End of training
Browse files- README.md +92 -0
- all_results.json +22 -0
- config.json +42 -0
- eval_results.json +17 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- runs/Feb02_18-14-01_modal/events.out.tfevents.1738520042.modal.2.0 +3 -0
- runs/Feb02_18-14-01_modal/events.out.tfevents.1738520042.modal.2.1 +3 -0
- runs/Feb02_18-14-01_modal/events.out.tfevents.1738520607.modal.2.2 +3 -0
- runs/Feb02_18-14-01_modal/events.out.tfevents.1738520607.modal.2.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +2432 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: squarerun2
|
| 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 |
+
# squarerun2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.4284
|
| 22 |
+
- F1 Macro: 0.4676
|
| 23 |
+
- F1 Micro: 0.5606
|
| 24 |
+
- F1 Weighted: 0.5361
|
| 25 |
+
- Precision Macro: 0.4718
|
| 26 |
+
- Precision Micro: 0.5606
|
| 27 |
+
- Precision Weighted: 0.5334
|
| 28 |
+
- Recall Macro: 0.4835
|
| 29 |
+
- Recall Micro: 0.5606
|
| 30 |
+
- Recall Weighted: 0.5606
|
| 31 |
+
- Accuracy: 0.5606
|
| 32 |
+
|
| 33 |
+
## Model description
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Intended uses & limitations
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training and evaluation data
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training procedure
|
| 46 |
+
|
| 47 |
+
### Training hyperparameters
|
| 48 |
+
|
| 49 |
+
The following hyperparameters were used during training:
|
| 50 |
+
- learning_rate: 0.0001
|
| 51 |
+
- train_batch_size: 8
|
| 52 |
+
- eval_batch_size: 8
|
| 53 |
+
- seed: 42
|
| 54 |
+
- gradient_accumulation_steps: 2
|
| 55 |
+
- total_train_batch_size: 16
|
| 56 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 57 |
+
- lr_scheduler_type: linear
|
| 58 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 59 |
+
- num_epochs: 20
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | F1 Weighted | Precision Macro | Precision Micro | Precision Weighted | Recall Macro | Recall Micro | Recall Weighted | Accuracy |
|
| 64 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:---------------:|:------------------:|:------------:|:------------:|:---------------:|:--------:|
|
| 65 |
+
| 1.9016 | 1.0 | 29 | 1.8764 | 0.1011 | 0.2424 | 0.1401 | 0.0721 | 0.2424 | 0.1001 | 0.1761 | 0.2424 | 0.2424 | 0.2424 |
|
| 66 |
+
| 1.8787 | 2.0 | 58 | 1.8750 | 0.0485 | 0.2045 | 0.0695 | 0.0292 | 0.2045 | 0.0418 | 0.1429 | 0.2045 | 0.2045 | 0.2045 |
|
| 67 |
+
| 1.9345 | 3.0 | 87 | 1.8624 | 0.0485 | 0.2045 | 0.0695 | 0.0292 | 0.2045 | 0.0418 | 0.1429 | 0.2045 | 0.2045 | 0.2045 |
|
| 68 |
+
| 1.6663 | 4.0 | 116 | 1.7239 | 0.2230 | 0.3561 | 0.2738 | 0.3173 | 0.3561 | 0.3549 | 0.2725 | 0.3561 | 0.3561 | 0.3561 |
|
| 69 |
+
| 1.3847 | 5.0 | 145 | 1.4880 | 0.3420 | 0.4697 | 0.4038 | 0.4521 | 0.4697 | 0.4846 | 0.3893 | 0.4697 | 0.4697 | 0.4697 |
|
| 70 |
+
| 1.6559 | 6.0 | 174 | 1.4056 | 0.3479 | 0.4773 | 0.4108 | 0.3865 | 0.4773 | 0.4276 | 0.3870 | 0.4773 | 0.4773 | 0.4773 |
|
| 71 |
+
| 1.335 | 7.0 | 203 | 1.3768 | 0.3875 | 0.5152 | 0.4527 | 0.3933 | 0.5152 | 0.4447 | 0.4265 | 0.5152 | 0.5152 | 0.5152 |
|
| 72 |
+
| 1.2514 | 8.0 | 232 | 1.2345 | 0.4536 | 0.5606 | 0.5207 | 0.4701 | 0.5606 | 0.5257 | 0.4766 | 0.5606 | 0.5606 | 0.5606 |
|
| 73 |
+
| 0.6979 | 9.0 | 261 | 1.1501 | 0.5305 | 0.6364 | 0.6097 | 0.5491 | 0.6364 | 0.6127 | 0.5391 | 0.6364 | 0.6364 | 0.6364 |
|
| 74 |
+
| 1.0417 | 10.0 | 290 | 1.1654 | 0.5206 | 0.6136 | 0.5900 | 0.5215 | 0.6136 | 0.5935 | 0.5464 | 0.6136 | 0.6136 | 0.6136 |
|
| 75 |
+
| 0.7314 | 11.0 | 319 | 1.1566 | 0.5376 | 0.6212 | 0.6109 | 0.5387 | 0.6212 | 0.6154 | 0.5514 | 0.6212 | 0.6212 | 0.6212 |
|
| 76 |
+
| 0.7902 | 12.0 | 348 | 1.1624 | 0.5397 | 0.6212 | 0.6140 | 0.5422 | 0.6212 | 0.6209 | 0.5505 | 0.6212 | 0.6212 | 0.6212 |
|
| 77 |
+
| 0.7503 | 13.0 | 377 | 1.1359 | 0.5377 | 0.6288 | 0.6126 | 0.5472 | 0.6288 | 0.6143 | 0.5455 | 0.6288 | 0.6288 | 0.6288 |
|
| 78 |
+
| 0.586 | 14.0 | 406 | 1.1512 | 0.5441 | 0.6288 | 0.6141 | 0.5361 | 0.6288 | 0.6033 | 0.5557 | 0.6288 | 0.6288 | 0.6288 |
|
| 79 |
+
| 0.6869 | 15.0 | 435 | 1.1306 | 0.5323 | 0.6288 | 0.6117 | 0.5270 | 0.6288 | 0.6043 | 0.5475 | 0.6288 | 0.6288 | 0.6288 |
|
| 80 |
+
| 0.5498 | 16.0 | 464 | 1.1293 | 0.5373 | 0.6288 | 0.6117 | 0.5353 | 0.6288 | 0.6039 | 0.5471 | 0.6288 | 0.6288 | 0.6288 |
|
| 81 |
+
| 0.5037 | 17.0 | 493 | 1.1635 | 0.5290 | 0.6212 | 0.6005 | 0.5374 | 0.6212 | 0.6022 | 0.5398 | 0.6212 | 0.6212 | 0.6212 |
|
| 82 |
+
| 0.3624 | 18.0 | 522 | 1.0994 | 0.5700 | 0.6591 | 0.6414 | 0.5815 | 0.6591 | 0.6409 | 0.5743 | 0.6591 | 0.6591 | 0.6591 |
|
| 83 |
+
| 0.3387 | 19.0 | 551 | 1.0944 | 0.5643 | 0.6515 | 0.6367 | 0.5556 | 0.6515 | 0.6268 | 0.5781 | 0.6515 | 0.6515 | 0.6515 |
|
| 84 |
+
| 0.4052 | 20.0 | 580 | 1.0934 | 0.5683 | 0.6591 | 0.6432 | 0.5681 | 0.6591 | 0.6393 | 0.5798 | 0.6591 | 0.6591 | 0.6591 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.48.1
|
| 90 |
+
- Pytorch 2.5.1+cu124
|
| 91 |
+
- Datasets 3.2.0
|
| 92 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.5606060606060606,
|
| 4 |
+
"eval_f1_macro": 0.46758403361344536,
|
| 5 |
+
"eval_f1_micro": 0.5606060606060606,
|
| 6 |
+
"eval_f1_weighted": 0.5360739750445633,
|
| 7 |
+
"eval_loss": 1.4283688068389893,
|
| 8 |
+
"eval_precision_macro": 0.4717948717948718,
|
| 9 |
+
"eval_precision_micro": 0.5606060606060606,
|
| 10 |
+
"eval_precision_weighted": 0.5334387834387835,
|
| 11 |
+
"eval_recall_macro": 0.48350340136054426,
|
| 12 |
+
"eval_recall_micro": 0.5606060606060606,
|
| 13 |
+
"eval_recall_weighted": 0.5606060606060606,
|
| 14 |
+
"eval_runtime": 1.2017,
|
| 15 |
+
"eval_samples_per_second": 54.922,
|
| 16 |
+
"eval_steps_per_second": 7.489,
|
| 17 |
+
"total_flos": 7.160580716109005e+17,
|
| 18 |
+
"train_loss": 1.0144407548781098,
|
| 19 |
+
"train_runtime": 564.1231,
|
| 20 |
+
"train_samples_per_second": 16.379,
|
| 21 |
+
"train_steps_per_second": 1.028
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "-",
|
| 13 |
+
"1": "0",
|
| 14 |
+
"2": "1",
|
| 15 |
+
"3": "2",
|
| 16 |
+
"4": "3",
|
| 17 |
+
"5": "4",
|
| 18 |
+
"6": "5"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"-": "0",
|
| 25 |
+
"0": "1",
|
| 26 |
+
"1": "2",
|
| 27 |
+
"2": "3",
|
| 28 |
+
"3": "4",
|
| 29 |
+
"4": "5",
|
| 30 |
+
"5": "6"
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"qkv_bias": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.48.1"
|
| 42 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.5606060606060606,
|
| 4 |
+
"eval_f1_macro": 0.46758403361344536,
|
| 5 |
+
"eval_f1_micro": 0.5606060606060606,
|
| 6 |
+
"eval_f1_weighted": 0.5360739750445633,
|
| 7 |
+
"eval_loss": 1.4283688068389893,
|
| 8 |
+
"eval_precision_macro": 0.4717948717948718,
|
| 9 |
+
"eval_precision_micro": 0.5606060606060606,
|
| 10 |
+
"eval_precision_weighted": 0.5334387834387835,
|
| 11 |
+
"eval_recall_macro": 0.48350340136054426,
|
| 12 |
+
"eval_recall_micro": 0.5606060606060606,
|
| 13 |
+
"eval_recall_weighted": 0.5606060606060606,
|
| 14 |
+
"eval_runtime": 1.2017,
|
| 15 |
+
"eval_samples_per_second": 54.922,
|
| 16 |
+
"eval_steps_per_second": 7.489
|
| 17 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c753e072b68e1af8805e209f25b589f002957f45467f7ff14b69e616432ddc98
|
| 3 |
+
size 343239356
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessorFast",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
runs/Feb02_18-14-01_modal/events.out.tfevents.1738520042.modal.2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c7616db421a43793d614e421ba09cb193c74dd2a58d06d88a2c59fd29bbcc1b
|
| 3 |
+
size 83019
|
runs/Feb02_18-14-01_modal/events.out.tfevents.1738520042.modal.2.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c42e5a1604c54a7ed848701590fd8d02bbf8716c1bce0d69f0514f8c584c1161
|
| 3 |
+
size 83019
|
runs/Feb02_18-14-01_modal/events.out.tfevents.1738520607.modal.2.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0033bea0f144513bb338479a3caae14601c4f56b98bd97b5222445a0080c7dd4
|
| 3 |
+
size 921
|
runs/Feb02_18-14-01_modal/events.out.tfevents.1738520607.modal.2.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e23c5d7fad24087d2f921edf87f4e1e52fedace4f61b8d0d34d2537229a6785c
|
| 3 |
+
size 921
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 7.160580716109005e+17,
|
| 4 |
+
"train_loss": 1.0144407548781098,
|
| 5 |
+
"train_runtime": 564.1231,
|
| 6 |
+
"train_samples_per_second": 16.379,
|
| 7 |
+
"train_steps_per_second": 1.028
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6590909090909091,
|
| 3 |
+
"best_model_checkpoint": "squarerun2/checkpoint-522",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 580,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06896551724137931,
|
| 13 |
+
"grad_norm": 2.9724416732788086,
|
| 14 |
+
"learning_rate": 3.448275862068966e-06,
|
| 15 |
+
"loss": 1.9767,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13793103448275862,
|
| 20 |
+
"grad_norm": 1.7837220430374146,
|
| 21 |
+
"learning_rate": 6.896551724137932e-06,
|
| 22 |
+
"loss": 1.9373,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.20689655172413793,
|
| 27 |
+
"grad_norm": 1.9200481176376343,
|
| 28 |
+
"learning_rate": 1.0344827586206897e-05,
|
| 29 |
+
"loss": 1.9422,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.27586206896551724,
|
| 34 |
+
"grad_norm": 1.8607347011566162,
|
| 35 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 36 |
+
"loss": 1.9203,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3448275862068966,
|
| 41 |
+
"grad_norm": 2.282787322998047,
|
| 42 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 43 |
+
"loss": 1.8967,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.41379310344827586,
|
| 48 |
+
"grad_norm": 1.8788440227508545,
|
| 49 |
+
"learning_rate": 2.0689655172413793e-05,
|
| 50 |
+
"loss": 1.9576,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4827586206896552,
|
| 55 |
+
"grad_norm": 1.689126968383789,
|
| 56 |
+
"learning_rate": 2.413793103448276e-05,
|
| 57 |
+
"loss": 1.9238,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5517241379310345,
|
| 62 |
+
"grad_norm": 1.5710227489471436,
|
| 63 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 64 |
+
"loss": 1.9468,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.6206896551724138,
|
| 69 |
+
"grad_norm": 1.6929808855056763,
|
| 70 |
+
"learning_rate": 3.103448275862069e-05,
|
| 71 |
+
"loss": 1.83,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6896551724137931,
|
| 76 |
+
"grad_norm": 1.9147762060165405,
|
| 77 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 78 |
+
"loss": 1.8844,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.7586206896551724,
|
| 83 |
+
"grad_norm": 1.0664433240890503,
|
| 84 |
+
"learning_rate": 3.793103448275862e-05,
|
| 85 |
+
"loss": 1.8893,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.8275862068965517,
|
| 90 |
+
"grad_norm": 1.2909166812896729,
|
| 91 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 92 |
+
"loss": 1.8794,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.896551724137931,
|
| 97 |
+
"grad_norm": 2.562612771987915,
|
| 98 |
+
"learning_rate": 4.482758620689655e-05,
|
| 99 |
+
"loss": 1.8722,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.9655172413793104,
|
| 104 |
+
