End of training
Browse files- README.md +86 -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_20-35-20_modal/events.out.tfevents.1738528521.modal.2.0 +3 -0
- runs/Feb02_20-35-20_modal/events.out.tfevents.1738528521.modal.2.1 +3 -0
- runs/Feb02_20-35-20_modal/events.out.tfevents.1738528920.modal.2.2 +3 -0
- runs/Feb02_20-35-20_modal/events.out.tfevents.1738528920.modal.2.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +1724 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: squarerun_earlystop
|
| 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 |
+
# squarerun_earlystop
|
| 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: 1.3037
|
| 22 |
+
- F1 Macro: 0.4518
|
| 23 |
+
- F1 Micro: 0.5303
|
| 24 |
+
- F1 Weighted: 0.4968
|
| 25 |
+
- Precision Macro: 0.4451
|
| 26 |
+
- Precision Micro: 0.5303
|
| 27 |
+
- Precision Weighted: 0.4972
|
| 28 |
+
- Recall Macro: 0.4879
|
| 29 |
+
- Recall Micro: 0.5303
|
| 30 |
+
- Recall Weighted: 0.5303
|
| 31 |
+
- Accuracy: 0.5303
|
| 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: 40
|
| 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 |
+
| 1.9079 | 1.0 | 29 | 1.8821 | 0.0791 | 0.1894 | 0.1087 | 0.0565 | 0.1894 | 0.0775 | 0.1369 | 0.1894 | 0.1894 | 0.1894 |
|
| 66 |
+
| 1.8597 | 2.0 | 58 | 1.8469 | 0.1862 | 0.2879 | 0.2344 | 0.1884 | 0.2879 | 0.2345 | 0.2281 | 0.2879 | 0.2879 | 0.2879 |
|
| 67 |
+
| 1.9027 | 3.0 | 87 | 1.7611 | 0.1729 | 0.3106 | 0.2221 | 0.1526 | 0.3106 | 0.1941 | 0.2359 | 0.3106 | 0.3106 | 0.3106 |
|
| 68 |
+
| 1.5401 | 4.0 | 116 | 1.6302 | 0.2466 | 0.3788 | 0.3014 | 0.2602 | 0.3788 | 0.3007 | 0.2993 | 0.3788 | 0.3788 | 0.3788 |
|
| 69 |
+
| 1.4 | 5.0 | 145 | 1.5180 | 0.2897 | 0.3864 | 0.3245 | 0.4033 | 0.3864 | 0.4498 | 0.3426 | 0.3864 | 0.3864 | 0.3864 |
|
| 70 |
+
| 1.6258 | 6.0 | 174 | 1.4915 | 0.3342 | 0.4545 | 0.3925 | 0.4129 | 0.4545 | 0.4454 | 0.3678 | 0.4545 | 0.4545 | 0.4545 |
|
| 71 |
+
| 1.3579 | 7.0 | 203 | 1.3221 | 0.4270 | 0.5303 | 0.4918 | 0.4623 | 0.5303 | 0.5269 | 0.4614 | 0.5303 | 0.5303 | 0.5303 |
|
| 72 |
+
| 1.236 | 8.0 | 232 | 1.3025 | 0.4404 | 0.5303 | 0.5073 | 0.4672 | 0.5303 | 0.5370 | 0.4579 | 0.5303 | 0.5303 | 0.5303 |
|
| 73 |
+
| 0.7554 | 9.0 | 261 | 1.2687 | 0.4409 | 0.5227 | 0.5085 | 0.4555 | 0.5227 | 0.5196 | 0.4547 | 0.5227 | 0.5227 | 0.5227 |
|
| 74 |
+
| 1.2034 | 10.0 | 290 | 1.3682 | 0.4223 | 0.5152 | 0.4898 | 0.4735 | 0.5152 | 0.5571 | 0.4478 | 0.5152 | 0.5152 | 0.5152 |
|
| 75 |
+
| 0.8037 | 11.0 | 319 | 1.1536 | 0.5364 | 0.6212 | 0.6067 | 0.5305 | 0.6212 | 0.6093 | 0.5558 | 0.6212 | 0.6212 | 0.6212 |
|
| 76 |
+
| 0.593 | 12.0 | 348 | 1.4809 | 0.4485 | 0.4924 | 0.5033 | 0.5444 | 0.4924 | 0.6405 | 0.4709 | 0.4924 | 0.4924 | 0.4924 |
|
| 77 |
+
| 0.732 | 13.0 | 377 | 1.1918 | 0.5145 | 0.5909 | 0.5809 | 0.5642 | 0.5909 | 0.6448 | 0.5288 | 0.5909 | 0.5909 | 0.5909 |
|
| 78 |
+
| 0.8642 | 14.0 | 406 | 1.1884 | 0.5114 | 0.5985 | 0.5884 | 0.5284 | 0.5985 | 0.6108 | 0.5244 | 0.5985 | 0.5985 | 0.5985 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.48.1
|
| 84 |
+
- Pytorch 2.5.1+cu124
|
| 85 |
+
- Datasets 3.2.0
|
| 86 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.0,
|
| 3 |
+
"eval_accuracy": 0.5303030303030303,
|
| 4 |
+
"eval_f1_macro": 0.45183408691763977,
|
| 5 |
+
"eval_f1_micro": 0.5303030303030303,
|
| 6 |
+
"eval_f1_weighted": 0.4968217608209532,
|
| 7 |
+
"eval_loss": 1.3036777973175049,
|
| 8 |
+
"eval_precision_macro": 0.445124716553288,
|
| 9 |
+
"eval_precision_micro": 0.5303030303030303,
|
| 10 |
+
"eval_precision_weighted": 0.49716209716209714,
|
| 11 |
+
"eval_recall_macro": 0.4879251700680272,
|
| 12 |
+
"eval_recall_micro": 0.5303030303030303,
|
| 13 |
+
"eval_recall_weighted": 0.5303030303030303,
|
| 14 |
+
"eval_runtime": 1.189,
|
| 15 |
+
"eval_samples_per_second": 55.508,
|
| 16 |
+
"eval_steps_per_second": 7.569,
|
| 17 |
+
"total_flos": 5.0124065012763034e+17,
|
| 18 |
+
"train_loss": 1.2848335812831748,
|
| 19 |
+
"train_runtime": 397.0629,
|
| 20 |
+
"train_samples_per_second": 46.542,
|
| 21 |
+
"train_steps_per_second": 2.921
|
| 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": 14.0,
|
| 3 |
+
"eval_accuracy": 0.5303030303030303,
|
| 4 |
+
"eval_f1_macro": 0.45183408691763977,
|
| 5 |
+
"eval_f1_micro": 0.5303030303030303,
|
| 6 |
+
"eval_f1_weighted": 0.4968217608209532,
|
| 7 |
+
"eval_loss": 1.3036777973175049,
|
| 8 |
+
"eval_precision_macro": 0.445124716553288,
|
| 9 |
+
"eval_precision_micro": 0.5303030303030303,
|
| 10 |
+
"eval_precision_weighted": 0.49716209716209714,
|
| 11 |
+
"eval_recall_macro": 0.4879251700680272,
|
| 12 |
+
"eval_recall_micro": 0.5303030303030303,
|
| 13 |
+
"eval_recall_weighted": 0.5303030303030303,
|
| 14 |
+
"eval_runtime": 1.189,
|
| 15 |
+
"eval_samples_per_second": 55.508,
|
| 16 |
+
"eval_steps_per_second": 7.569
|
| 17 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fde8587a7577d39c089be75f061c2f32599a2e805e69552b9b6de60b76f901c2
|
| 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_20-35-20_modal/events.out.tfevents.1738528521.modal.2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7988713192aba71d98445af7221e854962f33fa1a3771a0b71f84087ae620c76
|
| 3 |
+
size 59688
|
runs/Feb02_20-35-20_modal/events.out.tfevents.1738528521.modal.2.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:042d1277f7a7c76a5f3500716dae9b0f3fecbd4ace040a8762d9e80c321adb0a
|
| 3 |
+
size 59688
|
runs/Feb02_20-35-20_modal/events.out.tfevents.1738528920.modal.2.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d41d5808b743cb0244412f1e9b69c89e7bae4fafae92150d0c6ce4a52014a62c
|
| 3 |
+
size 921
|
runs/Feb02_20-35-20_modal/events.out.tfevents.1738528920.modal.2.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60d1dad1e9944c6b3d9b467267fe98504cc35b9f9175ea3ac627b6279fd01a90
|
| 3 |
+
size 921
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.0,
|
| 3 |
+
"total_flos": 5.0124065012763034e+17,
|
| 4 |
+
"train_loss": 1.2848335812831748,
|
| 5 |
+
"train_runtime": 397.0629,
|
| 6 |
+
"train_samples_per_second": 46.542,
|
| 7 |
+
"train_steps_per_second": 2.921
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1724 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.1536208391189575,
|
| 3 |
+
"best_model_checkpoint": "squarerun_earlystop/checkpoint-319",
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 406,
|
| 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": 2.7594025135040283,
|
| 14 |
+
"learning_rate": 1.724137931034483e-06,
|
| 15 |
+
"loss": 1.9367,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13793103448275862,
|
| 20 |
+
"grad_norm": 1.8562699556350708,
|
| 21 |
+
"learning_rate": 3.448275862068966e-06,
|
| 22 |
+
"loss": 1.9474,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.20689655172413793,
|
| 27 |
+
"grad_norm": 2.0168490409851074,
|
| 28 |
+
"learning_rate": 5.172413793103448e-06,
|
| 29 |
+
"loss": 1.9574,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.27586206896551724,
|
| 34 |
+
"grad_norm": 1.8773648738861084,
|
| 35 |
+
"learning_rate": 6.896551724137932e-06,
|
| 36 |
+
"loss": 1.9342,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3448275862068966,
|
| 41 |
+
"grad_norm": 2.7246925830841064,
|
| 42 |
+
"learning_rate": 8.620689655172414e-06,
|
| 43 |
+
"loss": 1.9447,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.41379310344827586,
|
| 48 |
+
"grad_norm": 1.8781946897506714,
|
| 49 |
+
"learning_rate": 1.0344827586206897e-05,
|
| 50 |
+
"loss": 1.9496,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4827586206896552,
|
| 55 |
+
"grad_norm": 1.8623287677764893,
|
| 56 |
+
"learning_rate": 1.206896551724138e-05,
|
| 57 |
+
"loss": 1.9467,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5517241379310345,
|
| 62 |
+
"grad_norm": 1.9005070924758911,
|
| 63 |
+
"learning_rate": 1.3793103448275863e-05,
|
| 64 |
+
"loss": 1.9104,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.6206896551724138,
|
| 69 |
+
"grad_norm": 1.8667243719100952,
