End of training
Browse files- README.md +120 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- all_results.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +50 -0
- train_results.json +7 -0
- trainer_state.json +2286 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Mistral-7B-v0.1_district-court-db
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Mistral-7B-v0.1_district-court-db
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0353
|
| 22 |
+
- Precision Micro: 0.8057
|
| 23 |
+
- Precision Macro: 0.7027
|
| 24 |
+
- Recall Micro: 0.8057
|
| 25 |
+
- Recall Macro: 0.6940
|
| 26 |
+
- F1 Micro: 0.8057
|
| 27 |
+
- F1 Macro: 0.6867
|
| 28 |
+
- Accuracy: 0.8057
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 3e-05
|
| 48 |
+
- train_batch_size: 4
|
| 49 |
+
- eval_batch_size: 4
|
| 50 |
+
- seed: 42
|
| 51 |
+
- gradient_accumulation_steps: 4
|
| 52 |
+
- total_train_batch_size: 16
|
| 53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
+
- lr_scheduler_type: constant
|
| 55 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 56 |
+
- num_epochs: 2.0
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision Micro | Precision Macro | Recall Micro | Recall Macro | F1 Micro | F1 Macro | Accuracy |
|
| 61 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:---------------:|:------------:|:------------:|:--------:|:--------:|:--------:|
|
| 62 |
+
| 0.1114 | 0.04 | 50 | 0.2315 | 0.3613 | 0.1236 | 0.3613 | 0.1194 | 0.3613 | 0.0986 | 0.3613 |
|
| 63 |
+
| 0.1009 | 0.08 | 100 | 0.1300 | 0.4868 | 0.2602 | 0.4868 | 0.2927 | 0.4868 | 0.2574 | 0.4868 |
|
| 64 |
+
| 0.0655 | 0.12 | 150 | 0.1111 | 0.5821 | 0.4592 | 0.5821 | 0.3260 | 0.5821 | 0.3407 | 0.5821 |
|
| 65 |
+
| 0.0675 | 0.16 | 200 | 0.0980 | 0.6104 | 0.4309 | 0.6104 | 0.4116 | 0.6104 | 0.3994 | 0.6104 |
|
| 66 |
+
| 0.0613 | 0.2 | 250 | 0.0868 | 0.6349 | 0.5027 | 0.6349 | 0.4238 | 0.6349 | 0.4328 | 0.6349 |
|
| 67 |
+
| 0.0423 | 0.24 | 300 | 0.0829 | 0.6406 | 0.4971 | 0.6406 | 0.5150 | 0.6406 | 0.4838 | 0.6406 |
|
| 68 |
+
| 0.0495 | 0.28 | 350 | 0.0647 | 0.6840 | 0.5621 | 0.6840 | 0.5110 | 0.6840 | 0.5118 | 0.6840 |
|
| 69 |
+
| 0.0696 | 0.32 | 400 | 0.0583 | 0.7236 | 0.5854 | 0.7236 | 0.5476 | 0.7236 | 0.5523 | 0.7236 |
|
| 70 |
+
| 0.0551 | 0.36 | 450 | 0.0470 | 0.7538 | 0.6037 | 0.7538 | 0.5804 | 0.7538 | 0.5801 | 0.7538 |
|
| 71 |
+
| 0.0485 | 0.4 | 500 | 0.0467 | 0.7632 | 0.6244 | 0.7632 | 0.6093 | 0.7632 | 0.5976 | 0.7632 |
|
| 72 |
+
| 0.0514 | 0.44 | 550 | 0.0491 | 0.7453 | 0.6624 | 0.7453 | 0.6055 | 0.7453 | 0.6149 | 0.7453 |
|
| 73 |
+
| 0.0537 | 0.48 | 600 | 0.0469 | 0.7547 | 0.6565 | 0.7547 | 0.6140 | 0.7547 | 0.5956 | 0.7547 |
|
| 74 |
+
| 0.0503 | 0.52 | 650 | 0.0473 | 0.7434 | 0.6365 | 0.7434 | 0.5711 | 0.7434 | 0.5711 | 0.7434 |
|
| 75 |
+
| 0.0502 | 0.56 | 700 | 0.0429 | 0.7991 | 0.6675 | 0.7991 | 0.6430 | 0.7991 | 0.6487 | 0.7991 |
|
| 76 |
+
| 0.0568 | 0.6 | 750 | 0.0421 | 0.7830 | 0.6400 | 0.7830 | 0.6197 | 0.7830 | 0.6035 | 0.7830 |
|
| 77 |
+
| 0.0456 | 0.64 | 800 | 0.0385 | 0.8038 | 0.6660 | 0.8038 | 0.7100 | 0.8038 | 0.6795 | 0.8038 |
|
| 78 |
+
| 0.0465 | 0.68 | 850 | 0.0423 | 0.7868 | 0.7080 | 0.7868 | 0.6536 | 0.7868 | 0.6638 | 0.7868 |
|
| 79 |
+
| 0.0517 | 0.72 | 900 | 0.0405 | 0.7830 | 0.6482 | 0.7830 | 0.5953 | 0.7830 | 0.6044 | 0.7830 |
|
| 80 |
+
| 0.0449 | 0.76 | 950 | 0.0395 | 0.7962 | 0.6783 | 0.7962 | 0.6782 | 0.7962 | 0.6595 | 0.7962 |
|
| 81 |
+
| 0.0438 | 0.79 | 1000 | 0.0415 | 0.7651 | 0.6310 | 0.7651 | 0.6519 | 0.7651 | 0.6270 | 0.7651 |
|
| 82 |
+
| 0.0368 | 0.83 | 1050 | 0.0367 | 0.8142 | 0.7077 | 0.8142 | 0.6998 | 0.8142 | 0.6885 | 0.8142 |
|
| 83 |
+
| 0.0351 | 0.87 | 1100 | 0.0350 | 0.8151 | 0.6864 | 0.8151 | 0.6838 | 0.8151 | 0.6796 | 0.8151 |
|
| 84 |
+
| 0.042 | 0.91 | 1150 | 0.0362 | 0.8066 | 0.6895 | 0.8066 | 0.6593 | 0.8066 | 0.6627 | 0.8066 |
|
| 85 |
+
| 0.0449 | 0.95 | 1200 | 0.0367 | 0.7925 | 0.6685 | 0.7925 | 0.6671 | 0.7925 | 0.6583 | 0.7925 |
|
| 86 |
+
| 0.0331 | 0.99 | 1250 | 0.0382 | 0.8019 | 0.6760 | 0.8019 | 0.6848 | 0.8019 | 0.6661 | 0.8019 |
|
| 87 |
+
| 0.0367 | 1.03 | 1300 | 0.0372 | 0.8038 | 0.7119 | 0.8038 | 0.6501 | 0.8038 | 0.6590 | 0.8038 |
|
| 88 |
+
| 0.0357 | 1.07 | 1350 | 0.0375 | 0.7991 | 0.6822 | 0.7991 | 0.6657 | 0.7991 | 0.6639 | 0.7991 |
|
| 89 |
+
| 0.0405 | 1.11 | 1400 | 0.0354 | 0.8104 | 0.6735 | 0.8104 | 0.7011 | 0.8104 | 0.6823 | 0.8104 |
|
| 90 |
+
| 0.0281 | 1.15 | 1450 | 0.0338 | 0.8302 | 0.6881 | 0.8302 | 0.7082 | 0.8302 | 0.6937 | 0.8302 |
|
| 91 |
+
| 0.0362 | 1.19 | 1500 | 0.0351 | 0.8123 | 0.7044 | 0.8123 | 0.6559 | 0.8123 | 0.6607 | 0.8123 |
|
| 92 |
+
| 0.0214 | 1.23 | 1550 | 0.0350 | 0.8104 | 0.7081 | 0.8104 | 0.6749 | 0.8104 | 0.6779 | 0.8104 |
|
| 93 |
+
| 0.0321 | 1.27 | 1600 | 0.0368 | 0.8094 | 0.7541 | 0.8094 | 0.7254 | 0.8094 | 0.7278 | 0.8094 |
|
| 94 |
+
| 0.0332 | 1.31 | 1650 | 0.0339 | 0.8255 | 0.7291 | 0.8255 | 0.7104 | 0.8255 | 0.7081 | 0.8255 |
|
| 95 |
+
| 0.0306 | 1.35 | 1700 | 0.0339 | 0.8179 | 0.6816 | 0.8179 | 0.6804 | 0.8179 | 0.6770 | 0.8179 |
|
| 96 |
+
| 0.0231 | 1.39 | 1750 | 0.0373 | 0.8179 | 0.6983 | 0.8179 | 0.6881 | 0.8179 | 0.6890 | 0.8179 |
|
| 97 |
+
| 0.0351 | 1.43 | 1800 | 0.0356 | 0.8217 | 0.6989 | 0.8217 | 0.6917 | 0.8217 | 0.6893 | 0.8217 |
|
| 98 |
+
| 0.0259 | 1.47 | 1850 | 0.0335 | 0.8208 | 0.6999 | 0.8208 | 0.6823 | 0.8208 | 0.6885 | 0.8208 |
|
| 99 |
+
| 0.0371 | 1.51 | 1900 | 0.0367 | 0.8123 | 0.7412 | 0.8123 | 0.6617 | 0.8123 | 0.6817 | 0.8123 |
|
| 100 |
+
| 0.0288 | 1.55 | 1950 | 0.0347 | 0.8179 | 0.6758 | 0.8179 | 0.6916 | 0.8179 | 0.6808 | 0.8179 |
|
| 101 |
+
| 0.0252 | 1.59 | 2000 | 0.0357 | 0.8113 | 0.7003 | 0.8113 | 0.6714 | 0.8113 | 0.6787 | 0.8113 |
|
| 102 |
+
| 0.0374 | 1.63 | 2050 | 0.0332 | 0.8208 | 0.7747 | 0.8208 | 0.7233 | 0.8208 | 0.7379 | 0.8208 |
|
| 103 |
+
| 0.0356 | 1.67 | 2100 | 0.0323 | 0.8283 | 0.7425 | 0.8283 | 0.7046 | 0.8283 | 0.7162 | 0.8283 |
|
| 104 |
+
| 0.0294 | 1.71 | 2150 | 0.0346 | 0.8113 | 0.7173 | 0.8113 | 0.7227 | 0.8113 | 0.7101 | 0.8113 |
|
| 105 |
+
| 0.035 | 1.75 | 2200 | 0.0338 | 0.8236 | 0.7591 | 0.8236 | 0.7307 | 0.8236 | 0.7390 | 0.8236 |
|
| 106 |
+
| 0.0432 | 1.79 | 2250 | 0.0348 | 0.8217 | 0.7694 | 0.8217 | 0.7204 | 0.8217 | 0.7295 | 0.8217 |
|
| 107 |
+
| 0.0325 | 1.83 | 2300 | 0.0324 | 0.8330 | 0.7441 | 0.8330 | 0.7231 | 0.8330 | 0.7261 | 0.8330 |
|
| 108 |
+
| 0.0318 | 1.87 | 2350 | 0.0321 | 0.8311 | 0.7397 | 0.8311 | 0.7241 | 0.8311 | 0.7248 | 0.8311 |
|
| 109 |
+
| 0.0315 | 1.91 | 2400 | 0.0335 | 0.8179 | 0.6793 | 0.8179 | 0.7035 | 0.8179 | 0.6858 | 0.8179 |
|
| 110 |
+
| 0.0331 | 1.95 | 2450 | 0.0335 | 0.8179 | 0.7295 | 0.8179 | 0.6879 | 0.8179 | 0.6956 | 0.8179 |
|
| 111 |
+
| 0.0293 | 1.99 | 2500 | 0.0353 | 0.8057 | 0.7027 | 0.8057 | 0.6940 | 0.8057 | 0.6867 | 0.8057 |
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
### Framework versions
|
| 115 |
+
|
| 116 |
+
- PEFT 0.7.1
|
| 117 |
+
- Transformers 4.37.2
|
| 118 |
+
- Pytorch 2.1.2+cu121
|
| 119 |
+
- Datasets 2.17.1
|
| 120 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"score",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "SEQ_CLS"
|
| 32 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a422c5174be4eb7630594a16f33d5bc3e20cdf0c0d2abdbf1a70dd0cd05a2b8
|
| 3 |
+
size 337444704
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.05790289470982191,
|
| 4 |
+
"train_runtime": 10296.0519,
|
| 5 |
+
"train_samples_per_second": 3.91,
|
| 6 |
+
"train_steps_per_second": 0.244
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"clean_up_tokenization_spaces": false,
|
| 41 |
+
"eos_token": "</s>",
|
| 42 |
+
"legacy": true,
|
| 43 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
+
"pad_token": "[PAD]",
|
| 45 |
+
"sp_model_kwargs": {},
|
| 46 |
+
"spaces_between_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": false
|
| 50 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.05790289470982191,
|
| 4 |
+
"train_runtime": 10296.0519,
|
| 5 |
+
"train_samples_per_second": 3.91,
|
| 6 |
+
"train_steps_per_second": 0.244
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9996026226902444,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2516,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 3e-05,
|
| 14 |
+
"loss": 2.1025,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 3e-05,
|
| 20 |
+
"loss": 0.2678,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 3e-05,
|
| 26 |
+
"loss": 0.1686,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 3e-05,
|
| 32 |
+
"loss": 0.1283,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 3e-05,
|
| 38 |
+
"loss": 0.1114,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"eval_accuracy": 0.3613207547169811,
|
| 44 |
+
"eval_f1_macro": 0.09860460155366327,
|
| 45 |
+
"eval_f1_micro": 0.3613207547169811,
|
| 46 |
+
"eval_loss": 0.2315492480993271,
|
| 47 |
+
"eval_precision_macro": 0.12357052455449527,
|
| 48 |
+
"eval_precision_micro": 0.3613207547169811,
|
| 49 |
+
"eval_recall_macro": 0.11941290624193263,
|
| 50 |
+
"eval_recall_micro": 0.3613207547169811,
|
| 51 |
+
"eval_runtime": 66.9606,
|
| 52 |
+
"eval_samples_per_second": 15.83,
|
| 53 |
+
"eval_steps_per_second": 3.958,
|
| 54 |
+
"step": 50
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.05,
|
| 58 |
+
"learning_rate": 3e-05,
|
| 59 |
+
"loss": 0.6159,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.06,
|
| 64 |
+
"learning_rate": 3e-05,
|
| 65 |
+
"loss": 0.1207,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06,
|
| 70 |
+
"learning_rate": 3e-05,
|
| 71 |
+
"loss": 0.0914,
|
| 72 |
+
"step": 80
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07,
|
