Model save
Browse files- README.md +111 -0
- adapter_config.json +25 -0
- adapter_model.safetensors +3 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
- train_results.json +8 -0
- trainer_state.json +1244 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: zephyr-7b-sft-lora-accum4-lr5e_6
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# zephyr-7b-sft-lora-accum4-lr5e_6
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.0318
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 16
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- num_epochs: 50.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.0685 | 0.55 | 13 | 2.0233 |
|
| 55 |
+
| 1.9972 | 1.57 | 27 | 1.9438 |
|
| 56 |
+
| 1.9109 | 2.55 | 40 | 1.8720 |
|
| 57 |
+
| 1.8583 | 3.57 | 54 | 1.8096 |
|
| 58 |
+
| 1.7903 | 4.55 | 67 | 1.7596 |
|
| 59 |
+
| 1.7454 | 5.57 | 81 | 1.7169 |
|
| 60 |
+
| 1.7146 | 6.55 | 94 | 1.6789 |
|
| 61 |
+
| 1.6737 | 7.57 | 108 | 1.6395 |
|
| 62 |
+
| 1.6289 | 8.55 | 121 | 1.6056 |
|
| 63 |
+
| 1.5934 | 9.57 | 135 | 1.5665 |
|
| 64 |
+
| 1.565 | 10.55 | 148 | 1.5258 |
|
| 65 |
+
| 1.519 | 11.57 | 162 | 1.4776 |
|
| 66 |
+
| 1.4593 | 12.55 | 175 | 1.4281 |
|
| 67 |
+
| 1.4156 | 13.57 | 189 | 1.3676 |
|
| 68 |
+
| 1.3512 | 14.55 | 202 | 1.3222 |
|
| 69 |
+
| 1.3146 | 15.57 | 216 | 1.2825 |
|
| 70 |
+
| 1.2798 | 16.55 | 229 | 1.2492 |
|
| 71 |
+
| 1.2532 | 17.57 | 243 | 1.2225 |
|
| 72 |
+
| 1.2277 | 18.55 | 256 | 1.2033 |
|
| 73 |
+
| 1.208 | 19.57 | 270 | 1.1832 |
|
| 74 |
+
| 1.1944 | 20.55 | 283 | 1.1732 |
|
| 75 |
+
| 1.1799 | 21.57 | 297 | 1.1586 |
|
| 76 |
+
| 1.1621 | 22.55 | 310 | 1.1494 |
|
| 77 |
+
| 1.1448 | 23.57 | 324 | 1.1393 |
|
| 78 |
+
| 1.1564 | 24.55 | 337 | 1.1301 |
|
| 79 |
+
| 1.1293 | 25.57 | 351 | 1.1233 |
|
| 80 |
+
| 1.1228 | 26.55 | 364 | 1.1160 |
|
| 81 |
+
| 1.1266 | 27.57 | 378 | 1.1106 |
|
| 82 |
+
| 1.1159 | 28.55 | 391 | 1.1047 |
|
| 83 |
+
| 1.125 | 29.57 | 405 | 1.0989 |
|
| 84 |
+
| 1.094 | 30.55 | 418 | 1.0941 |
|
| 85 |
+
| 1.1077 | 31.57 | 432 | 1.0903 |
|
| 86 |
+
| 1.0874 | 32.55 | 445 | 1.0834 |
|
| 87 |
+
| 1.0957 | 33.57 | 459 | 1.0769 |
|
| 88 |
+
| 1.0755 | 34.55 | 472 | 1.0750 |
|
| 89 |
+
| 1.0705 | 35.57 | 486 | 1.0719 |
|
| 90 |
+
| 1.0749 | 36.55 | 499 | 1.0688 |
|
| 91 |
+
| 1.0742 | 37.57 | 513 | 1.0641 |
|
| 92 |
+
| 1.064 | 38.55 | 526 | 1.0626 |
|
| 93 |
+
| 1.0569 | 39.57 | 540 | 1.0593 |
|
| 94 |
+
| 1.0686 | 40.55 | 553 | 1.0554 |
|
| 95 |
+
| 1.059 | 41.57 | 567 | 1.0517 |
|
| 96 |
+
| 1.0588 | 42.55 | 580 | 1.0469 |
|
| 97 |
+
| 1.0447 | 43.57 | 594 | 1.0471 |
|
| 98 |
+
| 1.0356 | 44.55 | 607 | 1.0421 |
|
| 99 |
+
| 1.0431 | 45.57 | 621 | 1.0416 |
|
| 100 |
+
| 1.0195 | 46.55 | 634 | 1.0387 |
|
| 101 |
+
| 1.0326 | 47.57 | 648 | 1.0356 |
|
| 102 |
+
| 1.0227 | 48.55 | 661 | 1.0341 |
|
| 103 |
+
| 1.0403 | 49.57 | 675 | 1.0317 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.35.0
|
| 109 |
+
- Pytorch 2.1.0
|
| 110 |
+
- Datasets 2.14.6
|
| 111 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 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": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 64,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj",
|
| 21 |
+
"o_proj",
|
| 22 |
+
"k_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "CAUSAL_LM"
|
| 25 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9435755e3d67dd8cbbebd059af79f299f62fd57cfa90bb9ae366f6636c5b32c
|
| 3 |
+
size 109086672
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.57,
|
| 3 |
+
"eval_loss": 1.031841516494751,
|
| 4 |
+
"eval_runtime": 3.9721,
|
| 5 |
+
"eval_samples": 83,
|
| 6 |
+
"eval_samples_per_second": 20.896,
|
| 7 |
+
"eval_steps_per_second": 1.511,
|
| 8 |
+
"train_loss": 1.2869272242652046,
|
| 9 |
+
"train_runtime": 6519.8949,
|
| 10 |
+
"train_samples": 746,
|
| 11 |
+
"train_samples_per_second": 5.721,
|
| 12 |
+
"train_steps_per_second": 0.176
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.57,
|
| 3 |
+
"eval_loss": 1.031841516494751,
|
| 4 |
+
"eval_runtime": 3.9721,
|
| 5 |
+
"eval_samples": 83,
|
| 6 |
+
"eval_samples_per_second": 20.896,
|
| 7 |
+
"eval_steps_per_second": 1.511
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": true,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"spaces_between_special_tokens": false,
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": false
|
| 41 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.57,
|
| 3 |
+
"train_loss": 1.2869272242652046,
|
| 4 |
+
"train_runtime": 6519.8949,
|
| 5 |
+
"train_samples": 746,
|
| 6 |
+
"train_samples_per_second": 5.721,
|
| 7 |
+
"train_steps_per_second": 0.176
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.57446808510638,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 675,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 4.999990671457219e-06,
|
| 14 |
+
"loss": 2.0607,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.21,
|
| 19 |
+
"learning_rate": 4.9997667899113055e-06,
|
| 20 |
+
"loss": 2.0852,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.43,
|
| 25 |
+