"grad_norm": 1.766555905342102,
|
| 105 |
+
"learning_rate": 4.827586206896552e-05,
|
| 106 |
+
"loss": 1.9016,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0,
|
| 111 |
+
"eval_accuracy": 0.24242424242424243,
|
| 112 |
+
"eval_f1_macro": 0.1010989010989011,
|
| 113 |
+
"eval_f1_micro": 0.24242424242424243,
|
| 114 |
+
"eval_f1_weighted": 0.14009324009324012,
|
| 115 |
+
"eval_loss": 1.8763961791992188,
|
| 116 |
+
"eval_precision_macro": 0.07205977686035006,
|
| 117 |
+
"eval_precision_micro": 0.24242424242424243,
|
| 118 |
+
"eval_precision_weighted": 0.10010783738990092,
|
| 119 |
+
"eval_recall_macro": 0.1760846560846561,
|
| 120 |
+
"eval_recall_micro": 0.24242424242424243,
|
| 121 |
+
"eval_recall_weighted": 0.24242424242424243,
|
| 122 |
+
"eval_runtime": 2.3126,
|
| 123 |
+
"eval_samples_per_second": 57.08,
|
| 124 |
+
"eval_steps_per_second": 7.351,
|
| 125 |
+
"step": 29
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.0344827586206897,
|
| 129 |
+
"grad_norm": 2.116236448287964,
|
| 130 |
+
"learning_rate": 5.172413793103449e-05,
|
| 131 |
+
"loss": 1.9127,
|
| 132 |
+
"step": 30
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.103448275862069,
|
| 136 |
+
"grad_norm": 1.5244780778884888,
|
| 137 |
+
"learning_rate": 5.517241379310345e-05,
|
| 138 |
+
"loss": 1.8217,
|
| 139 |
+
"step": 32
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.1724137931034484,
|
| 143 |
+
"grad_norm": 1.2253153324127197,
|
| 144 |
+
"learning_rate": 5.862068965517241e-05,
|
| 145 |
+
"loss": 1.8662,
|
| 146 |
+
"step": 34
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.2413793103448276,
|
| 150 |
+
"grad_norm": 1.1567929983139038,
|
| 151 |
+
"learning_rate": 6.206896551724138e-05,
|
| 152 |
+
"loss": 1.9031,
|
| 153 |
+
"step": 36
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.3103448275862069,
|
| 157 |
+
"grad_norm": 1.4619667530059814,
|
| 158 |
+
"learning_rate": 6.551724137931034e-05,
|
| 159 |
+
"loss": 1.8464,
|
| 160 |
+
"step": 38
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.3793103448275863,
|
| 164 |
+
"grad_norm": 1.5786610841751099,
|
| 165 |
+
"learning_rate": 6.896551724137931e-05,
|
| 166 |
+
"loss": 1.9057,
|
| 167 |
+
"step": 40
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.4482758620689655,
|
| 171 |
+
"grad_norm": 1.1554012298583984,
|
| 172 |
+
"learning_rate": 7.241379310344828e-05,
|
| 173 |
+
"loss": 1.8748,
|
| 174 |
+
"step": 42
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.5172413793103448,
|
| 178 |
+
"grad_norm": 2.0982630252838135,
|
| 179 |
+
"learning_rate": 7.586206896551724e-05,
|
| 180 |
+
"loss": 1.9052,
|
| 181 |
+
"step": 44
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.5862068965517242,
|
| 185 |
+
"grad_norm": 1.046858787536621,
|
| 186 |
+
"learning_rate": 7.931034482758621e-05,
|
| 187 |
+
"loss": 1.9363,
|
| 188 |
+
"step": 46
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.6551724137931034,
|
| 192 |
+
"grad_norm": 1.05802583694458,
|
| 193 |
+
"learning_rate": 8.275862068965517e-05,
|
| 194 |
+
"loss": 1.8712,
|
| 195 |
+
"step": 48
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.7241379310344827,
|
| 199 |
+
"grad_norm": 1.0946681499481201,
|
| 200 |
+
"learning_rate": 8.620689655172413e-05,
|
| 201 |
+
"loss": 1.9325,
|
| 202 |
+
"step": 50
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.793103448275862,
|
| 206 |
+
"grad_norm": 1.3410812616348267,
|
| 207 |
+
"learning_rate": 8.96551724137931e-05,
|
| 208 |
+
"loss": 1.8671,
|
| 209 |
+
"step": 52
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.8620689655172413,
|
| 213 |
+
"grad_norm": 1.4638521671295166,
|
| 214 |
+
"learning_rate": 9.310344827586207e-05,
|
| 215 |
+
"loss": 1.9462,
|
| 216 |
+
"step": 54
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.9310344827586206,
|
| 220 |
+
"grad_norm": 1.6821434497833252,
|
| 221 |
+
"learning_rate": 9.655172413793105e-05,
|
| 222 |
+
"loss": 1.8823,
|
| 223 |
+
"step": 56
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.0,
|
| 227 |
+
"grad_norm": 0.771202564239502,
|
| 228 |
+
"learning_rate": 0.0001,
|
| 229 |
+
"loss": 1.8787,
|
| 230 |
+
"step": 58
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.0,
|
| 234 |
+
"eval_accuracy": 0.20454545454545456,
|
| 235 |
+
"eval_f1_macro": 0.04851752021563342,
|
| 236 |
+
"eval_f1_micro": 0.20454545454545456,
|
| 237 |
+
"eval_f1_weighted": 0.06946826758147512,
|
| 238 |
+
"eval_loss": 1.8749967813491821,
|
| 239 |
+
"eval_precision_macro": 0.029220779220779224,
|
| 240 |
+
"eval_precision_micro": 0.20454545454545456,
|
| 241 |
+
"eval_precision_weighted": 0.04183884297520662,
|
| 242 |
+
"eval_recall_macro": 0.14285714285714285,
|
| 243 |
+
"eval_recall_micro": 0.20454545454545456,
|
| 244 |
+
"eval_recall_weighted": 0.20454545454545456,
|
| 245 |
+
"eval_runtime": 2.315,
|
| 246 |
+
"eval_samples_per_second": 57.02,
|
| 247 |
+
"eval_steps_per_second": 7.343,
|
| 248 |
+
"step": 58
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.0689655172413794,
|
| 252 |
+
"grad_norm": 1.4094064235687256,
|
| 253 |
+
"learning_rate": 9.96168582375479e-05,
|
| 254 |
+
"loss": 1.9068,
|
| 255 |
+
"step": 60
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.1379310344827585,
|
| 259 |
+
"grad_norm": 0.7938138246536255,
|
| 260 |
+
"learning_rate": 9.92337164750958e-05,
|
| 261 |
+
"loss": 1.847,
|
| 262 |
+
"step": 62
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.206896551724138,
|
| 266 |
+
"grad_norm": 1.7750108242034912,
|
| 267 |
+
"learning_rate": 9.885057471264369e-05,
|
| 268 |
+
"loss": 1.8632,
|
| 269 |
+
"step": 64
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.2758620689655173,
|
| 273 |
+
"grad_norm": 2.120215654373169,
|
| 274 |
+
"learning_rate": 9.846743295019157e-05,
|
| 275 |
+
"loss": 1.9374,
|
| 276 |
+
"step": 66
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.344827586206897,
|
| 280 |
+
"grad_norm": 1.1951868534088135,
|
| 281 |
+
"learning_rate": 9.808429118773947e-05,
|
| 282 |
+
"loss": 1.789,
|
| 283 |
+
"step": 68
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.413793103448276,
|
| 287 |
+
"grad_norm": 1.5802347660064697,
|
| 288 |
+
"learning_rate": 9.770114942528736e-05,
|
| 289 |
+
"loss": 1.8232,
|
| 290 |
+
"step": 70
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.4827586206896552,
|
| 294 |
+
"grad_norm": 1.5989313125610352,
|
| 295 |
+
"learning_rate": 9.731800766283526e-05,
|
| 296 |
+
"loss": 1.9379,
|
| 297 |
+
"step": 72
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.5517241379310347,
|
| 301 |
+
"grad_norm": 1.3577500581741333,
|
| 302 |
+
"learning_rate": 9.693486590038314e-05,
|
| 303 |
+
"loss": 1.905,
|
| 304 |
+
"step": 74
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.6206896551724137,
|
| 308 |
+
"grad_norm": 1.2363930940628052,
|
| 309 |
+
"learning_rate": 9.655172413793105e-05,
|
| 310 |
+
"loss": 1.8514,
|
| 311 |
+
"step": 76
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.689655172413793,
|
| 315 |
+
"grad_norm": 1.6196924448013306,
|
| 316 |
+
"learning_rate": 9.616858237547893e-05,
|
| 317 |
+
"loss": 1.9273,
|
| 318 |
+
"step": 78
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.7586206896551726,
|
| 322 |
+
"grad_norm": 1.13129460811615,
|
| 323 |
+
"learning_rate": 9.578544061302682e-05,
|
| 324 |
+
"loss": 1.9407,
|
| 325 |
+
"step": 80
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.8275862068965516,
|
| 329 |
+
"grad_norm": 1.0212408304214478,
|
| 330 |
+
"learning_rate": 9.540229885057472e-05,
|
| 331 |
+
"loss": 1.8273,
|
| 332 |
+
"step": 82
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.896551724137931,
|
| 336 |
+
"grad_norm": 0.8608859777450562,
|
| 337 |
+
"learning_rate": 9.501915708812261e-05,
|
| 338 |
+
"loss": 1.8769,
|
| 339 |
+
"step": 84
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.9655172413793105,
|
| 343 |
+
"grad_norm": 1.2102094888687134,
|
| 344 |
+
"learning_rate": 9.463601532567051e-05,
|
| 345 |
+
"loss": 1.9345,
|
| 346 |
+
"step": 86
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.0,
|
| 350 |
+
"eval_accuracy": 0.20454545454545456,
|
| 351 |
+
"eval_f1_macro": 0.04851752021563342,
|
| 352 |
+
"eval_f1_micro": 0.20454545454545456,
|
| 353 |
+
"eval_f1_weighted": 0.06946826758147512,
|
| 354 |
+
"eval_loss": 1.8624200820922852,
|
| 355 |
+
"eval_precision_macro": 0.029220779220779224,
|
| 356 |
+
"eval_precision_micro": 0.20454545454545456,
|
| 357 |
+
"eval_precision_weighted": 0.04183884297520662,
|
| 358 |
+
"eval_recall_macro": 0.14285714285714285,
|
| 359 |
+
"eval_recall_micro": 0.20454545454545456,
|
| 360 |
+
"eval_recall_weighted": 0.20454545454545456,
|
| 361 |
+
"eval_runtime": 2.3224,
|
| 362 |
+
"eval_samples_per_second": 56.838,
|
| 363 |
+
"eval_steps_per_second": 7.32,
|
| 364 |
+
"step": 87
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 3.0344827586206895,
|
| 368 |
+
"grad_norm": 1.7206976413726807,
|
| 369 |
+
"learning_rate": 9.425287356321839e-05,
|
| 370 |
+
"loss": 1.9875,
|
| 371 |
+
"step": 88
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.103448275862069,
|
| 375 |
+
"grad_norm": 1.0909031629562378,
|
| 376 |
+
"learning_rate": 9.38697318007663e-05,
|
| 377 |
+
"loss": 1.7979,
|
| 378 |
+
"step": 90
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.1724137931034484,
|
| 382 |
+
"grad_norm": 1.2875232696533203,
|
| 383 |
+
"learning_rate": 9.348659003831418e-05,
|
| 384 |
+
"loss": 1.8964,
|
| 385 |
+
"step": 92
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 3.2413793103448274,
|
| 389 |
+
"grad_norm": 1.6919517517089844,
|
| 390 |
+
"learning_rate": 9.310344827586207e-05,
|
| 391 |
+
"loss": 1.8316,
|
| 392 |
+
"step": 94
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.310344827586207,
|
| 396 |
+
"grad_norm": 1.7749555110931396,
|
| 397 |
+
"learning_rate": 9.272030651340997e-05,
|
| 398 |
+
"loss": 1.8712,
|
| 399 |
+
"step": 96
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.3793103448275863,
|
| 403 |
+
"grad_norm": 1.273366093635559,
|
| 404 |
+
"learning_rate": 9.233716475095786e-05,
|
| 405 |
+
"loss": 1.8105,
|
| 406 |
+
"step": 98
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 3.4482758620689653,
|
| 410 |
+
"grad_norm": 1.3420616388320923,
|
| 411 |
+
"learning_rate": 9.195402298850575e-05,
|
| 412 |
+
"loss": 1.7223,
|
| 413 |
+
"step": 100
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.5172413793103448,
|
| 417 |
+
"grad_norm": 2.060871124267578,
|
| 418 |
+
"learning_rate": 9.157088122605364e-05,
|
| 419 |
+
"loss": 1.9009,
|
| 420 |
+
"step": 102
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.586206896551724,
|
| 424 |
+
"grad_norm": 1.3717443943023682,
|
| 425 |
+
"learning_rate": 9.118773946360154e-05,
|
| 426 |
+
"loss": 1.7423,
|
| 427 |
+
"step": 104
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 3.655172413793103,
|
| 431 |
+
"grad_norm": 2.35315203666687,
|
| 432 |
+
"learning_rate": 9.080459770114943e-05,
|
| 433 |
+
"loss": 1.8381,
|
| 434 |
+
"step": 106
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.7241379310344827,
|
| 438 |
+
"grad_norm": 1.7000161409378052,
|
| 439 |
+
"learning_rate": 9.042145593869731e-05,
|
| 440 |
+
"loss": 1.6663,
|
| 441 |
+
"step": 108
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.793103448275862,