| 76 |
+
"learning_rate": 3e-05,
|
| 77 |
+
"loss": 0.0971,
|
| 78 |
+
"step": 90
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.08,
|
| 82 |
+
"learning_rate": 3e-05,
|
| 83 |
+
"loss": 0.1009,
|
| 84 |
+
"step": 100
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.08,
|
| 88 |
+
"eval_accuracy": 0.4867924528301887,
|
| 89 |
+
"eval_f1_macro": 0.2574441564495774,
|
| 90 |
+
"eval_f1_micro": 0.4867924528301887,
|
| 91 |
+
"eval_loss": 0.1300116926431656,
|
| 92 |
+
"eval_precision_macro": 0.26018914773023644,
|
| 93 |
+
"eval_precision_micro": 0.4867924528301887,
|
| 94 |
+
"eval_recall_macro": 0.2927378841554505,
|
| 95 |
+
"eval_recall_micro": 0.4867924528301887,
|
| 96 |
+
"eval_runtime": 66.8969,
|
| 97 |
+
"eval_samples_per_second": 15.845,
|
| 98 |
+
"eval_steps_per_second": 3.961,
|
| 99 |
+
"step": 100
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"learning_rate": 3e-05,
|
| 104 |
+
"loss": 0.2813,
|
| 105 |
+
"step": 110
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.1,
|
| 109 |
+
"learning_rate": 3e-05,
|
| 110 |
+
"loss": 0.0721,
|
| 111 |
+
"step": 120
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.1,
|
| 115 |
+
"learning_rate": 3e-05,
|
| 116 |
+
"loss": 0.0789,
|
| 117 |
+
"step": 130
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"learning_rate": 3e-05,
|
| 122 |
+
"loss": 0.0559,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 3e-05,
|
| 128 |
+
"loss": 0.0655,
|
| 129 |
+
"step": 150
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.12,
|
| 133 |
+
"eval_accuracy": 0.5820754716981132,
|
| 134 |
+
"eval_f1_macro": 0.3406909384301982,
|
| 135 |
+
"eval_f1_micro": 0.5820754716981132,
|
| 136 |
+
"eval_loss": 0.11111029237508774,
|
| 137 |
+
"eval_precision_macro": 0.4592469495612598,
|
| 138 |
+
"eval_precision_micro": 0.5820754716981132,
|
| 139 |
+
"eval_recall_macro": 0.32597718546465326,
|
| 140 |
+
"eval_recall_micro": 0.5820754716981132,
|
| 141 |
+
"eval_runtime": 67.3369,
|
| 142 |
+
"eval_samples_per_second": 15.742,
|
| 143 |
+
"eval_steps_per_second": 3.935,
|
| 144 |
+
"step": 150
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.13,
|
| 148 |
+
"learning_rate": 3e-05,
|
| 149 |
+
"loss": 0.2815,
|
| 150 |
+
"step": 160
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.14,
|
| 154 |
+
"learning_rate": 3e-05,
|
| 155 |
+
"loss": 0.0738,
|
| 156 |
+
"step": 170
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14,
|
| 160 |
+
"learning_rate": 3e-05,
|
| 161 |
+
"loss": 0.06,
|
| 162 |
+
"step": 180
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.15,
|
| 166 |
+
"learning_rate": 3e-05,
|
| 167 |
+
"loss": 0.064,
|
| 168 |
+
"step": 190
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.16,
|
| 172 |
+
"learning_rate": 3e-05,
|
| 173 |
+
"loss": 0.0675,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.16,
|
| 178 |
+
"eval_accuracy": 0.6103773584905661,
|
| 179 |
+
"eval_f1_macro": 0.39941812670769666,
|
| 180 |
+
"eval_f1_micro": 0.6103773584905661,
|
| 181 |
+
"eval_loss": 0.09801042824983597,
|
| 182 |
+
"eval_precision_macro": 0.4309243547594424,
|
| 183 |
+
"eval_precision_micro": 0.6103773584905661,
|
| 184 |
+
"eval_recall_macro": 0.4115863977855726,
|
| 185 |
+
"eval_recall_micro": 0.6103773584905661,
|
| 186 |
+
"eval_runtime": 66.8379,
|
| 187 |
+
"eval_samples_per_second": 15.859,
|
| 188 |
+
"eval_steps_per_second": 3.965,
|
| 189 |
+
"step": 200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.17,
|
| 193 |
+
"learning_rate": 3e-05,
|
| 194 |
+
"loss": 0.2238,
|
| 195 |
+
"step": 210
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 3e-05,
|
| 200 |
+
"loss": 0.0665,
|
| 201 |
+
"step": 220
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.18,
|
| 205 |
+
"learning_rate": 3e-05,
|
| 206 |
+
"loss": 0.0526,
|
| 207 |
+
"step": 230
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.19,
|
| 211 |
+
"learning_rate": 3e-05,
|
| 212 |
+
"loss": 0.0622,
|
| 213 |
+
"step": 240
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2,
|
| 217 |
+
"learning_rate": 3e-05,
|
| 218 |
+
"loss": 0.0613,
|
| 219 |
+
"step": 250
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2,
|
| 223 |
+
"eval_accuracy": 0.6349056603773585,
|
| 224 |
+
"eval_f1_macro": 0.43281084183779084,
|
| 225 |
+
"eval_f1_micro": 0.6349056603773585,
|
| 226 |
+
"eval_loss": 0.0867743045091629,
|
| 227 |
+
"eval_precision_macro": 0.5027159556787124,
|
| 228 |
+
"eval_precision_micro": 0.6349056603773585,
|
| 229 |
+
"eval_recall_macro": 0.42379042156244773,
|
| 230 |
+
"eval_recall_micro": 0.6349056603773585,
|
| 231 |
+
"eval_runtime": 66.7898,
|
| 232 |
+
"eval_samples_per_second": 15.871,
|
| 233 |
+
"eval_steps_per_second": 3.968,
|
| 234 |
+
"step": 250
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.21,
|
| 238 |
+
"learning_rate": 3e-05,
|
| 239 |
+
"loss": 0.211,
|
| 240 |
+
"step": 260
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.21,
|
| 244 |
+
"learning_rate": 3e-05,
|
| 245 |
+
"loss": 0.0642,
|
| 246 |
+
"step": 270
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.22,
|
| 250 |
+
"learning_rate": 3e-05,
|
| 251 |
+
"loss": 0.0571,
|
| 252 |
+
"step": 280
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.23,
|
| 256 |
+
"learning_rate": 3e-05,
|
| 257 |
+
"loss": 0.0595,
|
| 258 |
+
"step": 290
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.24,
|
| 262 |
+
"learning_rate": 3e-05,
|
| 263 |
+
"loss": 0.0423,
|
| 264 |
+
"step": 300
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.24,
|
| 268 |
+
"eval_accuracy": 0.6405660377358491,
|
| 269 |
+
"eval_f1_macro": 0.48377541137861874,
|
| 270 |
+
"eval_f1_micro": 0.6405660377358491,
|
| 271 |
+
"eval_loss": 0.08292412012815475,
|
| 272 |
+
"eval_precision_macro": 0.4971153033333408,
|
| 273 |
+
"eval_precision_micro": 0.6405660377358491,
|
| 274 |
+
"eval_recall_macro": 0.5150079548728711,
|
| 275 |
+
"eval_recall_micro": 0.6405660377358491,
|
| 276 |
+
"eval_runtime": 66.8647,
|
| 277 |
+
"eval_samples_per_second": 15.853,
|
| 278 |
+
"eval_steps_per_second": 3.963,
|
| 279 |
+
"step": 300
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.25,
|
| 283 |
+
"learning_rate": 3e-05,
|
| 284 |
+
"loss": 0.1501,
|
| 285 |
+
"step": 310
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 3e-05,
|
| 290 |
+
"loss": 0.0583,
|
| 291 |
+
"step": 320
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.26,
|
| 295 |
+
"learning_rate": 3e-05,
|
| 296 |
+
"loss": 0.0406,
|
| 297 |
+
"step": 330
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.27,
|
| 301 |
+
"learning_rate": 3e-05,
|
| 302 |
+
"loss": 0.0512,
|
| 303 |
+
"step": 340
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.28,
|
| 307 |
+
"learning_rate": 3e-05,
|
| 308 |
+
"loss": 0.0495,
|
| 309 |
+
"step": 350
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"eval_accuracy": 0.6839622641509434,
|
| 314 |
+
"eval_f1_macro": 0.5117892165590059,
|
| 315 |
+
"eval_f1_micro": 0.6839622641509434,
|
| 316 |
+
"eval_loss": 0.06472181528806686,
|
| 317 |
+
"eval_precision_macro": 0.5620645130448471,
|
| 318 |
+
"eval_precision_micro": 0.6839622641509434,
|
| 319 |
+
"eval_recall_macro": 0.5110243944495119,
|
| 320 |
+
"eval_recall_micro": 0.6839622641509434,
|
| 321 |
+
"eval_runtime": 66.951,
|
| 322 |
+
"eval_samples_per_second": 15.832,
|
| 323 |
+
"eval_steps_per_second": 3.958,
|
| 324 |
+
"step": 350
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.29,
|
| 328 |
+
"learning_rate": 3e-05,
|
| 329 |
+
"loss": 0.126,
|
| 330 |
+
"step": 360
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.29,
|
| 334 |
+
"learning_rate": 3e-05,
|
| 335 |
+
"loss": 0.0659,
|
| 336 |
+
"step": 370
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.3,
|
| 340 |
+
"learning_rate": 3e-05,
|
| 341 |
+
"loss": 0.0521,
|
| 342 |
+
"step": 380
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.31,
|
| 346 |
+
"learning_rate": 3e-05,
|
| 347 |
+
"loss": 0.0558,
|
| 348 |
+
"step": 390
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.32,
|
| 352 |
+
"learning_rate": 3e-05,
|
| 353 |
+
"loss": 0.0696,
|
| 354 |
+
"step": 400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.32,
|
| 358 |
+
"eval_accuracy": 0.7235849056603774,
|
| 359 |
+
"eval_f1_macro": 0.5523304099808589,
|
| 360 |
+
"eval_f1_micro": 0.7235849056603774,
|
| 361 |
+
"eval_loss": 0.05833260715007782,
|
| 362 |
+
"eval_precision_macro": 0.5853706474287289,
|
| 363 |
+
"eval_precision_micro": 0.7235849056603774,
|
| 364 |
+
"eval_recall_macro": 0.5476004753387752,
|
| 365 |
+
"eval_recall_micro": 0.7235849056603774,
|
| 366 |
+
"eval_runtime": 67.3456,
|
| 367 |
+
"eval_samples_per_second": 15.74,
|
| 368 |
+
"eval_steps_per_second": 3.935,
|
| 369 |
+
"step": 400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.33,
|
| 373 |
+
"learning_rate": 3e-05,
|
| 374 |
+
"loss": 0.0861,
|
| 375 |
+
"step": 410
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.33,
|
| 379 |
+
"learning_rate": 3e-05,
|
| 380 |
+
"loss": 0.0457,
|
| 381 |
+
"step": 420
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.34,
|
| 385 |
+
"learning_rate": 3e-05,
|
| 386 |
+
"loss": 0.0549,
|
| 387 |
+
"step": 430
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.35,
|
| 391 |
+
"learning_rate": 3e-05,
|
| 392 |
+
"loss": 0.0505,
|
| 393 |
+
"step": 440
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.36,
|
| 397 |
+
"learning_rate": 3e-05,
|
| 398 |
+
"loss": 0.0551,
|
| 399 |
+
"step": 450
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.36,
|
| 403 |
+
"eval_accuracy": 0.7537735849056604,
|
| 404 |
+
"eval_f1_macro": 0.580144082849279,
|
| 405 |
+