"learning_rate": 4.999067203154777e-06,
|
| 26 |
+
"loss": 2.0685,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.55,
|
| 31 |
+
"eval_loss": 2.0233097076416016,
|
| 32 |
+
"eval_runtime": 4.0604,
|
| 33 |
+
"eval_samples_per_second": 20.441,
|
| 34 |
+
"eval_steps_per_second": 1.478,
|
| 35 |
+
"step": 13
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.06,
|
| 39 |
+
"learning_rate": 4.997901370250966e-06,
|
| 40 |
+
"loss": 2.0386,
|
| 41 |
+
"step": 15
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.28,
|
| 45 |
+
"learning_rate": 4.99626950870707e-06,
|
| 46 |
+
"loss": 2.0152,
|
| 47 |
+
"step": 20
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.49,
|
| 51 |
+
"learning_rate": 4.994171922976349e-06,
|
| 52 |
+
"loss": 1.9972,
|
| 53 |
+
"step": 25
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.57,
|
| 57 |
+
"eval_loss": 1.9437636137008667,
|
| 58 |
+
"eval_runtime": 3.9692,
|
| 59 |
+
"eval_samples_per_second": 20.911,
|
| 60 |
+
"eval_steps_per_second": 1.512,
|
| 61 |
+
"step": 27
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.13,
|
| 65 |
+
"learning_rate": 4.991609004401324e-06,
|
| 66 |
+
"loss": 1.956,
|
| 67 |
+
"step": 30
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.34,
|
| 71 |
+
"learning_rate": 4.988581231140772e-06,
|
| 72 |
+
"loss": 1.9288,
|
| 73 |
+
"step": 35
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.55,
|
| 77 |
+
"learning_rate": 4.985089168080509e-06,
|
| 78 |
+
"loss": 1.9109,
|
| 79 |
+
"step": 40
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.55,
|
| 83 |
+
"eval_loss": 1.8719902038574219,
|
| 84 |
+
"eval_runtime": 3.9854,
|
| 85 |
+
"eval_samples_per_second": 20.826,
|
| 86 |
+
"eval_steps_per_second": 1.505,
|
| 87 |
+
"step": 40
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.19,
|
| 91 |
+
"learning_rate": 4.981133466728004e-06,
|
| 92 |
+
"loss": 1.8712,
|
| 93 |
+
"step": 45
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.4,
|
| 97 |
+
"learning_rate": 4.976714865090827e-06,
|
| 98 |
+
"loss": 1.8583,
|
| 99 |
+
"step": 50
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.57,
|
| 103 |
+
"eval_loss": 1.809607744216919,
|
| 104 |
+
"eval_runtime": 3.9774,
|
| 105 |
+
"eval_samples_per_second": 20.868,
|
| 106 |
+
"eval_steps_per_second": 1.509,
|
| 107 |
+
"step": 54
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 4.04,
|
| 111 |
+
"learning_rate": 4.971834187538963e-06,
|
| 112 |
+
"loss": 1.843,
|
| 113 |
+
"step": 55
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.26,
|
| 117 |
+
"learning_rate": 4.966492344651006e-06,
|
| 118 |
+
"loss": 1.8171,
|
| 119 |
+
"step": 60
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.47,
|
| 123 |
+
"learning_rate": 4.960690333044279e-06,
|
| 124 |
+
"loss": 1.7903,
|
| 125 |
+
"step": 65
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.55,
|
| 129 |
+
"eval_loss": 1.7595775127410889,
|
| 130 |
+
"eval_runtime": 3.9935,
|
| 131 |
+
"eval_samples_per_second": 20.784,
|
| 132 |
+
"eval_steps_per_second": 1.502,
|
| 133 |
+
"step": 67
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.11,
|
| 137 |
+
"learning_rate": 4.954429235188897e-06,
|
| 138 |
+
"loss": 1.7816,
|
| 139 |
+
"step": 70
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.32,
|
| 143 |
+
"learning_rate": 4.947710219205808e-06,
|
| 144 |
+
"loss": 1.765,
|
| 145 |
+
"step": 75
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.53,
|
| 149 |
+
"learning_rate": 4.940534538648862e-06,
|
| 150 |
+
"loss": 1.7454,
|
| 151 |
+
"step": 80
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 5.57,
|
| 155 |
+
"eval_loss": 1.7169337272644043,
|
| 156 |
+
"eval_runtime": 3.9846,
|
| 157 |
+
"eval_samples_per_second": 20.83,
|
| 158 |
+
"eval_steps_per_second": 1.506,
|
| 159 |
+
"step": 81
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.17,
|
| 163 |
+
"learning_rate": 4.932903532270939e-06,
|
| 164 |
+
"loss": 1.7242,
|
| 165 |
+
"step": 85
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.38,
|
| 169 |
+
"learning_rate": 4.924818623774178e-06,
|
| 170 |
+
"loss": 1.7146,
|
| 171 |
+
"step": 90
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.55,
|
| 175 |
+
"eval_loss": 1.6789494752883911,
|
| 176 |
+
"eval_runtime": 3.9897,
|
| 177 |
+
"eval_samples_per_second": 20.803,
|
| 178 |
+
"eval_steps_per_second": 1.504,
|
| 179 |
+
"step": 94
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 7.02,
|
| 183 |
+
"learning_rate": 4.916281321544362e-06,
|
| 184 |
+
"loss": 1.7114,
|
| 185 |
+
"step": 95
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.23,
|
| 189 |
+
"learning_rate": 4.907293218369499e-06,
|
| 190 |
+
"loss": 1.6893,
|
| 191 |
+
"step": 100
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.45,
|
| 195 |
+
"learning_rate": 4.897855991142658e-06,
|
| 196 |
+
"loss": 1.6737,
|
| 197 |
+
"step": 105
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 7.57,
|
| 201 |
+
"eval_loss": 1.6394565105438232,
|
| 202 |
+
"eval_runtime": 3.9863,
|
| 203 |
+
"eval_samples_per_second": 20.821,
|
| 204 |
+
"eval_steps_per_second": 1.505,
|
