learning_rate": 0.00017964368982531487,
|
1282 |
+
"loss": 1.5286,
|
1283 |
+
"step": 207
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.65,
|
1287 |
+
"learning_rate": 0.00017944390916199203,
|
1288 |
+
"loss": 1.5161,
|
1289 |
+
"step": 208
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 0.65,
|
1293 |
+
"learning_rate": 0.00017924326517398793,
|
1294 |
+
"loss": 1.6024,
|
1295 |
+
"step": 209
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 0.65,
|
1299 |
+
"learning_rate": 0.00017904176004172027,
|
1300 |
+
"loss": 1.5727,
|
1301 |
+
"step": 210
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 0.66,
|
1305 |
+
"learning_rate": 0.0001788393959549649,
|
1306 |
+
"loss": 1.5752,
|
1307 |
+
"step": 211
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 0.66,
|
1311 |
+
"learning_rate": 0.00017863617511283203,
|
1312 |
+
"loss": 1.5845,
|
1313 |
+
"step": 212
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.66,
|
1317 |
+
"learning_rate": 0.00017843209972374233,
|
1318 |
+
"loss": 1.6082,
|
1319 |
+
"step": 213
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.67,
|
1323 |
+
"learning_rate": 0.00017822717200540283,
|
1324 |
+
"loss": 1.5895,
|
1325 |
+
"step": 214
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.67,
|
1329 |
+
"learning_rate": 0.00017802139418478298,
|
1330 |
+
"loss": 1.5836,
|
1331 |
+
"step": 215
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 0.67,
|
1335 |
+
"learning_rate": 0.00017781476849809038,
|
1336 |
+
"loss": 1.5996,
|
1337 |
+
"step": 216
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 0.67,
|
1341 |
+
"learning_rate": 0.00017760729719074644,
|
1342 |
+
"loss": 1.6256,
|
1343 |
+
"step": 217
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.68,
|
1347 |
+
"learning_rate": 0.000177398982517362,
|
1348 |
+
"loss": 1.628,
|
1349 |
+
"step": 218
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 0.68,
|
1353 |
+
"learning_rate": 0.00017718982674171284,
|
1354 |
+
"loss": 1.5543,
|
1355 |
+
"step": 219
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.68,
|
1359 |
+
"learning_rate": 0.00017697983213671515,
|
1360 |
+
"loss": 1.5732,
|
1361 |
+
"step": 220
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.69,
|
1365 |
+
"learning_rate": 0.0001767690009844007,
|
1366 |
+
"loss": 1.5892,
|
1367 |
+
"step": 221
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.69,
|
1371 |
+
"learning_rate": 0.0001765573355758921,
|
1372 |
+
"loss": 1.6524,
|
1373 |
+
"step": 222
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 0.69,
|
1377 |
+
"learning_rate": 0.00017634483821137787,
|
1378 |
+
"loss": 1.5694,
|
1379 |
+
"step": 223
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 0.7,
|
1383 |
+
"learning_rate": 0.0001761315112000876,
|
1384 |
+
"loss": 1.6006,
|
1385 |
+
"step": 224
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.7,
|
1389 |
+
"learning_rate": 0.00017591735686026661,
|
1390 |
+
"loss": 1.6161,
|
1391 |
+
"step": 225
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 0.7,
|
1395 |
+
"learning_rate": 0.00017570237751915092,
|
1396 |
+
"loss": 1.595,
|
1397 |
+
"step": 226
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 0.71,
|
1401 |
+
"learning_rate": 0.00017548657551294192,
|
1402 |
+
"loss": 1.6072,
|
1403 |
+
"step": 227
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.71,
|
1407 |
+
"learning_rate": 0.000175269953186781,
|
1408 |
+
"loss": 1.5855,
|
1409 |
+
"step": 228
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.71,
|
1413 |
+
"learning_rate": 0.00017505251289472406,
|
1414 |
+
"loss": 1.597,
|
1415 |
+
"step": 229
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 0.72,
|
1419 |
+
"learning_rate": 0.0001748342569997158,
|
1420 |
+
"loss": 1.5837,
|
1421 |
+
"step": 230
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 0.72,
|
1425 |
+
"learning_rate": 0.00017461518787356432,
|
1426 |
+
"loss": 1.5422,
|
1427 |
+
"step": 231
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.72,
|
1431 |
+
"learning_rate": 0.00017439530789691506,
|
1432 |
+
"loss": 1.5837,
|
1433 |
+
"step": 232
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 0.72,
|
1437 |
+
"learning_rate": 0.0001741746194592251,
|
1438 |
+
"loss": 1.6038,
|
1439 |
+
"step": 233
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.73,
|
1443 |
+
"learning_rate": 0.00017395312495873717,
|
1444 |
+
"loss": 1.5882,
|
1445 |
+
"step": 234
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.73,
|
1449 |
+
"learning_rate": 0.00017373082680245347,
|
1450 |
+
"loss": 1.5763,
|
1451 |
+
"step": 235
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.73,
|
1455 |
+
"learning_rate": 0.00017350772740610976,
|
1456 |
+
"loss": 1.6046,
|
1457 |
+
"step": 236
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 0.74,
|
1461 |
+
"learning_rate": 0.00017328382919414877,
|
1462 |
+
"loss": 1.594,
|
1463 |
+
"step": 237
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 0.74,
|
1467 |
+
"learning_rate": 0.00017305913459969414,
|
1468 |
+
"loss": 1.5903,
|
1469 |
+
"step": 238
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 0.74,
|
1473 |
+
"learning_rate": 0.00017283364606452396,
|
1474 |
+
"loss": 1.5704,
|
1475 |
+
"step": 239
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 0.75,
|
1479 |
+
"learning_rate": 0.0001726073660390439,
|
1480 |
+
"loss": 1.588,
|
1481 |
+
"step": 240
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.75,
|
1485 |
+
"learning_rate": 0.00017238029698226113,
|
1486 |
+
"loss": 1.6273,
|
1487 |
+
"step": 241
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.75,
|
1491 |
+
"learning_rate": 0.00017215244136175705,
|
1492 |
+
"loss": 1.5166,
|
1493 |
+
"step": 242
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.76,
|
1497 |
+
"learning_rate": 0.00017192380165366092,
|
1498 |
+
"loss": 1.5813,
|
1499 |
+
"step": 243
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 0.76,
|
1503 |
+
"learning_rate": 0.0001716943803426226,
|
1504 |
+
"loss": 1.5654,
|
1505 |
+
"step": 244
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 0.76,
|
1509 |
+
"learning_rate": 0.0001714641799217858,
|
1510 |
+
"loss": 1.5548,
|
1511 |
+
"step": 245
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 0.77,
|
1515 |
+
"learning_rate": 0.00017123320289276085,
|
1516 |
+
"loss": 1.5491,
|
1517 |
+
"step": 246
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 0.77,
|
1521 |
+
"learning_rate": 0.0001710014517655976,
|
1522 |
+
"loss": 1.5903,
|
1523 |
+
"step": 247
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.77,
|
1527 |
+
"learning_rate": 0.00017076892905875806,
|
1528 |
+
"loss": 1.5687,
|
1529 |
+
"step": 248
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.77,
|
1533 |
+
"learning_rate": 0.00017053563729908905,
|
1534 |
+
"loss": 1.5975,
|
1535 |
+
"step": 249
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.78,
|
1539 |
+
"learning_rate": 0.00017030157902179485,
|
1540 |
+
"loss": 1.6055,
|
1541 |
+
"step": 250
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 0.78,
|
1545 |
+
"eval_loss": 1.60513174533844,
|
1546 |
+
"eval_runtime": 233.7813,