"eval_f1_micro": 0.7537735849056603,
|
| 406 |
+
"eval_loss": 0.04702736809849739,
|
| 407 |
+
"eval_precision_macro": 0.6037061602706483,
|
| 408 |
+
"eval_precision_micro": 0.7537735849056604,
|
| 409 |
+
"eval_recall_macro": 0.5804359588026832,
|
| 410 |
+
"eval_recall_micro": 0.7537735849056604,
|
| 411 |
+
"eval_runtime": 66.8194,
|
| 412 |
+
"eval_samples_per_second": 15.864,
|
| 413 |
+
"eval_steps_per_second": 3.966,
|
| 414 |
+
"step": 450
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.37,
|
| 418 |
+
"learning_rate": 3e-05,
|
| 419 |
+
"loss": 0.0701,
|
| 420 |
+
"step": 460
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.37,
|
| 424 |
+
"learning_rate": 3e-05,
|
| 425 |
+
"loss": 0.0483,
|
| 426 |
+
"step": 470
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.38,
|
| 430 |
+
"learning_rate": 3e-05,
|
| 431 |
+
"loss": 0.0427,
|
| 432 |
+
"step": 480
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.39,
|
| 436 |
+
"learning_rate": 3e-05,
|
| 437 |
+
"loss": 0.0437,
|
| 438 |
+
"step": 490
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.4,
|
| 442 |
+
"learning_rate": 3e-05,
|
| 443 |
+
"loss": 0.0485,
|
| 444 |
+
"step": 500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4,
|
| 448 |
+
"eval_accuracy": 0.7632075471698113,
|
| 449 |
+
"eval_f1_macro": 0.5976025328641371,
|
| 450 |
+
"eval_f1_micro": 0.7632075471698113,
|
| 451 |
+
"eval_loss": 0.046745266765356064,
|
| 452 |
+
"eval_precision_macro": 0.6244027962032025,
|
| 453 |
+
"eval_precision_micro": 0.7632075471698113,
|
| 454 |
+
"eval_recall_macro": 0.6092701629048938,
|
| 455 |
+
"eval_recall_micro": 0.7632075471698113,
|
| 456 |
+
"eval_runtime": 66.8345,
|
| 457 |
+
"eval_samples_per_second": 15.86,
|
| 458 |
+
"eval_steps_per_second": 3.965,
|
| 459 |
+
"step": 500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.41,
|
| 463 |
+
"learning_rate": 3e-05,
|
| 464 |
+
"loss": 0.0676,
|
| 465 |
+
"step": 510
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.41,
|
| 469 |
+
"learning_rate": 3e-05,
|
| 470 |
+
"loss": 0.0424,
|
| 471 |
+
"step": 520
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.42,
|
| 475 |
+
"learning_rate": 3e-05,
|
| 476 |
+
"loss": 0.0533,
|
| 477 |
+
"step": 530
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.43,
|
| 481 |
+
"learning_rate": 3e-05,
|
| 482 |
+
"loss": 0.0405,
|
| 483 |
+
"step": 540
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.44,
|
| 487 |
+
"learning_rate": 3e-05,
|
| 488 |
+
"loss": 0.0514,
|
| 489 |
+
"step": 550
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.44,
|
| 493 |
+
"eval_accuracy": 0.7452830188679245,
|
| 494 |
+
"eval_f1_macro": 0.6148723643378806,
|
| 495 |
+
"eval_f1_micro": 0.7452830188679244,
|
| 496 |
+
"eval_loss": 0.0491117425262928,
|
| 497 |
+
"eval_precision_macro": 0.6623956744108057,
|
| 498 |
+
"eval_precision_micro": 0.7452830188679245,
|
| 499 |
+
"eval_recall_macro": 0.6055074363524768,
|
| 500 |
+
"eval_recall_micro": 0.7452830188679245,
|
| 501 |
+
"eval_runtime": 66.8014,
|
| 502 |
+
"eval_samples_per_second": 15.868,
|
| 503 |
+
"eval_steps_per_second": 3.967,
|
| 504 |
+
"step": 550
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.45,
|
| 508 |
+
"learning_rate": 3e-05,
|
| 509 |
+
"loss": 0.0657,
|
| 510 |
+
"step": 560
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.45,
|
| 514 |
+
"learning_rate": 3e-05,
|
| 515 |
+
"loss": 0.0491,
|
| 516 |
+
"step": 570
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.46,
|
| 520 |
+
"learning_rate": 3e-05,
|
| 521 |
+
"loss": 0.0415,
|
| 522 |
+
"step": 580
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.47,
|
| 526 |
+
"learning_rate": 3e-05,
|
| 527 |
+
"loss": 0.0485,
|
| 528 |
+
"step": 590
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.48,
|
| 532 |
+
"learning_rate": 3e-05,
|
| 533 |
+
"loss": 0.0537,
|
| 534 |
+
"step": 600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.48,
|
| 538 |
+
"eval_accuracy": 0.7547169811320755,
|
| 539 |
+
"eval_f1_macro": 0.5955912007854481,
|
| 540 |
+
"eval_f1_micro": 0.7547169811320754,
|
| 541 |
+
"eval_loss": 0.04687512293457985,
|
| 542 |
+
"eval_precision_macro": 0.6564521374886103,
|
| 543 |
+
"eval_precision_micro": 0.7547169811320755,
|
| 544 |
+
"eval_recall_macro": 0.6140077817767989,
|
| 545 |
+
"eval_recall_micro": 0.7547169811320755,
|
| 546 |
+
"eval_runtime": 67.0823,
|
| 547 |
+
"eval_samples_per_second": 15.801,
|
| 548 |
+
"eval_steps_per_second": 3.95,
|
| 549 |
+
"step": 600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.48,
|
| 553 |
+
"learning_rate": 3e-05,
|
| 554 |
+
"loss": 0.0494,
|
| 555 |
+
"step": 610
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.49,
|
| 559 |
+
"learning_rate": 3e-05,
|
| 560 |
+
"loss": 0.0472,
|
| 561 |
+
"step": 620
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.5,
|
| 565 |
+
"learning_rate": 3e-05,
|
| 566 |
+
"loss": 0.045,
|
| 567 |
+
"step": 630
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.51,
|
| 571 |
+
"learning_rate": 3e-05,
|
| 572 |
+
"loss": 0.0447,
|
| 573 |
+
"step": 640
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.52,
|
| 577 |
+
"learning_rate": 3e-05,
|
| 578 |
+
"loss": 0.0503,
|
| 579 |
+
"step": 650
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.52,
|
| 583 |
+
"eval_accuracy": 0.7433962264150943,
|
| 584 |
+
"eval_f1_macro": 0.5711369889957133,
|
| 585 |
+
"eval_f1_micro": 0.7433962264150943,
|
| 586 |
+
"eval_loss": 0.04730157181620598,
|
| 587 |
+
"eval_precision_macro": 0.6365229300442473,
|
| 588 |
+
"eval_precision_micro": 0.7433962264150943,
|
| 589 |
+
"eval_recall_macro": 0.5711131524489298,
|
| 590 |
+
"eval_recall_micro": 0.7433962264150943,
|
| 591 |
+
"eval_runtime": 66.9933,
|
| 592 |
+
"eval_samples_per_second": 15.822,
|
| 593 |
+
"eval_steps_per_second": 3.956,
|
| 594 |
+
"step": 650
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.52,
|
| 598 |
+
"learning_rate": 3e-05,
|
| 599 |
+
"loss": 0.0632,
|
| 600 |
+
"step": 660
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.53,
|
| 604 |
+
"learning_rate": 3e-05,
|
| 605 |
+
"loss": 0.0525,
|
| 606 |
+
"step": 670
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.54,
|
| 610 |
+
"learning_rate": 3e-05,
|
| 611 |
+
"loss": 0.0369,
|
| 612 |
+
"step": 680
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.55,
|
| 616 |
+
"learning_rate": 3e-05,
|
| 617 |
+
"loss": 0.0392,
|
| 618 |
+
"step": 690
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.56,
|
| 622 |
+
"learning_rate": 3e-05,
|
| 623 |
+
"loss": 0.0502,
|
| 624 |
+
"step": 700
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.56,
|
| 628 |
+
"eval_accuracy": 0.7990566037735849,
|
| 629 |
+
"eval_f1_macro": 0.6486516495348912,
|
| 630 |
+
"eval_f1_micro": 0.799056603773585,
|
| 631 |
+
"eval_loss": 0.04286834970116615,
|
| 632 |
+
"eval_precision_macro": 0.6674675949162269,
|
| 633 |
+
"eval_precision_micro": 0.7990566037735849,
|
| 634 |
+
"eval_recall_macro": 0.6430318401752134,
|
| 635 |
+
"eval_recall_micro": 0.7990566037735849,
|
| 636 |
+
"eval_runtime": 66.7816,
|
| 637 |
+
"eval_samples_per_second": 15.873,
|
| 638 |
+
"eval_steps_per_second": 3.968,
|
| 639 |
+
"step": 700
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.56,
|
| 643 |
+
"learning_rate": 3e-05,
|
| 644 |
+
"loss": 0.0562,
|
| 645 |
+
"step": 710
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.57,
|
| 649 |
+
"learning_rate": 3e-05,
|
| 650 |
+
"loss": 0.0417,
|
| 651 |
+
"step": 720
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.58,
|
| 655 |
+
"learning_rate": 3e-05,
|
| 656 |
+
"loss": 0.0384,
|
| 657 |
+
"step": 730
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.59,
|
| 661 |
+
"learning_rate": 3e-05,
|
| 662 |
+
"loss": 0.0386,
|
| 663 |
+
"step": 740
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.6,
|
| 667 |
+
"learning_rate": 3e-05,
|
| 668 |
+
"loss": 0.0568,
|
| 669 |
+
"step": 750
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.6,
|
| 673 |
+
"eval_accuracy": 0.7830188679245284,
|
| 674 |
+
"eval_f1_macro": 0.6035355055785452,
|
| 675 |
+
"eval_f1_micro": 0.7830188679245284,
|
| 676 |
+
"eval_loss": 0.04214347526431084,
|
| 677 |
+
"eval_precision_macro": 0.6399716318087022,
|
| 678 |
+
"eval_precision_micro": 0.7830188679245284,
|
| 679 |
+
"eval_recall_macro": 0.6197061339803496,
|
| 680 |
+
"eval_recall_micro": 0.7830188679245284,
|
| 681 |
+
"eval_runtime": 66.9036,
|
| 682 |
+
"eval_samples_per_second": 15.844,
|
| 683 |
+
"eval_steps_per_second": 3.961,
|
| 684 |
+
"step": 750
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.6,
|
| 688 |
+
"learning_rate": 3e-05,
|
| 689 |
+
"loss": 0.0524,
|
| 690 |
+
"step": 760
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.61,
|
| 694 |
+
"learning_rate": 3e-05,
|
| 695 |
+
"loss": 0.0403,
|
| 696 |
+
"step": 770
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.62,
|
| 700 |
+
"learning_rate": 3e-05,
|
| 701 |
+
"loss": 0.0346,
|
| 702 |
+
"step": 780
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.63,
|
| 706 |
+
"learning_rate": 3e-05,
|
| 707 |
+
"loss": 0.0436,
|
| 708 |
+
"step": 790
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.64,
|
| 712 |
+
"learning_rate": 3e-05,
|
| 713 |
+
"loss": 0.0456,
|
| 714 |
+
"step": 800
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.64,
|
| 718 |
+
"eval_accuracy": 0.8037735849056604,
|
| 719 |
+
"eval_f1_macro": 0.6795100443217031,
|
| 720 |
+
"eval_f1_micro": 0.8037735849056604,
|
| 721 |
+
"eval_loss": 0.03851619362831116,
|
| 722 |
+
"eval_precision_macro": 0.6660272950062351,
|
| 723 |
+
"eval_precision_micro": 0.8037735849056604,