| 205 |
+
"step": 108
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 8.09,
|
| 209 |
+
"learning_rate": 4.8879714005491205e-06,
|
| 210 |
+
"loss": 1.6691,
|
| 211 |
+
"step": 110
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 8.3,
|
| 215 |
+
"learning_rate": 4.8776412907378845e-06,
|
| 216 |
+
"loss": 1.6507,
|
| 217 |
+
"step": 115
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 8.51,
|
| 221 |
+
"learning_rate": 4.8668675889776095e-06,
|
| 222 |
+
"loss": 1.6289,
|
| 223 |
+
"step": 120
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 8.55,
|
| 227 |
+
"eval_loss": 1.605614185333252,
|
| 228 |
+
"eval_runtime": 4.0005,
|
| 229 |
+
"eval_samples_per_second": 20.748,
|
| 230 |
+
"eval_steps_per_second": 1.5,
|
| 231 |
+
"step": 121
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 9.15,
|
| 235 |
+
"learning_rate": 4.855652305297052e-06,
|
| 236 |
+
"loss": 1.6312,
|
| 237 |
+
"step": 125
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.36,
|
| 241 |
+
"learning_rate": 4.843997532110051e-06,
|
| 242 |
+
"loss": 1.5965,
|
| 243 |
+
"step": 130
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 9.57,
|
| 247 |
+
"learning_rate": 4.83190544382516e-06,
|
| 248 |
+
"loss": 1.5934,
|
| 249 |
+
"step": 135
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 9.57,
|
| 253 |
+
"eval_loss": 1.5665417909622192,
|
| 254 |
+
"eval_runtime": 3.9832,
|
| 255 |
+
"eval_samples_per_second": 20.838,
|
| 256 |
+
"eval_steps_per_second": 1.506,
|
| 257 |
+
"step": 135
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 10.21,
|
| 261 |
+
"learning_rate": 4.819378296439962e-06,
|
| 262 |
+
"loss": 1.5634,
|
| 263 |
+
"step": 140
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 10.43,
|
| 267 |
+
"learning_rate": 4.80641842712018e-06,
|
| 268 |
+
"loss": 1.565,
|
| 269 |
+
"step": 145
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 10.55,
|
| 273 |
+
"eval_loss": 1.5258013010025024,
|
| 274 |
+
"eval_runtime": 3.9933,
|
| 275 |
+
"eval_samples_per_second": 20.785,
|
| 276 |
+
"eval_steps_per_second": 1.503,
|
| 277 |
+
"step": 148
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 11.06,
|
| 281 |
+
"learning_rate": 4.793028253763633e-06,
|
| 282 |
+
"loss": 1.5491,
|
| 283 |
+
"step": 150
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 11.28,
|
| 287 |
+
"learning_rate": 4.7792102745491345e-06,
|
| 288 |
+
"loss": 1.5353,
|
| 289 |
+
"step": 155
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 11.49,
|
| 293 |
+
"learning_rate": 4.764967067470409e-06,
|
| 294 |
+
"loss": 1.519,
|
| 295 |
+
"step": 160
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 11.57,
|
| 299 |
+
"eval_loss": 1.4776073694229126,
|
| 300 |
+
"eval_runtime": 3.9813,
|
| 301 |
+
"eval_samples_per_second": 20.847,
|
| 302 |
+
"eval_steps_per_second": 1.507,
|
| 303 |
+
"step": 162
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 12.13,
|
| 307 |
+
"learning_rate": 4.750301289855128e-06,
|
| 308 |
+
"loss": 1.4823,
|
| 309 |
+
"step": 165
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 12.34,
|
| 313 |
+
"learning_rate": 4.735215677869129e-06,
|
| 314 |
+
"loss": 1.4795,
|
| 315 |
+
"step": 170
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 12.55,
|
| 319 |
+
"learning_rate": 4.7197130460059385e-06,
|
| 320 |
+
"loss": 1.4593,
|
| 321 |
+
"step": 175
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 12.55,
|
| 325 |
+
"eval_loss": 1.4280617237091064,
|
| 326 |
+
"eval_runtime": 3.9852,
|
| 327 |
+
"eval_samples_per_second": 20.827,
|
| 328 |
+
"eval_steps_per_second": 1.506,
|
| 329 |
+
"step": 175
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 13.19,
|
| 333 |
+
"learning_rate": 4.7037962865616795e-06,
|
| 334 |
+
"loss": 1.4393,
|
| 335 |
+
"step": 180
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 13.4,
|
| 339 |
+
"learning_rate": 4.687468369095457e-06,
|
| 340 |
+
"loss": 1.4156,
|
| 341 |
+
"step": 185
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 13.57,
|
| 345 |
+
"eval_loss": 1.3676358461380005,
|
| 346 |
+
"eval_runtime": 3.9729,
|
| 347 |
+
"eval_samples_per_second": 20.892,
|
| 348 |
+
"eval_steps_per_second": 1.51,
|
| 349 |
+
"step": 189
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 14.04,
|
| 353 |
+
"learning_rate": 4.6707323398753346e-06,
|
| 354 |
+
"loss": 1.3898,
|
| 355 |
+
"step": 190
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 14.26,
|
| 359 |
+
"learning_rate": 4.6535913213100005e-06,
|
| 360 |
+
"loss": 1.3671,
|
| 361 |
+
"step": 195
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 14.47,
|
| 365 |
+
"learning_rate": 4.636048511366222e-06,
|
| 366 |
+
"loss": 1.3512,
|
| 367 |
+
"step": 200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 14.55,
|
| 371 |
+
"eval_loss": 1.3222225904464722,
|
| 372 |
+
"eval_runtime": 4.0174,
|
| 373 |
+
"eval_samples_per_second": 20.66,
|
| 374 |
+
"eval_steps_per_second": 1.494,
|
| 375 |
+
"step": 202
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 15.11,
|
| 379 |
+
"learning_rate": 4.618107182972209e-06,
|
| 380 |
+
"loss": 1.3308,