|
1547 |
+
"eval_samples_per_second": 16.353,
|
1548 |
+
"eval_steps_per_second": 4.089,
|
1549 |
+
"step": 250
|
1550 |
+
}
|
1551 |
+
],
|
1552 |
+
"logging_steps": 1,
|
1553 |
+
"max_steps": 963,
|
1554 |
+
"num_train_epochs": 3,
|
1555 |
+
"save_steps": 50,
|
1556 |
+
"total_flos": 7.01067914379264e+17,
|
1557 |
+
"trial_name": null,
|
1558 |
+
"trial_params": null
|
1559 |
+
}
|
checkpoint-250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f61cafb89242b653e455003b5517e685ecccfa6180af5fb7d0bfb35b4fc77a4
|
3 |
+
size 4475
|
checkpoint-300/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-300/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-300/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:219facdff16b696735f1a84fdd92a0cbac9e197db9eef71c8ce3344d57718790
|
3 |
+
size 84046925
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a343ddfe6887de6fbae314359ede72e86a4b1ca90c8dca7f14f5c67e99f3f746
|
3 |
+
size 168039557
|
checkpoint-300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65057c4c38794cbabddcd3f77e0f9ae9b434f793b5e38c88f0b54b3a59c2a015
|
3 |
+
size 14575
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d16d35aca2529b2ee06dff7108489f02d74e6fa0dc4c995236c9afa17fe97a23
|
3 |
+
size 627
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,1867 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6023043394088745,
|
3 |
+
"best_model_checkpoint": "./lora-out/checkpoint-300",
|
4 |
+
"epoch": 0.9331259720062208,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 2e-05,
|
14 |
+
"loss": 1.7924,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4e-05,
|
20 |
+
"loss": 1.8083,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 6e-05,
|
26 |
+
"loss": 1.8177,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 8e-05,
|
32 |
+
"loss": 1.7595,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"learning_rate": 0.0001,
|
38 |
+
"loss": 1.6598,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 0.00012,
|
44 |
+
"loss": 1.6919,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 0.00014,
|
50 |
+
"loss": 1.6706,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 0.00016,
|
56 |
+
"loss": 1.6879,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.03,
|
61 |
+
"learning_rate": 0.00018,
|
62 |
+
"loss": 1.7051,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.7022,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 0.000199999456645141,
|
74 |
+
"loss": 1.6809,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.04,
|
79 |
+
"learning_rate": 0.00019999782658646859,
|
80 |
+
"loss": 1.6098,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.04,
|
85 |
+
"learning_rate": 0.0001999951098416968,
|
86 |
+
"loss": 1.7014,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 0.00019999130644034888,
|
92 |
+
"loss": 1.5885,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.05,
|
97 |
+
"learning_rate": 0.00019998641642375657,
|
98 |
+
"loss": 1.6243,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.05,
|
103 |
+
"learning_rate": 0.00019998043984506027,
|
104 |
+
"loss": 1.6484,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.05,
|
109 |
+
"learning_rate": 0.00019997337676920803,
|
110 |
+
"loss": 1.6093,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.06,
|
115 |
+
"learning_rate": 0.00019996522727295496,
|
116 |
+
"loss": 1.6173,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.06,
|
121 |
+
"learning_rate": 0.00019995599144486247,
|
122 |
+
"loss": 1.646,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.06,
|
127 |
+
"learning_rate": 0.00019994566938529712,
|
128 |
+
"loss": 1.6469,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.07,
|
133 |
+
"learning_rate": 0.00019993426120642983,
|
134 |
+
"loss": 1.6564,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.07,
|
139 |
+
"learning_rate": 0.00019992176703223432,
|
140 |
+
"loss": 1.5901,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.07,
|
145 |
+
"learning_rate": 0.000199908186998486,
|
146 |
+
"loss": 1.664,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.07,
|
151 |
+
"learning_rate": 0.00019989352125276047,
|
152 |
+
"loss": 1.6275,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.08,
|
157 |
+
"learning_rate": 0.00019987776995443178,
|
158 |
+
"loss": 1.5839,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.08,
|
163 |
+
"learning_rate": 0.00019986093327467076,
|
164 |
+
"loss": 1.5611,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.08,
|
169 |
+
"learning_rate": 0.00019984301139644334,
|
170 |
+
"loss": 1.669,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.09,
|
175 |
+
"learning_rate": 0.0001998240045145083,
|
176 |
+
"loss": 1.5641,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.09,
|
181 |
+
"learning_rate": 0.00019980391283541522,
|
182 |
+
"loss": 1.6023,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.09,
|
187 |
+
"learning_rate": 0.00019978273657750238,
|
188 |
+
"loss": 1.6309,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.1,
|
193 |
+
"learning_rate": 0.0001997604759708942,
|
194 |
+
"loss": 1.6353,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.1,
|
199 |
+
"learning_rate": 0.00019973713125749884,
|
200 |
+
"loss": 1.6328,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.1,
|
205 |
+
"learning_rate": 0.00019971270269100564,
|
206 |
+
"loss": 1.5683,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.11,
|
211 |
+
"learning_rate": 0.00019968719053688213,
|
212 |
+
"loss": 1.6217,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.11,
|
217 |
+
"learning_rate": 0.0001996605950723714,
|
218 |
+
"loss": 1.5734,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.11,
|
223 |
+
"learning_rate": 0.00019963291658648896,
|
224 |
+
"loss": 1.6162,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.12,
|
229 |
+
"learning_rate": 0.00019960415538001957,
|
230 |
+
"loss": 1.5922,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.12,
|
235 |
+
"learning_rate": 0.0001995743117655141,
|
236 |
+
"loss": 1.5806,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.12,
|
241 |
+
"learning_rate": 0.000199543386067286,
|
242 |
+
"loss": 1.5938,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.12,
|
247 |
+
"learning_rate": 0.00019951137862140778,
|
248 |
+
"loss": 1.6386,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.13,
|
253 |
+
"learning_rate": 0.00019947828977570756,
|
254 |
+
"loss": 1.6476,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.13,
|
259 |
+
"learning_rate": 0.00019944411988976496,
|
260 |
+
"loss": 1.6557,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.13,
|
265 |
+
"learning_rate": 0.00019940886933490749,
|
266 |
+
"loss": 1.5836,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.14,
|
271 |
+
"learning_rate": 0.00019937253849420635,
|
272 |
+
"loss": 1.6421,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.14,
|
277 |
+
"learning_rate": 0.0001993351277624723,
|
278 |
+
"loss": 1.629,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.14,
|
283 |
+
"learning_rate": 0.00019929663754625145,
|
284 |
+
"loss": 1.6392,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.15,