|
| 724 |
+
"eval_recall_macro": 0.7100461955802515,
|
| 725 |
+
"eval_recall_micro": 0.8037735849056604,
|
| 726 |
+
"eval_runtime": 66.7565,
|
| 727 |
+
"eval_samples_per_second": 15.879,
|
| 728 |
+
"eval_steps_per_second": 3.97,
|
| 729 |
+
"step": 800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.64,
|
| 733 |
+
"learning_rate": 3e-05,
|
| 734 |
+
"loss": 0.0404,
|
| 735 |
+
"step": 810
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.65,
|
| 739 |
+
"learning_rate": 3e-05,
|
| 740 |
+
"loss": 0.0415,
|
| 741 |
+
"step": 820
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.66,
|
| 745 |
+
"learning_rate": 3e-05,
|
| 746 |
+
"loss": 0.034,
|
| 747 |
+
"step": 830
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.67,
|
| 751 |
+
"learning_rate": 3e-05,
|
| 752 |
+
"loss": 0.0465,
|
| 753 |
+
"step": 840
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.68,
|
| 757 |
+
"learning_rate": 3e-05,
|
| 758 |
+
"loss": 0.0465,
|
| 759 |
+
"step": 850
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.68,
|
| 763 |
+
"eval_accuracy": 0.7867924528301887,
|
| 764 |
+
"eval_f1_macro": 0.6637790925123535,
|
| 765 |
+
"eval_f1_micro": 0.7867924528301887,
|
| 766 |
+
"eval_loss": 0.04226187616586685,
|
| 767 |
+
"eval_precision_macro": 0.70799384577877,
|
| 768 |
+
"eval_precision_micro": 0.7867924528301887,
|
| 769 |
+
"eval_recall_macro": 0.6535685213398926,
|
| 770 |
+
"eval_recall_micro": 0.7867924528301887,
|
| 771 |
+
"eval_runtime": 66.8456,
|
| 772 |
+
"eval_samples_per_second": 15.857,
|
| 773 |
+
"eval_steps_per_second": 3.964,
|
| 774 |
+
"step": 850
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.68,
|
| 778 |
+
"learning_rate": 3e-05,
|
| 779 |
+
"loss": 0.0428,
|
| 780 |
+
"step": 860
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.69,
|
| 784 |
+
"learning_rate": 3e-05,
|
| 785 |
+
"loss": 0.0455,
|
| 786 |
+
"step": 870
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7,
|
| 790 |
+
"learning_rate": 3e-05,
|
| 791 |
+
"loss": 0.0467,
|
| 792 |
+
"step": 880
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.71,
|
| 796 |
+
"learning_rate": 3e-05,
|
| 797 |
+
"loss": 0.0381,
|
| 798 |
+
"step": 890
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.72,
|
| 802 |
+
"learning_rate": 3e-05,
|
| 803 |
+
"loss": 0.0517,
|
| 804 |
+
"step": 900
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.72,
|
| 808 |
+
"eval_accuracy": 0.7830188679245284,
|
| 809 |
+
"eval_f1_macro": 0.604409711538349,
|
| 810 |
+
"eval_f1_micro": 0.7830188679245284,
|
| 811 |
+
"eval_loss": 0.04051998630166054,
|
| 812 |
+
"eval_precision_macro": 0.6482245905845607,
|
| 813 |
+
"eval_precision_micro": 0.7830188679245284,
|
| 814 |
+
"eval_recall_macro": 0.5953272937433359,
|
| 815 |
+
"eval_recall_micro": 0.7830188679245284,
|
| 816 |
+
"eval_runtime": 66.9721,
|
| 817 |
+
"eval_samples_per_second": 15.827,
|
| 818 |
+
"eval_steps_per_second": 3.957,
|
| 819 |
+
"step": 900
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.72,
|
| 823 |
+
"learning_rate": 3e-05,
|
| 824 |
+
"loss": 0.0406,
|
| 825 |
+
"step": 910
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.73,
|
| 829 |
+
"learning_rate": 3e-05,
|
| 830 |
+
"loss": 0.037,
|
| 831 |
+
"step": 920
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.74,
|
| 835 |
+
"learning_rate": 3e-05,
|
| 836 |
+
"loss": 0.0445,
|
| 837 |
+
"step": 930
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.75,
|
| 841 |
+
"learning_rate": 3e-05,
|
| 842 |
+
"loss": 0.0359,
|
| 843 |
+
"step": 940
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.76,
|
| 847 |
+
"learning_rate": 3e-05,
|
| 848 |
+
"loss": 0.0449,
|
| 849 |
+
"step": 950
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.76,
|
| 853 |
+
"eval_accuracy": 0.7962264150943397,
|
| 854 |
+
"eval_f1_macro": 0.6595487480161657,
|
| 855 |
+
"eval_f1_micro": 0.7962264150943396,
|
| 856 |
+
"eval_loss": 0.03951858729124069,
|
| 857 |
+
"eval_precision_macro": 0.678313535245044,
|
| 858 |
+
"eval_precision_micro": 0.7962264150943397,
|
| 859 |
+
"eval_recall_macro": 0.6782248779232171,
|
| 860 |
+
"eval_recall_micro": 0.7962264150943397,
|
| 861 |
+
"eval_runtime": 67.2586,
|
| 862 |
+
"eval_samples_per_second": 15.76,
|
| 863 |
+
"eval_steps_per_second": 3.94,
|
| 864 |
+
"step": 950
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.76,
|
| 868 |
+
"learning_rate": 3e-05,
|
| 869 |
+
"loss": 0.0473,
|
| 870 |
+
"step": 960
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.77,
|
| 874 |
+
"learning_rate": 3e-05,
|
| 875 |
+
"loss": 0.0387,
|
| 876 |
+
"step": 970
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.78,
|
| 880 |
+
"learning_rate": 3e-05,
|
| 881 |
+
"loss": 0.0393,
|
| 882 |
+
"step": 980
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.79,
|
| 886 |
+
"learning_rate": 3e-05,
|
| 887 |
+
"loss": 0.0344,
|
| 888 |
+
"step": 990
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.79,
|
| 892 |
+
"learning_rate": 3e-05,
|
| 893 |
+
"loss": 0.0438,
|
| 894 |
+
"step": 1000
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.79,
|
| 898 |
+
"eval_accuracy": 0.7650943396226415,
|
| 899 |
+
"eval_f1_macro": 0.6269730408930883,
|
| 900 |
+
"eval_f1_micro": 0.7650943396226415,
|
| 901 |
+
"eval_loss": 0.041479434818029404,
|
| 902 |
+
"eval_precision_macro": 0.6310264924491513,
|
| 903 |
+
"eval_precision_micro": 0.7650943396226415,
|
| 904 |
+
"eval_recall_macro": 0.651893356526834,
|
| 905 |
+
"eval_recall_micro": 0.7650943396226415,
|
| 906 |
+
"eval_runtime": 66.8963,
|
| 907 |
+
"eval_samples_per_second": 15.845,
|
| 908 |
+
"eval_steps_per_second": 3.961,
|
| 909 |
+
"step": 1000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8,
|
| 913 |
+
"learning_rate": 3e-05,
|
| 914 |
+
"loss": 0.0454,
|
| 915 |
+
"step": 1010
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.81,
|
| 919 |
+
"learning_rate": 3e-05,
|
| 920 |
+
"loss": 0.0389,
|
| 921 |
+
"step": 1020
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.82,
|
| 925 |
+
"learning_rate": 3e-05,
|
| 926 |
+
"loss": 0.0385,
|
| 927 |
+
"step": 1030
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.83,
|
| 931 |
+
"learning_rate": 3e-05,
|
| 932 |
+
"loss": 0.0465,
|
| 933 |
+
"step": 1040
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.83,
|
| 937 |
+
"learning_rate": 3e-05,
|
| 938 |
+
"loss": 0.0368,
|
| 939 |
+
"step": 1050
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.83,
|
| 943 |
+
"eval_accuracy": 0.8141509433962264,
|
| 944 |
+
"eval_f1_macro": 0.6884941209926929,
|
| 945 |
+
"eval_f1_micro": 0.8141509433962264,
|
| 946 |
+
"eval_loss": 0.036739904433488846,
|
| 947 |
+
"eval_precision_macro": 0.7076595104531683,
|
| 948 |
+
"eval_precision_micro": 0.8141509433962264,
|
| 949 |
+
"eval_recall_macro": 0.6998335623662951,
|
| 950 |
+
"eval_recall_micro": 0.8141509433962264,
|
| 951 |
+
"eval_runtime": 66.8429,
|
| 952 |
+
"eval_samples_per_second": 15.858,
|
| 953 |
+
"eval_steps_per_second": 3.965,
|
| 954 |
+
"step": 1050
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.84,
|
| 958 |
+
"learning_rate": 3e-05,
|
| 959 |
+
"loss": 0.0315,
|
| 960 |
+
"step": 1060
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.85,
|
| 964 |
+
"learning_rate": 3e-05,
|
| 965 |
+
"loss": 0.048,
|
| 966 |
+
"step": 1070
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.86,
|
| 970 |
+
"learning_rate": 3e-05,
|
| 971 |
+
"loss": 0.0423,
|
| 972 |
+
"step": 1080
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.87,
|
| 976 |
+
"learning_rate": 3e-05,
|
| 977 |
+
"loss": 0.0399,
|
| 978 |
+
"step": 1090
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.87,
|
| 982 |
+
"learning_rate": 3e-05,
|
| 983 |
+
"loss": 0.0351,
|
| 984 |
+
"step": 1100
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.87,
|
| 988 |
+
"eval_accuracy": 0.8150943396226416,
|
| 989 |
+
"eval_f1_macro": 0.6795761385716744,
|
| 990 |
+
"eval_f1_micro": 0.8150943396226416,
|
| 991 |
+
"eval_loss": 0.03497824817895889,
|
| 992 |
+
"eval_precision_macro": 0.6863775670636837,
|
| 993 |
+
"eval_precision_micro": 0.8150943396226416,
|
| 994 |
+
"eval_recall_macro": 0.6837727133564548,
|
| 995 |
+
"eval_recall_micro": 0.8150943396226416,
|
| 996 |
+
"eval_runtime": 66.7682,
|
| 997 |
+
"eval_samples_per_second": 15.876,
|
| 998 |
+
"eval_steps_per_second": 3.969,
|
| 999 |
+
"step": 1100
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.88,
|
| 1003 |
+
"learning_rate": 3e-05,
|
| 1004 |
+
"loss": 0.0356,
|
| 1005 |
+
"step": 1110
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.89,
|
| 1009 |
+
"learning_rate": 3e-05,
|
| 1010 |
+
"loss": 0.034,
|
| 1011 |
+
"step": 1120
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.9,
|
| 1015 |
+
"learning_rate": 3e-05,
|
| 1016 |
+
"loss": 0.0379,
|
| 1017 |
+
"step": 1130
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.91,
|
| 1021 |
+
"learning_rate": 3e-05,
|
| 1022 |
+
"loss": 0.0354,
|
| 1023 |
+
"step": 1140
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.91,
|
| 1027 |
+
"learning_rate": 3e-05,
|
| 1028 |
+
"loss": 0.042,
|
| 1029 |
+
"step": 1150
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.91,
|
| 1033 |
+
"eval_accuracy": 0.8066037735849056,
|
| 1034 |
+
"eval_f1_macro": 0.662741723846436,
|
| 1035 |
+
"eval_f1_micro": 0.8066037735849056,
|
| 1036 |
+
"eval_loss": 0.036217570304870605,
|
| 1037 |
+
"eval_precision_macro": 0.6895018843592504,
|
| 1038 |
+
"eval_precision_micro": 0.8066037735849056,
|
| 1039 |
+
"eval_recall_macro": 0.6592689442585865,
|
| 1040 |
+
"eval_recall_micro": 0.8066037735849056,
|
| 1041 |
+
"eval_runtime": 66.8597,