|
| 381 |
+
"step": 205
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 15.32,
|
| 385 |
+
"learning_rate": 4.599770683406992e-06,
|
| 386 |
+
"loss": 1.3194,
|
| 387 |
+
"step": 210
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 15.53,
|
| 391 |
+
"learning_rate": 4.58104243367592e-06,
|
| 392 |
+
"loss": 1.3146,
|
| 393 |
+
"step": 215
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 15.57,
|
| 397 |
+
"eval_loss": 1.2824859619140625,
|
| 398 |
+
"eval_runtime": 3.9833,
|
| 399 |
+
"eval_samples_per_second": 20.837,
|
| 400 |
+
"eval_steps_per_second": 1.506,
|
| 401 |
+
"step": 216
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 16.17,
|
| 405 |
+
"learning_rate": 4.561925927872421e-06,
|
| 406 |
+
"loss": 1.3001,
|
| 407 |
+
"step": 220
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 16.38,
|
| 411 |
+
"learning_rate": 4.542424732526105e-06,
|
| 412 |
+
"loss": 1.2798,
|
| 413 |
+
"step": 225
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 16.55,
|
| 417 |
+
"eval_loss": 1.2492066621780396,
|
| 418 |
+
"eval_runtime": 3.9849,
|
| 419 |
+
"eval_samples_per_second": 20.829,
|
| 420 |
+
"eval_steps_per_second": 1.506,
|
| 421 |
+
"step": 229
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 17.02,
|
| 425 |
+
"learning_rate": 4.522542485937369e-06,
|
| 426 |
+
"loss": 1.259,
|
| 427 |
+
"step": 230
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 17.23,
|
| 431 |
+
"learning_rate": 4.5022828974986044e-06,
|
| 432 |
+
"loss": 1.2516,
|
| 433 |
+
"step": 235
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 17.45,
|
| 437 |
+
"learning_rate": 4.481649747002146e-06,
|
| 438 |
+
"loss": 1.2532,
|
| 439 |
+
"step": 240
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 17.57,
|
| 443 |
+
"eval_loss": 1.22245192527771,
|
| 444 |
+
"eval_runtime": 3.9686,
|
| 445 |
+
"eval_samples_per_second": 20.914,
|
| 446 |
+
"eval_steps_per_second": 1.512,
|
| 447 |
+
"step": 243
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 18.09,
|
| 451 |
+
"learning_rate": 4.460646883935079e-06,
|
| 452 |
+
"loss": 1.2491,
|
| 453 |
+
"step": 245
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 18.3,
|
| 457 |
+
"learning_rate": 4.43927822676105e-06,
|
| 458 |
+
"loss": 1.2058,
|
| 459 |
+
"step": 250
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 18.51,
|
| 463 |
+
"learning_rate": 4.417547762189207e-06,
|
| 464 |
+
"loss": 1.2277,
|
| 465 |
+
"step": 255
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 18.55,
|
| 469 |
+
"eval_loss": 1.2032711505889893,
|
| 470 |
+
"eval_runtime": 3.9983,
|
| 471 |
+
"eval_samples_per_second": 20.759,
|
| 472 |
+
"eval_steps_per_second": 1.501,
|
| 473 |
+
"step": 256
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 19.15,
|
| 477 |
+
"learning_rate": 4.395459544430407e-06,
|
| 478 |
+
"loss": 1.2244,
|
| 479 |
+
"step": 260
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 19.36,
|
| 483 |
+
"learning_rate": 4.373017694440828e-06,
|
| 484 |
+
"loss": 1.1986,
|
| 485 |
+
"step": 265
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 19.57,
|
| 489 |
+
"learning_rate": 4.35022639915313e-06,
|
| 490 |
+
"loss": 1.208,
|
| 491 |
+
"step": 270
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 19.57,
|
| 495 |
+
"eval_loss": 1.18324875831604,
|
| 496 |
+
"eval_runtime": 3.9861,
|
| 497 |
+
"eval_samples_per_second": 20.822,
|
| 498 |
+
"eval_steps_per_second": 1.505,
|
| 499 |
+
"step": 270
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 20.21,
|
| 503 |
+
"learning_rate": 4.32708991069531e-06,
|
| 504 |
+
"loss": 1.1919,
|
| 505 |
+
"step": 275
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 20.43,
|
| 509 |
+
"learning_rate": 4.30361254559739e-06,
|
| 510 |
+
"loss": 1.1944,
|
| 511 |
+
"step": 280
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 20.55,
|
| 515 |
+
"eval_loss": 1.1732494831085205,
|
| 516 |
+
"eval_runtime": 3.9909,
|
| 517 |
+
"eval_samples_per_second": 20.797,
|
| 518 |
+
"eval_steps_per_second": 1.503,
|
| 519 |
+
"step": 283
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 21.06,
|
| 523 |
+
"learning_rate": 4.279798683986084e-06,
|
| 524 |
+
"loss": 1.18,
|
| 525 |
+
"step": 285
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 21.28,
|
| 529 |
+
"learning_rate": 4.255652768767619e-06,
|
| 530 |
+
"loss": 1.1806,
|
| 531 |
+
"step": 290
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 21.49,
|
| 535 |
+
"learning_rate": 4.2311793047988145e-06,
|
| 536 |
+
"loss": 1.1799,
|
| 537 |
+
"step": 295
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 21.57,
|
| 541 |
+
"eval_loss": 1.158596158027649,
|
| 542 |
+
"eval_runtime": 3.993,
|
| 543 |
+
"eval_samples_per_second": 20.787,
|
| 544 |
+
"eval_steps_per_second": 1.503,
|
| 545 |
+
"step": 297
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 22.13,
|
| 549 |
+
"learning_rate": 4.206382858046636e-06,
|
| 550 |
+
"loss": 1.1803,
|
| 551 |
+
"step": 300
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 22.34,
|
| 555 |
+
"learning_rate": 4.181268054736319e-06,
|
| 556 |
+