|
289 |
+
"learning_rate": 0.00019925706826382064,
|
290 |
+
"loss": 1.5677,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.15,
|
295 |
+
"learning_rate": 0.00019921642034518317,
|
296 |
+
"loss": 1.6144,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.15,
|
301 |
+
"learning_rate": 0.00019917469423206389,
|
302 |
+
"loss": 1.6068,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.16,
|
307 |
+
"learning_rate": 0.00019913189037790456,
|
308 |
+
"loss": 1.6421,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.16,
|
313 |
+
"eval_loss": 1.621693730354309,
|
314 |
+
"eval_runtime": 233.7603,
|
315 |
+
"eval_samples_per_second": 16.354,
|
316 |
+
"eval_steps_per_second": 4.09,
|
317 |
+
"step": 50
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.16,
|
321 |
+
"learning_rate": 0.0001990880092478588,
|
322 |
+
"loss": 1.6172,
|
323 |
+
"step": 51
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.16,
|
327 |
+
"learning_rate": 0.0001990430513187871,
|
328 |
+
"loss": 1.6095,
|
329 |
+
"step": 52
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.16,
|
333 |
+
"learning_rate": 0.00019899701707925166,
|
334 |
+
"loss": 1.5967,
|
335 |
+
"step": 53
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.17,
|
339 |
+
"learning_rate": 0.00019894990702951106,
|
340 |
+
"loss": 1.617,
|
341 |
+
"step": 54
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.17,
|
345 |
+
"learning_rate": 0.00019890172168151473,
|
346 |
+
"loss": 1.5932,
|
347 |
+
"step": 55
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.17,
|
351 |
+
"learning_rate": 0.0001988524615588976,
|
352 |
+
"loss": 1.6548,
|
353 |
+
"step": 56
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.18,
|
357 |
+
"learning_rate": 0.00019880212719697413,
|
358 |
+
"loss": 1.6033,
|
359 |
+
"step": 57
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.18,
|
363 |
+
"learning_rate": 0.00019875071914273278,
|
364 |
+
"loss": 1.6063,
|
365 |
+
"step": 58
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.18,
|
369 |
+
"learning_rate": 0.00019869823795482986,
|
370 |
+
"loss": 1.6107,
|
371 |
+
"step": 59
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.19,
|
375 |
+
"learning_rate": 0.00019864468420358354,
|
376 |
+
"loss": 1.5758,
|
377 |
+
"step": 60
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.19,
|
381 |
+
"learning_rate": 0.00019859005847096763,
|
382 |
+
"loss": 1.5723,
|
383 |
+
"step": 61
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.19,
|
387 |
+
"learning_rate": 0.00019853436135060527,
|
388 |
+
"loss": 1.542,
|
389 |
+
"step": 62
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.2,
|
393 |
+
"learning_rate": 0.00019847759344776252,
|
394 |
+
"loss": 1.5611,
|
395 |
+
"step": 63
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.2,
|
399 |
+
"learning_rate": 0.00019841975537934162,
|
400 |
+
"loss": 1.6157,
|
401 |
+
"step": 64
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2,
|
405 |
+
"learning_rate": 0.00019836084777387458,
|
406 |
+
"loss": 1.5589,
|
407 |
+
"step": 65
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.21,
|
411 |
+
"learning_rate": 0.00019830087127151598,
|
412 |
+
"loss": 1.6077,
|
413 |
+
"step": 66
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.21,
|
417 |
+
"learning_rate": 0.00019823982652403634,
|
418 |
+
"loss": 1.5473,
|
419 |
+
"step": 67
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.21,
|
423 |
+
"learning_rate": 0.00019817771419481487,
|
424 |
+
"loss": 1.6265,
|
425 |
+
"step": 68
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.21,
|
429 |
+
"learning_rate": 0.0001981145349588323,
|
430 |
+
"loss": 1.6074,
|
431 |
+
"step": 69
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.22,
|
435 |
+
"learning_rate": 0.00019805028950266348,
|
436 |
+
"loss": 1.6195,
|
437 |
+
"step": 70
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.22,
|
441 |
+
"learning_rate": 0.00019798497852447006,
|
442 |
+
"loss": 1.5876,
|
443 |
+
"step": 71
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.22,
|
447 |
+
"learning_rate": 0.0001979186027339928,
|
448 |
+
"loss": 1.5978,
|
449 |
+
"step": 72
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.23,
|
453 |
+
"learning_rate": 0.00019785116285254381,
|
454 |
+
"loss": 1.533,
|
455 |
+
"step": 73
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.23,
|
459 |
+
"learning_rate": 0.00019778265961299888,
|
460 |
+
"loss": 1.5888,
|
461 |
+
"step": 74
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.23,
|
465 |
+
"learning_rate": 0.0001977130937597894,
|
466 |
+
"loss": 1.6211,
|
467 |
+
"step": 75
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.24,
|
471 |
+
"learning_rate": 0.00019764246604889415,
|
472 |
+
"loss": 1.6091,
|
473 |
+
"step": 76
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.24,
|
477 |
+
"learning_rate": 0.00019757077724783147,
|
478 |
+
"loss": 1.6012,
|
479 |
+
"step": 77
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.24,
|
483 |
+
"learning_rate": 0.0001974980281356504,
|
484 |
+
"loss": 1.6401,
|
485 |
+
"step": 78
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.25,
|
489 |
+
"learning_rate": 0.0001974242195029227,
|
490 |
+
"loss": 1.6111,
|
491 |
+
"step": 79
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.25,
|
495 |
+
"learning_rate": 0.00019734935215173392,
|
496 |
+
"loss": 1.6208,
|
497 |
+
"step": 80
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.25,
|
501 |
+
"learning_rate": 0.00019727342689567482,
|
502 |
+
"loss": 1.6038,
|
503 |
+
"step": 81
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.26,
|
507 |
+
"learning_rate": 0.00019719644455983256,
|
508 |
+
"loss": 1.5915,
|
509 |
+
"step": 82
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.26,
|
513 |
+
"learning_rate": 0.0001971184059807817,
|
514 |
+
"loss": 1.5872,
|
515 |
+
"step": 83
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.26,
|
519 |
+
"learning_rate": 0.000197039312006575,
|
520 |
+
"loss": 1.5984,
|
521 |
+
"step": 84
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.26,
|
525 |
+
"learning_rate": 0.0001969591634967344,
|
526 |
+
"loss": 1.5996,
|
527 |
+
"step": 85
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.27,
|
531 |
+
"learning_rate": 0.00019687796132224152,
|
532 |
+
"loss": 1.6056,
|
533 |
+
"step": 86
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.27,
|
537 |
+
"learning_rate": 0.0001967957063655283,
|
538 |
+
"loss": 1.6099,
|
539 |
+
"step": 87
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.27,
|
543 |
+
"learning_rate": 0.0001967123995204674,
|
544 |
+
"loss": 1.6295,
|
545 |
+
"step": 88
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.28,
|
549 |
+
"learning_rate": 0.00019662804169236225,
|
550 |
+
"loss": 1.5482,
|
551 |
+
"step": 89
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.28,
|
555 |
+
"learning_rate": 0.00019654263379793773,
|
556 |
+
"loss": 1.5781,
|
557 |
+
"step": 90
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.28,
|
561 |
+
"learning_rate": 0.00019645617676532963,
|
562 |
+
"loss": 1.5954,
|
563 |
+
"step": 91