|
| 445 |
+
"grad_norm": 2.3289718627929688,
|
| 446 |
+
"learning_rate": 9.003831417624522e-05,
|
| 447 |
+
"loss": 1.7653,
|
| 448 |
+
"step": 110
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.862068965517241,
|
| 452 |
+
"grad_norm": 2.581888437271118,
|
| 453 |
+
"learning_rate": 8.96551724137931e-05,
|
| 454 |
+
"loss": 1.8899,
|
| 455 |
+
"step": 112
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.9310344827586206,
|
| 459 |
+
"grad_norm": 2.3343546390533447,
|
| 460 |
+
"learning_rate": 8.9272030651341e-05,
|
| 461 |
+
"loss": 1.7854,
|
| 462 |
+
"step": 114
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.0,
|
| 466 |
+
"grad_norm": 1.989835262298584,
|
| 467 |
+
"learning_rate": 8.888888888888889e-05,
|
| 468 |
+
"loss": 1.6663,
|
| 469 |
+
"step": 116
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 4.0,
|
| 473 |
+
"eval_accuracy": 0.3560606060606061,
|
| 474 |
+
"eval_f1_macro": 0.2230450801010059,
|
| 475 |
+
"eval_f1_micro": 0.3560606060606061,
|
| 476 |
+
"eval_f1_weighted": 0.27375266721108504,
|
| 477 |
+
"eval_loss": 1.7238999605178833,
|
| 478 |
+
"eval_precision_macro": 0.31727902915703876,
|
| 479 |
+
"eval_precision_micro": 0.3560606060606061,
|
| 480 |
+
"eval_precision_weighted": 0.3548852832560697,
|
| 481 |
+
"eval_recall_macro": 0.27251700680272106,
|
| 482 |
+
"eval_recall_micro": 0.3560606060606061,
|
| 483 |
+
"eval_recall_weighted": 0.3560606060606061,
|
| 484 |
+
"eval_runtime": 2.3156,
|
| 485 |
+
"eval_samples_per_second": 57.004,
|
| 486 |
+
"eval_steps_per_second": 7.341,
|
| 487 |
+
"step": 116
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 4.068965517241379,
|
| 491 |
+
"grad_norm": 2.951305389404297,
|
| 492 |
+
"learning_rate": 8.850574712643679e-05,
|
| 493 |
+
"loss": 1.6573,
|
| 494 |
+
"step": 118
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.137931034482759,
|
| 498 |
+
"grad_norm": 2.0035061836242676,
|
| 499 |
+
"learning_rate": 8.812260536398468e-05,
|
| 500 |
+
"loss": 1.5898,
|
| 501 |
+
"step": 120
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.206896551724138,
|
| 505 |
+
"grad_norm": 1.7943332195281982,
|
| 506 |
+
"learning_rate": 8.773946360153256e-05,
|
| 507 |
+
"loss": 1.5183,
|
| 508 |
+
"step": 122
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 4.275862068965517,
|
| 512 |
+
"grad_norm": 2.8160884380340576,
|
| 513 |
+
"learning_rate": 8.735632183908047e-05,
|
| 514 |
+
"loss": 1.3985,
|
| 515 |
+
"step": 124
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.344827586206897,
|
| 519 |
+
"grad_norm": 2.5276668071746826,
|
| 520 |
+
"learning_rate": 8.697318007662835e-05,
|
| 521 |
+
"loss": 1.5588,
|
| 522 |
+
"step": 126
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.413793103448276,
|
| 526 |
+
"grad_norm": 1.8822064399719238,
|
| 527 |
+
"learning_rate": 8.659003831417625e-05,
|
| 528 |
+
"loss": 1.6377,
|
| 529 |
+
"step": 128
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 4.482758620689655,
|
| 533 |
+
"grad_norm": 3.416983127593994,
|
| 534 |
+
"learning_rate": 8.620689655172413e-05,
|
| 535 |
+
"loss": 1.8148,
|
| 536 |
+
"step": 130
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.551724137931035,
|
| 540 |
+
"grad_norm": 3.465373992919922,
|
| 541 |
+
"learning_rate": 8.582375478927204e-05,
|
| 542 |
+
"loss": 1.7206,
|
| 543 |
+
"step": 132
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.620689655172414,
|
| 547 |
+
"grad_norm": 2.2419955730438232,
|
| 548 |
+
"learning_rate": 8.544061302681992e-05,
|
| 549 |
+
"loss": 1.8184,
|
| 550 |
+
"step": 134
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 4.689655172413794,
|
| 554 |
+
"grad_norm": 2.772228240966797,
|
| 555 |
+
"learning_rate": 8.505747126436782e-05,
|
| 556 |
+
"loss": 1.6022,
|
| 557 |
+
"step": 136
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 4.758620689655173,
|
| 561 |
+
"grad_norm": 2.6388156414031982,
|
| 562 |
+
"learning_rate": 8.467432950191571e-05,
|
| 563 |
+
"loss": 1.5941,
|
| 564 |
+
"step": 138
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 4.827586206896552,
|
| 568 |
+
"grad_norm": 2.489682674407959,
|
| 569 |
+
"learning_rate": 8.42911877394636e-05,
|
| 570 |
+
"loss": 1.476,
|
| 571 |
+
"step": 140
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 4.896551724137931,
|
| 575 |
+
"grad_norm": 2.517737865447998,
|
| 576 |
+
"learning_rate": 8.39080459770115e-05,
|
| 577 |
+
"loss": 1.5529,
|
| 578 |
+
"step": 142
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.9655172413793105,
|
| 582 |
+
"grad_norm": 1.9954488277435303,
|
| 583 |
+
"learning_rate": 8.35249042145594e-05,
|
| 584 |
+
"loss": 1.3847,
|
| 585 |
+
"step": 144
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 5.0,
|
| 589 |
+
"eval_accuracy": 0.4696969696969697,
|
| 590 |
+
"eval_f1_macro": 0.3420460214829701,
|
| 591 |
+
"eval_f1_micro": 0.4696969696969697,
|
| 592 |
+
"eval_f1_weighted": 0.4038214256266929,
|
| 593 |
+
"eval_loss": 1.4879895448684692,
|
| 594 |
+
"eval_precision_macro": 0.4520649449711235,
|
| 595 |
+
"eval_precision_micro": 0.4696969696969697,
|
| 596 |
+
"eval_precision_weighted": 0.4845688001294408,
|
| 597 |
+
"eval_recall_macro": 0.38925170068027215,
|
| 598 |
+
"eval_recall_micro": 0.4696969696969697,
|
| 599 |
+
"eval_recall_weighted": 0.4696969696969697,
|
| 600 |
+
"eval_runtime": 2.3198,
|
| 601 |
+
"eval_samples_per_second": 56.9,
|
| 602 |
+
"eval_steps_per_second": 7.328,
|
| 603 |
+
"step": 145
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.0344827586206895,
|
| 607 |
+
"grad_norm": 2.7297556400299072,
|
| 608 |
+
"learning_rate": 8.314176245210729e-05,
|
| 609 |
+
"loss": 1.6994,
|
| 610 |
+
"step": 146
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 5.103448275862069,
|
| 614 |
+
"grad_norm": 2.7157135009765625,
|
| 615 |
+
"learning_rate": 8.275862068965517e-05,
|
| 616 |
+
"loss": 1.409,
|
| 617 |
+
"step": 148
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.172413793103448,
|
| 621 |
+
"grad_norm": 3.6584227085113525,
|
| 622 |
+
"learning_rate": 8.237547892720307e-05,
|
| 623 |
+
"loss": 1.3627,
|
| 624 |
+
"step": 150
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.241379310344827,
|
| 628 |
+
"grad_norm": 2.6041762828826904,
|
| 629 |
+
"learning_rate": 8.199233716475096e-05,
|
| 630 |
+
"loss": 1.3385,
|
| 631 |
+
"step": 152
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 5.310344827586207,
|
| 635 |
+
"grad_norm": 2.7281856536865234,
|
| 636 |
+
"learning_rate": 8.160919540229886e-05,
|
| 637 |
+
"loss": 1.4468,
|
| 638 |
+
"step": 154
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 5.379310344827586,
|
| 642 |
+
"grad_norm": 2.5631356239318848,
|
| 643 |
+
"learning_rate": 8.122605363984674e-05,
|
| 644 |
+
"loss": 1.3639,
|
| 645 |
+
"step": 156
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.448275862068965,
|
| 649 |
+
"grad_norm": 3.118602991104126,
|
| 650 |
+
"learning_rate": 8.084291187739465e-05,
|
| 651 |
+
"loss": 1.5097,
|
| 652 |
+
"step": 158
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 5.517241379310345,
|
| 656 |
+
"grad_norm": 2.653867483139038,
|
| 657 |
+
"learning_rate": 8.045977011494253e-05,
|
| 658 |
+
"loss": 1.3556,
|
| 659 |
+
"step": 160
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.586206896551724,
|
| 663 |
+
"grad_norm": 2.3653130531311035,
|
| 664 |
+
"learning_rate": 8.007662835249042e-05,
|
| 665 |
+
"loss": 1.504,
|
| 666 |
+
"step": 162
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.655172413793103,
|
| 670 |
+
"grad_norm": 2.039597749710083,
|
| 671 |
+
"learning_rate": 7.969348659003832e-05,
|
| 672 |
+
"loss": 1.3222,
|
| 673 |
+
"step": 164
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 5.724137931034483,
|
| 677 |
+
"grad_norm": 2.91522216796875,
|
| 678 |
+
"learning_rate": 7.931034482758621e-05,
|
| 679 |
+
"loss": 1.2761,
|
| 680 |
+
"step": 166
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 5.793103448275862,
|
| 684 |
+
"grad_norm": 2.8554606437683105,
|
| 685 |
+
"learning_rate": 7.892720306513411e-05,
|
| 686 |
+
"loss": 1.3019,
|
| 687 |
+
"step": 168
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 5.862068965517241,
|
| 691 |
+
"grad_norm": 3.730526924133301,
|
| 692 |
+
"learning_rate": 7.854406130268199e-05,
|
| 693 |
+
"loss": 1.2626,
|
| 694 |
+
"step": 170
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 5.931034482758621,
|
| 698 |
+
"grad_norm": 5.193080425262451,
|
| 699 |
+
"learning_rate": 7.81609195402299e-05,
|
| 700 |
+
"loss": 1.5394,
|
| 701 |
+
"step": 172
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 6.0,
|
| 705 |
+
"grad_norm": 2.901132583618164,
|
| 706 |
+
"learning_rate": 7.777777777777778e-05,
|
| 707 |
+
"loss": 1.6559,
|
| 708 |
+
"step": 174
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 6.0,
|
| 712 |
+
"eval_accuracy": 0.4772727272727273,
|
| 713 |
+
"eval_f1_macro": 0.3479108279730525,
|
| 714 |
+
"eval_f1_micro": 0.4772727272727273,
|
| 715 |
+
"eval_f1_weighted": 0.4108418905152118,
|
| 716 |
+
"eval_loss": 1.4056475162506104,
|
| 717 |
+
"eval_precision_macro": 0.3864548957927566,
|
| 718 |
+
"eval_precision_micro": 0.4772727272727273,
|
| 719 |
+
"eval_precision_weighted": 0.42757837676034927,
|
| 720 |
+
"eval_recall_macro": 0.38701436130007555,
|
| 721 |
+
"eval_recall_micro": 0.4772727272727273,
|
| 722 |
+
"eval_recall_weighted": 0.4772727272727273,
|
| 723 |
+
"eval_runtime": 2.3209,
|
| 724 |
+
"eval_samples_per_second": 56.874,
|
| 725 |
+
"eval_steps_per_second": 7.325,
|
| 726 |
+
"step": 174
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 6.068965517241379,
|
| 730 |
+
"grad_norm": 3.3514347076416016,
|
| 731 |
+
"learning_rate": 7.739463601532568e-05,
|
| 732 |
+
"loss": 1.2022,
|
| 733 |
+
"step": 176
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 6.137931034482759,
|
| 737 |
+
"grad_norm": 2.6016125679016113,
|
| 738 |
+
"learning_rate": 7.701149425287356e-05,
|
| 739 |
+
"loss": 1.1793,
|
| 740 |
+
"step": 178
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 6.206896551724138,
|
| 744 |
+
"grad_norm": 3.9388816356658936,
|
| 745 |
+
"learning_rate": 7.662835249042147e-05,
|
| 746 |
+
"loss": 1.2841,
|
| 747 |
+
"step": 180
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 6.275862068965517,
|
| 751 |
+
"grad_norm": 2.01733660697937,
|
| 752 |
+
"learning_rate": 7.624521072796935e-05,
|
| 753 |
+
"loss": 1.3875,
|
| 754 |
+
"step": 182
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 6.344827586206897,
|
| 758 |
+
"grad_norm": 2.873060703277588,
|
| 759 |
+
"learning_rate": 7.586206896551724e-05,
|
| 760 |
+
"loss": 1.3029,
|
| 761 |
+
"step": 184
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 6.413793103448276,
|
| 765 |
+
"grad_norm": 3.8860301971435547,
|
| 766 |
+
"learning_rate": 7.547892720306514e-05,
|
| 767 |
+
"loss": 1.0694,
|
| 768 |
+
"step": 186
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 6.482758620689655,
|
| 772 |
+
"grad_norm": 4.136936664581299,
|
| 773 |
+
"learning_rate": 7.509578544061303e-05,
|
| 774 |
+
"loss": 1.0778,
|
| 775 |
+
"step": 188
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 6.551724137931035,
|
| 779 |
+
"grad_norm": 2.326791763305664,
|
| 780 |
+
"learning_rate": 7.471264367816091e-05,
|
| 781 |