|
| 70 |
+
"learning_rate": 1.5517241379310346e-05,
|
| 71 |
+
"loss": 1.8702,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6896551724137931,
|
| 76 |
+
"grad_norm": 2.1068148612976074,
|
| 77 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 78 |
+
"loss": 1.9145,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.7586206896551724,
|
| 83 |
+
"grad_norm": 1.2688392400741577,
|
| 84 |
+
"learning_rate": 1.896551724137931e-05,
|
| 85 |
+
"loss": 1.9089,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.8275862068965517,
|
| 90 |
+
"grad_norm": 1.5856612920761108,
|
| 91 |
+
"learning_rate": 2.0689655172413793e-05,
|
| 92 |
+
"loss": 1.915,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.896551724137931,
|
| 97 |
+
"grad_norm": 2.54569935798645,
|
| 98 |
+
"learning_rate": 2.2413793103448276e-05,
|
| 99 |
+
"loss": 1.8866,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.9655172413793104,
|
| 104 |
+
"grad_norm": 1.6762207746505737,
|
| 105 |
+
"learning_rate": 2.413793103448276e-05,
|
| 106 |
+
"loss": 1.9079,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0,
|
| 111 |
+
"eval_accuracy": 0.1893939393939394,
|
| 112 |
+
"eval_f1_macro": 0.07908887360942154,
|
| 113 |
+
"eval_f1_micro": 0.1893939393939394,
|
| 114 |
+
"eval_f1_weighted": 0.10867467716782785,
|
| 115 |
+
"eval_loss": 1.8821076154708862,
|
| 116 |
+
"eval_precision_macro": 0.05654761904761905,
|
| 117 |
+
"eval_precision_micro": 0.1893939393939394,
|
| 118 |
+
"eval_precision_weighted": 0.07749368686868686,
|
| 119 |
+
"eval_recall_macro": 0.13693121693121693,
|
| 120 |
+
"eval_recall_micro": 0.1893939393939394,
|
| 121 |
+
"eval_recall_weighted": 0.1893939393939394,
|
| 122 |
+
"eval_runtime": 2.3123,
|
| 123 |
+
"eval_samples_per_second": 57.086,
|
| 124 |
+
"eval_steps_per_second": 7.352,
|
| 125 |
+
"step": 29
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.0344827586206897,
|
| 129 |
+
"grad_norm": 2.2096035480499268,
|
| 130 |
+
"learning_rate": 2.5862068965517244e-05,
|
| 131 |
+
"loss": 1.89,
|
| 132 |
+
"step": 30
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.103448275862069,
|
| 136 |
+
"grad_norm": 1.5493906736373901,
|
| 137 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 138 |
+
"loss": 1.8294,
|
| 139 |
+
"step": 32
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.1724137931034484,
|
| 143 |
+
"grad_norm": 1.3173717260360718,
|
| 144 |
+
"learning_rate": 2.9310344827586206e-05,
|
| 145 |
+
"loss": 1.8368,
|
| 146 |
+
"step": 34
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.2413793103448276,
|
| 150 |
+
"grad_norm": 1.1894272565841675,
|
| 151 |
+
"learning_rate": 3.103448275862069e-05,
|
| 152 |
+
"loss": 1.9087,
|
| 153 |
+
"step": 36
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.3103448275862069,
|
| 157 |
+
"grad_norm": 1.8291478157043457,
|
| 158 |
+
"learning_rate": 3.275862068965517e-05,
|
| 159 |
+
"loss": 1.8554,
|
| 160 |
+
"step": 38
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.3793103448275863,
|
| 164 |
+
"grad_norm": 1.853824257850647,
|
| 165 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 166 |
+
"loss": 1.8932,
|
| 167 |
+
"step": 40
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.4482758620689655,
|
| 171 |
+
"grad_norm": 1.5440897941589355,
|
| 172 |
+
"learning_rate": 3.620689655172414e-05,
|
| 173 |
+
"loss": 1.8864,
|
| 174 |
+
"step": 42
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.5172413793103448,
|
| 178 |
+
"grad_norm": 2.2528514862060547,
|
| 179 |
+
"learning_rate": 3.793103448275862e-05,
|
| 180 |
+
"loss": 1.8693,
|
| 181 |
+
"step": 44
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.5862068965517242,
|
| 185 |
+
"grad_norm": 1.5831176042556763,
|
| 186 |
+
"learning_rate": 3.965517241379311e-05,
|
| 187 |
+
"loss": 1.943,
|
| 188 |
+
"step": 46
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.6551724137931034,
|
| 192 |
+
"grad_norm": 1.6178966760635376,
|
| 193 |
+
"learning_rate": 4.1379310344827587e-05,
|
| 194 |
+
"loss": 1.8708,
|
| 195 |
+
"step": 48
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.7241379310344827,
|
| 199 |
+
"grad_norm": 1.557183027267456,
|
| 200 |
+
"learning_rate": 4.3103448275862066e-05,
|
| 201 |
+
"loss": 1.9144,
|
| 202 |
+
"step": 50
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.793103448275862,
|
| 206 |
+
"grad_norm": 1.8258789777755737,
|
| 207 |
+
"learning_rate": 4.482758620689655e-05,
|
| 208 |
+
"loss": 1.8375,
|
| 209 |
+
"step": 52
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.8620689655172413,
|
| 213 |
+
"grad_norm": 2.0916709899902344,
|
| 214 |
+
"learning_rate": 4.655172413793104e-05,
|
| 215 |
+
"loss": 1.9264,
|
| 216 |
+
"step": 54
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.9310344827586206,
|
| 220 |
+
"grad_norm": 2.1662747859954834,
|
| 221 |
+
"learning_rate": 4.827586206896552e-05,
|
| 222 |
+
"loss": 1.8365,
|
| 223 |
+
"step": 56
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.0,
|
| 227 |
+
"grad_norm": 1.7327982187271118,
|
| 228 |
+
"learning_rate": 5e-05,
|
| 229 |
+
"loss": 1.8597,
|
| 230 |
+
"step": 58
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.0,
|
| 234 |
+
"eval_accuracy": 0.2878787878787879,
|
| 235 |
+
"eval_f1_macro": 0.1861596677647032,
|
| 236 |
+
"eval_f1_micro": 0.2878787878787879,
|
| 237 |
+
"eval_f1_weighted": 0.23435453610119228,
|
| 238 |
+
"eval_loss": 1.8469468355178833,
|
| 239 |
+
"eval_precision_macro": 0.18836650821944942,
|
| 240 |
+
"eval_precision_micro": 0.2878787878787879,
|
| 241 |
+
"eval_precision_weighted": 0.23453479761969068,
|
| 242 |
+
"eval_recall_macro": 0.22805744520030236,
|
| 243 |
+
"eval_recall_micro": 0.2878787878787879,
|
| 244 |
+
"eval_recall_weighted": 0.2878787878787879,
|
| 245 |
+
"eval_runtime": 2.319,
|
| 246 |
+
"eval_samples_per_second": 56.921,
|
| 247 |
+
"eval_steps_per_second": 7.331,
|
| 248 |
+
"step": 58
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.0689655172413794,
|
| 252 |
+
"grad_norm": 2.041114091873169,
|
| 253 |
+
"learning_rate": 5.172413793103449e-05,
|
| 254 |
+
"loss": 1.8907,
|
| 255 |
+
"step": 60
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.1379310344827585,
|
| 259 |
+
"grad_norm": 1.7124186754226685,
|
| 260 |
+
"learning_rate": 5.344827586206896e-05,
|
| 261 |
+
"loss": 1.8079,
|
| 262 |
+
"step": 62
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.206896551724138,
|
| 266 |
+
"grad_norm": 2.1433985233306885,
|
| 267 |
+
"learning_rate": 5.517241379310345e-05,
|
| 268 |
+
"loss": 1.8424,
|
| 269 |
+
"step": 64
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.2758620689655173,
|
| 273 |
+
"grad_norm": 2.639194965362549,
|
| 274 |
+
"learning_rate": 5.689655172413794e-05,
|
| 275 |
+
"loss": 1.907,
|
| 276 |
+
"step": 66
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.344827586206897,
|
| 280 |
+
"grad_norm": 1.93711519241333,
|
| 281 |
+
"learning_rate": 5.862068965517241e-05,
|
| 282 |
+
"loss": 1.7818,
|
| 283 |
+
"step": 68
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.413793103448276,
|
| 287 |
+
"grad_norm": 2.6230249404907227,
|
| 288 |
+
"learning_rate": 6.03448275862069e-05,
|
| 289 |
+
"loss": 1.8183,
|
| 290 |
+
"step": 70
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.4827586206896552,
|
| 294 |
+
"grad_norm": 1.7783054113388062,
|
| 295 |
+
"learning_rate": 6.206896551724138e-05,
|
| 296 |
+
"loss": 1.8002,
|
| 297 |
+
"step": 72
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.5517241379310347,
|
| 301 |
+
"grad_norm": 1.6677814722061157,
|
| 302 |
+
"learning_rate": 6.379310344827587e-05,
|
| 303 |
+
"loss": 1.788,
|
| 304 |
+
"step": 74
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.6206896551724137,
|
| 308 |
+
"grad_norm": 2.2913436889648438,
|
| 309 |
+
"learning_rate": 6.551724137931034e-05,
|
| 310 |
+
"loss": 1.8614,
|
| 311 |
+
"step": 76
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.689655172413793,