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.29,
|
567 |
+
"learning_rate": 0.000196368671534075,
|
568 |
+
"loss": 1.619,
|
569 |
+
"step": 92
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.29,
|
573 |
+
"learning_rate": 0.0001962801190551016,
|
574 |
+
"loss": 1.6153,
|
575 |
+
"step": 93
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.29,
|
579 |
+
"learning_rate": 0.0001961905202907179,
|
580 |
+
"loss": 1.6008,
|
581 |
+
"step": 94
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.3,
|
585 |
+
"learning_rate": 0.00019609987621460232,
|
586 |
+
"loss": 1.5891,
|
587 |
+
"step": 95
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.3,
|
591 |
+
"learning_rate": 0.0001960081878117929,
|
592 |
+
"loss": 1.6438,
|
593 |
+
"step": 96
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.3,
|
597 |
+
"learning_rate": 0.0001959154560786764,
|
598 |
+
"loss": 1.5576,
|
599 |
+
"step": 97
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.3,
|
603 |
+
"learning_rate": 0.00019582168202297758,
|
604 |
+
"loss": 1.646,
|
605 |
+
"step": 98
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.31,
|
609 |
+
"learning_rate": 0.00019572686666374822,
|
610 |
+
"loss": 1.6269,
|
611 |
+
"step": 99
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.31,
|
615 |
+
"learning_rate": 0.00019563101103135602,
|
616 |
+
"loss": 1.6288,
|
617 |
+
"step": 100
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.31,
|
621 |
+
"eval_loss": 1.6143836975097656,
|
622 |
+
"eval_runtime": 233.6412,
|
623 |
+
"eval_samples_per_second": 16.363,
|
624 |
+
"eval_steps_per_second": 4.092,
|
625 |
+
"step": 100
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.31,
|
629 |
+
"learning_rate": 0.00019553411616747348,
|
630 |
+
"loss": 1.5667,
|
631 |
+
"step": 101
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.32,
|
635 |
+
"learning_rate": 0.00019543618312506647,
|
636 |
+
"loss": 1.6221,
|
637 |
+
"step": 102
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.32,
|
641 |
+
"learning_rate": 0.0001953372129683829,
|
642 |
+
"loss": 1.5992,
|
643 |
+
"step": 103
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.32,
|
647 |
+
"learning_rate": 0.0001952372067729411,
|
648 |
+
"loss": 1.6138,
|
649 |
+
"step": 104
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.33,
|
653 |
+
"learning_rate": 0.00019513616562551807,
|
654 |
+
"loss": 1.51,
|
655 |
+
"step": 105
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.33,
|
659 |
+
"learning_rate": 0.00019503409062413782,
|
660 |
+
"loss": 1.6227,
|
661 |
+
"step": 106
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.33,
|
665 |
+
"learning_rate": 0.00019493098287805927,
|
666 |
+
"loss": 1.6014,
|
667 |
+
"step": 107
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.34,
|
671 |
+
"learning_rate": 0.00019482684350776434,
|
672 |
+
"loss": 1.625,
|
673 |
+
"step": 108
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.34,
|
677 |
+
"learning_rate": 0.0001947216736449457,
|
678 |
+
"loss": 1.6109,
|
679 |
+
"step": 109
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.34,
|
683 |
+
"learning_rate": 0.0001946154744324945,
|
684 |
+
"loss": 1.62,
|
685 |
+
"step": 110
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.35,
|
689 |
+
"learning_rate": 0.00019450824702448778,
|
690 |
+
"loss": 1.5878,
|
691 |
+
"step": 111
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.35,
|
695 |
+
"learning_rate": 0.0001943999925861763,
|
696 |
+
"loss": 1.6264,
|
697 |
+
"step": 112
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.35,
|
701 |
+
"learning_rate": 0.00019429071229397157,
|
702 |
+
"loss": 1.6186,
|
703 |
+
"step": 113
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.35,
|
707 |
+
"learning_rate": 0.0001941804073354331,
|
708 |
+
"loss": 1.6363,
|
709 |
+
"step": 114
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.36,
|
713 |
+
"learning_rate": 0.00019406907890925562,
|
714 |
+
"loss": 1.5341,
|
715 |
+
"step": 115
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.36,
|
719 |
+
"learning_rate": 0.00019395672822525593,
|
720 |
+
"loss": 1.5986,
|
721 |
+
"step": 116
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.36,
|
725 |
+
"learning_rate": 0.00019384335650435985,
|
726 |
+
"loss": 1.6181,
|
727 |
+
"step": 117
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.37,
|
731 |
+
"learning_rate": 0.0001937289649785889,
|
732 |
+
"loss": 1.6118,
|
733 |
+
"step": 118
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.37,
|
737 |
+
"learning_rate": 0.0001936135548910469,
|
738 |
+
"loss": 1.6404,
|
739 |
+
"step": 119
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.37,
|
743 |
+
"learning_rate": 0.00019349712749590649,
|
744 |
+
"loss": 1.583,
|
745 |
+
"step": 120
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.38,
|
749 |
+
"learning_rate": 0.00019337968405839547,
|
750 |
+
"loss": 1.5827,
|
751 |
+
"step": 121
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.38,
|
755 |
+
"learning_rate": 0.00019326122585478308,
|
756 |
+
"loss": 1.6392,
|
757 |
+
"step": 122
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.38,
|
761 |
+
"learning_rate": 0.00019314175417236616,
|
762 |
+
"loss": 1.5861,
|
763 |
+
"step": 123
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.39,
|
767 |
+
"learning_rate": 0.00019302127030945508,
|
768 |
+
"loss": 1.5738,
|
769 |
+
"step": 124
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.39,
|
773 |
+
"learning_rate": 0.0001928997755753597,
|
774 |
+
"loss": 1.5915,
|
775 |
+
"step": 125
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.39,
|
779 |
+
"learning_rate": 0.00019277727129037508,
|
780 |
+
"loss": 1.617,
|
781 |
+
"step": 126
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.4,
|
785 |
+
"learning_rate": 0.0001926537587857672,
|
786 |
+
"loss": 1.5582,
|
787 |
+
"step": 127
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.4,
|
791 |
+
"learning_rate": 0.00019252923940375844,
|
792 |
+
"loss": 1.6294,
|
793 |
+
"step": 128
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.4,
|
797 |
+
"learning_rate": 0.00019240371449751306,
|
798 |
+
"loss": 1.6087,
|
799 |
+
"step": 129
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.4,
|
803 |
+
"learning_rate": 0.00019227718543112236,
|
804 |
+
"loss": 1.5749,
|
805 |
+
"step": 130
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.41,
|
809 |
+
"learning_rate": 0.00019214965357959005,
|
810 |
+
"loss": 1.6041,
|
811 |
+
"step": 131
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.41,
|
815 |
+
"learning_rate": 0.00019202112032881715,
|
816 |
+
"loss": 1.6106,
|
817 |
+
"step": 132
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.41,
|
821 |
+
"learning_rate": 0.00019189158707558695,
|
822 |
+
"loss": 1.5553,
|
823 |
+
"step": 133
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.42,
|
827 |
+
"learning_rate": 0.00019176105522754995,
|
828 |
+
"loss": 1.5638,
|
829 |
+
"step": 134
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.42,
|
833 |
+
"learning_rate": 0.0001916295262032084,
|
834 |
+
"loss": 1.5921,
|
835 |
+
"step": 135
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.42,