+
"loss": 1.2761,
|
| 782 |
+
"step": 190
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 6.620689655172414,
|
| 786 |
+
"grad_norm": 3.5550026893615723,
|
| 787 |
+
"learning_rate": 7.432950191570882e-05,
|
| 788 |
+
"loss": 1.3036,
|
| 789 |
+
"step": 192
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.689655172413794,
|
| 793 |
+
"grad_norm": 2.3610475063323975,
|
| 794 |
+
"learning_rate": 7.39463601532567e-05,
|
| 795 |
+
"loss": 1.2765,
|
| 796 |
+
"step": 194
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 6.758620689655173,
|
| 800 |
+
"grad_norm": 3.0064663887023926,
|
| 801 |
+
"learning_rate": 7.35632183908046e-05,
|
| 802 |
+
"loss": 1.5579,
|
| 803 |
+
"step": 196
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 6.827586206896552,
|
| 807 |
+
"grad_norm": 2.8558247089385986,
|
| 808 |
+
"learning_rate": 7.31800766283525e-05,
|
| 809 |
+
"loss": 1.1987,
|
| 810 |
+
"step": 198
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 6.896551724137931,
|
| 814 |
+
"grad_norm": 3.3801021575927734,
|
| 815 |
+
"learning_rate": 7.279693486590039e-05,
|
| 816 |
+
"loss": 1.1622,
|
| 817 |
+
"step": 200
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 6.9655172413793105,
|
| 821 |
+
"grad_norm": 3.4124093055725098,
|
| 822 |
+
"learning_rate": 7.241379310344828e-05,
|
| 823 |
+
"loss": 1.335,
|
| 824 |
+
"step": 202
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 7.0,
|
| 828 |
+
"eval_accuracy": 0.5151515151515151,
|
| 829 |
+
"eval_f1_macro": 0.38747536212974004,
|
| 830 |
+
"eval_f1_micro": 0.5151515151515151,
|
| 831 |
+
"eval_f1_weighted": 0.4526784325171422,
|
| 832 |
+
"eval_loss": 1.3767547607421875,
|
| 833 |
+
"eval_precision_macro": 0.3933148791431466,
|
| 834 |
+
"eval_precision_micro": 0.5151515151515151,
|
| 835 |
+
"eval_precision_weighted": 0.44469956019158147,
|
| 836 |
+
"eval_recall_macro": 0.4265457294028723,
|
| 837 |
+
"eval_recall_micro": 0.5151515151515151,
|
| 838 |
+
"eval_recall_weighted": 0.5151515151515151,
|
| 839 |
+
"eval_runtime": 2.312,
|
| 840 |
+
"eval_samples_per_second": 57.094,
|
| 841 |
+
"eval_steps_per_second": 7.353,
|
| 842 |
+
"step": 203
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 7.0344827586206895,
|
| 846 |
+
"grad_norm": 3.0827553272247314,
|
| 847 |
+
"learning_rate": 7.203065134099617e-05,
|
| 848 |
+
"loss": 1.0667,
|
| 849 |
+
"step": 204
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 7.103448275862069,
|
| 853 |
+
"grad_norm": 1.9460029602050781,
|
| 854 |
+
"learning_rate": 7.164750957854408e-05,
|
| 855 |
+
"loss": 1.0915,
|
| 856 |
+
"step": 206
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 7.172413793103448,
|
| 860 |
+
"grad_norm": 3.7591891288757324,
|
| 861 |
+
"learning_rate": 7.126436781609196e-05,
|
| 862 |
+
"loss": 1.2813,
|
| 863 |
+
"step": 208
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 7.241379310344827,
|
| 867 |
+
"grad_norm": 2.6194112300872803,
|
| 868 |
+
"learning_rate": 7.088122605363985e-05,
|
| 869 |
+
"loss": 1.1527,
|
| 870 |
+
"step": 210
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 7.310344827586207,
|
| 874 |
+
"grad_norm": 3.020498514175415,
|
| 875 |
+
"learning_rate": 7.049808429118773e-05,
|
| 876 |
+
"loss": 1.2731,
|
| 877 |
+
"step": 212
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 7.379310344827586,
|
| 881 |
+
"grad_norm": 3.303375005722046,
|
| 882 |
+
"learning_rate": 7.011494252873564e-05,
|
| 883 |
+
"loss": 1.0312,
|
| 884 |
+
"step": 214
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 7.448275862068965,
|
| 888 |
+
"grad_norm": 2.705366849899292,
|
| 889 |
+
"learning_rate": 6.973180076628352e-05,
|
| 890 |
+
"loss": 1.2032,
|
| 891 |
+
"step": 216
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 7.517241379310345,
|
| 895 |
+
"grad_norm": 3.3683817386627197,
|
| 896 |
+
"learning_rate": 6.934865900383142e-05,
|
| 897 |
+
"loss": 1.166,
|
| 898 |
+
"step": 218
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 7.586206896551724,
|
| 902 |
+
"grad_norm": 3.079350471496582,
|
| 903 |
+
"learning_rate": 6.896551724137931e-05,
|
| 904 |
+
"loss": 0.9884,
|
| 905 |
+
"step": 220
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 7.655172413793103,
|
| 909 |
+
"grad_norm": 2.3934454917907715,
|
| 910 |
+
"learning_rate": 6.858237547892721e-05,
|
| 911 |
+
"loss": 1.1715,
|
| 912 |
+
"step": 222
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 7.724137931034483,
|
| 916 |
+
"grad_norm": 3.6560773849487305,
|
| 917 |
+
"learning_rate": 6.81992337164751e-05,
|
| 918 |
+
"loss": 1.0007,
|
| 919 |
+
"step": 224
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 7.793103448275862,
|
| 923 |
+
"grad_norm": 4.3467912673950195,
|
| 924 |
+
"learning_rate": 6.781609195402298e-05,
|
| 925 |
+
"loss": 1.4675,
|
| 926 |
+
"step": 226
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 7.862068965517241,
|
| 930 |
+
"grad_norm": 2.5141751766204834,
|
| 931 |
+
"learning_rate": 6.74329501915709e-05,
|
| 932 |
+
"loss": 0.9672,
|
| 933 |
+
"step": 228
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 7.931034482758621,
|
| 937 |
+
"grad_norm": 4.107297897338867,
|
| 938 |
+
"learning_rate": 6.704980842911877e-05,
|
| 939 |
+
"loss": 1.4593,
|
| 940 |
+
"step": 230
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 8.0,
|
| 944 |
+
"grad_norm": 2.193042278289795,
|
| 945 |
+
"learning_rate": 6.666666666666667e-05,
|
| 946 |
+
"loss": 1.2514,
|
| 947 |
+
"step": 232
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 8.0,
|
| 951 |
+
"eval_accuracy": 0.5606060606060606,
|
| 952 |
+
"eval_f1_macro": 0.4536205964777393,
|
| 953 |
+
"eval_f1_micro": 0.5606060606060606,
|
| 954 |
+
"eval_f1_weighted": 0.5206725615816525,
|
| 955 |
+
"eval_loss": 1.2344759702682495,
|
| 956 |
+
"eval_precision_macro": 0.47009218749545173,
|
| 957 |
+
"eval_precision_micro": 0.5606060606060606,
|
| 958 |
+
"eval_precision_weighted": 0.5257434050758826,
|
| 959 |
+
"eval_recall_macro": 0.4766061980347694,
|
| 960 |
+
"eval_recall_micro": 0.5606060606060606,
|
| 961 |
+
"eval_recall_weighted": 0.5606060606060606,
|
| 962 |
+
"eval_runtime": 2.3242,
|
| 963 |
+
"eval_samples_per_second": 56.794,
|
| 964 |
+
"eval_steps_per_second": 7.314,
|
| 965 |
+
"step": 232
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 8.068965517241379,
|
| 969 |
+
"grad_norm": 3.166414260864258,
|
| 970 |
+
"learning_rate": 6.628352490421456e-05,
|
| 971 |
+
"loss": 0.8487,
|
| 972 |
+
"step": 234
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 8.137931034482758,
|
| 976 |
+
"grad_norm": 3.4050002098083496,
|
| 977 |
+
"learning_rate": 6.590038314176246e-05,
|
| 978 |
+
"loss": 1.2154,
|
| 979 |
+
"step": 236
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 8.206896551724139,
|
| 983 |
+
"grad_norm": 2.827500104904175,
|
| 984 |
+
"learning_rate": 6.551724137931034e-05,
|
| 985 |
+
"loss": 1.1884,
|
| 986 |
+
"step": 238
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 8.275862068965518,
|
| 990 |
+
"grad_norm": 3.644810199737549,
|
| 991 |
+
"learning_rate": 6.513409961685824e-05,
|
| 992 |
+
"loss": 1.1444,
|
| 993 |
+
"step": 240
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 8.344827586206897,
|
| 997 |
+
"grad_norm": 2.5931830406188965,
|
| 998 |
+
"learning_rate": 6.475095785440613e-05,
|
| 999 |
+
"loss": 0.9335,
|
| 1000 |
+
"step": 242
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 8.413793103448276,
|
| 1004 |
+
"grad_norm": 4.586955547332764,
|
| 1005 |
+
"learning_rate": 6.436781609195403e-05,
|
| 1006 |
+
"loss": 1.174,
|
| 1007 |
+
"step": 244
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 8.482758620689655,
|
| 1011 |
+
"grad_norm": 4.06891393661499,
|
| 1012 |
+
"learning_rate": 6.398467432950191e-05,
|
| 1013 |
+
"loss": 1.1579,
|
| 1014 |
+
"step": 246
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 8.551724137931034,
|
| 1018 |
+
"grad_norm": 3.6428885459899902,
|
| 1019 |
+
"learning_rate": 6.360153256704982e-05,
|
| 1020 |
+
"loss": 0.8764,
|
| 1021 |
+
"step": 248
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 8.620689655172415,
|
| 1025 |
+
"grad_norm": 6.163786888122559,
|
| 1026 |
+
"learning_rate": 6.32183908045977e-05,
|
| 1027 |
+
"loss": 1.0204,
|
| 1028 |
+
"step": 250
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 8.689655172413794,
|
| 1032 |
+
"grad_norm": 2.775923252105713,
|
| 1033 |
+
"learning_rate": 6.283524904214559e-05,
|
| 1034 |
+
"loss": 0.8183,
|
| 1035 |
+
"step": 252
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 8.758620689655173,
|
| 1039 |
+
"grad_norm": 3.2083027362823486,
|
| 1040 |
+
"learning_rate": 6.245210727969349e-05,
|
| 1041 |
+
"loss": 1.3757,
|
| 1042 |
+
"step": 254
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 8.827586206896552,
|
| 1046 |
+
"grad_norm": 5.378493309020996,
|
| 1047 |
+
"learning_rate": 6.206896551724138e-05,
|
| 1048 |
+
"loss": 1.0219,
|
| 1049 |
+
"step": 256
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 8.89655172413793,
|
| 1053 |
+
"grad_norm": 3.8027050495147705,
|
| 1054 |
+
"learning_rate": 6.168582375478928e-05,
|
| 1055 |
+
"loss": 1.0405,
|
| 1056 |
+
"step": 258
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 8.96551724137931,
|
| 1060 |
+
"grad_norm": 3.604165554046631,
|
| 1061 |
+
"learning_rate": 6.130268199233716e-05,
|
| 1062 |
+
"loss": 0.6979,
|
| 1063 |
+
"step": 260
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 9.0,
|
| 1067 |
+
"eval_accuracy": 0.6363636363636364,
|
| 1068 |
+
"eval_f1_macro": 0.530518587020135,
|
| 1069 |
+
"eval_f1_micro": 0.6363636363636364,
|
| 1070 |
+
"eval_f1_weighted": 0.6097181236324214,
|
| 1071 |
+
"eval_loss": 1.1500554084777832,
|
| 1072 |
+
"eval_precision_macro": 0.5490794091920358,
|
| 1073 |
+
"eval_precision_micro": 0.6363636363636364,
|
| 1074 |
+
"eval_precision_weighted": 0.6127338831200314,
|
| 1075 |
+
"eval_recall_macro": 0.5391232048374907,
|
| 1076 |
+
"eval_recall_micro": 0.6363636363636364,
|
| 1077 |
+
"eval_recall_weighted": 0.6363636363636364,
|
| 1078 |
+
"eval_runtime": 2.3286,
|
| 1079 |
+
"eval_samples_per_second": 56.687,
|
| 1080 |
+
"eval_steps_per_second": 7.301,
|
| 1081 |
+
"step": 261
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 9.03448275862069,
|
| 1085 |
+
"grad_norm": 2.9546728134155273,
|
| 1086 |
+
"learning_rate": 6.091954022988506e-05,
|
| 1087 |
+
"loss": 0.9733,
|
| 1088 |
+
"step": 262
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 9.10344827586207,
|
| 1092 |
+
"grad_norm": 3.742382049560547,
|
| 1093 |
+
"learning_rate": 6.053639846743295e-05,
|
| 1094 |
+
"loss": 0.8539,
|
| 1095 |
+
"step": 264
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 9.172413793103448,
|
| 1099 |
+
"grad_norm": 4.167463779449463,
|
| 1100 |
+
"learning_rate": 6.0153256704980845e-05,
|
| 1101 |
+
"loss": 0.9605,
|
| 1102 |
+
"step": 266
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 9.241379310344827,
|
| 1106 |
+
"grad_norm": 2.0738613605499268,
|
| 1107 |
+
"learning_rate": 5.977011494252874e-05,
|
| 1108 |
+
"loss": 0.7348,
|
| 1109 |
+
"step": 268
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 9.310344827586206,
|
| 1113 |
+
"grad_norm": 3.2274346351623535,
|
| 1114 |
+
"learning_rate": 5.9386973180076635e-05,
|
| 1115 |
+
