Hugging Face's logo

corranm
/
vit-base-patch16-224

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
Metrics Community
corranm commited on
Commit
9c3035b
·
verified ·
1 Parent(s): bac525d

End of training

Browse files
Files changed (13) hide show
  1. README.md +100 -0
  2. all_results.json +22 -0
  3. config.json +42 -0
  4. eval_results.json +17 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +23 -0
  7. runs/Feb02_22-35-12_modal/events.out.tfevents.1738535713.modal.2.0 +3 -0
  8. runs/Feb02_22-35-12_modal/events.out.tfevents.1738535713.modal.2.1 +3 -0
  9. runs/Feb02_22-35-12_modal/events.out.tfevents.1738536564.modal.2.2 +3 -0
  10. runs/Feb02_22-35-12_modal/events.out.tfevents.1738536564.modal.2.3 +3 -0
  11. train_results.json +8 -0
  12. trainer_state.json +3627 -0
  13. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: vit-base-patch16-224
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # vit-base-patch16-224
16
+
17
+ This model was trained from scratch on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3122
20
+ - F1 Macro: 0.5397
21
+ - F1 Micro: 0.6212
22
+ - F1 Weighted: 0.6077
23
+ - Precision Macro: 0.5343
24
+ - Precision Micro: 0.6212
25
+ - Precision Weighted: 0.6084
26
+ - Recall Macro: 0.5571
27
+ - Recall Micro: 0.6212
28
+ - Recall Weighted: 0.6212
29
+ - Accuracy: 0.6212
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 0.0001
49
+ - train_batch_size: 8
50
+ - eval_batch_size: 8
51
+ - seed: 42
52
+ - gradient_accumulation_steps: 2
53
+ - total_train_batch_size: 16
54
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 30
58
+
59
+ ### Training results
60
+
61
+ | 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 |
62
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:---------------:|:------------------:|:------------:|:------------:|:---------------:|:--------:|
63
+ | 1.9037 | 1.0 | 29 | 1.8618 | 0.1250 | 0.2197 | 0.1592 | 0.1401 | 0.2197 | 0.1692 | 0.1674 | 0.2197 | 0.2197 | 0.2197 |
64
+ | 1.6981 | 2.0 | 58 | 1.8760 | 0.1537 | 0.2424 | 0.1896 | 0.2152 | 0.2424 | 0.2787 | 0.2068 | 0.2424 | 0.2424 | 0.2424 |
65
+ | 1.7426 | 3.0 | 87 | 1.6971 | 0.2272 | 0.3333 | 0.2622 | 0.1959 | 0.3333 | 0.2233 | 0.2846 | 0.3333 | 0.3333 | 0.3333 |
66
+ | 1.1847 | 4.0 | 116 | 1.5082 | 0.3360 | 0.4242 | 0.3911 | 0.3925 | 0.4242 | 0.4281 | 0.3553 | 0.4242 | 0.4242 | 0.4242 |
67
+ | 1.3906 | 5.0 | 145 | 1.4063 | 0.3152 | 0.4621 | 0.3815 | 0.2727 | 0.4621 | 0.3279 | 0.3785 | 0.4621 | 0.4621 | 0.4621 |
68
+ | 1.5575 | 6.0 | 174 | 1.3833 | 0.4414 | 0.4621 | 0.4526 | 0.4850 | 0.4621 | 0.4941 | 0.4402 | 0.4621 | 0.4621 | 0.4621 |
69
+ | 1.1063 | 7.0 | 203 | 1.2431 | 0.4750 | 0.5833 | 0.5453 | 0.5898 | 0.5833 | 0.6329 | 0.4890 | 0.5833 | 0.5833 | 0.5833 |