|
839 |
+
"learning_rate": 0.00019149700143190096,
|
840 |
+
"loss": 1.5837,
|
841 |
+
"step": 136
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.43,
|
845 |
+
"learning_rate": 0.00019136348235378726,
|
846 |
+
"loss": 1.6341,
|
847 |
+
"step": 137
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.43,
|
851 |
+
"learning_rate": 0.00019122897041983205,
|
852 |
+
"loss": 1.5678,
|
853 |
+
"step": 138
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.43,
|
857 |
+
"learning_rate": 0.00019109346709178963,
|
858 |
+
"loss": 1.6137,
|
859 |
+
"step": 139
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.44,
|
863 |
+
"learning_rate": 0.0001909569738421878,
|
864 |
+
"loss": 1.6324,
|
865 |
+
"step": 140
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.44,
|
869 |
+
"learning_rate": 0.00019081949215431194,
|
870 |
+
"loss": 1.612,
|
871 |
+
"step": 141
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.44,
|
875 |
+
"learning_rate": 0.00019068102352218897,
|
876 |
+
"loss": 1.5908,
|
877 |
+
"step": 142
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.44,
|
881 |
+
"learning_rate": 0.00019054156945057097,
|
882 |
+
"loss": 1.6087,
|
883 |
+
"step": 143
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.45,
|
887 |
+
"learning_rate": 0.00019040113145491887,
|
888 |
+
"loss": 1.5613,
|
889 |
+
"step": 144
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.45,
|
893 |
+
"learning_rate": 0.000190259711061386,
|
894 |
+
"loss": 1.6072,
|
895 |
+
"step": 145
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.45,
|
899 |
+
"learning_rate": 0.00019011730980680156,
|
900 |
+
"loss": 1.5722,
|
901 |
+
"step": 146
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.46,
|
905 |
+
"learning_rate": 0.0001899739292386538,
|
906 |
+
"loss": 1.5961,
|
907 |
+
"step": 147
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.46,
|
911 |
+
"learning_rate": 0.00018982957091507325,
|
912 |
+
"loss": 1.5409,
|
913 |
+
"step": 148
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.46,
|
917 |
+
"learning_rate": 0.0001896842364048159,
|
918 |
+
"loss": 1.6557,
|
919 |
+
"step": 149
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.47,
|
923 |
+
"learning_rate": 0.000189537927287246,
|
924 |
+
"loss": 1.5725,
|
925 |
+
"step": 150
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 0.47,
|
929 |
+
"eval_loss": 1.6101970672607422,
|
930 |
+
"eval_runtime": 233.5313,
|
931 |
+
"eval_samples_per_second": 16.37,
|
932 |
+
"eval_steps_per_second": 4.094,
|
933 |
+
"step": 150
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.47,
|
937 |
+
"learning_rate": 0.00018939064515231888,
|
938 |
+
"loss": 1.5949,
|
939 |
+
"step": 151
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.47,
|
943 |
+
"learning_rate": 0.0001892423916005639,
|
944 |
+
"loss": 1.6191,
|
945 |
+
"step": 152
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.48,
|
949 |
+
"learning_rate": 0.00018909316824306674,
|
950 |
+
"loss": 1.5487,
|
951 |
+
"step": 153
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.48,
|
955 |
+
"learning_rate": 0.00018894297670145216,
|
956 |
+
"loss": 1.5104,
|
957 |
+
"step": 154
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.48,
|
961 |
+
"learning_rate": 0.00018879181860786623,
|
962 |
+
"loss": 1.6392,
|
963 |
+
"step": 155
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.49,
|
967 |
+
"learning_rate": 0.00018863969560495866,
|
968 |
+
"loss": 1.5932,
|
969 |
+
"step": 156
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.49,
|
973 |
+
"learning_rate": 0.00018848660934586491,
|
974 |
+
"loss": 1.6213,
|
975 |
+
"step": 157
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.49,
|
979 |
+
"learning_rate": 0.0001883325614941882,
|
980 |
+
"loss": 1.5515,
|
981 |
+
"step": 158
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.49,
|
985 |
+
"learning_rate": 0.00018817755372398155,
|
986 |
+
"loss": 1.6166,
|
987 |
+
"step": 159
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.5,
|
991 |
+
"learning_rate": 0.00018802158771972943,
|
992 |
+
"loss": 1.6552,
|
993 |
+
"step": 160
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.5,
|
997 |
+
"learning_rate": 0.00018786466517632956,
|
998 |
+
"loss": 1.6378,
|
999 |
+
"step": 161
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.5,
|
1003 |
+
"learning_rate": 0.00018770678779907448,
|
1004 |
+
"loss": 1.5176,
|
1005 |
+
"step": 162
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.51,
|
1009 |
+
"learning_rate": 0.00018754795730363302,
|
1010 |
+
"loss": 1.5793,
|
1011 |
+
"step": 163
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.51,
|
1015 |
+
"learning_rate": 0.00018738817541603156,
|
1016 |
+
"loss": 1.6616,
|
1017 |
+
"step": 164
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.51,
|
1021 |
+
"learning_rate": 0.00018722744387263544,
|
1022 |
+
"loss": 1.6055,
|
1023 |
+
"step": 165
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.52,
|
1027 |
+
"learning_rate": 0.00018706576442012994,
|
1028 |
+
"loss": 1.6204,
|
1029 |
+
"step": 166
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.52,
|
1033 |
+
"learning_rate": 0.00018690313881550137,
|
1034 |
+
"loss": 1.5952,
|
1035 |
+
"step": 167
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.52,
|
1039 |
+
"learning_rate": 0.00018673956882601803,
|
1040 |
+
"loss": 1.6271,
|
1041 |
+
"step": 168
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.53,
|
1045 |
+
"learning_rate": 0.00018657505622921082,
|
1046 |
+
"loss": 1.538,
|
1047 |
+
"step": 169
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.53,
|
1051 |
+
"learning_rate": 0.00018640960281285417,
|
1052 |
+
"loss": 1.5874,
|
1053 |
+
"step": 170
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.53,
|
1057 |
+
"learning_rate": 0.0001862432103749464,
|
1058 |
+
"loss": 1.5694,
|
1059 |
+
"step": 171
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.53,
|
1063 |
+
"learning_rate": 0.00018607588072369033,
|
1064 |
+
"loss": 1.583,
|
1065 |
+
"step": 172
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.54,
|
1069 |
+
"learning_rate": 0.00018590761567747354,
|
1070 |
+
"loss": 1.5961,
|
1071 |
+
"step": 173
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.54,
|
1075 |
+
"learning_rate": 0.00018573841706484866,
|
1076 |
+
"loss": 1.582,
|
1077 |
+
"step": 174
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.54,
|
1081 |
+
"learning_rate": 0.0001855682867245134,
|
1082 |
+
"loss": 1.6427,
|
1083 |
+
"step": 175
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.55,
|
1087 |
+
"learning_rate": 0.00018539722650529075,
|
1088 |
+
"loss": 1.604,
|
1089 |
+
"step": 176
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.55,
|
1093 |
+
"learning_rate": 0.00018522523826610868,
|
1094 |
+
"loss": 1.577,
|
1095 |
+
"step": 177
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.55,
|
1099 |
+
"learning_rate": 0.00018505232387598018,
|
1100 |
+
"loss": 1.6339,
|
1101 |
+
"step": 178
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.56,
|
1105 |
+
"learning_rate": 0.00018487848521398265,
|
1106 |
+
"loss": 1.5993,
|
1107 |
+