"loss": 0.9138,
|
| 1116 |
+
"step": 270
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 9.379310344827585,
|
| 1120 |
+
"grad_norm": 3.5369961261749268,
|
| 1121 |
+
"learning_rate": 5.900383141762452e-05,
|
| 1122 |
+
"loss": 0.7026,
|
| 1123 |
+
"step": 272
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 9.448275862068966,
|
| 1127 |
+
"grad_norm": 3.977078914642334,
|
| 1128 |
+
"learning_rate": 5.862068965517241e-05,
|
| 1129 |
+
"loss": 1.0063,
|
| 1130 |
+
"step": 274
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 9.517241379310345,
|
| 1134 |
+
"grad_norm": 3.6526713371276855,
|
| 1135 |
+
"learning_rate": 5.823754789272031e-05,
|
| 1136 |
+
"loss": 0.7266,
|
| 1137 |
+
"step": 276
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 9.586206896551724,
|
| 1141 |
+
"grad_norm": 1.9557095766067505,
|
| 1142 |
+
"learning_rate": 5.78544061302682e-05,
|
| 1143 |
+
"loss": 0.7732,
|
| 1144 |
+
"step": 278
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 9.655172413793103,
|
| 1148 |
+
"grad_norm": 1.2573161125183105,
|
| 1149 |
+
"learning_rate": 5.747126436781609e-05,
|
| 1150 |
+
"loss": 0.5661,
|
| 1151 |
+
"step": 280
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 9.724137931034482,
|
| 1155 |
+
"grad_norm": 2.927410364151001,
|
| 1156 |
+
"learning_rate": 5.708812260536399e-05,
|
| 1157 |
+
"loss": 1.0745,
|
| 1158 |
+
"step": 282
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 9.793103448275861,
|
| 1162 |
+
"grad_norm": 4.574418544769287,
|
| 1163 |
+
"learning_rate": 5.670498084291188e-05,
|
| 1164 |
+
"loss": 0.9002,
|
| 1165 |
+
"step": 284
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 9.862068965517242,
|
| 1169 |
+
"grad_norm": 3.5535728931427,
|
| 1170 |
+
"learning_rate": 5.632183908045977e-05,
|
| 1171 |
+
"loss": 0.9265,
|
| 1172 |
+
"step": 286
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 9.931034482758621,
|
| 1176 |
+
"grad_norm": 4.7521162033081055,
|
| 1177 |
+
"learning_rate": 5.593869731800766e-05,
|
| 1178 |
+
"loss": 0.8453,
|
| 1179 |
+
"step": 288
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 10.0,
|
| 1183 |
+
"grad_norm": 4.0816216468811035,
|
| 1184 |
+
"learning_rate": 5.555555555555556e-05,
|
| 1185 |
+
"loss": 1.0417,
|
| 1186 |
+
"step": 290
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 10.0,
|
| 1190 |
+
"eval_accuracy": 0.6136363636363636,
|
| 1191 |
+
"eval_f1_macro": 0.5205916396815399,
|
| 1192 |
+
"eval_f1_micro": 0.6136363636363636,
|
| 1193 |
+
"eval_f1_weighted": 0.5899988122518645,
|
| 1194 |
+
"eval_loss": 1.1654376983642578,
|
| 1195 |
+
"eval_precision_macro": 0.5214674214674214,
|
| 1196 |
+
"eval_precision_micro": 0.6136363636363636,
|
| 1197 |
+
"eval_precision_weighted": 0.5934943844034754,
|
| 1198 |
+
"eval_recall_macro": 0.5463643235071807,
|
| 1199 |
+
"eval_recall_micro": 0.6136363636363636,
|
| 1200 |
+
"eval_recall_weighted": 0.6136363636363636,
|
| 1201 |
+
"eval_runtime": 2.3259,
|
| 1202 |
+
"eval_samples_per_second": 56.753,
|
| 1203 |
+
"eval_steps_per_second": 7.309,
|
| 1204 |
+
"step": 290
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 10.068965517241379,
|
| 1208 |
+
"grad_norm": 4.20100736618042,
|
| 1209 |
+
"learning_rate": 5.517241379310345e-05,
|
| 1210 |
+
"loss": 0.9384,
|
| 1211 |
+
"step": 292
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 10.137931034482758,
|
| 1215 |
+
"grad_norm": 3.5482981204986572,
|
| 1216 |
+
"learning_rate": 5.478927203065134e-05,
|
| 1217 |
+
"loss": 0.7163,
|
| 1218 |
+
"step": 294
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 10.206896551724139,
|
| 1222 |
+
"grad_norm": 5.511715412139893,
|
| 1223 |
+
"learning_rate": 5.440613026819924e-05,
|
| 1224 |
+
"loss": 1.0096,
|
| 1225 |
+
"step": 296
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 10.275862068965518,
|
| 1229 |
+
"grad_norm": 4.4264984130859375,
|
| 1230 |
+
"learning_rate": 5.402298850574713e-05,
|
| 1231 |
+
"loss": 0.775,
|
| 1232 |
+
"step": 298
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 10.344827586206897,
|
| 1236 |
+
"grad_norm": 2.2772464752197266,
|
| 1237 |
+
"learning_rate": 5.363984674329502e-05,
|
| 1238 |
+
"loss": 1.0071,
|
| 1239 |
+
"step": 300
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 10.413793103448276,
|
| 1243 |
+
"grad_norm": 2.6942243576049805,
|
| 1244 |
+
"learning_rate": 5.325670498084292e-05,
|
| 1245 |
+
"loss": 0.6,
|
| 1246 |
+
"step": 302
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 10.482758620689655,
|
| 1250 |
+
"grad_norm": 3.3119990825653076,
|
| 1251 |
+
"learning_rate": 5.287356321839081e-05,
|
| 1252 |
+
"loss": 0.7233,
|
| 1253 |
+
"step": 304
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 10.551724137931034,
|
| 1257 |
+
"grad_norm": 3.8363144397735596,
|
| 1258 |
+
"learning_rate": 5.24904214559387e-05,
|
| 1259 |
+
"loss": 1.084,
|
| 1260 |
+
"step": 306
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 10.620689655172415,
|
| 1264 |
+
"grad_norm": 3.457904815673828,
|
| 1265 |
+
"learning_rate": 5.2107279693486586e-05,
|
| 1266 |
+
"loss": 0.7188,
|
| 1267 |
+
"step": 308
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 10.689655172413794,
|
| 1271 |
+
"grad_norm": 4.752615451812744,
|
| 1272 |
+
"learning_rate": 5.172413793103449e-05,
|
| 1273 |
+
"loss": 1.0076,
|
| 1274 |
+
"step": 310
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 10.758620689655173,
|
| 1278 |
+
"grad_norm": 2.8279869556427,
|
| 1279 |
+
"learning_rate": 5.1340996168582377e-05,
|
| 1280 |
+
"loss": 1.0505,
|
| 1281 |
+
"step": 312
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 10.827586206896552,
|
| 1285 |
+
"grad_norm": 5.538084506988525,
|
| 1286 |
+
"learning_rate": 5.0957854406130265e-05,
|
| 1287 |
+
"loss": 0.6474,
|
| 1288 |
+
"step": 314
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 10.89655172413793,
|
| 1292 |
+
"grad_norm": 3.197183847427368,
|
| 1293 |
+
"learning_rate": 5.057471264367817e-05,
|
| 1294 |
+
"loss": 0.6146,
|
| 1295 |
+
"step": 316
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 10.96551724137931,
|
| 1299 |
+
"grad_norm": 3.427384614944458,
|
| 1300 |
+
"learning_rate": 5.0191570881226055e-05,
|
| 1301 |
+
"loss": 0.7314,
|
| 1302 |
+
"step": 318
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 11.0,
|
| 1306 |
+
"eval_accuracy": 0.6212121212121212,
|
| 1307 |
+
"eval_f1_macro": 0.537594465565654,
|
| 1308 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 1309 |
+
"eval_f1_weighted": 0.6109434365736887,
|
| 1310 |
+
"eval_loss": 1.1566157341003418,
|
| 1311 |
+
"eval_precision_macro": 0.5386796536796536,
|
| 1312 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 1313 |
+
"eval_precision_weighted": 0.6153512396694215,
|
| 1314 |
+
"eval_recall_macro": 0.5513832199546485,
|
| 1315 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 1316 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 1317 |
+
"eval_runtime": 2.3247,
|
| 1318 |
+
"eval_samples_per_second": 56.78,
|
| 1319 |
+
"eval_steps_per_second": 7.313,
|
| 1320 |
+
"step": 319
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 11.03448275862069,
|
| 1324 |
+
"grad_norm": 3.1624715328216553,
|
| 1325 |
+
"learning_rate": 4.980842911877395e-05,
|
| 1326 |
+
"loss": 0.5936,
|
| 1327 |
+
"step": 320
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 11.10344827586207,
|
| 1331 |
+
"grad_norm": 3.2586793899536133,
|
| 1332 |
+
"learning_rate": 4.9425287356321845e-05,
|
| 1333 |
+
"loss": 0.7724,
|
| 1334 |
+
"step": 322
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 11.172413793103448,
|
| 1338 |
+
"grad_norm": 4.481448173522949,
|
| 1339 |
+
"learning_rate": 4.904214559386973e-05,
|
| 1340 |
+
"loss": 0.6748,
|
| 1341 |
+
"step": 324
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 11.241379310344827,
|
| 1345 |
+
"grad_norm": 2.7534396648406982,
|
| 1346 |
+
"learning_rate": 4.865900383141763e-05,
|
| 1347 |
+
"loss": 0.5199,
|
| 1348 |
+
"step": 326
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 11.310344827586206,
|
| 1352 |
+
"grad_norm": 2.4173717498779297,
|
| 1353 |
+
"learning_rate": 4.827586206896552e-05,
|
| 1354 |
+
"loss": 0.8016,
|
| 1355 |
+
"step": 328
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 11.379310344827585,
|
| 1359 |
+
"grad_norm": 2.85591459274292,
|
| 1360 |
+
"learning_rate": 4.789272030651341e-05,
|
| 1361 |
+
"loss": 0.8319,
|
| 1362 |
+
"step": 330
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 11.448275862068966,
|
| 1366 |
+
"grad_norm": 5.3054585456848145,
|
| 1367 |
+
"learning_rate": 4.7509578544061307e-05,
|
| 1368 |
+
"loss": 1.0745,
|
| 1369 |
+
"step": 332
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 11.517241379310345,
|
| 1373 |
+
"grad_norm": 3.0006418228149414,
|
| 1374 |
+
"learning_rate": 4.7126436781609195e-05,
|
| 1375 |
+
"loss": 0.5067,
|
| 1376 |
+
"step": 334
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 11.586206896551724,
|
| 1380 |
+
"grad_norm": 3.4974889755249023,
|
| 1381 |
+
"learning_rate": 4.674329501915709e-05,
|
| 1382 |
+
"loss": 0.7971,
|
| 1383 |
+
"step": 336
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 11.655172413793103,
|
| 1387 |
+
"grad_norm": 3.117962598800659,
|
| 1388 |
+
"learning_rate": 4.6360153256704985e-05,
|
| 1389 |
+
"loss": 0.6665,
|
| 1390 |
+
"step": 338
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 11.724137931034482,
|
| 1394 |
+
"grad_norm": 4.9846343994140625,
|
| 1395 |
+
"learning_rate": 4.597701149425287e-05,
|
| 1396 |
+
"loss": 0.7402,
|
| 1397 |
+
"step": 340
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 11.793103448275861,
|
| 1401 |
+
"grad_norm": 6.1209001541137695,
|
| 1402 |
+
"learning_rate": 4.559386973180077e-05,
|
| 1403 |
+
"loss": 0.9042,
|
| 1404 |
+
"step": 342
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 11.862068965517242,
|
| 1408 |
+
"grad_norm": 2.3766987323760986,
|
| 1409 |
+
"learning_rate": 4.5210727969348656e-05,
|
| 1410 |
+
"loss": 0.6191,
|
| 1411 |
+
"step": 344
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 11.931034482758621,
|
| 1415 |
+
"grad_norm": 5.1854143142700195,
|
| 1416 |
+
"learning_rate": 4.482758620689655e-05,
|
| 1417 |
+
"loss": 0.6116,
|
| 1418 |
+
"step": 346
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 12.0,
|
| 1422 |
+
"grad_norm": 5.495875835418701,
|
| 1423 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 1424 |
+
"loss": 0.7902,
|
| 1425 |
+
"step": 348
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 12.0,
|
| 1429 |
+
"eval_accuracy": 0.6212121212121212,
|
| 1430 |
+
"eval_f1_macro": 0.5396961800902688,
|
| 1431 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 1432 |
+
"eval_f1_weighted": 0.6140481105214648,
|
| 1433 |
+
"eval_loss": 1.1624207496643066,
|
| 1434 |
+
"eval_precision_macro": 0.5422025161353321,
|
| 1435 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 1436 |
+
"eval_precision_weighted": 0.6208899459169562,
|
| 1437 |
+
"eval_recall_macro": 0.5504686318972033,
|
| 1438 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 1439 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 1440 |
+
"eval_runtime": 2.3261,
|
| 1441 |
+
"eval_samples_per_second": 56.747,
|
| 1442 |
+
"eval_steps_per_second": 7.308,
|
| 1443 |
+
"step": 348