70
+ | 1.1503 | 8.0 | 232 | 1.3635 | 0.4036 | 0.4924 | 0.4586 | 0.4145 | 0.4924 | 0.4762 | 0.4436 | 0.4924 | 0.4924 | 0.4924 |
71
+ | 0.5124 | 9.0 | 261 | 1.1603 | 0.5463 | 0.6288 | 0.6136 | 0.5488 | 0.6288 | 0.6113 | 0.5551 | 0.6288 | 0.6288 | 0.6288 |
72
+ | 0.6648 | 10.0 | 290 | 1.4136 | 0.4184 | 0.5 | 0.4713 | 0.4713 | 0.5 | 0.5275 | 0.4413 | 0.5 | 0.5 | 0.5 |
73
+ | 0.2917 | 11.0 | 319 | 1.2004 | 0.5155 | 0.6061 | 0.5892 | 0.5180 | 0.6061 | 0.5882 | 0.5268 | 0.6061 | 0.6061 | 0.6061 |
74
+ | 0.4962 | 12.0 | 348 | 1.3730 | 0.4970 | 0.5682 | 0.5671 | 0.5094 | 0.5682 | 0.5909 | 0.5109 | 0.5682 | 0.5682 | 0.5682 |
75
+ | 0.5723 | 13.0 | 377 | 1.3377 | 0.5705 | 0.6136 | 0.6077 | 0.7050 | 0.6136 | 0.6879 | 0.5756 | 0.6136 | 0.6136 | 0.6136 |
76
+ | 0.4589 | 14.0 | 406 | 1.3717 | 0.5648 | 0.6136 | 0.6094 | 0.6239 | 0.6136 | 0.6458 | 0.5609 | 0.6136 | 0.6136 | 0.6136 |
77
+ | 0.2544 | 15.0 | 435 | 1.4129 | 0.5086 | 0.5985 | 0.5793 | 0.5140 | 0.5985 | 0.5772 | 0.5187 | 0.5985 | 0.5985 | 0.5985 |
78
+ | 0.3179 | 16.0 | 464 | 1.3589 | 0.5882 | 0.6439 | 0.6347 | 0.6912 | 0.6439 | 0.6603 | 0.5777 | 0.6439 | 0.6439 | 0.6439 |
79
+ | 0.1304 | 17.0 | 493 | 1.5604 | 0.5010 | 0.5758 | 0.5606 | 0.5123 | 0.5758 | 0.5669 | 0.5076 | 0.5758 | 0.5758 | 0.5758 |
80
+ | 0.0887 | 18.0 | 522 | 1.6231 | 0.5091 | 0.6061 | 0.5800 | 0.5344 | 0.6061 | 0.5917 | 0.5190 | 0.6061 | 0.6061 | 0.6061 |
81
+ | 0.0254 | 19.0 | 551 | 1.6095 | 0.5625 | 0.6136 | 0.6070 | 0.6642 | 0.6136 | 0.6353 | 0.5520 | 0.6136 | 0.6136 | 0.6136 |
82
+ | 0.0908 | 20.0 | 580 | 1.6941 | 0.5270 | 0.6136 | 0.5962 | 0.5331 | 0.6136 | 0.6004 | 0.5381 | 0.6136 | 0.6136 | 0.6136 |
83
+ | 0.0913 | 21.0 | 609 | 1.6917 | 0.5537 | 0.6136 | 0.6018 | 0.5909 | 0.6136 | 0.6169 | 0.5579 | 0.6136 | 0.6136 | 0.6136 |
84
+ | 0.015 | 22.0 | 638 | 1.8274 | 0.4866 | 0.5682 | 0.5512 | 0.4855 | 0.5682 | 0.5477 | 0.5003 | 0.5682 | 0.5682 | 0.5682 |
85
+ | 0.0156 | 23.0 | 667 | 1.7322 | 0.5772 | 0.6439 | 0.6233 | 0.6870 | 0.6439 | 0.6598 | 0.5802 | 0.6439 | 0.6439 | 0.6439 |
86
+ | 0.0275 | 24.0 | 696 | 1.6262 | 0.5293 | 0.6212 | 0.6006 | 0.5274 | 0.6212 | 0.5913 | 0.5422 | 0.6212 | 0.6212 | 0.6212 |
87
+ | 0.0034 | 25.0 | 725 | 1.7278 | 0.5680 | 0.6591 | 0.6409 | 0.5674 | 0.6591 | 0.6333 | 0.5786 | 0.6591 | 0.6591 | 0.6591 |
88
+ | 0.0021 | 26.0 | 754 | 1.7111 | 0.5542 | 0.6439 | 0.6250 | 0.5506 | 0.6439 | 0.6148 | 0.5657 | 0.6439 | 0.6439 | 0.6439 |
89
+ | 0.0021 | 27.0 | 783 | 1.7412 | 0.5556 | 0.6439 | 0.6257 | 0.5507 | 0.6439 | 0.6163 | 0.5684 | 0.6439 | 0.6439 | 0.6439 |
90
+ | 0.0079 | 28.0 | 812 | 1.8651 | 0.5506 | 0.6364 | 0.6176 | 0.5427 | 0.6364 | 0.6078 | 0.5670 | 0.6364 | 0.6364 | 0.6364 |
91