|
| 1042 |
+
"eval_samples_per_second": 15.854,
|
| 1043 |
+
"eval_steps_per_second": 3.964,
|
| 1044 |
+
"step": 1150
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.92,
|
| 1048 |
+
"learning_rate": 3e-05,
|
| 1049 |
+
"loss": 0.0405,
|
| 1050 |
+
"step": 1160
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.93,
|
| 1054 |
+
"learning_rate": 3e-05,
|
| 1055 |
+
"loss": 0.0408,
|
| 1056 |
+
"step": 1170
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.94,
|
| 1060 |
+
"learning_rate": 3e-05,
|
| 1061 |
+
"loss": 0.0522,
|
| 1062 |
+
"step": 1180
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.95,
|
| 1066 |
+
"learning_rate": 3e-05,
|
| 1067 |
+
"loss": 0.0356,
|
| 1068 |
+
"step": 1190
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.95,
|
| 1072 |
+
"learning_rate": 3e-05,
|
| 1073 |
+
"loss": 0.0449,
|
| 1074 |
+
"step": 1200
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.95,
|
| 1078 |
+
"eval_accuracy": 0.7924528301886793,
|
| 1079 |
+
"eval_f1_macro": 0.6582734622403671,
|
| 1080 |
+
"eval_f1_micro": 0.7924528301886793,
|
| 1081 |
+
"eval_loss": 0.036735132336616516,
|
| 1082 |
+
"eval_precision_macro": 0.6685428560679947,
|
| 1083 |
+
"eval_precision_micro": 0.7924528301886793,
|
| 1084 |
+
"eval_recall_macro": 0.6671460190032963,
|
| 1085 |
+
"eval_recall_micro": 0.7924528301886793,
|
| 1086 |
+
"eval_runtime": 66.7753,
|
| 1087 |
+
"eval_samples_per_second": 15.874,
|
| 1088 |
+
"eval_steps_per_second": 3.969,
|
| 1089 |
+
"step": 1200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.96,
|
| 1093 |
+
"learning_rate": 3e-05,
|
| 1094 |
+
"loss": 0.0422,
|
| 1095 |
+
"step": 1210
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.97,
|
| 1099 |
+
"learning_rate": 3e-05,
|
| 1100 |
+
"loss": 0.0469,
|
| 1101 |
+
"step": 1220
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.98,
|
| 1105 |
+
"learning_rate": 3e-05,
|
| 1106 |
+
"loss": 0.0403,
|
| 1107 |
+
"step": 1230
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.99,
|
| 1111 |
+
"learning_rate": 3e-05,
|
| 1112 |
+
"loss": 0.0401,
|
| 1113 |
+
"step": 1240
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.99,
|
| 1117 |
+
"learning_rate": 3e-05,
|
| 1118 |
+
"loss": 0.0331,
|
| 1119 |
+
"step": 1250
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.99,
|
| 1123 |
+
"eval_accuracy": 0.8018867924528302,
|
| 1124 |
+
"eval_f1_macro": 0.6660554002763479,
|
| 1125 |
+
"eval_f1_micro": 0.8018867924528302,
|
| 1126 |
+
"eval_loss": 0.038156915456056595,
|
| 1127 |
+
"eval_precision_macro": 0.6760235498659594,
|
| 1128 |
+
"eval_precision_micro": 0.8018867924528302,
|
| 1129 |
+
"eval_recall_macro": 0.6847602869615839,
|
| 1130 |
+
"eval_recall_micro": 0.8018867924528302,
|
| 1131 |
+
"eval_runtime": 66.972,
|
| 1132 |
+
"eval_samples_per_second": 15.828,
|
| 1133 |
+
"eval_steps_per_second": 3.957,
|
| 1134 |
+
"step": 1250
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.0,
|
| 1138 |
+
"learning_rate": 3e-05,
|
| 1139 |
+
"loss": 0.0403,
|
| 1140 |
+
"step": 1260
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.01,
|
| 1144 |
+
"learning_rate": 3e-05,
|
| 1145 |
+
"loss": 0.0391,
|
| 1146 |
+
"step": 1270
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.02,
|
| 1150 |
+
"learning_rate": 3e-05,
|
| 1151 |
+
"loss": 0.0315,
|
| 1152 |
+
"step": 1280
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.03,
|
| 1156 |
+
"learning_rate": 3e-05,
|
| 1157 |
+
"loss": 0.0334,
|
| 1158 |
+
"step": 1290
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.03,
|
| 1162 |
+
"learning_rate": 3e-05,
|
| 1163 |
+
"loss": 0.0367,
|
| 1164 |
+
"step": 1300
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.03,
|
| 1168 |
+
"eval_accuracy": 0.8037735849056604,
|
| 1169 |
+
"eval_f1_macro": 0.6590298558707023,
|
| 1170 |
+
"eval_f1_micro": 0.8037735849056604,
|
| 1171 |
+
"eval_loss": 0.037248801440000534,
|
| 1172 |
+
"eval_precision_macro": 0.711878576411288,
|
| 1173 |
+
"eval_precision_micro": 0.8037735849056604,
|
| 1174 |
+
"eval_recall_macro": 0.6500565322393169,
|
| 1175 |
+
"eval_recall_micro": 0.8037735849056604,
|
| 1176 |
+
"eval_runtime": 66.9977,
|
| 1177 |
+
"eval_samples_per_second": 15.821,
|
| 1178 |
+
"eval_steps_per_second": 3.955,
|
| 1179 |
+
"step": 1300
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.04,
|
| 1183 |
+
"learning_rate": 3e-05,
|
| 1184 |
+
"loss": 0.0323,
|
| 1185 |
+
"step": 1310
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.05,
|
| 1189 |
+
"learning_rate": 3e-05,
|
| 1190 |
+
"loss": 0.0283,
|
| 1191 |
+
"step": 1320
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.06,
|
| 1195 |
+
"learning_rate": 3e-05,
|
| 1196 |
+
"loss": 0.0317,
|
| 1197 |
+
"step": 1330
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.06,
|
| 1201 |
+
"learning_rate": 3e-05,
|
| 1202 |
+
"loss": 0.0368,
|
| 1203 |
+
"step": 1340
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.07,
|
| 1207 |
+
"learning_rate": 3e-05,
|
| 1208 |
+
"loss": 0.0357,
|
| 1209 |
+
"step": 1350
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.07,
|
| 1213 |
+
"eval_accuracy": 0.7990566037735849,
|
| 1214 |
+
"eval_f1_macro": 0.6639410239226647,
|
| 1215 |
+
"eval_f1_micro": 0.799056603773585,
|
| 1216 |
+
"eval_loss": 0.03749080002307892,
|
| 1217 |
+
"eval_precision_macro": 0.68220871249212,
|
| 1218 |
+
"eval_precision_micro": 0.7990566037735849,
|
| 1219 |
+
"eval_recall_macro": 0.6657052159769387,
|
| 1220 |
+
"eval_recall_micro": 0.7990566037735849,
|
| 1221 |
+
"eval_runtime": 67.3114,
|
| 1222 |
+
"eval_samples_per_second": 15.748,
|
| 1223 |
+
"eval_steps_per_second": 3.937,
|
| 1224 |
+
"step": 1350
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.08,
|
| 1228 |
+
"learning_rate": 3e-05,
|
| 1229 |
+
"loss": 0.0411,
|
| 1230 |
+
"step": 1360
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.09,
|
| 1234 |
+
"learning_rate": 3e-05,
|
| 1235 |
+
"loss": 0.035,
|
| 1236 |
+
"step": 1370
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.1,
|
| 1240 |
+
"learning_rate": 3e-05,
|
| 1241 |
+
"loss": 0.0365,
|
| 1242 |
+
"step": 1380
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.1,
|
| 1246 |
+
"learning_rate": 3e-05,
|
| 1247 |
+
"loss": 0.0321,
|
| 1248 |
+
"step": 1390
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.11,
|
| 1252 |
+
"learning_rate": 3e-05,
|
| 1253 |
+
"loss": 0.0405,
|
| 1254 |
+
"step": 1400
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.11,
|
| 1258 |
+
"eval_accuracy": 0.810377358490566,
|
| 1259 |
+
"eval_f1_macro": 0.6823173521717408,
|
| 1260 |
+
"eval_f1_micro": 0.8103773584905661,
|
| 1261 |
+
"eval_loss": 0.03539792075753212,
|
| 1262 |
+
"eval_precision_macro": 0.6735195406597105,
|
| 1263 |
+
"eval_precision_micro": 0.810377358490566,
|
| 1264 |
+
"eval_recall_macro": 0.7010849626749771,
|
| 1265 |
+
"eval_recall_micro": 0.810377358490566,
|
| 1266 |
+
"eval_runtime": 66.9573,
|
| 1267 |
+
"eval_samples_per_second": 15.831,
|
| 1268 |
+
"eval_steps_per_second": 3.958,
|
| 1269 |
+
"step": 1400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.12,
|
| 1273 |
+
"learning_rate": 3e-05,
|
| 1274 |
+
"loss": 0.0403,
|
| 1275 |
+
"step": 1410
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.13,
|
| 1279 |
+
"learning_rate": 3e-05,
|
| 1280 |
+
"loss": 0.0355,
|
| 1281 |
+
"step": 1420
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.14,
|
| 1285 |
+
"learning_rate": 3e-05,
|
| 1286 |
+
"loss": 0.0262,
|
| 1287 |
+
"step": 1430
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.14,
|
| 1291 |
+
"learning_rate": 3e-05,
|
| 1292 |
+
"loss": 0.0314,
|
| 1293 |
+
"step": 1440
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.15,
|
| 1297 |
+
"learning_rate": 3e-05,
|
| 1298 |
+
"loss": 0.0281,
|
| 1299 |
+
"step": 1450
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.15,
|
| 1303 |
+
"eval_accuracy": 0.8301886792452831,
|
| 1304 |
+
"eval_f1_macro": 0.6936579743869716,
|
| 1305 |
+
"eval_f1_micro": 0.8301886792452831,
|
| 1306 |
+
"eval_loss": 0.03378523513674736,
|
| 1307 |
+
"eval_precision_macro": 0.6880699408956382,
|
| 1308 |
+
"eval_precision_micro": 0.8301886792452831,
|
| 1309 |
+
"eval_recall_macro": 0.7081810763903263,
|
| 1310 |
+
"eval_recall_micro": 0.8301886792452831,
|
| 1311 |
+
"eval_runtime": 66.8615,
|
| 1312 |
+
"eval_samples_per_second": 15.854,
|
| 1313 |
+
"eval_steps_per_second": 3.963,
|
| 1314 |
+
"step": 1450
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.16,
|
| 1318 |
+
"learning_rate": 3e-05,
|
| 1319 |
+
"loss": 0.0426,
|
| 1320 |
+
"step": 1460
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.17,
|
| 1324 |
+
"learning_rate": 3e-05,
|
| 1325 |
+
"loss": 0.0331,
|
| 1326 |
+
"step": 1470
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.18,
|
| 1330 |
+
"learning_rate": 3e-05,
|
| 1331 |
+
"loss": 0.0274,
|
| 1332 |
+
"step": 1480
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.18,
|
| 1336 |
+
"learning_rate": 3e-05,
|
| 1337 |
+
"loss": 0.0303,
|
| 1338 |
+
"step": 1490
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.19,
|
| 1342 |
+
"learning_rate": 3e-05,
|
| 1343 |
+
"loss": 0.0362,
|
| 1344 |
+
"step": 1500
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.19,
|
| 1348 |
+
"eval_accuracy": 0.8122641509433962,
|
| 1349 |
+
"eval_f1_macro": 0.6607417290714642,
|
| 1350 |
+
"eval_f1_micro": 0.8122641509433962,
|
| 1351 |
+
"eval_loss": 0.0350893959403038,
|
| 1352 |
+
"eval_precision_macro": 0.7043834982343933,
|
| 1353 |
+
"eval_precision_micro": 0.8122641509433962,
|
| 1354 |
+
"eval_recall_macro": 0.6559410812932247,
|
| 1355 |
+