|
| 315 |
+
"grad_norm": 2.1580638885498047,
|
| 316 |
+
"learning_rate": 6.724137931034483e-05,
|
| 317 |
+
"loss": 1.9277,
|
| 318 |
+
"step": 78
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.7586206896551726,
|
| 322 |
+
"grad_norm": 2.206195831298828,
|
| 323 |
+
"learning_rate": 6.896551724137931e-05,
|
| 324 |
+
"loss": 1.8815,
|
| 325 |
+
"step": 80
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.8275862068965516,
|
| 329 |
+
"grad_norm": 1.749338150024414,
|
| 330 |
+
"learning_rate": 7.06896551724138e-05,
|
| 331 |
+
"loss": 1.7088,
|
| 332 |
+
"step": 82
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.896551724137931,
|
| 336 |
+
"grad_norm": 1.626955270767212,
|
| 337 |
+
"learning_rate": 7.241379310344828e-05,
|
| 338 |
+
"loss": 1.8376,
|
| 339 |
+
"step": 84
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.9655172413793105,
|
| 343 |
+
"grad_norm": 1.9347732067108154,
|
| 344 |
+
"learning_rate": 7.413793103448277e-05,
|
| 345 |
+
"loss": 1.9027,
|
| 346 |
+
"step": 86
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.0,
|
| 350 |
+
"eval_accuracy": 0.3106060606060606,
|
| 351 |
+
"eval_f1_macro": 0.17294549642243576,
|
| 352 |
+
"eval_f1_micro": 0.3106060606060606,
|
| 353 |
+
"eval_f1_weighted": 0.22206095246104496,
|
| 354 |
+
"eval_loss": 1.7611310482025146,
|
| 355 |
+
"eval_precision_macro": 0.15255920550038196,
|
| 356 |
+
"eval_precision_micro": 0.3106060606060606,
|
| 357 |
+
"eval_precision_weighted": 0.1940568789499271,
|
| 358 |
+
"eval_recall_macro": 0.23585789871504156,
|
| 359 |
+
"eval_recall_micro": 0.3106060606060606,
|
| 360 |
+
"eval_recall_weighted": 0.3106060606060606,
|
| 361 |
+
"eval_runtime": 2.3347,
|
| 362 |
+
"eval_samples_per_second": 56.539,
|
| 363 |
+
"eval_steps_per_second": 7.282,
|
| 364 |
+
"step": 87
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 3.0344827586206895,
|
| 368 |
+
"grad_norm": 2.2112436294555664,
|
| 369 |
+
"learning_rate": 7.586206896551724e-05,
|
| 370 |
+
"loss": 1.8942,
|
| 371 |
+
"step": 88
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.103448275862069,
|
| 375 |
+
"grad_norm": 1.7872307300567627,
|
| 376 |
+
"learning_rate": 7.758620689655173e-05,
|
| 377 |
+
"loss": 1.662,
|
| 378 |
+
"step": 90
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.1724137931034484,
|
| 382 |
+
"grad_norm": 1.9869877099990845,
|
| 383 |
+
"learning_rate": 7.931034482758621e-05,
|
| 384 |
+
"loss": 1.7751,
|
| 385 |
+
"step": 92
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 3.2413793103448274,
|
| 389 |
+
"grad_norm": 2.021848440170288,
|
| 390 |
+
"learning_rate": 8.103448275862069e-05,
|
| 391 |
+
"loss": 1.7261,
|
| 392 |
+
"step": 94
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.310344827586207,
|
| 396 |
+
"grad_norm": 3.4642999172210693,
|
| 397 |
+
"learning_rate": 8.275862068965517e-05,
|
| 398 |
+
"loss": 1.774,
|
| 399 |
+
"step": 96
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.3793103448275863,
|
| 403 |
+
"grad_norm": 2.333994150161743,
|
| 404 |
+
"learning_rate": 8.448275862068966e-05,
|
| 405 |
+
"loss": 1.7085,
|
| 406 |
+
"step": 98
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 3.4482758620689653,
|
| 410 |
+
"grad_norm": 2.7643978595733643,
|
| 411 |
+
"learning_rate": 8.620689655172413e-05,
|
| 412 |
+
"loss": 1.6867,
|
| 413 |
+
"step": 100
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.5172413793103448,
|
| 417 |
+
"grad_norm": 2.4885361194610596,
|
| 418 |
+
"learning_rate": 8.793103448275862e-05,
|
| 419 |
+
"loss": 1.8514,
|
| 420 |
+
"step": 102
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.586206896551724,
|
| 424 |
+
"grad_norm": 1.7879903316497803,
|
| 425 |
+
"learning_rate": 8.96551724137931e-05,
|
| 426 |
+
"loss": 1.639,
|
| 427 |
+
"step": 104
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 3.655172413793103,
|
| 431 |
+
"grad_norm": 3.6773548126220703,
|
| 432 |
+
"learning_rate": 9.137931034482759e-05,
|
| 433 |
+
"loss": 1.7757,
|
| 434 |
+
"step": 106
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.7241379310344827,
|
| 438 |
+
"grad_norm": 2.4036428928375244,
|
| 439 |
+
"learning_rate": 9.310344827586207e-05,
|
| 440 |
+
"loss": 1.6385,
|
| 441 |
+
"step": 108
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.793103448275862,
|
| 445 |
+
"grad_norm": 2.5688936710357666,
|
| 446 |
+
"learning_rate": 9.482758620689656e-05,
|
| 447 |
+
"loss": 1.6298,
|
| 448 |
+
"step": 110
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.862068965517241,
|
| 452 |
+
"grad_norm": 3.3116631507873535,
|
| 453 |
+
"learning_rate": 9.655172413793105e-05,
|
| 454 |
+
"loss": 1.7618,
|
| 455 |
+
"step": 112
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.9310344827586206,
|
| 459 |
+
"grad_norm": 2.488884925842285,
|
| 460 |
+
"learning_rate": 9.827586206896552e-05,
|
| 461 |
+
"loss": 1.567,
|
| 462 |
+
"step": 114
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.0,
|
| 466 |
+
"grad_norm": 2.22160005569458,
|
| 467 |
+
"learning_rate": 0.0001,
|
| 468 |
+
"loss": 1.5401,
|
| 469 |
+
"step": 116
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 4.0,
|
| 473 |
+
"eval_accuracy": 0.3787878787878788,
|
| 474 |
+
"eval_f1_macro": 0.2465531802753436,
|
| 475 |
+
"eval_f1_micro": 0.3787878787878788,
|
| 476 |
+
"eval_f1_weighted": 0.3014117539447724,
|
| 477 |
+
"eval_loss": 1.630239486694336,
|
| 478 |
+
"eval_precision_macro": 0.2601781537007802,
|
| 479 |
+
"eval_precision_micro": 0.3787878787878788,
|
| 480 |
+
"eval_precision_weighted": 0.30067037235303745,
|
| 481 |
+
"eval_recall_macro": 0.29933484504913077,
|
| 482 |
+
"eval_recall_micro": 0.3787878787878788,
|
| 483 |
+
"eval_recall_weighted": 0.3787878787878788,
|
| 484 |
+
"eval_runtime": 2.2953,
|
| 485 |
+
"eval_samples_per_second": 57.508,
|
| 486 |
+
"eval_steps_per_second": 7.406,
|
| 487 |
+
"step": 116
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 4.068965517241379,
|
| 491 |
+
"grad_norm": 4.651881694793701,
|
| 492 |
+
"learning_rate": 9.980842911877395e-05,
|
| 493 |
+
"loss": 1.5738,
|
| 494 |
+
"step": 118
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.137931034482759,
|
| 498 |
+
"grad_norm": 2.5916430950164795,
|
| 499 |
+
"learning_rate": 9.96168582375479e-05,
|
| 500 |
+
"loss": 1.5169,
|
| 501 |
+
"step": 120
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.206896551724138,
|
| 505 |
+
"grad_norm": 2.5187177658081055,
|
| 506 |
+
"learning_rate": 9.942528735632183e-05,
|
| 507 |
+
"loss": 1.5412,
|
| 508 |
+
"step": 122
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 4.275862068965517,
|
| 512 |
+
"grad_norm": 3.8361008167266846,
|
| 513 |
+
"learning_rate": 9.92337164750958e-05,
|
| 514 |
+
"loss": 1.4326,
|
| 515 |
+
"step": 124
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.344827586206897,
|
| 519 |
+
"grad_norm": 2.278944969177246,
|
| 520 |
+
"learning_rate": 9.904214559386974e-05,
|
| 521 |
+
"loss": 1.5543,
|
| 522 |
+
"step": 126
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.413793103448276,
|
| 526 |
+
"grad_norm": 3.5142998695373535,
|
| 527 |
+
"learning_rate": 9.885057471264369e-05,
|
| 528 |
+
"loss": 1.452,
|
| 529 |
+
"step": 128
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 4.482758620689655,
|
| 533 |
+
"grad_norm": 2.6121275424957275,
|
| 534 |
+
"learning_rate": 9.865900383141762e-05,
|
| 535 |
+
"loss": 1.7841,
|
| 536 |
+
"step": 130
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.551724137931035,
|
| 540 |
+
"grad_norm": 3.0184738636016846,
|
| 541 |
+
"learning_rate": 9.846743295019157e-05,
|
| 542 |
+
"loss": 1.7388,
|
| 543 |
+
"step": 132
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.620689655172414,
|
| 547 |
+
"grad_norm": 2.688973903656006,
|
| 548 |
+
"learning_rate": 9.827586206896552e-05,
|
| 549 |
+
"loss": 1.6655,
|
| 550 |
+
"step": 134
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 4.689655172413794,
|
| 554 |