"step": 179
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.56,
|
1111 |
+
"learning_rate": 0.0001847037241692378,
|
1112 |
+
"loss": 1.6286,
|
1113 |
+
"step": 180
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.56,
|
1117 |
+
"learning_rate": 0.00018452804264089084,
|
1118 |
+
"loss": 1.5963,
|
1119 |
+
"step": 181
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.57,
|
1123 |
+
"learning_rate": 0.00018435144253809,
|
1124 |
+
"loss": 1.5856,
|
1125 |
+
"step": 182
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.57,
|
1129 |
+
"learning_rate": 0.00018417392577996578,
|
1130 |
+
"loss": 1.5787,
|
1131 |
+
"step": 183
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.57,
|
1135 |
+
"learning_rate": 0.00018399549429561006,
|
1136 |
+
"loss": 1.5876,
|
1137 |
+
"step": 184
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.58,
|
1141 |
+
"learning_rate": 0.00018381615002405509,
|
1142 |
+
"loss": 1.5565,
|
1143 |
+
"step": 185
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.58,
|
1147 |
+
"learning_rate": 0.00018363589491425248,
|
1148 |
+
"loss": 1.5897,
|
1149 |
+
"step": 186
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.58,
|
1153 |
+
"learning_rate": 0.0001834547309250521,
|
1154 |
+
"loss": 1.5951,
|
1155 |
+
"step": 187
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.58,
|
1159 |
+
"learning_rate": 0.00018327266002518056,
|
1160 |
+
"loss": 1.5447,
|
1161 |
+
"step": 188
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.59,
|
1165 |
+
"learning_rate": 0.00018308968419322003,
|
1166 |
+
"loss": 1.6087,
|
1167 |
+
"step": 189
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.59,
|
1171 |
+
"learning_rate": 0.00018290580541758668,
|
1172 |
+
"loss": 1.5946,
|
1173 |
+
"step": 190
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.59,
|
1177 |
+
"learning_rate": 0.00018272102569650905,
|
1178 |
+
"loss": 1.6148,
|
1179 |
+
"step": 191
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.6,
|
1183 |
+
"learning_rate": 0.00018253534703800627,
|
1184 |
+
"loss": 1.649,
|
1185 |
+
"step": 192
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.6,
|
1189 |
+
"learning_rate": 0.0001823487714598664,
|
1190 |
+
"loss": 1.6312,
|
1191 |
+
"step": 193
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.6,
|
1195 |
+
"learning_rate": 0.0001821613009896244,
|
1196 |
+
"loss": 1.5858,
|
1197 |
+
"step": 194
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.61,
|
1201 |
+
"learning_rate": 0.00018197293766454003,
|
1202 |
+
"loss": 1.5925,
|
1203 |
+
"step": 195
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.61,
|
1207 |
+
"learning_rate": 0.0001817836835315759,
|
1208 |
+
"loss": 1.5604,
|
1209 |
+
"step": 196
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.61,
|
1213 |
+
"learning_rate": 0.00018159354064737506,
|
1214 |
+
"loss": 1.6125,
|
1215 |
+
"step": 197
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.62,
|
1219 |
+
"learning_rate": 0.0001814025110782387,
|
1220 |
+
"loss": 1.5954,
|
1221 |
+
"step": 198
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.62,
|
1225 |
+
"learning_rate": 0.00018121059690010368,
|
1226 |
+
"loss": 1.5937,
|
1227 |
+
"step": 199
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.62,
|
1231 |
+
"learning_rate": 0.00018101780019852008,
|
1232 |
+
"loss": 1.5582,
|
1233 |
+
"step": 200
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.62,
|
1237 |
+
"eval_loss": 1.6065257787704468,
|
1238 |
+
"eval_runtime": 233.7919,
|
1239 |
+
"eval_samples_per_second": 16.352,
|
1240 |
+
"eval_steps_per_second": 4.089,
|
1241 |
+
"step": 200
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.63,
|
1245 |
+
"learning_rate": 0.00018082412306862837,
|
1246 |
+
"loss": 1.5628,
|
1247 |
+
"step": 201
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 0.63,
|
1251 |
+
"learning_rate": 0.00018062956761513675,
|
1252 |
+
"loss": 1.5735,
|
1253 |
+
"step": 202
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 0.63,
|
1257 |
+
"learning_rate": 0.00018043413595229818,
|
1258 |
+
"loss": 1.6011,
|
1259 |
+
"step": 203
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 0.63,
|
1263 |
+
"learning_rate": 0.00018023783020388763,
|
1264 |
+
"loss": 1.5434,
|
1265 |
+
"step": 204
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 0.64,
|
1269 |
+
"learning_rate": 0.00018004065250317868,
|
1270 |
+
"loss": 1.5533,
|
1271 |
+
"step": 205
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.64,
|
1275 |
+
"learning_rate": 0.00017984260499292058,
|
1276 |
+
"loss": 1.6074,
|
1277 |
+
"step": 206
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.64,
|
1281 |
+
"learning_rate": 0.00017964368982531487,
|
1282 |
+
"loss": 1.5286,
|
1283 |
+
"step": 207
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.65,
|
1287 |
+
"learning_rate": 0.00017944390916199203,
|
1288 |
+
"loss": 1.5161,
|
1289 |
+
"step": 208
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 0.65,
|
1293 |
+
"learning_rate": 0.00017924326517398793,
|
1294 |
+
"loss": 1.6024,
|
1295 |
+
"step": 209
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 0.65,
|
1299 |
+
"learning_rate": 0.00017904176004172027,
|
1300 |
+
"loss": 1.5727,
|
1301 |
+
"step": 210
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 0.66,
|
1305 |
+
"learning_rate": 0.0001788393959549649,
|
1306 |
+
"loss": 1.5752,
|
1307 |
+
"step": 211
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 0.66,
|
1311 |
+
"learning_rate": 0.00017863617511283203,
|
1312 |
+
"loss": 1.5845,
|
1313 |
+
"step": 212
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.66,
|
1317 |
+
"learning_rate": 0.00017843209972374233,
|
1318 |
+
"loss": 1.6082,
|
1319 |
+
"step": 213
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.67,
|
1323 |
+
"learning_rate": 0.00017822717200540283,
|
1324 |
+
"loss": 1.5895,
|
1325 |
+
"step": 214
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.67,
|
1329 |
+
"learning_rate": 0.00017802139418478298,
|
1330 |
+
"loss": 1.5836,
|
1331 |
+
"step": 215
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 0.67,
|
1335 |
+
"learning_rate": 0.00017781476849809038,
|
1336 |
+
"loss": 1.5996,
|
1337 |
+
"step": 216
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 0.67,
|
1341 |
+
"learning_rate": 0.00017760729719074644,
|
1342 |
+
"loss": 1.6256,
|
1343 |
+
"step": 217
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.68,
|
1347 |
+
"learning_rate": 0.000177398982517362,
|
1348 |
+
"loss": 1.628,
|
1349 |
+
"step": 218
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 0.68,
|
1353 |
+
"learning_rate": 0.00017718982674171284,
|
1354 |
+
"loss": 1.5543,
|
1355 |
+
"step": 219
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.68,
|
1359 |
+
"learning_rate": 0.00017697983213671515,
|
1360 |
+
"loss": 1.5732,
|
1361 |
+
"step": 220
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.69,
|
1365 |
+
"learning_rate": 0.0001767690009844007,
|
1366 |
+
"loss": 1.5892,
|
1367 |
+
"step": 221
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.69,
|
1371 |
+
"learning_rate": 0.0001765573355758921,
|
1372 |
+
"loss": 1.6524,
|
1373 |