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 12.068965517241379,
|
| 1447 |
+
"grad_norm": 4.319167613983154,
|
| 1448 |
+
"learning_rate": 4.406130268199234e-05,
|
| 1449 |
+
"loss": 0.7979,
|
| 1450 |
+
"step": 350
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 12.137931034482758,
|
| 1454 |
+
"grad_norm": 3.6471261978149414,
|
| 1455 |
+
"learning_rate": 4.367816091954024e-05,
|
| 1456 |
+
"loss": 0.7733,
|
| 1457 |
+
"step": 352
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 12.206896551724139,
|
| 1461 |
+
"grad_norm": 3.5435140132904053,
|
| 1462 |
+
"learning_rate": 4.3295019157088125e-05,
|
| 1463 |
+
"loss": 0.8753,
|
| 1464 |
+
"step": 354
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 12.275862068965518,
|
| 1468 |
+
"grad_norm": 3.007453441619873,
|
| 1469 |
+
"learning_rate": 4.291187739463602e-05,
|
| 1470 |
+
"loss": 0.5425,
|
| 1471 |
+
"step": 356
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 12.344827586206897,
|
| 1475 |
+
"grad_norm": 4.487671852111816,
|
| 1476 |
+
"learning_rate": 4.252873563218391e-05,
|
| 1477 |
+
"loss": 0.5562,
|
| 1478 |
+
"step": 358
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 12.413793103448276,
|
| 1482 |
+
"grad_norm": 3.367605447769165,
|
| 1483 |
+
"learning_rate": 4.21455938697318e-05,
|
| 1484 |
+
"loss": 0.625,
|
| 1485 |
+
"step": 360
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 12.482758620689655,
|
| 1489 |
+
"grad_norm": 5.727989673614502,
|
| 1490 |
+
"learning_rate": 4.17624521072797e-05,
|
| 1491 |
+
"loss": 0.6552,
|
| 1492 |
+
"step": 362
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 12.551724137931034,
|
| 1496 |
+
"grad_norm": 2.801624298095703,
|
| 1497 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 1498 |
+
"loss": 0.5104,
|
| 1499 |
+
"step": 364
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 12.620689655172415,
|
| 1503 |
+
"grad_norm": 4.306697368621826,
|
| 1504 |
+
"learning_rate": 4.099616858237548e-05,
|
| 1505 |
+
"loss": 0.6764,
|
| 1506 |
+
"step": 366
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 12.689655172413794,
|
| 1510 |
+
"grad_norm": 7.026360988616943,
|
| 1511 |
+
"learning_rate": 4.061302681992337e-05,
|
| 1512 |
+
"loss": 0.7224,
|
| 1513 |
+
"step": 368
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 12.758620689655173,
|
| 1517 |
+
"grad_norm": 5.398407936096191,
|
| 1518 |
+
"learning_rate": 4.0229885057471265e-05,
|
| 1519 |
+
"loss": 0.8992,
|
| 1520 |
+
"step": 370
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 12.827586206896552,
|
| 1524 |
+
"grad_norm": 2.986201524734497,
|
| 1525 |
+
"learning_rate": 3.984674329501916e-05,
|
| 1526 |
+
"loss": 0.5226,
|
| 1527 |
+
"step": 372
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 12.89655172413793,
|
| 1531 |
+
"grad_norm": 5.425571918487549,
|
| 1532 |
+
"learning_rate": 3.9463601532567055e-05,
|
| 1533 |
+
"loss": 0.6649,
|
| 1534 |
+
"step": 374
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 12.96551724137931,
|
| 1538 |
+
"grad_norm": 4.2015461921691895,
|
| 1539 |
+
"learning_rate": 3.908045977011495e-05,
|
| 1540 |
+
"loss": 0.7503,
|
| 1541 |
+
"step": 376
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 13.0,
|
| 1545 |
+
"eval_accuracy": 0.6287878787878788,
|
| 1546 |
+
"eval_f1_macro": 0.5376898842937335,
|
| 1547 |
+
"eval_f1_micro": 0.6287878787878788,
|
| 1548 |
+
"eval_f1_weighted": 0.6125773067483171,
|
| 1549 |
+
"eval_loss": 1.135877013206482,
|
| 1550 |
+
"eval_precision_macro": 0.5471859541424758,
|
| 1551 |
+
"eval_precision_micro": 0.6287878787878788,
|
| 1552 |
+
"eval_precision_weighted": 0.6142989641013356,
|
| 1553 |
+
"eval_recall_macro": 0.5455328798185941,
|
| 1554 |
+
"eval_recall_micro": 0.6287878787878788,
|
| 1555 |
+
"eval_recall_weighted": 0.6287878787878788,
|
| 1556 |
+
"eval_runtime": 2.3097,
|
| 1557 |
+
"eval_samples_per_second": 57.149,
|
| 1558 |
+
"eval_steps_per_second": 7.36,
|
| 1559 |
+
"step": 377
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 13.03448275862069,
|
| 1563 |
+
"grad_norm": 3.527031660079956,
|
| 1564 |
+
"learning_rate": 3.869731800766284e-05,
|
| 1565 |
+
"loss": 0.6196,
|
| 1566 |
+
"step": 378
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 13.10344827586207,
|
| 1570 |
+
"grad_norm": 4.090692520141602,
|
| 1571 |
+
"learning_rate": 3.831417624521073e-05,
|
| 1572 |
+
"loss": 0.4906,
|
| 1573 |
+
"step": 380
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 13.172413793103448,
|
| 1577 |
+
"grad_norm": 3.5445234775543213,
|
| 1578 |
+
"learning_rate": 3.793103448275862e-05,
|
| 1579 |
+
"loss": 0.6832,
|
| 1580 |
+
"step": 382
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 13.241379310344827,
|
| 1584 |
+
"grad_norm": 2.648242473602295,
|
| 1585 |
+
"learning_rate": 3.7547892720306517e-05,
|
| 1586 |
+
"loss": 0.7041,
|
| 1587 |
+
"step": 384
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 13.310344827586206,
|
| 1591 |
+
"grad_norm": 2.421206474304199,
|
| 1592 |
+
"learning_rate": 3.716475095785441e-05,
|
| 1593 |
+
"loss": 0.3506,
|
| 1594 |
+
"step": 386
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 13.379310344827585,
|
| 1598 |
+
"grad_norm": 4.197497367858887,
|
| 1599 |
+
"learning_rate": 3.67816091954023e-05,
|
| 1600 |
+
"loss": 0.7564,
|
| 1601 |
+
"step": 388
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 13.448275862068966,
|
| 1605 |
+
"grad_norm": 4.1512131690979,
|
| 1606 |
+
"learning_rate": 3.6398467432950195e-05,
|
| 1607 |
+
"loss": 0.7134,
|
| 1608 |
+
"step": 390
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 13.517241379310345,
|
| 1612 |
+
"grad_norm": 2.6926424503326416,
|
| 1613 |
+
"learning_rate": 3.601532567049808e-05,
|
| 1614 |
+
"loss": 0.5195,
|
| 1615 |
+
"step": 392
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 13.586206896551724,
|
| 1619 |
+
"grad_norm": 5.174130916595459,
|
| 1620 |
+
"learning_rate": 3.563218390804598e-05,
|
| 1621 |
+
"loss": 0.485,
|
| 1622 |
+
"step": 394
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 13.655172413793103,
|
| 1626 |
+
"grad_norm": 2.1289005279541016,
|
| 1627 |
+
"learning_rate": 3.5249042145593867e-05,
|
| 1628 |
+
"loss": 0.6963,
|
| 1629 |
+
"step": 396
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 13.724137931034482,
|
| 1633 |
+
"grad_norm": 5.4137654304504395,
|
| 1634 |
+
"learning_rate": 3.486590038314176e-05,
|
| 1635 |
+
"loss": 0.6374,
|
| 1636 |
+
"step": 398
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 13.793103448275861,
|
| 1640 |
+
"grad_norm": 3.6843011379241943,
|
| 1641 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 1642 |
+
"loss": 0.9498,
|
| 1643 |
+
"step": 400
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 13.862068965517242,
|
| 1647 |
+
"grad_norm": 4.690808296203613,
|
| 1648 |
+
"learning_rate": 3.409961685823755e-05,
|
| 1649 |
+
"loss": 0.7182,
|
| 1650 |
+
"step": 402
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 13.931034482758621,
|
| 1654 |
+
"grad_norm": 4.772737979888916,
|
| 1655 |
+
"learning_rate": 3.371647509578545e-05,
|
| 1656 |
+
"loss": 0.7981,
|
| 1657 |
+
"step": 404
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 14.0,
|
| 1661 |
+
"grad_norm": 6.463994979858398,
|
| 1662 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1663 |
+
"loss": 0.586,
|
| 1664 |
+
"step": 406
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 14.0,
|
| 1668 |
+
"eval_accuracy": 0.6287878787878788,
|
| 1669 |
+
"eval_f1_macro": 0.5440812816073651,
|
| 1670 |
+
"eval_f1_micro": 0.6287878787878788,
|
| 1671 |
+
"eval_f1_weighted": 0.614080662953901,
|
| 1672 |
+
"eval_loss": 1.151163101196289,
|
| 1673 |
+
"eval_precision_macro": 0.5361375661375661,
|
| 1674 |
+
"eval_precision_micro": 0.6287878787878788,
|
| 1675 |
+
"eval_precision_weighted": 0.6032631874298542,
|
| 1676 |
+
"eval_recall_macro": 0.5557218442932729,
|
| 1677 |
+
"eval_recall_micro": 0.6287878787878788,
|
| 1678 |
+
"eval_recall_weighted": 0.6287878787878788,
|
| 1679 |
+
"eval_runtime": 2.3161,
|
| 1680 |
+
"eval_samples_per_second": 56.992,
|
| 1681 |
+
"eval_steps_per_second": 7.34,
|
| 1682 |
+
"step": 406
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 14.068965517241379,
|
| 1686 |
+
"grad_norm": 4.363000392913818,
|
| 1687 |
+
"learning_rate": 3.295019157088123e-05,
|
| 1688 |
+
"loss": 0.5204,
|
| 1689 |
+
"step": 408
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 14.137931034482758,
|
| 1693 |
+
"grad_norm": 2.4504146575927734,
|
| 1694 |
+
"learning_rate": 3.256704980842912e-05,
|
| 1695 |
+
"loss": 0.3989,
|
| 1696 |
+
"step": 410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 14.206896551724139,
|
| 1700 |
+
"grad_norm": 2.4213919639587402,
|
| 1701 |
+
"learning_rate": 3.218390804597701e-05,
|
| 1702 |
+
"loss": 0.4246,
|
| 1703 |
+
"step": 412
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 14.275862068965518,
|
| 1707 |
+
"grad_norm": 4.8299031257629395,
|
| 1708 |
+
"learning_rate": 3.180076628352491e-05,
|
| 1709 |
+
"loss": 0.6999,
|
| 1710 |
+
"step": 414
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 14.344827586206897,
|
| 1714 |
+
"grad_norm": 2.637255907058716,
|
| 1715 |
+
"learning_rate": 3.1417624521072797e-05,
|
| 1716 |
+
"loss": 0.5376,
|
| 1717 |
+
"step": 416
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 14.413793103448276,
|
| 1721 |
+
"grad_norm": 3.4667327404022217,
|
| 1722 |
+
"learning_rate": 3.103448275862069e-05,
|
| 1723 |
+
"loss": 0.5109,
|
| 1724 |
+
"step": 418
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 14.482758620689655,
|
| 1728 |
+
"grad_norm": 6.673337459564209,
|
| 1729 |
+
"learning_rate": 3.065134099616858e-05,
|
| 1730 |
+
"loss": 0.4014,
|
| 1731 |
+
"step": 420
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 14.551724137931034,
|
| 1735 |
+
"grad_norm": 2.5311481952667236,
|
| 1736 |
+
"learning_rate": 3.0268199233716475e-05,
|
| 1737 |
+
"loss": 0.6741,
|
| 1738 |
+
"step": 422
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 14.620689655172415,
|
| 1742 |
+
"grad_norm": 3.339940071105957,
|
| 1743 |
+
"learning_rate": 2.988505747126437e-05,
|
| 1744 |
+
"loss": 0.4081,
|
| 1745 |
+
"step": 424
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 14.689655172413794,
|
| 1749 |
+
"grad_norm": 2.3433589935302734,
|
| 1750 |
+
"learning_rate": 2.950191570881226e-05,
|
| 1751 |
+
"loss": 0.5574,
|
| 1752 |
+
"step": 426
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 14.758620689655173,
|
| 1756 |
+
"grad_norm": 3.5291073322296143,
|
| 1757 |
+
"learning_rate": 2.9118773946360157e-05,
|
| 1758 |
+
"loss": 0.6136,
|
| 1759 |
+
"step": 428
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 14.827586206896552,
|
| 1763 |
+
"grad_norm": 3.0121891498565674,
|
| 1764 |
+
"learning_rate": 2.8735632183908045e-05,
|
| 1765 |
+
"loss": 0.3841,
|
| 1766 |
+
"step": 430
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 14.89655172413793,
|
| 1770 |
+
"grad_norm": 3.474233388900757,
|
| 1771 |
+
"learning_rate": 2.835249042145594e-05,
|
| 1772 |
+
"loss": 0.4371,
|
| 1773 |
+
"step": 432
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 14.96551724137931,
|
| 1777 |
+
"grad_norm": 3.466447591781616,
|
| 1778 |
+
"learning_rate": 2.796934865900383e-05,
|
| 1779 |