+
"grad_norm": 3.4905381202697754,
|
| 555 |
+
"learning_rate": 9.808429118773947e-05,
|
| 556 |
+
"loss": 1.6848,
|
| 557 |
+
"step": 136
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 4.758620689655173,
|
| 561 |
+
"grad_norm": 4.4559783935546875,
|
| 562 |
+
"learning_rate": 9.789272030651341e-05,
|
| 563 |
+
"loss": 1.5301,
|
| 564 |
+
"step": 138
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 4.827586206896552,
|
| 568 |
+
"grad_norm": 2.9265379905700684,
|
| 569 |
+
"learning_rate": 9.770114942528736e-05,
|
| 570 |
+
"loss": 1.5221,
|
| 571 |
+
"step": 140
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 4.896551724137931,
|
| 575 |
+
"grad_norm": 3.7354650497436523,
|
| 576 |
+
"learning_rate": 9.750957854406131e-05,
|
| 577 |
+
"loss": 1.6706,
|
| 578 |
+
"step": 142
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.9655172413793105,
|
| 582 |
+
"grad_norm": 1.8896524906158447,
|
| 583 |
+
"learning_rate": 9.731800766283526e-05,
|
| 584 |
+
"loss": 1.4,
|
| 585 |
+
"step": 144
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 5.0,
|
| 589 |
+
"eval_accuracy": 0.38636363636363635,
|
| 590 |
+
"eval_f1_macro": 0.28971739759733683,
|
| 591 |
+
"eval_f1_micro": 0.38636363636363635,
|
| 592 |
+
"eval_f1_weighted": 0.3245222936047404,
|
| 593 |
+
"eval_loss": 1.5179905891418457,
|
| 594 |
+
"eval_precision_macro": 0.40333043562252485,
|
| 595 |
+
"eval_precision_micro": 0.38636363636363635,
|
| 596 |
+
"eval_precision_weighted": 0.4498278935398611,
|
| 597 |
+
"eval_recall_macro": 0.342562358276644,
|
| 598 |
+
"eval_recall_micro": 0.38636363636363635,
|
| 599 |
+
"eval_recall_weighted": 0.38636363636363635,
|
| 600 |
+
"eval_runtime": 2.3124,
|
| 601 |
+
"eval_samples_per_second": 57.084,
|
| 602 |
+
"eval_steps_per_second": 7.352,
|
| 603 |
+
"step": 145
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.0344827586206895,
|
| 607 |
+
"grad_norm": 3.1451351642608643,
|
| 608 |
+
"learning_rate": 9.71264367816092e-05,
|
| 609 |
+
"loss": 1.7405,
|
| 610 |
+
"step": 146
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 5.103448275862069,
|
| 614 |
+
"grad_norm": 3.222198247909546,
|
| 615 |
+
"learning_rate": 9.693486590038314e-05,
|
| 616 |
+
"loss": 1.4106,
|
| 617 |
+
"step": 148
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.172413793103448,
|
| 621 |
+
"grad_norm": 3.350672721862793,
|
| 622 |
+
"learning_rate": 9.674329501915709e-05,
|
| 623 |
+
"loss": 1.3386,
|
| 624 |
+
"step": 150
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.241379310344827,
|
| 628 |
+
"grad_norm": 3.2664127349853516,
|
| 629 |
+
"learning_rate": 9.655172413793105e-05,
|
| 630 |
+
"loss": 1.2624,
|
| 631 |
+
"step": 152
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 5.310344827586207,
|
| 635 |
+
"grad_norm": 3.0906858444213867,
|
| 636 |
+
"learning_rate": 9.6360153256705e-05,
|
| 637 |
+
"loss": 1.4569,
|
| 638 |
+
"step": 154
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 5.379310344827586,
|
| 642 |
+
"grad_norm": 3.0391974449157715,
|
| 643 |
+
"learning_rate": 9.616858237547893e-05,
|
| 644 |
+
"loss": 1.3857,
|
| 645 |
+
"step": 156
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.448275862068965,
|
| 649 |
+
"grad_norm": 4.365240573883057,
|
| 650 |
+
"learning_rate": 9.597701149425288e-05,
|
| 651 |
+
"loss": 1.4081,
|
| 652 |
+
"step": 158
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 5.517241379310345,
|
| 656 |
+
"grad_norm": 2.9517900943756104,
|
| 657 |
+
"learning_rate": 9.578544061302682e-05,
|
| 658 |
+
"loss": 1.2797,
|
| 659 |
+
"step": 160
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.586206896551724,
|
| 663 |
+
"grad_norm": 4.0065693855285645,
|
| 664 |
+
"learning_rate": 9.559386973180077e-05,
|
| 665 |
+
"loss": 1.6445,
|
| 666 |
+
"step": 162
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.655172413793103,
|
| 670 |
+
"grad_norm": 3.3533987998962402,
|
| 671 |
+
"learning_rate": 9.540229885057472e-05,
|
| 672 |
+
"loss": 1.4004,
|
| 673 |
+
"step": 164
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 5.724137931034483,
|
| 677 |
+
"grad_norm": 2.4490716457366943,
|
| 678 |
+
"learning_rate": 9.521072796934867e-05,
|
| 679 |
+
"loss": 1.29,
|
| 680 |
+
"step": 166
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 5.793103448275862,
|
| 684 |
+
"grad_norm": 3.6202354431152344,
|
| 685 |
+
"learning_rate": 9.501915708812261e-05,
|
| 686 |
+
"loss": 1.5721,
|
| 687 |
+
"step": 168
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 5.862068965517241,
|
| 691 |
+
"grad_norm": 3.9141111373901367,
|
| 692 |
+
"learning_rate": 9.482758620689656e-05,
|
| 693 |
+
"loss": 1.3968,
|
| 694 |
+
"step": 170
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 5.931034482758621,
|
| 698 |
+
"grad_norm": 3.4564762115478516,
|
| 699 |
+
"learning_rate": 9.463601532567051e-05,
|
| 700 |
+
"loss": 1.7216,
|
| 701 |
+
"step": 172
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 6.0,
|
| 705 |
+
"grad_norm": 3.0670645236968994,
|
| 706 |
+
"learning_rate": 9.444444444444444e-05,
|
| 707 |
+
"loss": 1.6258,
|
| 708 |
+
"step": 174
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 6.0,
|
| 712 |
+
"eval_accuracy": 0.45454545454545453,
|
| 713 |
+
"eval_f1_macro": 0.33417309051028693,
|
| 714 |
+
"eval_f1_micro": 0.45454545454545453,
|
| 715 |
+
"eval_f1_weighted": 0.39252059608411566,
|
| 716 |
+
"eval_loss": 1.4914804697036743,
|
| 717 |
+
"eval_precision_macro": 0.4129126120204563,
|
| 718 |
+
"eval_precision_micro": 0.45454545454545453,
|
| 719 |
+
"eval_precision_weighted": 0.44543409915562315,
|
| 720 |
+
"eval_recall_macro": 0.3678155706727135,
|
| 721 |
+
"eval_recall_micro": 0.45454545454545453,
|
| 722 |
+
"eval_recall_weighted": 0.45454545454545453,
|
| 723 |
+
"eval_runtime": 2.3235,
|
| 724 |
+
"eval_samples_per_second": 56.81,
|
| 725 |
+
"eval_steps_per_second": 7.316,
|
| 726 |
+
"step": 174
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 6.068965517241379,
|
| 730 |
+
"grad_norm": 4.329052925109863,
|
| 731 |
+
"learning_rate": 9.425287356321839e-05,
|
| 732 |
+
"loss": 1.2878,
|
| 733 |
+
"step": 176
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 6.137931034482759,
|
| 737 |
+
"grad_norm": 3.1268393993377686,
|
| 738 |
+
"learning_rate": 9.406130268199235e-05,
|
| 739 |
+
"loss": 1.3256,
|
| 740 |
+
"step": 178
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 6.206896551724138,
|
| 744 |
+
"grad_norm": 3.9881491661071777,
|
| 745 |
+
"learning_rate": 9.38697318007663e-05,
|
| 746 |
+
"loss": 1.3112,
|
| 747 |
+
"step": 180
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 6.275862068965517,
|
| 751 |
+
"grad_norm": 2.776026964187622,
|
| 752 |
+
"learning_rate": 9.367816091954023e-05,
|
| 753 |
+
"loss": 1.466,
|
| 754 |
+
"step": 182
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 6.344827586206897,
|
| 758 |
+
"grad_norm": 4.8603949546813965,
|
| 759 |
+
"learning_rate": 9.348659003831418e-05,
|
| 760 |
+
"loss": 1.4044,
|
| 761 |
+
"step": 184
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 6.413793103448276,
|
| 765 |
+
"grad_norm": 2.983745813369751,
|
| 766 |
+
"learning_rate": 9.329501915708813e-05,
|
| 767 |
+
"loss": 1.1204,
|
| 768 |
+
"step": 186
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 6.482758620689655,
|
| 772 |
+
"grad_norm": 2.8195648193359375,
|
| 773 |
+
"learning_rate": 9.310344827586207e-05,
|
| 774 |
+
"loss": 1.2529,
|
| 775 |
+
"step": 188
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 6.551724137931035,
|
| 779 |
+
"grad_norm": 2.048353910446167,
|
| 780 |
+
"learning_rate": 9.291187739463601e-05,
|
| 781 |
+
"loss": 1.2915,
|
| 782 |
+
"step": 190
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 6.620689655172414,
|
| 786 |
+
"grad_norm": 3.2794029712677,
|
| 787 |
+
"learning_rate": 9.272030651340997e-05,
|
| 788 |
+
"loss": 1.1726,
|
| 789 |
+
"step": 192
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.689655172413794,