"loss": 1.1532,
|
| 557 |
+
"step": 305
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 22.55,
|
| 561 |
+
"learning_rate": 4.15583958048827e-06,
|
| 562 |
+
"loss": 1.1621,
|
| 563 |
+
"step": 310
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 22.55,
|
| 567 |
+
"eval_loss": 1.1493983268737793,
|
| 568 |
+
"eval_runtime": 3.9997,
|
| 569 |
+
"eval_samples_per_second": 20.752,
|
| 570 |
+
"eval_steps_per_second": 1.5,
|
| 571 |
+
"step": 310
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 23.19,
|
| 575 |
+
"learning_rate": 4.130102179443877e-06,
|
| 576 |
+
"loss": 1.1681,
|
| 577 |
+
"step": 315
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 23.4,
|
| 581 |
+
"learning_rate": 4.104060653380403e-06,
|
| 582 |
+
"loss": 1.1448,
|
| 583 |
+
"step": 320
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 23.57,
|
| 587 |
+
"eval_loss": 1.1393245458602905,
|
| 588 |
+
"eval_runtime": 3.9913,
|
| 589 |
+
"eval_samples_per_second": 20.795,
|
| 590 |
+
"eval_steps_per_second": 1.503,
|
| 591 |
+
"step": 324
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 24.04,
|
| 595 |
+
"learning_rate": 4.077719860815132e-06,
|
| 596 |
+
"loss": 1.1513,
|
| 597 |
+
"step": 325
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 24.26,
|
| 601 |
+
"learning_rate": 4.051084716098921e-06,
|
| 602 |
+
"loss": 1.1441,
|
| 603 |
+
"step": 330
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 24.47,
|
| 607 |
+
"learning_rate": 4.024160188499337e-06,
|
| 608 |
+
"loss": 1.1564,
|
| 609 |
+
"step": 335
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 24.55,
|
| 613 |
+
"eval_loss": 1.1301108598709106,
|
| 614 |
+
"eval_runtime": 3.9936,
|
| 615 |
+
"eval_samples_per_second": 20.783,
|
| 616 |
+
"eval_steps_per_second": 1.502,
|
| 617 |
+
"step": 337
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 25.11,
|
| 621 |
+
"learning_rate": 3.996951301273556e-06,
|
| 622 |
+
"loss": 1.1396,
|
| 623 |
+
"step": 340
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 25.32,
|
| 627 |
+
"learning_rate": 3.969463130731183e-06,
|
| 628 |
+
"loss": 1.1346,
|
| 629 |
+
"step": 345
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 25.53,
|
| 633 |
+
"learning_rate": 3.941700805287169e-06,
|
| 634 |
+
"loss": 1.1293,
|
| 635 |
+
"step": 350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 25.57,
|
| 639 |
+
"eval_loss": 1.1233478784561157,
|
| 640 |
+
"eval_runtime": 3.9814,
|
| 641 |
+
"eval_samples_per_second": 20.847,
|
| 642 |
+
"eval_steps_per_second": 1.507,
|
| 643 |
+
"step": 351
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 26.17,
|
| 647 |
+
"learning_rate": 3.913669504505015e-06,
|
| 648 |
+
"loss": 1.1483,
|
| 649 |
+
"step": 355
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 26.38,
|
| 653 |
+
"learning_rate": 3.8853744581304376e-06,
|
| 654 |
+
"loss": 1.1228,
|
| 655 |
+
"step": 360
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 26.55,
|
| 659 |
+
"eval_loss": 1.1160305738449097,
|
| 660 |
+
"eval_runtime": 3.9869,
|
| 661 |
+
"eval_samples_per_second": 20.818,
|
| 662 |
+
"eval_steps_per_second": 1.505,
|
| 663 |
+
"step": 364
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 27.02,
|
| 667 |
+
"learning_rate": 3.856820945115655e-06,
|
| 668 |
+
"loss": 1.1261,
|
| 669 |
+
"step": 365
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 27.23,
|
| 673 |
+
"learning_rate": 3.828014292634508e-06,
|
| 674 |
+
"loss": 1.1307,
|
| 675 |
+
"step": 370
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 27.45,
|
| 679 |
+
"learning_rate": 3.798959875088584e-06,
|
| 680 |
+
"loss": 1.1266,
|
| 681 |
+
"step": 375
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 27.57,
|
| 685 |
+
"eval_loss": 1.1105799674987793,
|
| 686 |
+
"eval_runtime": 3.9806,
|
| 687 |
+
"eval_samples_per_second": 20.851,
|
| 688 |
+
"eval_steps_per_second": 1.507,
|
| 689 |
+
"step": 378
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 28.09,
|
| 693 |
+
"learning_rate": 3.769663113104516e-06,
|
| 694 |
+
"loss": 1.1051,
|
| 695 |
+
"step": 380
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 28.3,
|
| 699 |
+
"learning_rate": 3.7401294725226707e-06,
|
| 700 |
+
"loss": 1.1152,
|
| 701 |
+
"step": 385
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 28.51,
|
| 705 |
+
"learning_rate": 3.7103644633774015e-06,
|
| 706 |
+
"loss": 1.1159,
|
| 707 |
+
"step": 390
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 28.55,
|
| 711 |
+
"eval_loss": 1.1047321557998657,
|
| 712 |
+
"eval_runtime": 3.9941,
|
| 713 |
+
"eval_samples_per_second": 20.781,
|
| 714 |
+
"eval_steps_per_second": 1.502,
|
| 715 |
+
"step": 391
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 29.15,
|
| 719 |
+
"learning_rate": 3.680373638869047e-06,
|
| 720 |
+
"loss": 1.1149,
|
| 721 |
+
"step": 395
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 29.36,
|
| 725 |
+
"learning_rate": 3.650162594327881e-06,
|
| 726 |
+
"loss": 1.0942,
|
| 727 |
+
"step": 400
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 29.57,
|
| 731 |
+
"learning_rate": 3.6197369661702052e-06,