+
"step": 222
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 0.69,
|
1377 |
+
"learning_rate": 0.00017634483821137787,
|
1378 |
+
"loss": 1.5694,
|
1379 |
+
"step": 223
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 0.7,
|
1383 |
+
"learning_rate": 0.0001761315112000876,
|
1384 |
+
"loss": 1.6006,
|
1385 |
+
"step": 224
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.7,
|
1389 |
+
"learning_rate": 0.00017591735686026661,
|
1390 |
+
"loss": 1.6161,
|
1391 |
+
"step": 225
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 0.7,
|
1395 |
+
"learning_rate": 0.00017570237751915092,
|
1396 |
+
"loss": 1.595,
|
1397 |
+
"step": 226
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 0.71,
|
1401 |
+
"learning_rate": 0.00017548657551294192,
|
1402 |
+
"loss": 1.6072,
|
1403 |
+
"step": 227
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.71,
|
1407 |
+
"learning_rate": 0.000175269953186781,
|
1408 |
+
"loss": 1.5855,
|
1409 |
+
"step": 228
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.71,
|
1413 |
+
"learning_rate": 0.00017505251289472406,
|
1414 |
+
"loss": 1.597,
|
1415 |
+
"step": 229
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 0.72,
|
1419 |
+
"learning_rate": 0.0001748342569997158,
|
1420 |
+
"loss": 1.5837,
|
1421 |
+
"step": 230
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 0.72,
|
1425 |
+
"learning_rate": 0.00017461518787356432,
|
1426 |
+
"loss": 1.5422,
|
1427 |
+
"step": 231
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.72,
|
1431 |
+
"learning_rate": 0.00017439530789691506,
|
1432 |
+
"loss": 1.5837,
|
1433 |
+
"step": 232
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 0.72,
|
1437 |
+
"learning_rate": 0.0001741746194592251,
|
1438 |
+
"loss": 1.6038,
|
1439 |
+
"step": 233
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.73,
|
1443 |
+
"learning_rate": 0.00017395312495873717,
|
1444 |
+
"loss": 1.5882,
|
1445 |
+
"step": 234
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.73,
|
1449 |
+
"learning_rate": 0.00017373082680245347,
|
1450 |
+
"loss": 1.5763,
|
1451 |
+
"step": 235
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.73,
|
1455 |
+
"learning_rate": 0.00017350772740610976,
|
1456 |
+
"loss": 1.6046,
|
1457 |
+
"step": 236
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 0.74,
|
1461 |
+
"learning_rate": 0.00017328382919414877,
|
1462 |
+
"loss": 1.594,
|
1463 |
+
"step": 237
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 0.74,
|
1467 |
+
"learning_rate": 0.00017305913459969414,
|
1468 |
+
"loss": 1.5903,
|
1469 |
+
"step": 238
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 0.74,
|
1473 |
+
"learning_rate": 0.00017283364606452396,
|
1474 |
+
"loss": 1.5704,
|
1475 |
+
"step": 239
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 0.75,
|
1479 |
+
"learning_rate": 0.0001726073660390439,
|
1480 |
+
"loss": 1.588,
|
1481 |
+
"step": 240
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.75,
|
1485 |
+
"learning_rate": 0.00017238029698226113,
|
1486 |
+
"loss": 1.6273,
|
1487 |
+
"step": 241
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.75,
|
1491 |
+
"learning_rate": 0.00017215244136175705,
|
1492 |
+
"loss": 1.5166,
|
1493 |
+
"step": 242
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.76,
|
1497 |
+
"learning_rate": 0.00017192380165366092,
|
1498 |
+
"loss": 1.5813,
|
1499 |
+
"step": 243
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 0.76,
|
1503 |
+
"learning_rate": 0.0001716943803426226,
|
1504 |
+
"loss": 1.5654,
|
1505 |
+
"step": 244
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 0.76,
|
1509 |
+
"learning_rate": 0.0001714641799217858,
|
1510 |
+
"loss": 1.5548,
|
1511 |
+
"step": 245
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 0.77,
|
1515 |
+
"learning_rate": 0.00017123320289276085,
|
1516 |
+
"loss": 1.5491,
|
1517 |
+
"step": 246
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 0.77,
|
1521 |
+
"learning_rate": 0.0001710014517655976,
|
1522 |
+
"loss": 1.5903,
|
1523 |
+
"step": 247
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.77,
|
1527 |
+
"learning_rate": 0.00017076892905875806,
|
1528 |
+
"loss": 1.5687,
|
1529 |
+
"step": 248
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.77,
|
1533 |
+
"learning_rate": 0.00017053563729908905,
|
1534 |
+
"loss": 1.5975,
|
1535 |
+
"step": 249
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.78,
|
1539 |
+
"learning_rate": 0.00017030157902179485,
|
1540 |
+
"loss": 1.6055,
|
1541 |
+
"step": 250
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 0.78,
|
1545 |
+
"eval_loss": 1.60513174533844,
|
1546 |
+
"eval_runtime": 233.7813,
|
1547 |
+
"eval_samples_per_second": 16.353,
|
1548 |
+
"eval_steps_per_second": 4.089,
|
1549 |
+
"step": 250
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.78,
|
1553 |
+
"learning_rate": 0.00017006675677040946,
|
1554 |
+
"loss": 1.4661,
|
1555 |
+
"step": 251
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.78,
|
1559 |
+
"learning_rate": 0.00016983117309676908,
|
1560 |
+
"loss": 1.6071,
|
1561 |
+
"step": 252
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 0.79,
|
1565 |
+
"learning_rate": 0.00016959483056098445,
|
1566 |
+
"loss": 1.5664,
|
1567 |
+
"step": 253
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 0.79,
|
1571 |
+
"learning_rate": 0.0001693577317314129,
|
1572 |
+
"loss": 1.5189,
|
1573 |
+
"step": 254
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 0.79,
|
1577 |
+
"learning_rate": 0.00016911987918463034,
|
1578 |
+
"loss": 1.5488,
|
1579 |
+
"step": 255
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 0.8,
|
1583 |
+
"learning_rate": 0.0001688812755054036,
|
1584 |
+
"loss": 1.6153,
|
1585 |
+
"step": 256
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.8,
|
1589 |
+
"learning_rate": 0.00016864192328666202,
|
1590 |
+
"loss": 1.536,
|
1591 |
+
"step": 257
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.8,
|
1595 |
+
"learning_rate": 0.00016840182512946943,
|
1596 |
+
"loss": 1.624,
|
1597 |
+
"step": 258
|
1598 |
+
},
|
1599 |
+
{
|
1600 |
+
"epoch": 0.81,
|
1601 |
+
"learning_rate": 0.00016816098364299582,
|
1602 |
+
"loss": 1.569,
|
1603 |
+
"step": 259
|
1604 |
+
},
|
1605 |
+
{
|
1606 |
+
"epoch": 0.81,
|
1607 |
+
"learning_rate": 0.00016791940144448902,
|
1608 |
+
"loss": 1.588,
|
1609 |
+
"step": 260
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 0.81,
|
1613 |
+
"learning_rate": 0.0001676770811592463,
|
1614 |
+
"loss": 1.5626,
|
1615 |
+
"step": 261
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 0.81,
|
1619 |
+
"learning_rate": 0.00016743402542058572,
|
1620 |
+
"loss": 1.5836,
|
1621 |
+
"step": 262
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 0.82,
|
1625 |
+
"learning_rate": 0.00016719023686981763,
|
1626 |
+
"loss": 1.5573,
|
1627 |
+
"step": 263
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.82,
|
1631 |
+
"learning_rate": 0.00016694571815621586,
|
1632 |
+
"loss": 1.5815,
|
1633 |
+
"step": 264
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.82,
|
1637 |
+
"learning_rate": 0.00016670047193698912,
|
1638 |
+
"loss": 1.64,
|