"eval_recall_micro": 0.8122641509433962,
|
| 1356 |
+
"eval_runtime": 67.0277,
|
| 1357 |
+
"eval_samples_per_second": 15.814,
|
| 1358 |
+
"eval_steps_per_second": 3.954,
|
| 1359 |
+
"step": 1500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.2,
|
| 1363 |
+
"learning_rate": 3e-05,
|
| 1364 |
+
"loss": 0.0359,
|
| 1365 |
+
"step": 1510
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 1.21,
|
| 1369 |
+
"learning_rate": 3e-05,
|
| 1370 |
+
"loss": 0.0223,
|
| 1371 |
+
"step": 1520
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.22,
|
| 1375 |
+
"learning_rate": 3e-05,
|
| 1376 |
+
"loss": 0.0284,
|
| 1377 |
+
"step": 1530
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.22,
|
| 1381 |
+
"learning_rate": 3e-05,
|
| 1382 |
+
"loss": 0.0445,
|
| 1383 |
+
"step": 1540
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.23,
|
| 1387 |
+
"learning_rate": 3e-05,
|
| 1388 |
+
"loss": 0.0214,
|
| 1389 |
+
"step": 1550
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.23,
|
| 1393 |
+
"eval_accuracy": 0.810377358490566,
|
| 1394 |
+
"eval_f1_macro": 0.6778793723330956,
|
| 1395 |
+
"eval_f1_micro": 0.8103773584905661,
|
| 1396 |
+
"eval_loss": 0.035039015114307404,
|
| 1397 |
+
"eval_precision_macro": 0.7081161930503027,
|
| 1398 |
+
"eval_precision_micro": 0.810377358490566,
|
| 1399 |
+
"eval_recall_macro": 0.6748998812700701,
|
| 1400 |
+
"eval_recall_micro": 0.810377358490566,
|
| 1401 |
+
"eval_runtime": 67.0902,
|
| 1402 |
+
"eval_samples_per_second": 15.8,
|
| 1403 |
+
"eval_steps_per_second": 3.95,
|
| 1404 |
+
"step": 1550
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.24,
|
| 1408 |
+
"learning_rate": 3e-05,
|
| 1409 |
+
"loss": 0.0396,
|
| 1410 |
+
"step": 1560
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.25,
|
| 1414 |
+
"learning_rate": 3e-05,
|
| 1415 |
+
"loss": 0.0421,
|
| 1416 |
+
"step": 1570
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.26,
|
| 1420 |
+
"learning_rate": 3e-05,
|
| 1421 |
+
"loss": 0.0367,
|
| 1422 |
+
"step": 1580
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 1.26,
|
| 1426 |
+
"learning_rate": 3e-05,
|
| 1427 |
+
"loss": 0.029,
|
| 1428 |
+
"step": 1590
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.27,
|
| 1432 |
+
"learning_rate": 3e-05,
|
| 1433 |
+
"loss": 0.0321,
|
| 1434 |
+
"step": 1600
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.27,
|
| 1438 |
+
"eval_accuracy": 0.809433962264151,
|
| 1439 |
+
"eval_f1_macro": 0.7277842533202593,
|
| 1440 |
+
"eval_f1_micro": 0.809433962264151,
|
| 1441 |
+
"eval_loss": 0.036841992288827896,
|
| 1442 |
+
"eval_precision_macro": 0.754059995164892,
|
| 1443 |
+
"eval_precision_micro": 0.809433962264151,
|
| 1444 |
+
"eval_recall_macro": 0.7253784421960152,
|
| 1445 |
+
"eval_recall_micro": 0.809433962264151,
|
| 1446 |
+
"eval_runtime": 67.1117,
|
| 1447 |
+
"eval_samples_per_second": 15.795,
|
| 1448 |
+
"eval_steps_per_second": 3.949,
|
| 1449 |
+
"step": 1600
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.28,
|
| 1453 |
+
"learning_rate": 3e-05,
|
| 1454 |
+
"loss": 0.0338,
|
| 1455 |
+
"step": 1610
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.29,
|
| 1459 |
+
"learning_rate": 3e-05,
|
| 1460 |
+
"loss": 0.0361,
|
| 1461 |
+
"step": 1620
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.3,
|
| 1465 |
+
"learning_rate": 3e-05,
|
| 1466 |
+
"loss": 0.0415,
|
| 1467 |
+
"step": 1630
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.3,
|
| 1471 |
+
"learning_rate": 3e-05,
|
| 1472 |
+
"loss": 0.0354,
|
| 1473 |
+
"step": 1640
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.31,
|
| 1477 |
+
"learning_rate": 3e-05,
|
| 1478 |
+
"loss": 0.0332,
|
| 1479 |
+
"step": 1650
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.31,
|
| 1483 |
+
"eval_accuracy": 0.8254716981132075,
|
| 1484 |
+
"eval_f1_macro": 0.7081292929169892,
|
| 1485 |
+
"eval_f1_micro": 0.8254716981132075,
|
| 1486 |
+
"eval_loss": 0.03387230262160301,
|
| 1487 |
+
"eval_precision_macro": 0.7291239674093415,
|
| 1488 |
+
"eval_precision_micro": 0.8254716981132075,
|
| 1489 |
+
"eval_recall_macro": 0.7104202884103088,
|
| 1490 |
+
"eval_recall_micro": 0.8254716981132075,
|
| 1491 |
+
"eval_runtime": 67.285,
|
| 1492 |
+
"eval_samples_per_second": 15.754,
|
| 1493 |
+
"eval_steps_per_second": 3.938,
|
| 1494 |
+
"step": 1650
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.32,
|
| 1498 |
+
"learning_rate": 3e-05,
|
| 1499 |
+
"loss": 0.0337,
|
| 1500 |
+
"step": 1660
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.33,
|
| 1504 |
+
"learning_rate": 3e-05,
|
| 1505 |
+
"loss": 0.0281,
|
| 1506 |
+
"step": 1670
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.34,
|
| 1510 |
+
"learning_rate": 3e-05,
|
| 1511 |
+
"loss": 0.0269,
|
| 1512 |
+
"step": 1680
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.34,
|
| 1516 |
+
"learning_rate": 3e-05,
|
| 1517 |
+
"loss": 0.0339,
|
| 1518 |
+
"step": 1690
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.35,
|
| 1522 |
+
"learning_rate": 3e-05,
|
| 1523 |
+
"loss": 0.0306,
|
| 1524 |
+
"step": 1700
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 1.35,
|
| 1528 |
+
"eval_accuracy": 0.8179245283018868,
|
| 1529 |
+
"eval_f1_macro": 0.6769788054372391,
|
| 1530 |
+
"eval_f1_micro": 0.8179245283018868,
|
| 1531 |
+
"eval_loss": 0.03388019651174545,
|
| 1532 |
+
"eval_precision_macro": 0.6816133549156956,
|
| 1533 |
+
"eval_precision_micro": 0.8179245283018868,
|
| 1534 |
+
"eval_recall_macro": 0.680429225227406,
|
| 1535 |
+
"eval_recall_micro": 0.8179245283018868,
|
| 1536 |
+
"eval_runtime": 67.4515,
|
| 1537 |
+
"eval_samples_per_second": 15.715,
|
| 1538 |
+
"eval_steps_per_second": 3.929,
|
| 1539 |
+
"step": 1700
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.36,
|
| 1543 |
+
"learning_rate": 3e-05,
|
| 1544 |
+
"loss": 0.0376,
|
| 1545 |
+
"step": 1710
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.37,
|
| 1549 |
+
"learning_rate": 3e-05,
|
| 1550 |
+
"loss": 0.0243,
|
| 1551 |
+
"step": 1720
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.37,
|
| 1555 |
+
"learning_rate": 3e-05,
|
| 1556 |
+
"loss": 0.0302,
|
| 1557 |
+
"step": 1730
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.38,
|
| 1561 |
+
"learning_rate": 3e-05,
|
| 1562 |
+
"loss": 0.0334,
|
| 1563 |
+
"step": 1740
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.39,
|
| 1567 |
+
"learning_rate": 3e-05,
|
| 1568 |
+
"loss": 0.0231,
|
| 1569 |
+
"step": 1750
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.39,
|
| 1573 |
+
"eval_accuracy": 0.8179245283018868,
|
| 1574 |
+
"eval_f1_macro": 0.6890240801949487,
|
| 1575 |
+
"eval_f1_micro": 0.8179245283018868,
|
| 1576 |
+
"eval_loss": 0.03725350275635719,
|
| 1577 |
+
"eval_precision_macro": 0.6983358697605533,
|
| 1578 |
+
"eval_precision_micro": 0.8179245283018868,
|
| 1579 |
+
"eval_recall_macro": 0.6881012857058126,
|
| 1580 |
+
"eval_recall_micro": 0.8179245283018868,
|
| 1581 |
+
"eval_runtime": 67.1945,
|
| 1582 |
+
"eval_samples_per_second": 15.775,
|
| 1583 |
+
"eval_steps_per_second": 3.944,
|
| 1584 |
+
"step": 1750
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.4,
|
| 1588 |
+
"learning_rate": 3e-05,
|
| 1589 |
+
"loss": 0.0351,
|
| 1590 |
+
"step": 1760
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 1.41,
|
| 1594 |
+
"learning_rate": 3e-05,
|
| 1595 |
+
"loss": 0.0312,
|
| 1596 |
+
"step": 1770
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 1.41,
|
| 1600 |
+
"learning_rate": 3e-05,
|
| 1601 |
+
"loss": 0.036,
|
| 1602 |
+
"step": 1780
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.42,
|
| 1606 |
+
"learning_rate": 3e-05,
|
| 1607 |
+
"loss": 0.0336,
|
| 1608 |
+
"step": 1790
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 1.43,
|
| 1612 |
+
"learning_rate": 3e-05,
|
| 1613 |
+
"loss": 0.0351,
|
| 1614 |
+
"step": 1800
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.43,
|
| 1618 |
+
"eval_accuracy": 0.8216981132075472,
|
| 1619 |
+
"eval_f1_macro": 0.6893274603000062,
|
| 1620 |
+
"eval_f1_micro": 0.821698113207547,
|
| 1621 |
+
"eval_loss": 0.035641398280858994,
|
| 1622 |
+
"eval_precision_macro": 0.6989494989333128,
|
| 1623 |
+
"eval_precision_micro": 0.8216981132075472,
|
| 1624 |
+
"eval_recall_macro": 0.6917495141935277,
|
| 1625 |
+
"eval_recall_micro": 0.8216981132075472,
|
| 1626 |
+
"eval_runtime": 72.4563,
|
| 1627 |
+
"eval_samples_per_second": 14.629,
|
| 1628 |
+
"eval_steps_per_second": 3.657,
|
| 1629 |
+
"step": 1800
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.44,
|
| 1633 |
+
"learning_rate": 3e-05,
|
| 1634 |
+
"loss": 0.0315,
|
| 1635 |
+
"step": 1810
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.45,
|
| 1639 |
+
"learning_rate": 3e-05,
|
| 1640 |
+
"loss": 0.0378,
|
| 1641 |
+
"step": 1820
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.45,
|
| 1645 |
+
"learning_rate": 3e-05,
|
| 1646 |
+
"loss": 0.0297,
|
| 1647 |
+
"step": 1830
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.46,
|
| 1651 |
+
"learning_rate": 3e-05,
|
| 1652 |
+
"loss": 0.0405,
|
| 1653 |
+
"step": 1840
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 1.47,
|
| 1657 |
+
"learning_rate": 3e-05,
|
| 1658 |
+
"loss": 0.0259,
|
| 1659 |
+
"step": 1850
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.47,
|
| 1663 |
+
"eval_accuracy": 0.8207547169811321,
|
| 1664 |
+
"eval_f1_macro": 0.6884764059910556,
|
| 1665 |
+
"eval_f1_micro": 0.8207547169811321,
|
| 1666 |
+
"eval_loss": 0.033535219728946686,
|
| 1667 |
+
"eval_precision_macro": 0.6999273971863751,
|
| 1668 |
+
"eval_precision_micro": 0.8207547169811321,
|
| 1669 |
+