+
"loss": 0.6869,
|
| 1780 |
+
"step": 434
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 15.0,
|
| 1784 |
+
"eval_accuracy": 0.6287878787878788,
|
| 1785 |
+
"eval_f1_macro": 0.5323304385684055,
|
| 1786 |
+
"eval_f1_micro": 0.6287878787878788,
|
| 1787 |
+
"eval_f1_weighted": 0.6116664108577855,
|
| 1788 |
+
"eval_loss": 1.13055419921875,
|
| 1789 |
+
"eval_precision_macro": 0.5269524536765916,
|
| 1790 |
+
"eval_precision_micro": 0.6287878787878788,
|
| 1791 |
+
"eval_precision_weighted": 0.6043089290542268,
|
| 1792 |
+
"eval_recall_macro": 0.547490551776266,
|
| 1793 |
+
"eval_recall_micro": 0.6287878787878788,
|
| 1794 |
+
"eval_recall_weighted": 0.6287878787878788,
|
| 1795 |
+
"eval_runtime": 2.3194,
|
| 1796 |
+
"eval_samples_per_second": 56.911,
|
| 1797 |
+
"eval_steps_per_second": 7.329,
|
| 1798 |
+
"step": 435
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 15.03448275862069,
|
| 1802 |
+
"grad_norm": 2.4587948322296143,
|
| 1803 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 1804 |
+
"loss": 0.6758,
|
| 1805 |
+
"step": 436
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 15.10344827586207,
|
| 1809 |
+
"grad_norm": 3.373725414276123,
|
| 1810 |
+
"learning_rate": 2.720306513409962e-05,
|
| 1811 |
+
"loss": 0.516,
|
| 1812 |
+
"step": 438
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 15.172413793103448,
|
| 1816 |
+
"grad_norm": 4.587845802307129,
|
| 1817 |
+
"learning_rate": 2.681992337164751e-05,
|
| 1818 |
+
"loss": 0.5093,
|
| 1819 |
+
"step": 440
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 15.241379310344827,
|
| 1823 |
+
"grad_norm": 6.124247074127197,
|
| 1824 |
+
"learning_rate": 2.6436781609195405e-05,
|
| 1825 |
+
"loss": 0.5237,
|
| 1826 |
+
"step": 442
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 15.310344827586206,
|
| 1830 |
+
"grad_norm": 3.777029514312744,
|
| 1831 |
+
"learning_rate": 2.6053639846743293e-05,
|
| 1832 |
+
"loss": 0.5128,
|
| 1833 |
+
"step": 444
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 15.379310344827585,
|
| 1837 |
+
"grad_norm": 2.960836887359619,
|
| 1838 |
+
"learning_rate": 2.5670498084291188e-05,
|
| 1839 |
+
"loss": 0.6366,
|
| 1840 |
+
"step": 446
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 15.448275862068966,
|
| 1844 |
+
"grad_norm": 3.1089887619018555,
|
| 1845 |
+
"learning_rate": 2.5287356321839083e-05,
|
| 1846 |
+
"loss": 0.5369,
|
| 1847 |
+
"step": 448
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 15.517241379310345,
|
| 1851 |
+
"grad_norm": 2.6847426891326904,
|
| 1852 |
+
"learning_rate": 2.4904214559386975e-05,
|
| 1853 |
+
"loss": 0.3325,
|
| 1854 |
+
"step": 450
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 15.586206896551724,
|
| 1858 |
+
"grad_norm": 6.938262462615967,
|
| 1859 |
+
"learning_rate": 2.4521072796934867e-05,
|
| 1860 |
+
"loss": 0.6207,
|
| 1861 |
+
"step": 452
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 15.655172413793103,
|
| 1865 |
+
"grad_norm": 1.7349634170532227,
|
| 1866 |
+
"learning_rate": 2.413793103448276e-05,
|
| 1867 |
+
"loss": 0.3663,
|
| 1868 |
+
"step": 454
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 15.724137931034482,
|
| 1872 |
+
"grad_norm": 1.5232642889022827,
|
| 1873 |
+
"learning_rate": 2.3754789272030653e-05,
|
| 1874 |
+
"loss": 0.5473,
|
| 1875 |
+
"step": 456
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 15.793103448275861,
|
| 1879 |
+
"grad_norm": 4.805527210235596,
|
| 1880 |
+
"learning_rate": 2.3371647509578545e-05,
|
| 1881 |
+
"loss": 0.3652,
|
| 1882 |
+
"step": 458
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 15.862068965517242,
|
| 1886 |
+
"grad_norm": 4.195865631103516,
|
| 1887 |
+
"learning_rate": 2.2988505747126437e-05,
|
| 1888 |
+
"loss": 0.5624,
|
| 1889 |
+
"step": 460
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 15.931034482758621,
|
| 1893 |
+
"grad_norm": 1.5092368125915527,
|
| 1894 |
+
"learning_rate": 2.2605363984674328e-05,
|
| 1895 |
+
"loss": 0.4081,
|
| 1896 |
+
"step": 462
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 16.0,
|
| 1900 |
+
"grad_norm": 3.367891311645508,
|
| 1901 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1902 |
+
"loss": 0.5498,
|
| 1903 |
+
"step": 464
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 16.0,
|
| 1907 |
+
"eval_accuracy": 0.6287878787878788,
|
| 1908 |
+
"eval_f1_macro": 0.5372783597671154,
|
| 1909 |
+
"eval_f1_micro": 0.6287878787878788,
|
| 1910 |
+
"eval_f1_weighted": 0.6117070792278643,
|
| 1911 |
+
"eval_loss": 1.1293154954910278,
|
| 1912 |
+
"eval_precision_macro": 0.5353323147440795,
|
| 1913 |
+
"eval_precision_micro": 0.6287878787878788,
|
| 1914 |
+
"eval_precision_weighted": 0.603853373305245,
|
| 1915 |
+
"eval_recall_macro": 0.5471201814058957,
|
| 1916 |
+
"eval_recall_micro": 0.6287878787878788,
|
| 1917 |
+
"eval_recall_weighted": 0.6287878787878788,
|
| 1918 |
+
"eval_runtime": 2.3165,
|
| 1919 |
+
"eval_samples_per_second": 56.983,
|
| 1920 |
+
"eval_steps_per_second": 7.339,
|
| 1921 |
+
"step": 464
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 16.06896551724138,
|
| 1925 |
+
"grad_norm": 3.580066442489624,
|
| 1926 |
+
"learning_rate": 2.183908045977012e-05,
|
| 1927 |
+
"loss": 0.4746,
|
| 1928 |
+
"step": 466
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 16.137931034482758,
|
| 1932 |
+
"grad_norm": 3.583418130874634,
|
| 1933 |
+
"learning_rate": 2.145593869731801e-05,
|
| 1934 |
+
"loss": 0.4795,
|
| 1935 |
+
"step": 468
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 16.20689655172414,
|
| 1939 |
+
"grad_norm": 2.073596239089966,
|
| 1940 |
+
"learning_rate": 2.10727969348659e-05,
|
| 1941 |
+
"loss": 0.3328,
|
| 1942 |
+
"step": 470
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 16.275862068965516,
|
| 1946 |
+
"grad_norm": 3.2745907306671143,
|
| 1947 |
+
"learning_rate": 2.0689655172413793e-05,
|
| 1948 |
+
"loss": 0.4395,
|
| 1949 |
+
"step": 472
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 16.344827586206897,
|
| 1953 |
+
"grad_norm": 1.9064489603042603,
|
| 1954 |
+
"learning_rate": 2.0306513409961685e-05,
|
| 1955 |
+
"loss": 0.3172,
|
| 1956 |
+
"step": 474
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 16.413793103448278,
|
| 1960 |
+
"grad_norm": 4.838860988616943,
|
| 1961 |
+
"learning_rate": 1.992337164750958e-05,
|
| 1962 |
+
"loss": 0.6758,
|
| 1963 |
+
"step": 476
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 16.482758620689655,
|
| 1967 |
+
"grad_norm": 1.598775029182434,
|
| 1968 |
+
"learning_rate": 1.9540229885057475e-05,
|
| 1969 |
+
"loss": 0.3767,
|
| 1970 |
+
"step": 478
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 16.551724137931036,
|
| 1974 |
+
"grad_norm": 4.009886264801025,
|
| 1975 |
+
"learning_rate": 1.9157088122605367e-05,
|
| 1976 |
+
"loss": 0.4511,
|
| 1977 |
+
"step": 480
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 16.620689655172413,
|
| 1981 |
+
"grad_norm": 3.5439836978912354,
|
| 1982 |
+
"learning_rate": 1.8773946360153258e-05,
|
| 1983 |
+
"loss": 0.4542,
|
| 1984 |
+
"step": 482
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 16.689655172413794,
|
| 1988 |
+
"grad_norm": 3.5532007217407227,
|
| 1989 |
+
"learning_rate": 1.839080459770115e-05,
|
| 1990 |
+
"loss": 0.5007,
|
| 1991 |
+
"step": 484
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 16.75862068965517,
|
| 1995 |
+
"grad_norm": 2.5344693660736084,
|
| 1996 |
+
"learning_rate": 1.800766283524904e-05,
|
| 1997 |
+
"loss": 0.3181,
|
| 1998 |
+
"step": 486
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 16.82758620689655,
|
| 2002 |
+
"grad_norm": 1.9428218603134155,
|
| 2003 |
+
"learning_rate": 1.7624521072796933e-05,
|
| 2004 |
+
"loss": 0.4047,
|
| 2005 |
+
"step": 488
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 16.896551724137932,
|
| 2009 |
+
"grad_norm": 2.117885112762451,
|
| 2010 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 2011 |
+
"loss": 0.3487,
|
| 2012 |
+
"step": 490
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 16.96551724137931,
|
| 2016 |
+
"grad_norm": 3.377067804336548,
|
| 2017 |
+
"learning_rate": 1.6858237547892723e-05,
|
| 2018 |
+
"loss": 0.5037,
|
| 2019 |
+
"step": 492
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 17.0,
|
| 2023 |
+
"eval_accuracy": 0.6212121212121212,
|
| 2024 |
+
"eval_f1_macro": 0.5290491049649699,
|
| 2025 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 2026 |
+
"eval_f1_weighted": 0.6005376615693997,
|
| 2027 |
+
"eval_loss": 1.163466453552246,
|
| 2028 |
+
"eval_precision_macro": 0.5374433106575963,
|
| 2029 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 2030 |
+
"eval_precision_weighted": 0.6021569865319866,
|
| 2031 |
+
"eval_recall_macro": 0.5397581254724112,
|
| 2032 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 2033 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 2034 |
+
"eval_runtime": 2.3304,
|
| 2035 |
+
"eval_samples_per_second": 56.642,
|
| 2036 |
+
"eval_steps_per_second": 7.295,
|
| 2037 |
+
"step": 493
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 17.03448275862069,
|
| 2041 |
+
"grad_norm": 3.5657002925872803,
|
| 2042 |
+
"learning_rate": 1.6475095785440615e-05,
|
| 2043 |
+
"loss": 0.4446,
|
| 2044 |
+
"step": 494
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 17.103448275862068,
|
| 2048 |
+
"grad_norm": 4.189113616943359,
|
| 2049 |
+
"learning_rate": 1.6091954022988507e-05,
|
| 2050 |
+
"loss": 0.3923,
|
| 2051 |
+
"step": 496
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 17.17241379310345,
|
| 2055 |
+
"grad_norm": 2.554723024368286,
|
| 2056 |
+
"learning_rate": 1.5708812260536398e-05,
|
| 2057 |
+
"loss": 0.358,
|
| 2058 |
+
"step": 498
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 17.24137931034483,
|
| 2062 |
+
"grad_norm": 3.3316357135772705,
|
| 2063 |
+
"learning_rate": 1.532567049808429e-05,
|
| 2064 |
+
"loss": 0.2683,
|
| 2065 |
+
"step": 500
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 17.310344827586206,
|
| 2069 |
+
"grad_norm": 3.2318475246429443,
|
| 2070 |
+
"learning_rate": 1.4942528735632185e-05,
|
| 2071 |
+
"loss": 0.3611,
|
| 2072 |
+
"step": 502
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 17.379310344827587,
|
| 2076 |
+
"grad_norm": 3.2837979793548584,
|
| 2077 |
+
"learning_rate": 1.4559386973180078e-05,
|
| 2078 |
+
"loss": 0.435,
|
| 2079 |
+
"step": 504
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 17.448275862068964,
|
| 2083 |
+
"grad_norm": 3.8966495990753174,
|
| 2084 |
+
"learning_rate": 1.417624521072797e-05,
|
| 2085 |
+
"loss": 0.2982,
|
| 2086 |
+
"step": 506
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 17.517241379310345,
|
| 2090 |
+
"grad_norm": 6.666224479675293,
|
| 2091 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 2092 |
+
"loss": 0.4624,
|
| 2093 |
+
"step": 508
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 17.586206896551722,
|
| 2097 |
+
"grad_norm": 4.43505334854126,
|
| 2098 |
+
"learning_rate": 1.3409961685823755e-05,
|
| 2099 |
+
"loss": 0.6202,
|
| 2100 |
+
"step": 510
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 17.655172413793103,
|
| 2104 |
+
"grad_norm": 3.7163617610931396,
|
| 2105 |
+
"learning_rate": 1.3026819923371647e-05,
|
| 2106 |
+