|
| 793 |
+
"grad_norm": 2.7745888233184814,
|
| 794 |
+
"learning_rate": 9.252873563218392e-05,
|
| 795 |
+
"loss": 1.2873,
|
| 796 |
+
"step": 194
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 6.758620689655173,
|
| 800 |
+
"grad_norm": 3.1752567291259766,
|
| 801 |
+
"learning_rate": 9.233716475095786e-05,
|
| 802 |
+
"loss": 1.4572,
|
| 803 |
+
"step": 196
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 6.827586206896552,
|
| 807 |
+
"grad_norm": 2.956439971923828,
|
| 808 |
+
"learning_rate": 9.21455938697318e-05,
|
| 809 |
+
"loss": 1.15,
|
| 810 |
+
"step": 198
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 6.896551724137931,
|
| 814 |
+
"grad_norm": 4.599544048309326,
|
| 815 |
+
"learning_rate": 9.195402298850575e-05,
|
| 816 |
+
"loss": 1.0882,
|
| 817 |
+
"step": 200
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 6.9655172413793105,
|
| 821 |
+
"grad_norm": 2.18859601020813,
|
| 822 |
+
"learning_rate": 9.17624521072797e-05,
|
| 823 |
+
"loss": 1.3579,
|
| 824 |
+
"step": 202
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 7.0,
|
| 828 |
+
"eval_accuracy": 0.5303030303030303,
|
| 829 |
+
"eval_f1_macro": 0.4270098934408117,
|
| 830 |
+
"eval_f1_micro": 0.5303030303030303,
|
| 831 |
+
"eval_f1_weighted": 0.4917944808690925,
|
| 832 |
+
"eval_loss": 1.3220996856689453,
|
| 833 |
+
"eval_precision_macro": 0.4622853094839513,
|
| 834 |
+
"eval_precision_micro": 0.5303030303030303,
|
| 835 |
+
"eval_precision_weighted": 0.5269497784546403,
|
| 836 |
+
"eval_recall_macro": 0.4613756613756614,
|
| 837 |
+
"eval_recall_micro": 0.5303030303030303,
|
| 838 |
+
"eval_recall_weighted": 0.5303030303030303,
|
| 839 |
+
"eval_runtime": 2.3356,
|
| 840 |
+
"eval_samples_per_second": 56.518,
|
| 841 |
+
"eval_steps_per_second": 7.279,
|
| 842 |
+
"step": 203
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 7.0344827586206895,
|
| 846 |
+
"grad_norm": 3.5771939754486084,
|
| 847 |
+
"learning_rate": 9.157088122605364e-05,
|
| 848 |
+
"loss": 1.1677,
|
| 849 |
+
"step": 204
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 7.103448275862069,
|
| 853 |
+
"grad_norm": 4.361037254333496,
|
| 854 |
+
"learning_rate": 9.137931034482759e-05,
|
| 855 |
+
"loss": 1.1697,
|
| 856 |
+
"step": 206
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 7.172413793103448,
|
| 860 |
+
"grad_norm": 3.966294527053833,
|
| 861 |
+
"learning_rate": 9.118773946360154e-05,
|
| 862 |
+
"loss": 1.4308,
|
| 863 |
+
"step": 208
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 7.241379310344827,
|
| 867 |
+
"grad_norm": 3.7766764163970947,
|
| 868 |
+
"learning_rate": 9.099616858237548e-05,
|
| 869 |
+
"loss": 1.2745,
|
| 870 |
+
"step": 210
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 7.310344827586207,
|
| 874 |
+
"grad_norm": 3.12256121635437,
|
| 875 |
+
"learning_rate": 9.080459770114943e-05,
|
| 876 |
+
"loss": 1.246,
|
| 877 |
+
"step": 212
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 7.379310344827586,
|
| 881 |
+
"grad_norm": 6.705962657928467,
|
| 882 |
+
"learning_rate": 9.061302681992338e-05,
|
| 883 |
+
"loss": 1.0487,
|
| 884 |
+
"step": 214
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 7.448275862068965,
|
| 888 |
+
"grad_norm": 3.5392026901245117,
|
| 889 |
+
"learning_rate": 9.042145593869731e-05,
|
| 890 |
+
"loss": 1.3188,
|
| 891 |
+
"step": 216
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 7.517241379310345,
|
| 895 |
+
"grad_norm": 3.6603386402130127,
|
| 896 |
+
"learning_rate": 9.022988505747126e-05,
|
| 897 |
+
"loss": 1.1814,
|
| 898 |
+
"step": 218
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 7.586206896551724,
|
| 902 |
+
"grad_norm": 3.4975929260253906,
|
| 903 |
+
"learning_rate": 9.003831417624522e-05,
|
| 904 |
+
"loss": 1.1921,
|
| 905 |
+
"step": 220
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 7.655172413793103,
|
| 909 |
+
"grad_norm": 2.4388949871063232,
|
| 910 |
+
"learning_rate": 8.984674329501917e-05,
|
| 911 |
+
"loss": 1.1733,
|
| 912 |
+
"step": 222
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 7.724137931034483,
|
| 916 |
+
"grad_norm": 4.060675621032715,
|
| 917 |
+
"learning_rate": 8.96551724137931e-05,
|
| 918 |
+
"loss": 1.1269,
|
| 919 |
+
"step": 224
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 7.793103448275862,
|
| 923 |
+
"grad_norm": 4.740964412689209,
|
| 924 |
+
"learning_rate": 8.946360153256705e-05,
|
| 925 |
+
"loss": 1.312,
|
| 926 |
+
"step": 226
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 7.862068965517241,
|
| 930 |
+
"grad_norm": 2.808018922805786,
|
| 931 |
+
"learning_rate": 8.9272030651341e-05,
|
| 932 |
+
"loss": 1.0676,
|
| 933 |
+
"step": 228
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 7.931034482758621,
|
| 937 |
+
"grad_norm": 3.1474294662475586,
|
| 938 |
+
"learning_rate": 8.908045977011495e-05,
|
| 939 |
+
"loss": 1.3769,
|
| 940 |
+
"step": 230
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 8.0,
|
| 944 |
+
"grad_norm": 3.1077136993408203,
|
| 945 |
+
"learning_rate": 8.888888888888889e-05,
|
| 946 |
+
"loss": 1.236,
|
| 947 |
+
"step": 232
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 8.0,
|
| 951 |
+
"eval_accuracy": 0.5303030303030303,
|
| 952 |
+
"eval_f1_macro": 0.4404058178034977,
|
| 953 |
+
"eval_f1_micro": 0.5303030303030303,
|
| 954 |
+
"eval_f1_weighted": 0.5073458619011424,
|
| 955 |
+
"eval_loss": 1.3025015592575073,
|
| 956 |
+
"eval_precision_macro": 0.4672230220942427,
|
| 957 |
+
"eval_precision_micro": 0.5303030303030303,
|
| 958 |
+
"eval_precision_weighted": 0.5369953051160421,
|
| 959 |
+
"eval_recall_macro": 0.4579365079365079,
|
| 960 |
+
"eval_recall_micro": 0.5303030303030303,
|
| 961 |
+
"eval_recall_weighted": 0.5303030303030303,
|
| 962 |
+
"eval_runtime": 2.3164,
|
| 963 |
+
"eval_samples_per_second": 56.984,
|
| 964 |
+
"eval_steps_per_second": 7.339,
|
| 965 |
+
"step": 232
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 8.068965517241379,
|
| 969 |
+
"grad_norm": 4.443036079406738,
|
| 970 |
+
"learning_rate": 8.869731800766284e-05,
|
| 971 |
+
"loss": 1.0253,
|
| 972 |
+
"step": 234
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 8.137931034482758,
|
| 976 |
+
"grad_norm": 4.066115856170654,
|
| 977 |
+
"learning_rate": 8.850574712643679e-05,
|
| 978 |
+
"loss": 1.0771,
|
| 979 |
+
"step": 236
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 8.206896551724139,
|
| 983 |
+
"grad_norm": 4.220799446105957,
|
| 984 |
+
"learning_rate": 8.831417624521074e-05,
|
| 985 |
+
"loss": 1.1984,
|
| 986 |
+
"step": 238
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 8.275862068965518,
|
| 990 |
+
"grad_norm": 2.096390962600708,
|
| 991 |
+
"learning_rate": 8.812260536398468e-05,
|
| 992 |
+
"loss": 1.0571,
|
| 993 |
+
"step": 240
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 8.344827586206897,
|
| 997 |
+
"grad_norm": 2.7211785316467285,
|
| 998 |
+
"learning_rate": 8.793103448275862e-05,
|
| 999 |
+
"loss": 1.0065,
|
| 1000 |
+
"step": 242
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 8.413793103448276,
|
| 1004 |
+
"grad_norm": 3.908750534057617,
|
| 1005 |
+
"learning_rate": 8.773946360153256e-05,
|
| 1006 |
+
"loss": 1.146,
|
| 1007 |
+
"step": 244
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 8.482758620689655,
|
| 1011 |
+
"grad_norm": 3.5071165561676025,
|
| 1012 |
+
"learning_rate": 8.754789272030651e-05,
|
| 1013 |
+
"loss": 1.079,
|
| 1014 |
+
"step": 246
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 8.551724137931034,
|
| 1018 |
+
"grad_norm": 2.588198184967041,
|
| 1019 |
+
"learning_rate": 8.735632183908047e-05,
|
| 1020 |
+
"loss": 1.0779,
|
| 1021 |
+
"step": 248
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 8.620689655172415,
|
| 1025 |
+
"grad_norm": 2.8031132221221924,
|
| 1026 |
+
"learning_rate": 8.716475095785441e-05,
|
| 1027 |
+
"loss": 1.2069,
|
| 1028 |
+
"step": 250