"eval_recall_macro": 0.6823064809142775,
|
| 1670 |
+
"eval_recall_micro": 0.8207547169811321,
|
| 1671 |
+
"eval_runtime": 75.3135,
|
| 1672 |
+
"eval_samples_per_second": 14.074,
|
| 1673 |
+
"eval_steps_per_second": 3.519,
|
| 1674 |
+
"step": 1850
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.48,
|
| 1678 |
+
"learning_rate": 3e-05,
|
| 1679 |
+
"loss": 0.0313,
|
| 1680 |
+
"step": 1860
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.49,
|
| 1684 |
+
"learning_rate": 3e-05,
|
| 1685 |
+
"loss": 0.0411,
|
| 1686 |
+
"step": 1870
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.49,
|
| 1690 |
+
"learning_rate": 3e-05,
|
| 1691 |
+
"loss": 0.0294,
|
| 1692 |
+
"step": 1880
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 1.5,
|
| 1696 |
+
"learning_rate": 3e-05,
|
| 1697 |
+
"loss": 0.0357,
|
| 1698 |
+
"step": 1890
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.51,
|
| 1702 |
+
"learning_rate": 3e-05,
|
| 1703 |
+
"loss": 0.0371,
|
| 1704 |
+
"step": 1900
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.51,
|
| 1708 |
+
"eval_accuracy": 0.8122641509433962,
|
| 1709 |
+
"eval_f1_macro": 0.6817031059683786,
|
| 1710 |
+
"eval_f1_micro": 0.8122641509433962,
|
| 1711 |
+
"eval_loss": 0.03668028488755226,
|
| 1712 |
+
"eval_precision_macro": 0.7411726936728738,
|
| 1713 |
+
"eval_precision_micro": 0.8122641509433962,
|
| 1714 |
+
"eval_recall_macro": 0.6617258448443556,
|
| 1715 |
+
"eval_recall_micro": 0.8122641509433962,
|
| 1716 |
+
"eval_runtime": 68.4416,
|
| 1717 |
+
"eval_samples_per_second": 15.488,
|
| 1718 |
+
"eval_steps_per_second": 3.872,
|
| 1719 |
+
"step": 1900
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.52,
|
| 1723 |
+
"learning_rate": 3e-05,
|
| 1724 |
+
"loss": 0.0414,
|
| 1725 |
+
"step": 1910
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.53,
|
| 1729 |
+
"learning_rate": 3e-05,
|
| 1730 |
+
"loss": 0.0359,
|
| 1731 |
+
"step": 1920
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.53,
|
| 1735 |
+
"learning_rate": 3e-05,
|
| 1736 |
+
"loss": 0.0364,
|
| 1737 |
+
"step": 1930
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.54,
|
| 1741 |
+
"learning_rate": 3e-05,
|
| 1742 |
+
"loss": 0.0328,
|
| 1743 |
+
"step": 1940
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.55,
|
| 1747 |
+
"learning_rate": 3e-05,
|
| 1748 |
+
"loss": 0.0288,
|
| 1749 |
+
"step": 1950
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.55,
|
| 1753 |
+
"eval_accuracy": 0.8179245283018868,
|
| 1754 |
+
"eval_f1_macro": 0.6808261949093507,
|
| 1755 |
+
"eval_f1_micro": 0.8179245283018868,
|
| 1756 |
+
"eval_loss": 0.03465178981423378,
|
| 1757 |
+
"eval_precision_macro": 0.6758330579285278,
|
| 1758 |
+
"eval_precision_micro": 0.8179245283018868,
|
| 1759 |
+
"eval_recall_macro": 0.6916444013212283,
|
| 1760 |
+
"eval_recall_micro": 0.8179245283018868,
|
| 1761 |
+
"eval_runtime": 67.4794,
|
| 1762 |
+
"eval_samples_per_second": 15.708,
|
| 1763 |
+
"eval_steps_per_second": 3.927,
|
| 1764 |
+
"step": 1950
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.56,
|
| 1768 |
+
"learning_rate": 3e-05,
|
| 1769 |
+
"loss": 0.0292,
|
| 1770 |
+
"step": 1960
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.57,
|
| 1774 |
+
"learning_rate": 3e-05,
|
| 1775 |
+
"loss": 0.0372,
|
| 1776 |
+
"step": 1970
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.57,
|
| 1780 |
+
"learning_rate": 3e-05,
|
| 1781 |
+
"loss": 0.0371,
|
| 1782 |
+
"step": 1980
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 1.58,
|
| 1786 |
+
"learning_rate": 3e-05,
|
| 1787 |
+
"loss": 0.0292,
|
| 1788 |
+
"step": 1990
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.59,
|
| 1792 |
+
"learning_rate": 3e-05,
|
| 1793 |
+
"loss": 0.0252,
|
| 1794 |
+
"step": 2000
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.59,
|
| 1798 |
+
"eval_accuracy": 0.8113207547169812,
|
| 1799 |
+
"eval_f1_macro": 0.6786603793711855,
|
| 1800 |
+
"eval_f1_micro": 0.8113207547169812,
|
| 1801 |
+
"eval_loss": 0.03572586923837662,
|
| 1802 |
+
"eval_precision_macro": 0.7003439014078875,
|
| 1803 |
+
"eval_precision_micro": 0.8113207547169812,
|
| 1804 |
+
"eval_recall_macro": 0.6714151723581485,
|
| 1805 |
+
"eval_recall_micro": 0.8113207547169812,
|
| 1806 |
+
"eval_runtime": 67.3677,
|
| 1807 |
+
"eval_samples_per_second": 15.735,
|
| 1808 |
+
"eval_steps_per_second": 3.934,
|
| 1809 |
+
"step": 2000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.6,
|
| 1813 |
+
"learning_rate": 3e-05,
|
| 1814 |
+
"loss": 0.0418,
|
| 1815 |
+
"step": 2010
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.61,
|
| 1819 |
+
"learning_rate": 3e-05,
|
| 1820 |
+
"loss": 0.0306,
|
| 1821 |
+
"step": 2020
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.61,
|
| 1825 |
+
"learning_rate": 3e-05,
|
| 1826 |
+
"loss": 0.0264,
|
| 1827 |
+
"step": 2030
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.62,
|
| 1831 |
+
"learning_rate": 3e-05,
|
| 1832 |
+
"loss": 0.0352,
|
| 1833 |
+
"step": 2040
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 1.63,
|
| 1837 |
+
"learning_rate": 3e-05,
|
| 1838 |
+
"loss": 0.0374,
|
| 1839 |
+
"step": 2050
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.63,
|
| 1843 |
+
"eval_accuracy": 0.8207547169811321,
|
| 1844 |
+
"eval_f1_macro": 0.7378651093912652,
|
| 1845 |
+
"eval_f1_micro": 0.8207547169811321,
|
| 1846 |
+
"eval_loss": 0.03318563476204872,
|
| 1847 |
+
"eval_precision_macro": 0.7746611477051377,
|
| 1848 |
+
"eval_precision_micro": 0.8207547169811321,
|
| 1849 |
+
"eval_recall_macro": 0.7232885741364632,
|
| 1850 |
+
"eval_recall_micro": 0.8207547169811321,
|
| 1851 |
+
"eval_runtime": 67.1675,
|
| 1852 |
+
"eval_samples_per_second": 15.781,
|
| 1853 |
+
"eval_steps_per_second": 3.945,
|
| 1854 |
+
"step": 2050
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 1.64,
|
| 1858 |
+
"learning_rate": 3e-05,
|
| 1859 |
+
"loss": 0.0334,
|
| 1860 |
+
"step": 2060
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 1.65,
|
| 1864 |
+
"learning_rate": 3e-05,
|
| 1865 |
+
"loss": 0.0275,
|
| 1866 |
+
"step": 2070
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.65,
|
| 1870 |
+
"learning_rate": 3e-05,
|
| 1871 |
+
"loss": 0.0367,
|
| 1872 |
+
"step": 2080
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.66,
|
| 1876 |
+
"learning_rate": 3e-05,
|
| 1877 |
+
"loss": 0.0347,
|
| 1878 |
+
"step": 2090
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.67,
|
| 1882 |
+
"learning_rate": 3e-05,
|
| 1883 |
+
"loss": 0.0356,
|
| 1884 |
+
"step": 2100
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 1.67,
|
| 1888 |
+
"eval_accuracy": 0.8283018867924529,
|
| 1889 |
+
"eval_f1_macro": 0.7162407407283602,
|
| 1890 |
+
"eval_f1_micro": 0.8283018867924529,
|
| 1891 |
+
"eval_loss": 0.032257240265607834,
|
| 1892 |
+
"eval_precision_macro": 0.7425264980116305,
|
| 1893 |
+
"eval_precision_micro": 0.8283018867924529,
|
| 1894 |
+
"eval_recall_macro": 0.7045621292629789,
|
| 1895 |
+
"eval_recall_micro": 0.8283018867924529,
|
| 1896 |
+
"eval_runtime": 67.05,
|
| 1897 |
+
"eval_samples_per_second": 15.809,
|
| 1898 |
+
"eval_steps_per_second": 3.952,
|
| 1899 |
+
"step": 2100
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.68,
|
| 1903 |
+
"learning_rate": 3e-05,
|
| 1904 |
+
"loss": 0.0345,
|
| 1905 |
+
"step": 2110
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.68,
|
| 1909 |
+
"learning_rate": 3e-05,
|
| 1910 |
+
"loss": 0.0324,
|
| 1911 |
+
"step": 2120
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 1.69,
|
| 1915 |
+
"learning_rate": 3e-05,
|
| 1916 |
+
"loss": 0.0317,
|
| 1917 |
+
"step": 2130
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 1.7,
|
| 1921 |
+
"learning_rate": 3e-05,
|
| 1922 |
+
"loss": 0.0372,
|
| 1923 |
+
"step": 2140
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 1.71,
|
| 1927 |
+
"learning_rate": 3e-05,
|
| 1928 |
+
"loss": 0.0294,
|
| 1929 |
+
"step": 2150
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.71,
|
| 1933 |
+
"eval_accuracy": 0.8113207547169812,
|
| 1934 |
+
"eval_f1_macro": 0.7100925220691637,
|
| 1935 |
+
"eval_f1_micro": 0.8113207547169812,
|
| 1936 |
+
"eval_loss": 0.03457261621952057,
|
| 1937 |
+
"eval_precision_macro": 0.7173368388422002,
|
| 1938 |
+
"eval_precision_micro": 0.8113207547169812,
|
| 1939 |
+
"eval_recall_macro": 0.722749933086757,
|
| 1940 |
+
"eval_recall_micro": 0.8113207547169812,
|
| 1941 |
+
"eval_runtime": 66.9989,
|
| 1942 |
+
"eval_samples_per_second": 15.821,
|
| 1943 |
+
"eval_steps_per_second": 3.955,
|
| 1944 |
+
"step": 2150
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 1.72,
|
| 1948 |
+
"learning_rate": 3e-05,
|
| 1949 |
+
"loss": 0.0322,
|
| 1950 |
+
"step": 2160
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 1.72,
|
| 1954 |
+
"learning_rate": 3e-05,
|
| 1955 |
+
"loss": 0.038,
|
| 1956 |
+
"step": 2170
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.73,
|
| 1960 |
+
"learning_rate": 3e-05,
|
| 1961 |
+
"loss": 0.0283,
|
| 1962 |
+
"step": 2180
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.74,
|
| 1966 |
+
"learning_rate": 3e-05,
|
| 1967 |
+
"loss": 0.0346,
|
| 1968 |
+
"step": 2190
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 1.75,
|
| 1972 |
+
"learning_rate": 3e-05,
|
| 1973 |
+
"loss": 0.035,
|
| 1974 |
+
"step": 2200
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.75,
|
| 1978 |
+
"eval_accuracy": 0.8235849056603773,
|
| 1979 |
+
"eval_f1_macro": 0.7390128397138074,
|
| 1980 |
+
"eval_f1_micro": 0.8235849056603773,
|
| 1981 |
+
"eval_loss": 0.033848535269498825,
|
| 1982 |
+
"eval_precision_macro": 0.7590826949473053,
|