1639 |
+
"step": 265
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"epoch": 0.83,
|
1643 |
+
"learning_rate": 0.0001664545008772518,
|
1644 |
+
"loss": 1.6395,
|
1645 |
+
"step": 266
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 0.83,
|
1649 |
+
"learning_rate": 0.00016620780764999536,
|
1650 |
+
"loss": 1.5927,
|
1651 |
+
"step": 267
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 0.83,
|
1655 |
+
"learning_rate": 0.00016596039493605913,
|
1656 |
+
"loss": 1.605,
|
1657 |
+
"step": 268
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 0.84,
|
1661 |
+
"learning_rate": 0.000165712265424101,
|
1662 |
+
"loss": 1.6219,
|
1663 |
+
"step": 269
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.84,
|
1667 |
+
"learning_rate": 0.0001654634218105686,
|
1668 |
+
"loss": 1.5458,
|
1669 |
+
"step": 270
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.84,
|
1673 |
+
"learning_rate": 0.0001652138667996696,
|
1674 |
+
"loss": 1.59,
|
1675 |
+
"step": 271
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.85,
|
1679 |
+
"learning_rate": 0.00016496360310334253,
|
1680 |
+
"loss": 1.633,
|
1681 |
+
"step": 272
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 0.85,
|
1685 |
+
"learning_rate": 0.0001647126334412274,
|
1686 |
+
"loss": 1.6108,
|
1687 |
+
"step": 273
|
1688 |
+
},
|
1689 |
+
{
|
1690 |
+
"epoch": 0.85,
|
1691 |
+
"learning_rate": 0.0001644609605406358,
|
1692 |
+
"loss": 1.5747,
|
1693 |
+
"step": 274
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 0.86,
|
1697 |
+
"learning_rate": 0.0001642085871365217,
|
1698 |
+
"loss": 1.5393,
|
1699 |
+
"step": 275
|
1700 |
+
},
|
1701 |
+
{
|
1702 |
+
"epoch": 0.86,
|
1703 |
+
"learning_rate": 0.00016395551597145133,
|
1704 |
+
"loss": 1.5768,
|
1705 |
+
"step": 276
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.86,
|
1709 |
+
"learning_rate": 0.00016370174979557368,
|
1710 |
+
"loss": 1.6278,
|
1711 |
+
"step": 277
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.86,
|
1715 |
+
"learning_rate": 0.0001634472913665904,
|
1716 |
+
"loss": 1.5983,
|
1717 |
+
"step": 278
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.87,
|
1721 |
+
"learning_rate": 0.00016319214344972602,
|
1722 |
+
"loss": 1.5701,
|
1723 |
+
"step": 279
|
1724 |
+
},
|
1725 |
+
{
|
1726 |
+
"epoch": 0.87,
|
1727 |
+
"learning_rate": 0.00016293630881769773,
|
1728 |
+
"loss": 1.5874,
|
1729 |
+
"step": 280
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 0.87,
|
1733 |
+
"learning_rate": 0.0001626797902506853,
|
1734 |
+
"loss": 1.5412,
|
1735 |
+
"step": 281
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 0.88,
|
1739 |
+
"learning_rate": 0.000162422590536301,
|
1740 |
+
"loss": 1.5733,
|
1741 |
+
"step": 282
|
1742 |
+
},
|
1743 |
+
{
|
1744 |
+
"epoch": 0.88,
|
1745 |
+
"learning_rate": 0.00016216471246955906,
|
1746 |
+
"loss": 1.6245,
|
1747 |
+
"step": 283
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.88,
|
1751 |
+
"learning_rate": 0.00016190615885284553,
|
1752 |
+
"loss": 1.5743,
|
1753 |
+
"step": 284
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.89,
|
1757 |
+
"learning_rate": 0.00016164693249588768,
|
1758 |
+
"loss": 1.5793,
|
1759 |
+
"step": 285
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.89,
|
1763 |
+
"learning_rate": 0.00016138703621572346,
|
1764 |
+
"loss": 1.5672,
|
1765 |
+
"step": 286
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 0.89,
|
1769 |
+
"learning_rate": 0.0001611264728366711,
|
1770 |
+
"loss": 1.5442,
|
1771 |
+
"step": 287
|
1772 |
+
},
|
1773 |
+
{
|
1774 |
+
"epoch": 0.9,
|
1775 |
+
"learning_rate": 0.0001608652451902981,
|
1776 |
+
"loss": 1.5765,
|
1777 |
+
"step": 288
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 0.9,
|
1781 |
+
"learning_rate": 0.00016060335611539072,
|
1782 |
+
"loss": 1.6058,
|
1783 |
+
"step": 289
|
1784 |
+
},
|
1785 |
+
{
|
1786 |
+
"epoch": 0.9,
|
1787 |
+
"learning_rate": 0.00016034080845792295,
|
1788 |
+
"loss": 1.6156,
|
1789 |
+
"step": 290
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.91,
|
1793 |
+
"learning_rate": 0.0001600776050710257,
|
1794 |
+
"loss": 1.6179,
|
1795 |
+
"step": 291
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 0.91,
|
1799 |
+
"learning_rate": 0.0001598137488149558,
|
1800 |
+
"loss": 1.5747,
|
1801 |
+
"step": 292
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.91,
|
1805 |
+
"learning_rate": 0.00015954924255706478,
|
1806 |
+
"loss": 1.5772,
|
1807 |
+
"step": 293
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 0.91,
|
1811 |
+
"learning_rate": 0.00015928408917176786,
|
1812 |
+
"loss": 1.6064,
|
1813 |
+
"step": 294
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"epoch": 0.92,
|
1817 |
+
"learning_rate": 0.00015901829154051265,
|
1818 |
+
"loss": 1.6082,
|
1819 |
+
"step": 295
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 0.92,
|
1823 |
+
"learning_rate": 0.00015875185255174787,
|
1824 |
+
"loss": 1.5768,
|
1825 |
+
"step": 296
|
1826 |
+
},
|
1827 |
+
{
|
1828 |
+
"epoch": 0.92,
|
1829 |
+
"learning_rate": 0.0001584847751008918,
|
1830 |
+
"loss": 1.5466,
|
1831 |
+
"step": 297
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.93,
|
1835 |
+
"learning_rate": 0.00015821706209030118,
|
1836 |
+
"loss": 1.5127,
|
1837 |
+
"step": 298
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 0.93,
|
1841 |
+
"learning_rate": 0.00015794871642923927,
|
1842 |
+
"loss": 1.5745,
|
1843 |
+
"step": 299
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.93,
|
1847 |
+
"learning_rate": 0.00015767974103384443,
|
1848 |
+
"loss": 1.5733,
|
1849 |
+
"step": 300
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 0.93,
|
1853 |
+
"eval_loss": 1.6023043394088745,
|
1854 |
+
"eval_runtime": 233.7298,
|
1855 |
+
"eval_samples_per_second": 16.356,
|
1856 |
+
"eval_steps_per_second": 4.09,
|
1857 |
+
"step": 300
|
1858 |
+
}
|
1859 |
+
],
|
1860 |
+
"logging_steps": 1,
|
1861 |
+
"max_steps": 963,
|
1862 |
+
"num_train_epochs": 3,
|
1863 |
+
"save_steps": 50,
|
1864 |
+
"total_flos": 8.412814972551168e+17,
|
1865 |
+
"trial_name": null,
|
1866 |
+
"trial_params": null
|
1867 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f61cafb89242b653e455003b5517e685ecccfa6180af5fb7d0bfb35b4fc77a4
|
3 |
+
size 4475
|
checkpoint-350/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-350/adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"o_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"v_proj",
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
checkpoint-350/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b2acf0965b728b9f39ff875af1a0bb542f43cde79c4a44aec31d97b0a6d6b82
|
3 |
+
size 84046925
|
checkpoint-350/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11cb718fc6f4900ddc9d4ea78c1d177248d5b82b9a7a5e9ba5cab022b06f42c3
|
3 |
+
size 168039557
|
checkpoint-350/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baa9a901b79ce6d4ba427b92cd20bcdf077fd9a1e8d53d67f2028575762241a6
|
3 |
+
size 14575
|
checkpoint-350/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daca21bf7aaa413d1759b6b33dab777d4a7f3e9ba04816c3ce7a0f4e706b5cdb
|
3 |
+
size 627
|