|
| 732 |
+
"loss": 1.125,
|
| 733 |
+
"step": 405
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 29.57,
|
| 737 |
+
"eval_loss": 1.098873496055603,
|
| 738 |
+
"eval_runtime": 3.9772,
|
| 739 |
+
"eval_samples_per_second": 20.869,
|
| 740 |
+
"eval_steps_per_second": 1.509,
|
| 741 |
+
"step": 405
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 30.21,
|
| 745 |
+
"learning_rate": 3.589102430846773e-06,
|
| 746 |
+
"loss": 1.1067,
|
| 747 |
+
"step": 410
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 30.43,
|
| 751 |
+
"learning_rate": 3.5582647037837446e-06,
|
| 752 |
+
"loss": 1.094,
|
| 753 |
+
"step": 415
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 30.55,
|
| 757 |
+
"eval_loss": 1.0941215753555298,
|
| 758 |
+
"eval_runtime": 3.9808,
|
| 759 |
+
"eval_samples_per_second": 20.85,
|
| 760 |
+
"eval_steps_per_second": 1.507,
|
| 761 |
+
"step": 418
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 31.06,
|
| 765 |
+
"learning_rate": 3.527229538316371e-06,
|
| 766 |
+
"loss": 1.1033,
|
| 767 |
+
"step": 420
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 31.28,
|
| 771 |
+
"learning_rate": 3.4960027246156043e-06,
|
| 772 |
+
"loss": 1.0886,
|
| 773 |
+
"step": 425
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 31.49,
|
| 777 |
+
"learning_rate": 3.4645900886078388e-06,
|
| 778 |
+
"loss": 1.1077,
|
| 779 |
+
"step": 430
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 31.57,
|
| 783 |
+
"eval_loss": 1.0902585983276367,
|
| 784 |
+
"eval_runtime": 3.9794,
|
| 785 |
+
"eval_samples_per_second": 20.857,
|
| 786 |
+
"eval_steps_per_second": 1.508,
|
| 787 |
+
"step": 432
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 32.13,
|
| 791 |
+
"learning_rate": 3.432997490887979e-06,
|
| 792 |
+
"loss": 1.1054,
|
| 793 |
+
"step": 435
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 32.34,
|
| 797 |
+
"learning_rate": 3.4012308256260366e-06,
|
| 798 |
+
"loss": 1.0936,
|
| 799 |
+
"step": 440
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 32.55,
|
| 803 |
+
"learning_rate": 3.369296019467473e-06,
|
| 804 |
+
"loss": 1.0874,
|
| 805 |
+
"step": 445
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 32.55,
|
| 809 |
+
"eval_loss": 1.0833797454833984,
|
| 810 |
+
"eval_runtime": 3.9868,
|
| 811 |
+
"eval_samples_per_second": 20.819,
|
| 812 |
+
"eval_steps_per_second": 1.505,
|
| 813 |
+
"step": 445
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 33.19,
|
| 817 |
+
"learning_rate": 3.3371990304274654e-06,
|
| 818 |
+
"loss": 1.0687,
|
| 819 |
+
"step": 450
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 33.4,
|
| 823 |
+
"learning_rate": 3.304945846779346e-06,
|
| 824 |
+
"loss": 1.0957,
|
| 825 |
+
"step": 455
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 33.57,
|
| 829 |
+
"eval_loss": 1.0769224166870117,
|
| 830 |
+
"eval_runtime": 3.9835,
|
| 831 |
+
"eval_samples_per_second": 20.836,
|
| 832 |
+
"eval_steps_per_second": 1.506,
|
| 833 |
+
"step": 459
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 34.04,
|
| 837 |
+
"learning_rate": 3.272542485937369e-06,
|
| 838 |
+
"loss": 1.0894,
|
| 839 |
+
"step": 460
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 34.26,
|
| 843 |
+
"learning_rate": 3.239994993334059e-06,
|
| 844 |
+
"loss": 1.0906,
|
| 845 |
+
"step": 465
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 34.47,
|
| 849 |
+
"learning_rate": 3.207309441292325e-06,
|
| 850 |
+
"loss": 1.0755,
|
| 851 |
+
"step": 470
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 34.55,
|
| 855 |
+
"eval_loss": 1.0749725103378296,
|
| 856 |
+
"eval_runtime": 3.9797,
|
| 857 |
+
"eval_samples_per_second": 20.856,
|
| 858 |
+
"eval_steps_per_second": 1.508,
|
| 859 |
+
"step": 472
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 35.11,
|
| 863 |
+
"learning_rate": 3.174491927892561e-06,
|
| 864 |
+
"loss": 1.0862,
|
| 865 |
+
"step": 475
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 35.32,
|
| 869 |
+
"learning_rate": 3.1415485758349344e-06,
|
| 870 |
+
"loss": 1.0767,
|
| 871 |
+
"step": 480
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 35.53,
|
| 875 |
+
"learning_rate": 3.1084855312970897e-06,
|
| 876 |
+
"loss": 1.0705,
|
| 877 |
+
"step": 485
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 35.57,
|
| 881 |
+
"eval_loss": 1.0719436407089233,
|
| 882 |
+
"eval_runtime": 3.9776,
|
| 883 |
+
"eval_samples_per_second": 20.867,
|
| 884 |
+
"eval_steps_per_second": 1.508,
|
| 885 |
+
"step": 486
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 36.17,
|
| 889 |
+
"learning_rate": 3.0753089627874668e-06,
|
| 890 |
+
"loss": 1.0786,
|
| 891 |
+
"step": 490
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 36.38,
|
| 895 |
+
"learning_rate": 3.0420250599944525e-06,
|
| 896 |
+
"loss": 1.0749,
|
| 897 |
+
"step": 495
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 36.55,
|
| 901 |
+
"eval_loss": 1.0687665939331055,
|
| 902 |
+
"eval_runtime": 3.9811,
|
| 903 |
+
"eval_samples_per_second": 20.848,
|
| 904 |
+
"eval_steps_per_second": 1.507,
|
| 905 |
+