| 1983 |
+
"eval_precision_micro": 0.8235849056603773,
|
| 1984 |
+
"eval_recall_macro": 0.730688195944597,
|
| 1985 |
+
"eval_recall_micro": 0.8235849056603773,
|
| 1986 |
+
"eval_runtime": 66.9638,
|
| 1987 |
+
"eval_samples_per_second": 15.829,
|
| 1988 |
+
"eval_steps_per_second": 3.957,
|
| 1989 |
+
"step": 2200
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.76,
|
| 1993 |
+
"learning_rate": 3e-05,
|
| 1994 |
+
"loss": 0.0347,
|
| 1995 |
+
"step": 2210
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 1.76,
|
| 1999 |
+
"learning_rate": 3e-05,
|
| 2000 |
+
"loss": 0.0252,
|
| 2001 |
+
"step": 2220
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.77,
|
| 2005 |
+
"learning_rate": 3e-05,
|
| 2006 |
+
"loss": 0.037,
|
| 2007 |
+
"step": 2230
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 1.78,
|
| 2011 |
+
"learning_rate": 3e-05,
|
| 2012 |
+
"loss": 0.0352,
|
| 2013 |
+
"step": 2240
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 1.79,
|
| 2017 |
+
"learning_rate": 3e-05,
|
| 2018 |
+
"loss": 0.0432,
|
| 2019 |
+
"step": 2250
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.79,
|
| 2023 |
+
"eval_accuracy": 0.8216981132075472,
|
| 2024 |
+
"eval_f1_macro": 0.7295141356598547,
|
| 2025 |
+
"eval_f1_micro": 0.821698113207547,
|
| 2026 |
+
"eval_loss": 0.03482788801193237,
|
| 2027 |
+
"eval_precision_macro": 0.7693704211435056,
|
| 2028 |
+
"eval_precision_micro": 0.8216981132075472,
|
| 2029 |
+
"eval_recall_macro": 0.7204303826474574,
|
| 2030 |
+
"eval_recall_micro": 0.8216981132075472,
|
| 2031 |
+
"eval_runtime": 67.0744,
|
| 2032 |
+
"eval_samples_per_second": 15.803,
|
| 2033 |
+
"eval_steps_per_second": 3.951,
|
| 2034 |
+
"step": 2250
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.8,
|
| 2038 |
+
"learning_rate": 3e-05,
|
| 2039 |
+
"loss": 0.0313,
|
| 2040 |
+
"step": 2260
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.8,
|
| 2044 |
+
"learning_rate": 3e-05,
|
| 2045 |
+
"loss": 0.0367,
|
| 2046 |
+
"step": 2270
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.81,
|
| 2050 |
+
"learning_rate": 3e-05,
|
| 2051 |
+
"loss": 0.0294,
|
| 2052 |
+
"step": 2280
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 1.82,
|
| 2056 |
+
"learning_rate": 3e-05,
|
| 2057 |
+
"loss": 0.0265,
|
| 2058 |
+
"step": 2290
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.83,
|
| 2062 |
+
"learning_rate": 3e-05,
|
| 2063 |
+
"loss": 0.0325,
|
| 2064 |
+
"step": 2300
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 1.83,
|
| 2068 |
+
"eval_accuracy": 0.8330188679245283,
|
| 2069 |
+
"eval_f1_macro": 0.7260646503551377,
|
| 2070 |
+
"eval_f1_micro": 0.8330188679245283,
|
| 2071 |
+
"eval_loss": 0.032365720719099045,
|
| 2072 |
+
"eval_precision_macro": 0.7440576765333733,
|
| 2073 |
+
"eval_precision_micro": 0.8330188679245283,
|
| 2074 |
+
"eval_recall_macro": 0.7231434220015308,
|
| 2075 |
+
"eval_recall_micro": 0.8330188679245283,
|
| 2076 |
+
"eval_runtime": 67.0867,
|
| 2077 |
+
"eval_samples_per_second": 15.8,
|
| 2078 |
+
"eval_steps_per_second": 3.95,
|
| 2079 |
+
"step": 2300
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.84,
|
| 2083 |
+
"learning_rate": 3e-05,
|
| 2084 |
+
"loss": 0.0361,
|
| 2085 |
+
"step": 2310
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 1.84,
|
| 2089 |
+
"learning_rate": 3e-05,
|
| 2090 |
+
"loss": 0.029,
|
| 2091 |
+
"step": 2320
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 1.85,
|
| 2095 |
+
"learning_rate": 3e-05,
|
| 2096 |
+
"loss": 0.0325,
|
| 2097 |
+
"step": 2330
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 1.86,
|
| 2101 |
+
"learning_rate": 3e-05,
|
| 2102 |
+
"loss": 0.0266,
|
| 2103 |
+
"step": 2340
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.87,
|
| 2107 |
+
"learning_rate": 3e-05,
|
| 2108 |
+
"loss": 0.0318,
|
| 2109 |
+
"step": 2350
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.87,
|
| 2113 |
+
"eval_accuracy": 0.8311320754716981,
|
| 2114 |
+
"eval_f1_macro": 0.7248036031015876,
|
| 2115 |
+
"eval_f1_micro": 0.8311320754716981,
|
| 2116 |
+
"eval_loss": 0.03213372081518173,
|
| 2117 |
+
"eval_precision_macro": 0.7397395837984007,
|
| 2118 |
+
"eval_precision_micro": 0.8311320754716981,
|
| 2119 |
+
"eval_recall_macro": 0.7241410864722072,
|
| 2120 |
+
"eval_recall_micro": 0.8311320754716981,
|
| 2121 |
+
"eval_runtime": 67.1828,
|
| 2122 |
+
"eval_samples_per_second": 15.778,
|
| 2123 |
+
"eval_steps_per_second": 3.944,
|
| 2124 |
+
"step": 2350
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.88,
|
| 2128 |
+
"learning_rate": 3e-05,
|
| 2129 |
+
"loss": 0.0339,
|
| 2130 |
+
"step": 2360
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.88,
|
| 2134 |
+
"learning_rate": 3e-05,
|
| 2135 |
+
"loss": 0.0359,
|
| 2136 |
+
"step": 2370
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 1.89,
|
| 2140 |
+
"learning_rate": 3e-05,
|
| 2141 |
+
"loss": 0.0296,
|
| 2142 |
+
"step": 2380
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 1.9,
|
| 2146 |
+
"learning_rate": 3e-05,
|
| 2147 |
+
"loss": 0.0249,
|
| 2148 |
+
"step": 2390
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 1.91,
|
| 2152 |
+
"learning_rate": 3e-05,
|
| 2153 |
+
"loss": 0.0315,
|
| 2154 |
+
"step": 2400
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.91,
|
| 2158 |
+
"eval_accuracy": 0.8179245283018868,
|
| 2159 |
+
"eval_f1_macro": 0.6858375088253653,
|
| 2160 |
+
"eval_f1_micro": 0.8179245283018868,
|
| 2161 |
+
"eval_loss": 0.033517900854349136,
|
| 2162 |
+
"eval_precision_macro": 0.6792945547363913,
|
| 2163 |
+
"eval_precision_micro": 0.8179245283018868,
|
| 2164 |
+
"eval_recall_macro": 0.7034801209007658,
|
| 2165 |
+
"eval_recall_micro": 0.8179245283018868,
|
| 2166 |
+
"eval_runtime": 67.2538,
|
| 2167 |
+
"eval_samples_per_second": 15.761,
|
| 2168 |
+
"eval_steps_per_second": 3.94,
|
| 2169 |
+
"step": 2400
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 1.92,
|
| 2173 |
+
"learning_rate": 3e-05,
|
| 2174 |
+
"loss": 0.037,
|
| 2175 |
+
"step": 2410
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 1.92,
|
| 2179 |
+
"learning_rate": 3e-05,
|
| 2180 |
+
"loss": 0.032,
|
| 2181 |
+
"step": 2420
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 1.93,
|
| 2185 |
+
"learning_rate": 3e-05,
|
| 2186 |
+
"loss": 0.0333,
|
| 2187 |
+
"step": 2430
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.94,
|
| 2191 |
+
"learning_rate": 3e-05,
|
| 2192 |
+
"loss": 0.0369,
|
| 2193 |
+
"step": 2440
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.95,
|
| 2197 |
+
"learning_rate": 3e-05,
|
| 2198 |
+
"loss": 0.0331,
|
| 2199 |
+
"step": 2450
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 1.95,
|
| 2203 |
+
"eval_accuracy": 0.8179245283018868,
|
| 2204 |
+
"eval_f1_macro": 0.6955540611871792,
|
| 2205 |
+
"eval_f1_micro": 0.8179245283018868,
|
| 2206 |
+
"eval_loss": 0.033520761877298355,
|
| 2207 |
+
"eval_precision_macro": 0.7294988206190055,
|
| 2208 |
+
"eval_precision_micro": 0.8179245283018868,
|
| 2209 |
+
"eval_recall_macro": 0.6879491415746545,
|
| 2210 |
+
"eval_recall_micro": 0.8179245283018868,
|
| 2211 |
+
"eval_runtime": 67.0948,
|
| 2212 |
+
"eval_samples_per_second": 15.799,
|
| 2213 |
+
"eval_steps_per_second": 3.95,
|
| 2214 |
+
"step": 2450
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.96,
|
| 2218 |
+
"learning_rate": 3e-05,
|
| 2219 |
+
"loss": 0.035,
|
| 2220 |
+
"step": 2460
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 1.96,
|
| 2224 |
+
"learning_rate": 3e-05,
|
| 2225 |
+
"loss": 0.0323,
|
| 2226 |
+
"step": 2470
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 1.97,
|
| 2230 |
+
"learning_rate": 3e-05,
|
| 2231 |
+
"loss": 0.0346,
|
| 2232 |
+
"step": 2480
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 1.98,
|
| 2236 |
+
"learning_rate": 3e-05,
|
| 2237 |
+
"loss": 0.0287,
|
| 2238 |
+
"step": 2490
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 1.99,
|
| 2242 |
+
"learning_rate": 3e-05,
|
| 2243 |
+
"loss": 0.0293,
|
| 2244 |
+
"step": 2500
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 1.99,
|
| 2248 |
+
"eval_accuracy": 0.8056603773584906,
|
| 2249 |
+
"eval_f1_macro": 0.6866675132658472,
|
| 2250 |
+
"eval_f1_micro": 0.8056603773584906,
|
| 2251 |
+
"eval_loss": 0.03530614450573921,
|
| 2252 |
+
"eval_precision_macro": 0.7026639102515493,
|
| 2253 |
+
"eval_precision_micro": 0.8056603773584906,
|
| 2254 |
+
"eval_recall_macro": 0.6939733521884667,
|
| 2255 |
+
"eval_recall_micro": 0.8056603773584906,
|
| 2256 |
+
"eval_runtime": 67.0079,
|
| 2257 |
+
"eval_samples_per_second": 15.819,
|
| 2258 |
+
"eval_steps_per_second": 3.955,
|
| 2259 |
+
"step": 2500
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.99,
|
| 2263 |
+
"learning_rate": 3e-05,
|
| 2264 |
+
"loss": 0.0347,
|
| 2265 |
+
"step": 2510
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 2.0,
|
| 2269 |
+
"step": 2516,
|
| 2270 |
+
"total_flos": 6.250904333773187e+17,
|
| 2271 |
+
"train_loss": 0.05790289470982191,
|
| 2272 |
+
"train_runtime": 10296.0519,
|
| 2273 |
+
"train_samples_per_second": 3.91,
|
| 2274 |
+
"train_steps_per_second": 0.244
|
| 2275 |
+
}
|
| 2276 |
+
],
|
| 2277 |
+
"logging_steps": 10,
|
| 2278 |
+
"max_steps": 2516,
|
| 2279 |
+
"num_input_tokens_seen": 0,
|
| 2280 |
+
"num_train_epochs": 2,
|
| 2281 |
+
"save_steps": 250,
|
| 2282 |
+
"total_flos": 6.250904333773187e+17,
|
| 2283 |
+
"train_batch_size": 4,
|
| 2284 |
+
"trial_name": null,
|
| 2285 |
+
"trial_params": null
|
| 2286 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aa409b842e6508386b92f28b3d9a90969b3355d546c84d641c78491d8d4d0e8
|
| 3 |
+
size 6712
|