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 8.689655172413794,
|
| 1032 |
+
"grad_norm": 3.2936129570007324,
|
| 1033 |
+
"learning_rate": 8.697318007662835e-05,
|
| 1034 |
+
"loss": 1.0423,
|
| 1035 |
+
"step": 252
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 8.758620689655173,
|
| 1039 |
+
"grad_norm": 3.772505760192871,
|
| 1040 |
+
"learning_rate": 8.67816091954023e-05,
|
| 1041 |
+
"loss": 1.2322,
|
| 1042 |
+
"step": 254
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 8.827586206896552,
|
| 1046 |
+
"grad_norm": 5.190494060516357,
|
| 1047 |
+
"learning_rate": 8.659003831417625e-05,
|
| 1048 |
+
"loss": 1.1618,
|
| 1049 |
+
"step": 256
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 8.89655172413793,
|
| 1053 |
+
"grad_norm": 3.416548728942871,
|
| 1054 |
+
"learning_rate": 8.63984674329502e-05,
|
| 1055 |
+
"loss": 1.2072,
|
| 1056 |
+
"step": 258
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 8.96551724137931,
|
| 1060 |
+
"grad_norm": 3.05737566947937,
|
| 1061 |
+
"learning_rate": 8.620689655172413e-05,
|
| 1062 |
+
"loss": 0.7554,
|
| 1063 |
+
"step": 260
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 9.0,
|
| 1067 |
+
"eval_accuracy": 0.5227272727272727,
|
| 1068 |
+
"eval_f1_macro": 0.4409491354837298,
|
| 1069 |
+
"eval_f1_micro": 0.5227272727272727,
|
| 1070 |
+
"eval_f1_weighted": 0.5085484244400937,
|
| 1071 |
+
"eval_loss": 1.2686671018600464,
|
| 1072 |
+
"eval_precision_macro": 0.4555427282335717,
|
| 1073 |
+
"eval_precision_micro": 0.5227272727272727,
|
| 1074 |
+
"eval_precision_weighted": 0.5195899195431687,
|
| 1075 |
+
"eval_recall_macro": 0.45465608465608465,
|
| 1076 |
+
"eval_recall_micro": 0.5227272727272727,
|
| 1077 |
+
"eval_recall_weighted": 0.5227272727272727,
|
| 1078 |
+
"eval_runtime": 2.311,
|
| 1079 |
+
"eval_samples_per_second": 57.118,
|
| 1080 |
+
"eval_steps_per_second": 7.356,
|
| 1081 |
+
"step": 261
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 9.03448275862069,
|
| 1085 |
+
"grad_norm": 3.317532539367676,
|
| 1086 |
+
"learning_rate": 8.601532567049809e-05,
|
| 1087 |
+
"loss": 1.0184,
|
| 1088 |
+
"step": 262
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 9.10344827586207,
|
| 1092 |
+
"grad_norm": 2.7105941772460938,
|
| 1093 |
+
"learning_rate": 8.582375478927204e-05,
|
| 1094 |
+
"loss": 1.001,
|
| 1095 |
+
"step": 264
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 9.172413793103448,
|
| 1099 |
+
"grad_norm": 4.116084575653076,
|
| 1100 |
+
"learning_rate": 8.563218390804599e-05,
|
| 1101 |
+
"loss": 1.1204,
|
| 1102 |
+
"step": 266
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 9.241379310344827,
|
| 1106 |
+
"grad_norm": 2.512586832046509,
|
| 1107 |
+
"learning_rate": 8.544061302681992e-05,
|
| 1108 |
+
"loss": 0.784,
|
| 1109 |
+
"step": 268
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 9.310344827586206,
|
| 1113 |
+
"grad_norm": 3.6794638633728027,
|
| 1114 |
+
"learning_rate": 8.524904214559387e-05,
|
| 1115 |
+
"loss": 0.9,
|
| 1116 |
+
"step": 270
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 9.379310344827585,
|
| 1120 |
+
"grad_norm": 4.9960832595825195,
|
| 1121 |
+
"learning_rate": 8.505747126436782e-05,
|
| 1122 |
+
"loss": 0.7855,
|
| 1123 |
+
"step": 272
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 9.448275862068966,
|
| 1127 |
+
"grad_norm": 5.506075382232666,
|
| 1128 |
+
"learning_rate": 8.486590038314178e-05,
|
| 1129 |
+
"loss": 0.9476,
|
| 1130 |
+
"step": 274
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 9.517241379310345,
|
| 1134 |
+
"grad_norm": 4.194758415222168,
|
| 1135 |
+
"learning_rate": 8.467432950191571e-05,
|
| 1136 |
+
"loss": 0.7085,
|
| 1137 |
+
"step": 276
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 9.586206896551724,
|
| 1141 |
+
"grad_norm": 1.5031163692474365,
|
| 1142 |
+
"learning_rate": 8.448275862068966e-05,
|
| 1143 |
+
"loss": 0.8127,
|
| 1144 |
+
"step": 278
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 9.655172413793103,
|
| 1148 |
+
"grad_norm": 1.31179678440094,
|
| 1149 |
+
"learning_rate": 8.42911877394636e-05,
|
| 1150 |
+
"loss": 0.564,
|
| 1151 |
+
"step": 280
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 9.724137931034482,
|
| 1155 |
+
"grad_norm": 3.820150852203369,
|
| 1156 |
+
"learning_rate": 8.409961685823755e-05,
|
| 1157 |
+
"loss": 1.018,
|
| 1158 |
+
"step": 282
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 9.793103448275861,
|
| 1162 |
+
"grad_norm": 4.5845465660095215,
|
| 1163 |
+
"learning_rate": 8.39080459770115e-05,
|
| 1164 |
+
"loss": 1.2035,
|
| 1165 |
+
"step": 284
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 9.862068965517242,
|
| 1169 |
+
"grad_norm": 6.150566577911377,
|
| 1170 |
+
"learning_rate": 8.371647509578544e-05,
|
| 1171 |
+
"loss": 1.0823,
|
| 1172 |
+
"step": 286
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 9.931034482758621,
|
| 1176 |
+
"grad_norm": 4.594326496124268,
|
| 1177 |
+
"learning_rate": 8.35249042145594e-05,
|
| 1178 |
+
"loss": 0.9801,
|
| 1179 |
+
"step": 288
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 10.0,
|
| 1183 |
+
"grad_norm": 4.550546646118164,
|
| 1184 |
+
"learning_rate": 8.333333333333334e-05,
|
| 1185 |
+
"loss": 1.2034,
|
| 1186 |
+
"step": 290
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 10.0,
|
| 1190 |
+
"eval_accuracy": 0.5151515151515151,
|
| 1191 |
+
"eval_f1_macro": 0.42231551060990824,
|
| 1192 |
+
"eval_f1_micro": 0.5151515151515151,
|
| 1193 |
+
"eval_f1_weighted": 0.48980373792849813,
|
| 1194 |
+
"eval_loss": 1.3682000637054443,
|
| 1195 |
+
"eval_precision_macro": 0.4735347621488278,
|
| 1196 |
+
"eval_precision_micro": 0.5151515151515151,
|
| 1197 |
+
"eval_precision_weighted": 0.5570637716417561,
|
| 1198 |
+
"eval_recall_macro": 0.44784580498866217,
|
| 1199 |
+
"eval_recall_micro": 0.5151515151515151,
|
| 1200 |
+
"eval_recall_weighted": 0.5151515151515151,
|
| 1201 |
+
"eval_runtime": 2.3231,
|
| 1202 |
+
"eval_samples_per_second": 56.821,
|
| 1203 |
+
"eval_steps_per_second": 7.318,
|
| 1204 |
+
"step": 290
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 10.068965517241379,
|
| 1208 |
+
"grad_norm": 5.808166027069092,
|
| 1209 |
+
"learning_rate": 8.314176245210729e-05,
|
| 1210 |
+
"loss": 1.1703,
|
| 1211 |
+
"step": 292
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 10.137931034482758,
|
| 1215 |
+
"grad_norm": 2.5559470653533936,
|
| 1216 |
+
"learning_rate": 8.295019157088123e-05,
|
| 1217 |
+
"loss": 0.8235,
|
| 1218 |
+
"step": 294
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 10.206896551724139,
|
| 1222 |
+
"grad_norm": 4.7338762283325195,
|
| 1223 |
+
"learning_rate": 8.275862068965517e-05,
|
| 1224 |
+
"loss": 0.9399,
|
| 1225 |
+
"step": 296
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 10.275862068965518,
|
| 1229 |
+
"grad_norm": 4.487349987030029,
|
| 1230 |
+
"learning_rate": 8.256704980842912e-05,
|
| 1231 |
+
"loss": 0.7128,
|
| 1232 |
+
"step": 298
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 10.344827586206897,
|
| 1236 |
+
"grad_norm": 3.328216791152954,
|
| 1237 |
+
"learning_rate": 8.237547892720307e-05,
|
| 1238 |
+
"loss": 1.0484,
|
| 1239 |
+
"step": 300
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 10.413793103448276,
|
| 1243 |
+
"grad_norm": 2.7354414463043213,
|
| 1244 |
+
"learning_rate": 8.218390804597702e-05,
|
| 1245 |
+
"loss": 0.73,
|
| 1246 |
+
"step": 302
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 10.482758620689655,
|
| 1250 |
+
"grad_norm": 4.714895248413086,
|
| 1251 |
+
"learning_rate": 8.199233716475096e-05,
|
| 1252 |
+
"loss": 0.8512,
|
| 1253 |
+
"step": 304
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 10.551724137931034,
|
| 1257 |
+
"grad_norm": 4.107720851898193,
|
| 1258 |
+
"learning_rate": 8.180076628352491e-05,
|
| 1259 |
+
"loss": 1.033,
|
| 1260 |
+
"step": 306
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 10.620689655172415,