"loss": 0.3422,
|
| 2107 |
+
"step": 512
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 17.724137931034484,
|
| 2111 |
+
"grad_norm": 2.855036735534668,
|
| 2112 |
+
"learning_rate": 1.2643678160919542e-05,
|
| 2113 |
+
"loss": 0.5171,
|
| 2114 |
+
"step": 514
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 17.79310344827586,
|
| 2118 |
+
"grad_norm": 3.121839761734009,
|
| 2119 |
+
"learning_rate": 1.2260536398467433e-05,
|
| 2120 |
+
"loss": 0.3575,
|
| 2121 |
+
"step": 516
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 17.862068965517242,
|
| 2125 |
+
"grad_norm": 2.77312970161438,
|
| 2126 |
+
"learning_rate": 1.1877394636015327e-05,
|
| 2127 |
+
"loss": 0.3051,
|
| 2128 |
+
"step": 518
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 17.93103448275862,
|
| 2132 |
+
"grad_norm": 2.2301366329193115,
|
| 2133 |
+
"learning_rate": 1.1494252873563218e-05,
|
| 2134 |
+
"loss": 0.4635,
|
| 2135 |
+
"step": 520
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 18.0,
|
| 2139 |
+
"grad_norm": 4.1137518882751465,
|
| 2140 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 2141 |
+
"loss": 0.3624,
|
| 2142 |
+
"step": 522
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 18.0,
|
| 2146 |
+
"eval_accuracy": 0.6590909090909091,
|
| 2147 |
+
"eval_f1_macro": 0.5699944413104846,
|
| 2148 |
+
"eval_f1_micro": 0.6590909090909091,
|
| 2149 |
+
"eval_f1_weighted": 0.6414064024247821,
|
| 2150 |
+
"eval_loss": 1.09944748878479,
|
| 2151 |
+
"eval_precision_macro": 0.5815085815085814,
|
| 2152 |
+
"eval_precision_micro": 0.6590909090909091,
|
| 2153 |
+
"eval_precision_weighted": 0.640854299945209,
|
| 2154 |
+
"eval_recall_macro": 0.5742857142857142,
|
| 2155 |
+
"eval_recall_micro": 0.6590909090909091,
|
| 2156 |
+
"eval_recall_weighted": 0.6590909090909091,
|
| 2157 |
+
"eval_runtime": 2.3246,
|
| 2158 |
+
"eval_samples_per_second": 56.785,
|
| 2159 |
+
"eval_steps_per_second": 7.313,
|
| 2160 |
+
"step": 522
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 18.06896551724138,
|
| 2164 |
+
"grad_norm": 5.545546054840088,
|
| 2165 |
+
"learning_rate": 1.0727969348659005e-05,
|
| 2166 |
+
"loss": 0.4351,
|
| 2167 |
+
"step": 524
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 18.137931034482758,
|
| 2171 |
+
"grad_norm": 2.5802762508392334,
|
| 2172 |
+
"learning_rate": 1.0344827586206897e-05,
|
| 2173 |
+
"loss": 0.3958,
|
| 2174 |
+
"step": 526
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 18.20689655172414,
|
| 2178 |
+
"grad_norm": 3.738755702972412,
|
| 2179 |
+
"learning_rate": 9.96168582375479e-06,
|
| 2180 |
+
"loss": 0.3933,
|
| 2181 |
+
"step": 528
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 18.275862068965516,
|
| 2185 |
+
"grad_norm": 2.6017744541168213,
|
| 2186 |
+
"learning_rate": 9.578544061302683e-06,
|
| 2187 |
+
"loss": 0.4367,
|
| 2188 |
+
"step": 530
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 18.344827586206897,
|
| 2192 |
+
"grad_norm": 4.551992416381836,
|
| 2193 |
+
"learning_rate": 9.195402298850575e-06,
|
| 2194 |
+
"loss": 0.3844,
|
| 2195 |
+
"step": 532
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 18.413793103448278,
|
| 2199 |
+
"grad_norm": 3.3013875484466553,
|
| 2200 |
+
"learning_rate": 8.812260536398467e-06,
|
| 2201 |
+
"loss": 0.3592,
|
| 2202 |
+
"step": 534
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 18.482758620689655,
|
| 2206 |
+
"grad_norm": 8.250885009765625,
|
| 2207 |
+
"learning_rate": 8.429118773946362e-06,
|
| 2208 |
+
"loss": 0.5747,
|
| 2209 |
+
"step": 536
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 18.551724137931036,
|
| 2213 |
+
"grad_norm": 2.1234164237976074,
|
| 2214 |
+
"learning_rate": 8.045977011494253e-06,
|
| 2215 |
+
"loss": 0.3561,
|
| 2216 |
+
"step": 538
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 18.620689655172413,
|
| 2220 |
+
"grad_norm": 2.730742931365967,
|
| 2221 |
+
"learning_rate": 7.662835249042145e-06,
|
| 2222 |
+
"loss": 0.3182,
|
| 2223 |
+
"step": 540
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 18.689655172413794,
|
| 2227 |
+
"grad_norm": 1.1862895488739014,
|
| 2228 |
+
"learning_rate": 7.279693486590039e-06,
|
| 2229 |
+
"loss": 0.2739,
|
| 2230 |
+
"step": 542
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 18.75862068965517,
|
| 2234 |
+
"grad_norm": 3.530163049697876,
|
| 2235 |
+
"learning_rate": 6.896551724137932e-06,
|
| 2236 |
+
"loss": 0.4006,
|
| 2237 |
+
"step": 544
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 18.82758620689655,
|
| 2241 |
+
"grad_norm": 3.7491860389709473,
|
| 2242 |
+
"learning_rate": 6.513409961685823e-06,
|
| 2243 |
+
"loss": 0.2657,
|
| 2244 |
+
"step": 546
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 18.896551724137932,
|
| 2248 |
+
"grad_norm": 6.904880523681641,
|
| 2249 |
+
"learning_rate": 6.130268199233717e-06,
|
| 2250 |
+
"loss": 0.4191,
|
| 2251 |
+
"step": 548
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 18.96551724137931,
|
| 2255 |
+
"grad_norm": 1.2763559818267822,
|
| 2256 |
+
"learning_rate": 5.747126436781609e-06,
|
| 2257 |
+
"loss": 0.3387,
|
| 2258 |
+
"step": 550
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 19.0,
|
| 2262 |
+
"eval_accuracy": 0.6515151515151515,
|
| 2263 |
+
"eval_f1_macro": 0.5642594468235355,
|
| 2264 |
+
"eval_f1_micro": 0.6515151515151515,
|
| 2265 |
+
"eval_f1_weighted": 0.6367337845877334,
|
| 2266 |
+
"eval_loss": 1.094382643699646,
|
| 2267 |
+
"eval_precision_macro": 0.5555528431468281,
|
| 2268 |
+
"eval_precision_micro": 0.6515151515151515,
|
| 2269 |
+
"eval_precision_weighted": 0.6268442283394436,
|
| 2270 |
+
"eval_recall_macro": 0.5781405895691609,
|
| 2271 |
+
"eval_recall_micro": 0.6515151515151515,
|
| 2272 |
+
"eval_recall_weighted": 0.6515151515151515,
|
| 2273 |
+
"eval_runtime": 2.3159,
|
| 2274 |
+
"eval_samples_per_second": 56.998,
|
| 2275 |
+
"eval_steps_per_second": 7.341,
|
| 2276 |
+
"step": 551
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 19.03448275862069,
|
| 2280 |
+
"grad_norm": 3.0644407272338867,
|
| 2281 |
+
"learning_rate": 5.3639846743295025e-06,
|
| 2282 |
+
"loss": 0.3165,
|
| 2283 |
+
"step": 552
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 19.103448275862068,
|
| 2287 |
+
"grad_norm": 3.8234410285949707,
|
| 2288 |
+
"learning_rate": 4.980842911877395e-06,
|
| 2289 |
+
"loss": 0.4086,
|
| 2290 |
+
"step": 554
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 19.17241379310345,
|
| 2294 |
+
"grad_norm": 1.5022215843200684,
|
| 2295 |
+
"learning_rate": 4.5977011494252875e-06,
|
| 2296 |
+
"loss": 0.2806,
|
| 2297 |
+
"step": 556
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 19.24137931034483,
|
| 2301 |
+
"grad_norm": 4.573976039886475,
|
| 2302 |
+
"learning_rate": 4.214559386973181e-06,
|
| 2303 |
+
"loss": 0.4335,
|
| 2304 |
+
"step": 558
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 19.310344827586206,
|
| 2308 |
+
"grad_norm": 3.7575619220733643,
|
| 2309 |
+
"learning_rate": 3.8314176245210725e-06,
|
| 2310 |
+
"loss": 0.2748,
|
| 2311 |
+
"step": 560
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 19.379310344827587,
|
| 2315 |
+
"grad_norm": 1.8237051963806152,
|
| 2316 |
+
"learning_rate": 3.448275862068966e-06,
|
| 2317 |
+
"loss": 0.3879,
|
| 2318 |
+
"step": 562
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 19.448275862068964,
|
| 2322 |
+
"grad_norm": 5.58415412902832,
|
| 2323 |
+
"learning_rate": 3.0651340996168583e-06,
|
| 2324 |
+
"loss": 0.2736,
|
| 2325 |
+
"step": 564
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 19.517241379310345,
|
| 2329 |
+
"grad_norm": 1.1507081985473633,
|
| 2330 |
+
"learning_rate": 2.6819923371647512e-06,
|
| 2331 |
+
"loss": 0.2612,
|
| 2332 |
+
"step": 566
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 19.586206896551722,
|
| 2336 |
+
"grad_norm": 1.060652494430542,
|
| 2337 |
+
"learning_rate": 2.2988505747126437e-06,
|
| 2338 |
+
"loss": 0.2706,
|
| 2339 |
+
"step": 568
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 19.655172413793103,
|
| 2343 |
+
"grad_norm": 1.4286646842956543,
|
| 2344 |
+
"learning_rate": 1.9157088122605362e-06,
|
| 2345 |
+
"loss": 0.2616,
|
| 2346 |
+
"step": 570
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 19.724137931034484,
|
| 2350 |
+
"grad_norm": 5.675417900085449,
|
| 2351 |
+
"learning_rate": 1.5325670498084292e-06,
|
| 2352 |
+
"loss": 0.4929,
|
| 2353 |
+
"step": 572
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 19.79310344827586,
|
| 2357 |
+
"grad_norm": 1.839812994003296,
|
| 2358 |
+
"learning_rate": 1.1494252873563219e-06,
|
| 2359 |
+
"loss": 0.2418,
|
| 2360 |
+
"step": 574
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 19.862068965517242,
|
| 2364 |
+
"grad_norm": 3.5628745555877686,
|
| 2365 |
+
"learning_rate": 7.662835249042146e-07,
|
| 2366 |
+
"loss": 0.4503,
|
| 2367 |
+
"step": 576
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 19.93103448275862,
|
| 2371 |
+
"grad_norm": 2.046889543533325,
|
| 2372 |
+
"learning_rate": 3.831417624521073e-07,
|
| 2373 |
+
"loss": 0.2689,
|
| 2374 |
+
"step": 578
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 20.0,
|
| 2378 |
+
"grad_norm": 1.0142828226089478,
|
| 2379 |
+
"learning_rate": 0.0,
|
| 2380 |
+
"loss": 0.4052,
|
| 2381 |
+
"step": 580
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 20.0,
|
| 2385 |
+
"eval_accuracy": 0.6590909090909091,
|
| 2386 |
+
"eval_f1_macro": 0.5683267149224223,
|
| 2387 |
+
"eval_f1_micro": 0.6590909090909091,
|
| 2388 |
+
"eval_f1_weighted": 0.6432058978241244,
|
| 2389 |
+
"eval_loss": 1.0934416055679321,
|
| 2390 |
+
"eval_precision_macro": 0.5681032097512798,
|
| 2391 |
+
"eval_precision_micro": 0.6590909090909091,
|
| 2392 |
+
"eval_precision_weighted": 0.6393054520079716,
|
| 2393 |
+
"eval_recall_macro": 0.5797581254724111,
|
| 2394 |
+
"eval_recall_micro": 0.6590909090909091,
|
| 2395 |
+
"eval_recall_weighted": 0.6590909090909091,
|
| 2396 |
+
"eval_runtime": 2.3382,
|
| 2397 |
+
"eval_samples_per_second": 56.454,
|
| 2398 |
+
"eval_steps_per_second": 7.271,
|
| 2399 |
+
"step": 580
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 20.0,
|
| 2403 |
+
"step": 580,
|
| 2404 |
+
"total_flos": 7.160580716109005e+17,
|
| 2405 |
+
"train_loss": 1.0144407548781098,
|
| 2406 |
+
"train_runtime": 564.1231,
|
| 2407 |
+
"train_samples_per_second": 16.379,
|
| 2408 |
+
"train_steps_per_second": 1.028
|
| 2409 |
+
}
|
| 2410 |
+
],
|
| 2411 |
+
"logging_steps": 2,
|
| 2412 |
+
"max_steps": 580,
|
| 2413 |
+
"num_input_tokens_seen": 0,
|
| 2414 |
+
"num_train_epochs": 20,
|
| 2415 |
+
"save_steps": 500,
|
| 2416 |
+
"stateful_callbacks": {
|
| 2417 |
+
"TrainerControl": {
|
| 2418 |
+
"args": {
|
| 2419 |
+
"should_epoch_stop": false,
|
| 2420 |
+
"should_evaluate": false,
|
| 2421 |
+
"should_log": false,
|
| 2422 |
+
"should_save": true,
|
| 2423 |
+
"should_training_stop": true
|
| 2424 |
+
},
|
| 2425 |
+
"attributes": {}
|
| 2426 |
+
}
|
| 2427 |
+
},
|
| 2428 |
+
"total_flos": 7.160580716109005e+17,
|
| 2429 |
+
"train_batch_size": 8,
|
| 2430 |
+
"trial_name": null,
|
| 2431 |
+
"trial_params": null
|
| 2432 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f27e42d077b3e0d5120101b33b80912067ee7a8b059ced3db427f67647da041
|
| 3 |
+
size 5368
|