"step": 499
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 37.02,
|
| 909 |
+
"learning_rate": 3.0086400326315853e-06,
|
| 910 |
+
"loss": 1.0646,
|
| 911 |
+
"step": 500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 37.23,
|
| 915 |
+
"learning_rate": 2.9751601092790185e-06,
|
| 916 |
+
"loss": 1.0734,
|
| 917 |
+
"step": 505
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 37.45,
|
| 921 |
+
"learning_rate": 2.941591536221469e-06,
|
| 922 |
+
"loss": 1.0742,
|
| 923 |
+
"step": 510
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 37.57,
|
| 927 |
+
"eval_loss": 1.064079761505127,
|
| 928 |
+
"eval_runtime": 3.9781,
|
| 929 |
+
"eval_samples_per_second": 20.864,
|
| 930 |
+
"eval_steps_per_second": 1.508,
|
| 931 |
+
"step": 513
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 38.09,
|
| 935 |
+
"learning_rate": 2.907940576282856e-06,
|
| 936 |
+
"loss": 1.0547,
|
| 937 |
+
"step": 515
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 38.3,
|
| 941 |
+
"learning_rate": 2.8742135076578608e-06,
|
| 942 |
+
"loss": 1.0686,
|
| 943 |
+
"step": 520
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 38.51,
|
| 947 |
+
"learning_rate": 2.840416622740617e-06,
|
| 948 |
+
"loss": 1.064,
|
| 949 |
+
"step": 525
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 38.55,
|
| 953 |
+
"eval_loss": 1.0626107454299927,
|
| 954 |
+
"eval_runtime": 3.9847,
|
| 955 |
+
"eval_samples_per_second": 20.829,
|
| 956 |
+
"eval_steps_per_second": 1.506,
|
| 957 |
+
"step": 526
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 39.15,
|
| 961 |
+
"learning_rate": 2.8065562269507464e-06,
|
| 962 |
+
"loss": 1.0739,
|
| 963 |
+
"step": 530
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 39.36,
|
| 967 |
+
"learning_rate": 2.7726386375569748e-06,
|
| 968 |
+
"loss": 1.0569,
|
| 969 |
+
"step": 535
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 39.57,
|
| 973 |
+
"learning_rate": 2.7386701824985257e-06,
|
| 974 |
+
"loss": 1.0569,
|
| 975 |
+
"step": 540
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 39.57,
|
| 979 |
+
"eval_loss": 1.0592881441116333,
|
| 980 |
+
"eval_runtime": 3.9656,
|
| 981 |
+
"eval_samples_per_second": 20.93,
|
| 982 |
+
"eval_steps_per_second": 1.513,
|
| 983 |
+
"step": 540
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 40.21,
|
| 987 |
+
"learning_rate": 2.7046571992045334e-06,
|
| 988 |
+
"loss": 1.0466,
|
| 989 |
+
"step": 545
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 40.43,
|
| 993 |
+
"learning_rate": 2.670606033411678e-06,
|
| 994 |
+
"loss": 1.0686,
|
| 995 |
+
"step": 550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 40.55,
|
| 999 |
+
"eval_loss": 1.0553538799285889,
|
| 1000 |
+
"eval_runtime": 3.9786,
|
| 1001 |
+
"eval_samples_per_second": 20.862,
|
| 1002 |
+
"eval_steps_per_second": 1.508,
|
| 1003 |
+
"step": 553
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 41.06,
|
| 1007 |
+
"learning_rate": 2.636523037980275e-06,
|
| 1008 |
+
"loss": 1.0564,
|
| 1009 |
+
"step": 555
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 41.28,
|
| 1013 |
+
"learning_rate": 2.602414571709036e-06,
|
| 1014 |
+
"loss": 1.0523,
|
| 1015 |
+
"step": 560
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 41.49,
|
| 1019 |
+
"learning_rate": 2.5682869981487154e-06,
|
| 1020 |
+
"loss": 1.059,
|
| 1021 |
+
"step": 565
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 41.57,
|
| 1025 |
+
"eval_loss": 1.0516701936721802,
|
| 1026 |
+
"eval_runtime": 3.9778,
|
| 1027 |
+
"eval_samples_per_second": 20.866,
|
| 1028 |
+
"eval_steps_per_second": 1.508,
|
| 1029 |
+
"step": 567
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 42.13,
|
| 1033 |
+
"learning_rate": 2.5341466844148775e-06,
|
| 1034 |
+
"loss": 1.0414,
|
| 1035 |
+
"step": 570
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 42.34,
|
| 1039 |
+
"learning_rate": 2.5e-06,
|
| 1040 |
+
"loss": 1.0394,
|
| 1041 |
+
"step": 575
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 42.55,
|
| 1045 |
+
"learning_rate": 2.465853315585123e-06,
|
| 1046 |
+
"loss": 1.0588,
|
| 1047 |
+
"step": 580
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 42.55,
|
| 1051 |
+
"eval_loss": 1.0469306707382202,
|
| 1052 |
+
"eval_runtime": 4.0006,
|
| 1053 |
+
"eval_samples_per_second": 20.747,
|
| 1054 |
+
"eval_steps_per_second": 1.5,
|
| 1055 |
+
"step": 580
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 43.19,
|
| 1059 |
+
"learning_rate": 2.431713001851286e-06,
|
| 1060 |
+
"loss": 1.0442,
|
| 1061 |
+
"step": 585
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 43.4,
|
| 1065 |
+
"learning_rate": 2.3975854282909645e-06,
|
| 1066 |
+
"loss": 1.0447,
|
| 1067 |
+
"step": 590
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 43.57,
|
| 1071 |
+
"eval_loss": 1.0471419095993042,
|
| 1072 |
+
"eval_runtime": 3.9796,
|
| 1073 |
+
"eval_samples_per_second": 20.856,
|
| 1074 |
+
"eval_steps_per_second": 1.508,
|
| 1075 |
+
"step": 594
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 44.04,
|
| 1079 |
+
"learning_rate": 2.3634769620197253e-06,