|
| 1264 |
+
"grad_norm": 2.4637210369110107,
|
| 1265 |
+
"learning_rate": 8.160919540229886e-05,
|
| 1266 |
+
"loss": 0.8492,
|
| 1267 |
+
"step": 308
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 10.689655172413794,
|
| 1271 |
+
"grad_norm": 4.778433799743652,
|
| 1272 |
+
"learning_rate": 8.14176245210728e-05,
|
| 1273 |
+
"loss": 1.1118,
|
| 1274 |
+
"step": 310
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 10.758620689655173,
|
| 1278 |
+
"grad_norm": 5.476203918457031,
|
| 1279 |
+
"learning_rate": 8.122605363984674e-05,
|
| 1280 |
+
"loss": 1.1105,
|
| 1281 |
+
"step": 312
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 10.827586206896552,
|
| 1285 |
+
"grad_norm": 4.607093811035156,
|
| 1286 |
+
"learning_rate": 8.103448275862069e-05,
|
| 1287 |
+
"loss": 0.7392,
|
| 1288 |
+
"step": 314
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 10.89655172413793,
|
| 1292 |
+
"grad_norm": 5.401411056518555,
|
| 1293 |
+
"learning_rate": 8.084291187739465e-05,
|
| 1294 |
+
"loss": 0.5906,
|
| 1295 |
+
"step": 316
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 10.96551724137931,
|
| 1299 |
+
"grad_norm": 4.555649757385254,
|
| 1300 |
+
"learning_rate": 8.06513409961686e-05,
|
| 1301 |
+
"loss": 0.8037,
|
| 1302 |
+
"step": 318
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 11.0,
|
| 1306 |
+
"eval_accuracy": 0.6212121212121212,
|
| 1307 |
+
"eval_f1_macro": 0.5363613475812564,
|
| 1308 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 1309 |
+
"eval_f1_weighted": 0.60671912281113,
|
| 1310 |
+
"eval_loss": 1.1536208391189575,
|
| 1311 |
+
"eval_precision_macro": 0.5305411174976392,
|
| 1312 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 1313 |
+
"eval_precision_weighted": 0.6092663740885084,
|
| 1314 |
+
"eval_recall_macro": 0.555774754346183,
|
| 1315 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 1316 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 1317 |
+
"eval_runtime": 2.3177,
|
| 1318 |
+
"eval_samples_per_second": 56.952,
|
| 1319 |
+
"eval_steps_per_second": 7.335,
|
| 1320 |
+
"step": 319
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 11.03448275862069,
|
| 1324 |
+
"grad_norm": 7.6678290367126465,
|
| 1325 |
+
"learning_rate": 8.045977011494253e-05,
|
| 1326 |
+
"loss": 0.7917,
|
| 1327 |
+
"step": 320
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 11.10344827586207,
|
| 1331 |
+
"grad_norm": 1.9151082038879395,
|
| 1332 |
+
"learning_rate": 8.026819923371648e-05,
|
| 1333 |
+
"loss": 0.7249,
|
| 1334 |
+
"step": 322
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 11.172413793103448,
|
| 1338 |
+
"grad_norm": 2.772256374359131,
|
| 1339 |
+
"learning_rate": 8.007662835249042e-05,
|
| 1340 |
+
"loss": 0.7255,
|
| 1341 |
+
"step": 324
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 11.241379310344827,
|
| 1345 |
+
"grad_norm": 2.4357872009277344,
|
| 1346 |
+
"learning_rate": 7.988505747126437e-05,
|
| 1347 |
+
"loss": 0.5105,
|
| 1348 |
+
"step": 326
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 11.310344827586206,
|
| 1352 |
+
"grad_norm": 4.2995195388793945,
|
| 1353 |
+
"learning_rate": 7.969348659003832e-05,
|
| 1354 |
+
"loss": 0.8066,
|
| 1355 |
+
"step": 328
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 11.379310344827585,
|
| 1359 |
+
"grad_norm": 2.9026498794555664,
|
| 1360 |
+
"learning_rate": 7.950191570881227e-05,
|
| 1361 |
+
"loss": 0.9017,
|
| 1362 |
+
"step": 330
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 11.448275862068966,
|
| 1366 |
+
"grad_norm": 4.70675802230835,
|
| 1367 |
+
"learning_rate": 7.931034482758621e-05,
|
| 1368 |
+
"loss": 1.0516,
|
| 1369 |
+
"step": 332
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 11.517241379310345,
|
| 1373 |
+
"grad_norm": 5.430378437042236,
|
| 1374 |
+
"learning_rate": 7.911877394636016e-05,
|
| 1375 |
+
"loss": 0.5592,
|
| 1376 |
+
"step": 334
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 11.586206896551724,
|
| 1380 |
+
"grad_norm": 4.292328357696533,
|
| 1381 |
+
"learning_rate": 7.892720306513411e-05,
|
| 1382 |
+
"loss": 0.691,
|
| 1383 |
+
"step": 336
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 11.655172413793103,
|
| 1387 |
+
"grad_norm": 3.9568679332733154,
|
| 1388 |
+
"learning_rate": 7.873563218390804e-05,
|
| 1389 |
+
"loss": 0.6625,
|
| 1390 |
+
"step": 338
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 11.724137931034482,
|
| 1394 |
+
"grad_norm": 3.103039503097534,
|
| 1395 |
+
"learning_rate": 7.854406130268199e-05,
|
| 1396 |
+
"loss": 0.7581,
|
| 1397 |
+
"step": 340
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 11.793103448275861,
|
| 1401 |
+
"grad_norm": 5.845880508422852,
|
| 1402 |
+
"learning_rate": 7.835249042145594e-05,
|
| 1403 |
+
"loss": 0.7748,
|
| 1404 |
+
"step": 342
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 11.862068965517242,
|
| 1408 |
+
"grad_norm": 3.2300820350646973,
|
| 1409 |
+
"learning_rate": 7.81609195402299e-05,
|
| 1410 |
+
"loss": 0.6572,
|
| 1411 |
+
"step": 344
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 11.931034482758621,
|
| 1415 |
+
"grad_norm": 5.324902534484863,
|
| 1416 |
+
"learning_rate": 7.796934865900383e-05,
|
| 1417 |
+
"loss": 0.8584,
|
| 1418 |
+
"step": 346
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 12.0,
|
| 1422 |
+
"grad_norm": 4.982322692871094,
|
| 1423 |
+
"learning_rate": 7.777777777777778e-05,
|
| 1424 |
+
"loss": 0.593,
|
| 1425 |
+
"step": 348
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 12.0,
|
| 1429 |
+
"eval_accuracy": 0.49242424242424243,
|
| 1430 |
+
"eval_f1_macro": 0.44853272706810665,
|
| 1431 |
+
"eval_f1_micro": 0.49242424242424243,
|
| 1432 |
+
"eval_f1_weighted": 0.5033254246484239,
|
| 1433 |
+
"eval_loss": 1.4808580875396729,
|
| 1434 |
+
"eval_precision_macro": 0.5443728685107995,
|
| 1435 |
+
"eval_precision_micro": 0.49242424242424243,
|
| 1436 |
+
"eval_precision_weighted": 0.6404539426091151,
|
| 1437 |
+
"eval_recall_macro": 0.47089191232048366,
|
| 1438 |
+
"eval_recall_micro": 0.49242424242424243,
|
| 1439 |
+
"eval_recall_weighted": 0.49242424242424243,
|
| 1440 |
+
"eval_runtime": 2.3168,
|
| 1441 |
+
"eval_samples_per_second": 56.975,
|
| 1442 |
+
"eval_steps_per_second": 7.338,
|
| 1443 |
+
"step": 348
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 12.068965517241379,
|
| 1447 |
+
"grad_norm": 5.828127384185791,
|
| 1448 |
+
"learning_rate": 7.758620689655173e-05,
|
| 1449 |
+
"loss": 1.1155,
|
| 1450 |
+
"step": 350
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 12.137931034482758,
|
| 1454 |
+
"grad_norm": 5.41758394241333,
|
| 1455 |
+
"learning_rate": 7.739463601532568e-05,
|
| 1456 |
+
"loss": 0.8559,
|
| 1457 |
+
"step": 352
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 12.206896551724139,
|
| 1461 |
+
"grad_norm": 4.14806604385376,
|
| 1462 |
+
"learning_rate": 7.720306513409961e-05,
|
| 1463 |
+
"loss": 0.989,
|
| 1464 |
+
"step": 354
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 12.275862068965518,
|
| 1468 |
+
"grad_norm": 2.6904520988464355,
|
| 1469 |
+
"learning_rate": 7.701149425287356e-05,
|
| 1470 |
+
"loss": 0.539,
|
| 1471 |
+
"step": 356
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 12.344827586206897,
|
| 1475 |
+
"grad_norm": 1.7748990058898926,
|
| 1476 |
+
"learning_rate": 7.681992337164752e-05,
|
| 1477 |
+
"loss": 0.6038,
|
| 1478 |
+
"step": 358
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 12.413793103448276,
|
| 1482 |
+
"grad_norm": 2.0579607486724854,
|
| 1483 |
+
"learning_rate": 7.662835249042147e-05,
|
| 1484 |
+
"loss": 0.7753,
|
| 1485 |
+
"step": 360
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 12.482758620689655,
|
| 1489 |
+
"grad_norm": 2.399552345275879,
|
| 1490 |
+
"learning_rate": 7.64367816091954e-05,
|
| 1491 |
+
"loss": 0.5238,
|
| 1492 |
+
"step": 362
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 12.551724137931034,
|
| 1496 |
+
"grad_norm": 3.3866896629333496,
|
| 1497 |
+
"learning_rate": 7.624521072796935e-05,
|
| 1498 |
+
"loss": 0.614,
|
| 1499 |
+
"step": 364
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 12.620689655172415,
|
| 1503 |
+
"grad_norm": 8.123571395874023,
|
| 1504 |
+
"learning_rate": 7.60536398467433e-05,
|
| 1505 |
+
"loss": 0.6223,
|
| 1506 |
+
"step": 366
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 12.689655172413794,
|
| 1510 |
+
"grad_norm": 7.095142841339111,
|
| 1511 |
+
"learning_rate": 7.586206896551724e-05,
|
| 1512 |
+
"loss": 0.7668,
|
| 1513 |
+
"step": 368
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 12.758620689655173,
|
| 1517 |
+
"grad_norm": 3.270301103591919,
|
| 1518 |
+
"learning_rate": 7.567049808429119e-05,
|
| 1519 |
+
"loss": 1.1208,
|
| 1520 |
+
"step": 370
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 12.827586206896552,
|
| 1524 |
+
"grad_norm": 2.6989779472351074,
|
| 1525 |
+
"learning_rate": 7.547892720306514e-05,
|
| 1526 |
+
"loss": 0.5682,
|
| 1527 |
+
"step": 372
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 12.89655172413793,
|
| 1531 |
+
"grad_norm": 5.336432456970215,
|
| 1532 |
+
"learning_rate": 7.528735632183909e-05,
|
| 1533 |
+
"loss": 0.6172,
|
| 1534 |
+
"step": 374
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 12.96551724137931,
|
| 1538 |
+
"grad_norm": 6.097706317901611,
|
| 1539 |
+
"learning_rate": 7.509578544061303e-05,
|
| 1540 |
+
"loss": 0.732,
|
| 1541 |
+
"step": 376
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 13.0,
|
| 1545 |
+
"eval_accuracy": 0.5909090909090909,
|
| 1546 |
+
"eval_f1_macro": 0.5144928051331992,
|
| 1547 |
+
"eval_f1_micro": 0.5909090909090909,
|
| 1548 |
+
"eval_f1_weighted": 0.5808570855592798,
|
| 1549 |
+
"eval_loss": 1.1917542219161987,
|
| 1550 |
+
"eval_precision_macro": 0.5641553452176186,
|
| 1551 |
+
"eval_precision_micro": 0.5909090909090909,
|
| 1552 |
+
"eval_precision_weighted": 0.6448181659246691,
|
| 1553 |
+
"eval_recall_macro": 0.5287603930461073,
|
| 1554 |
+
"eval_recall_micro": 0.5909090909090909,
|
| 1555 |
+
"eval_recall_weighted": 0.5909090909090909,
|
| 1556 |
+
"eval_runtime": 2.3205,
|
| 1557 |
+
"eval_samples_per_second": 56.883,
|
| 1558 |
+
"eval_steps_per_second": 7.326,
|
| 1559 |
+
"step": 377
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 13.03448275862069,
|
| 1563 |
+
"grad_norm": 4.893684387207031,
|
| 1564 |
+
"learning_rate": 7.490421455938698e-05,
|
| 1565 |
+
"loss": 0.7254,
|
| 1566 |
+
"step": 378
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 13.10344827586207,
|
| 1570 |
+
"grad_norm": 3.347688674926758,
|
| 1571 |
+
"learning_rate": 7.471264367816091e-05,
|
| 1572 |
+
"loss": 0.6572,
|
| 1573 |
+
"step": 380
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 13.172413793103448,
|
| 1577 |
+
"grad_norm": 3.368439197540283,
|
| 1578 |
+
"learning_rate": 7.452107279693486e-05,
|
| 1579 |
+
"loss": 0.7905,
|
| 1580 |
+
"step": 382
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 13.241379310344827,
|
| 1584 |
+
"grad_norm": 3.221909761428833,
|
| 1585 |
+
"learning_rate": 7.432950191570882e-05,
|
| 1586 |
+
"loss": 0.748,
|
| 1587 |
+
"step": 384
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 13.310344827586206,
|
| 1591 |
+
"grad_norm": 2.3360860347747803,
|
| 1592 |
+
"learning_rate": 7.413793103448277e-05,
|
| 1593 |
+
"loss": 0.2969,
|
| 1594 |
+
"step": 386
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 13.379310344827585,
|
| 1598 |
+
"grad_norm": 2.6463725566864014,
|
| 1599 |
+
"learning_rate": 7.39463601532567e-05,
|
| 1600 |
+
"loss": 0.5682,
|
| 1601 |
+
"step": 388
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 13.448275862068966,
|
| 1605 |
+
"grad_norm": 1.696847677230835,
|
| 1606 |
+
"learning_rate": 7.375478927203065e-05,
|
| 1607 |
+
"loss": 0.7344,
|
| 1608 |
+
"step": 390
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 13.517241379310345,
|
| 1612 |
+
"grad_norm": 2.6377010345458984,
|
| 1613 |
+
"learning_rate": 7.35632183908046e-05,
|
| 1614 |
+
"loss": 0.4448,
|
| 1615 |
+
"step": 392
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 13.586206896551724,
|
| 1619 |
+
"grad_norm": 11.842819213867188,
|
| 1620 |
+
"learning_rate": 7.337164750957855e-05,
|
| 1621 |
+
"loss": 0.6828,
|
| 1622 |
+
"step": 394
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 13.655172413793103,
|
| 1626 |
+
"grad_norm": 4.7342915534973145,
|
| 1627 |
+
"learning_rate": 7.31800766283525e-05,
|
| 1628 |
+
"loss": 0.8378,
|
| 1629 |
+
"step": 396
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 13.724137931034482,
|
| 1633 |
+
"grad_norm": 4.786142349243164,
|
| 1634 |
+
"learning_rate": 7.298850574712644e-05,
|
| 1635 |
+
"loss": 0.7508,
|
| 1636 |
+
"step": 398
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 13.793103448275861,
|
| 1640 |
+
"grad_norm": 7.012732028961182,
|
| 1641 |
+
"learning_rate": 7.279693486590039e-05,
|
| 1642 |
+
"loss": 0.875,
|
| 1643 |
+
"step": 400
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 13.862068965517242,
|
| 1647 |
+
"grad_norm": 7.100485801696777,
|
| 1648 |
+
"learning_rate": 7.260536398467434e-05,
|
| 1649 |
+
"loss": 0.8155,
|
| 1650 |
+
"step": 402
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 13.931034482758621,
|
| 1654 |
+
"grad_norm": 6.699406623840332,
|
| 1655 |
+
"learning_rate": 7.241379310344828e-05,
|
| 1656 |
+
"loss": 0.8326,
|
| 1657 |
+
"step": 404
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 14.0,
|
| 1661 |
+
"grad_norm": 3.8491220474243164,
|
| 1662 |
+
"learning_rate": 7.222222222222222e-05,
|
| 1663 |
+
"loss": 0.8642,
|
| 1664 |
+
"step": 406
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 14.0,
|
| 1668 |
+
"eval_accuracy": 0.5984848484848485,
|
| 1669 |
+
"eval_f1_macro": 0.5113535072443615,
|
| 1670 |
+
"eval_f1_micro": 0.5984848484848485,
|
| 1671 |
+
"eval_f1_weighted": 0.5883891667163884,
|
| 1672 |
+
"eval_loss": 1.1884046792984009,
|
| 1673 |
+
"eval_precision_macro": 0.5284200509472081,
|
| 1674 |
+
"eval_precision_micro": 0.5984848484848485,
|
| 1675 |
+
"eval_precision_weighted": 0.610834482351699,
|
| 1676 |
+
"eval_recall_macro": 0.5243537414965986,
|
| 1677 |
+
"eval_recall_micro": 0.5984848484848485,
|
| 1678 |
+
"eval_recall_weighted": 0.5984848484848485,
|
| 1679 |
+
"eval_runtime": 2.3348,
|
| 1680 |
+
"eval_samples_per_second": 56.536,
|
| 1681 |
+
"eval_steps_per_second": 7.281,
|
| 1682 |
+
"step": 406
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 14.0,
|
| 1686 |
+
"step": 406,
|
| 1687 |
+
"total_flos": 5.0124065012763034e+17,
|
| 1688 |
+
"train_loss": 1.2848335812831748,
|
| 1689 |
+
"train_runtime": 397.0629,
|
| 1690 |
+
"train_samples_per_second": 46.542,
|
| 1691 |
+
"train_steps_per_second": 2.921
|
| 1692 |
+
}
|
| 1693 |
+
],
|
| 1694 |
+
"logging_steps": 2,
|
| 1695 |
+
"max_steps": 1160,
|
| 1696 |
+
"num_input_tokens_seen": 0,
|
| 1697 |
+
"num_train_epochs": 40,
|
| 1698 |
+
"save_steps": 500,
|
| 1699 |
+
"stateful_callbacks": {
|
| 1700 |
+
"EarlyStoppingCallback": {
|
| 1701 |
+
"args": {
|
| 1702 |
+
"early_stopping_patience": 3,
|
| 1703 |
+
"early_stopping_threshold": 0.0
|
| 1704 |
+
},
|
| 1705 |
+
"attributes": {
|
| 1706 |
+
"early_stopping_patience_counter": 3
|
| 1707 |
+
}
|
| 1708 |
+
},
|
| 1709 |
+
"TrainerControl": {
|
| 1710 |
+
"args": {
|
| 1711 |
+
"should_epoch_stop": false,
|
| 1712 |
+
"should_evaluate": false,
|
| 1713 |
+
"should_log": false,
|
| 1714 |
+
"should_save": true,
|
| 1715 |
+
"should_training_stop": true
|
| 1716 |
+
},
|
| 1717 |
+
"attributes": {}
|
| 1718 |
+
}
|
| 1719 |
+
},
|
| 1720 |
+
"total_flos": 5.0124065012763034e+17,
|
| 1721 |
+
"train_batch_size": 8,
|
| 1722 |
+
"trial_name": null,
|
| 1723 |
+
"trial_params": null
|
| 1724 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dc21886c3b6c37cb63ef3663e12b5d93a033b72ef9aca441a35317dd3a6ba36
|
| 3 |
+
size 5368
|