|
| 1080 |
+
"loss": 1.0573,
|
| 1081 |
+
"step": 595
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 44.26,
|
| 1085 |
+
"learning_rate": 2.3293939665883233e-06,
|
| 1086 |
+
"loss": 1.0478,
|
| 1087 |
+
"step": 600
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 44.47,
|
| 1091 |
+
"learning_rate": 2.2953428007954682e-06,
|
| 1092 |
+
"loss": 1.0356,
|
| 1093 |
+
"step": 605
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 44.55,
|
| 1097 |
+
"eval_loss": 1.0420819520950317,
|
| 1098 |
+
"eval_runtime": 3.9978,
|
| 1099 |
+
"eval_samples_per_second": 20.762,
|
| 1100 |
+
"eval_steps_per_second": 1.501,
|
| 1101 |
+
"step": 607
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 45.11,
|
| 1105 |
+
"learning_rate": 2.261329817501475e-06,
|
| 1106 |
+
"loss": 1.0465,
|
| 1107 |
+
"step": 610
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 45.32,
|
| 1111 |
+
"learning_rate": 2.2273613624430256e-06,
|
| 1112 |
+
"loss": 1.0389,
|
| 1113 |
+
"step": 615
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 45.53,
|
| 1117 |
+
"learning_rate": 2.1934437730492544e-06,
|
| 1118 |
+
"loss": 1.0431,
|
| 1119 |
+
"step": 620
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 45.57,
|
| 1123 |
+
"eval_loss": 1.0415891408920288,
|
| 1124 |
+
"eval_runtime": 3.9789,
|
| 1125 |
+
"eval_samples_per_second": 20.86,
|
| 1126 |
+
"eval_steps_per_second": 1.508,
|
| 1127 |
+
"step": 621
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 46.17,
|
| 1131 |
+
"learning_rate": 2.159583377259384e-06,
|
| 1132 |
+
"loss": 1.045,
|
| 1133 |
+
"step": 625
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 46.38,
|
| 1137 |
+
"learning_rate": 2.1257864923421405e-06,
|
| 1138 |
+
"loss": 1.0195,
|
| 1139 |
+
"step": 630
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 46.55,
|
| 1143 |
+
"eval_loss": 1.038739562034607,
|
| 1144 |
+
"eval_runtime": 3.9849,
|
| 1145 |
+
"eval_samples_per_second": 20.829,
|
| 1146 |
+
"eval_steps_per_second": 1.506,
|
| 1147 |
+
"step": 634
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 47.02,
|
| 1151 |
+
"learning_rate": 2.092059423717145e-06,
|
| 1152 |
+
"loss": 1.0458,
|
| 1153 |
+
"step": 635
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 47.23,
|
| 1157 |
+
"learning_rate": 2.0584084637785316e-06,
|
| 1158 |
+
"loss": 1.0347,
|
| 1159 |
+
"step": 640
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 47.45,
|
| 1163 |
+
"learning_rate": 2.0248398907209827e-06,
|
| 1164 |
+
"loss": 1.0326,
|
| 1165 |
+
"step": 645
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 47.57,
|
| 1169 |
+
"eval_loss": 1.0356136560440063,
|
| 1170 |
+
"eval_runtime": 3.9756,
|
| 1171 |
+
"eval_samples_per_second": 20.877,
|
| 1172 |
+
"eval_steps_per_second": 1.509,
|
| 1173 |
+
"step": 648
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 48.09,
|
| 1177 |
+
"learning_rate": 1.991359967368416e-06,
|
| 1178 |
+
"loss": 1.0351,
|
| 1179 |
+
"step": 650
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 48.3,
|
| 1183 |
+
"learning_rate": 1.957974940005548e-06,
|
| 1184 |
+
"loss": 1.0422,
|
| 1185 |
+
"step": 655
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 48.51,
|
| 1189 |
+
"learning_rate": 1.9246910372125345e-06,
|
| 1190 |
+
"loss": 1.0227,
|
| 1191 |
+
"step": 660
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 48.55,
|
| 1195 |
+
"eval_loss": 1.0340739488601685,
|
| 1196 |
+
"eval_runtime": 3.9883,
|
| 1197 |
+
"eval_samples_per_second": 20.811,
|
| 1198 |
+
"eval_steps_per_second": 1.504,
|
| 1199 |
+
"step": 661
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 49.15,
|
| 1203 |
+
"learning_rate": 1.8915144687029107e-06,
|
| 1204 |
+
"loss": 1.0192,
|
| 1205 |
+
"step": 665
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 49.36,
|
| 1209 |
+
"learning_rate": 1.8584514241650667e-06,
|
| 1210 |
+
"loss": 1.0328,
|
| 1211 |
+
"step": 670
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 49.57,
|
| 1215 |
+
"learning_rate": 1.8255080721074391e-06,
|
| 1216 |
+
"loss": 1.0403,
|
| 1217 |
+
"step": 675
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 49.57,
|
| 1221 |
+
"eval_loss": 1.0316752195358276,
|
| 1222 |
+
"eval_runtime": 3.9751,
|
| 1223 |
+
"eval_samples_per_second": 20.88,
|
| 1224 |
+
"eval_steps_per_second": 1.509,
|
| 1225 |
+
"step": 675
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 49.57,
|
| 1229 |
+
"step": 675,
|
| 1230 |
+
"total_flos": 6306831714484224.0,
|
| 1231 |
+
"train_loss": 1.2869272242652046,
|
| 1232 |
+
"train_runtime": 6519.8949,
|
| 1233 |
+
"train_samples_per_second": 5.721,
|
| 1234 |
+
"train_steps_per_second": 0.176
|
| 1235 |
+
}
|
| 1236 |
+
],
|
| 1237 |
+
"logging_steps": 5,
|
| 1238 |
+
"max_steps": 1150,
|
| 1239 |
+
"num_train_epochs": 50,
|
| 1240 |
+
"save_steps": 500,
|
| 1241 |
+
"total_flos": 6306831714484224.0,
|
| 1242 |
+
"trial_name": null,
|
| 1243 |
+
"trial_params": null
|
| 1244 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:417bd8fb89805fdaa6b6528c335f8fcba489aae9aa8aa260c9f0d955e96b4332
|
| 3 |
+
size 5688
|