+ | 0.0018 | 29.0 | 841 | 1.8016 | 0.5508 | 0.6364 | 0.6184 | 0.5425 | 0.6364 | 0.6074 | 0.5654 | 0.6364 | 0.6364 | 0.6364 |
92
+ | 0.0068 | 30.0 | 870 | 1.7936 | 0.5510 | 0.6364 | 0.6182 | 0.5436 | 0.6364 | 0.6073 | 0.5650 | 0.6364 | 0.6364 | 0.6364 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.48.2
98
+ - Pytorch 2.6.0+cu124
99
+ - Datasets 3.2.0
100
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.6212121212121212,
4
+ "eval_f1_macro": 0.5397429122550751,
5
+ "eval_f1_micro": 0.6212121212121212,
6
+ "eval_f1_weighted": 0.6076638047507734,
7
+ "eval_loss": 1.312180519104004,
8
+ "eval_precision_macro": 0.5342918985776128,
9
+ "eval_precision_micro": 0.6212121212121212,
10
+ "eval_precision_weighted": 0.6083595697232062,
11
+ "eval_recall_macro": 0.5571428571428572,
12
+ "eval_recall_micro": 0.6212121212121212,
13
+ "eval_recall_weighted": 0.6212121212121212,
14
+ "eval_runtime": 1.1984,
15
+ "eval_samples_per_second": 55.071,
16
+ "eval_steps_per_second": 7.51,
17
+ "total_flos": 1.0740871074163507e+18,
18
+ "train_loss": 0.5336226776871167,
19
+ "train_runtime": 850.3912,
20
+ "train_samples_per_second": 16.298,
21
+ "train_steps_per_second": 1.023
22
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
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": "4.48.2"
42
+ }
eval_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.6212121212121212,
4
+ "eval_f1_macro": 0.5397429122550751,
5
+ "eval_f1_micro": 0.6212121212121212,
6
+ "eval_f1_weighted": 0.6076638047507734,
7
+ "eval_loss": 1.312180519104004,
8
+ "eval_precision_macro": 0.5342918985776128,
9
+ "eval_precision_micro": 0.6212121212121212,
10
+ "eval_precision_weighted": 0.6083595697232062,
11
+ "eval_recall_macro": 0.5571428571428572,
12
+ "eval_recall_micro": 0.6212121212121212,
13
+ "eval_recall_weighted": 0.6212121212121212,
14
+ "eval_runtime": 1.1984,
15
+ "eval_samples_per_second": 55.071,
16
+ "eval_steps_per_second": 7.51
17
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6424c2c2034924c4bbcbb2e8c8f43747f6e427b73870c1f99f00f0afb5450dc6
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_22-35-12_modal/events.out.tfevents.1738535713.modal.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79c6fa8b2c8e2b9440ea7a3657e92732faa815e6a2252e5efa4e42d99e1049c
3
+ size 122003
runs/Feb02_22-35-12_modal/events.out.tfevents.1738535713.modal.2.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87176a2f210688d493bb04175eccc68b901b7932fe001c3e3f8d0ef53893b84
3
+ size 122003
runs/Feb02_22-35-12_modal/events.out.tfevents.1738536564.modal.2.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba66dc99ef11dfb384b1711e6b574c1cb45c532f8cb4210448dda1c5b53efc0
3
+ size 921
runs/Feb02_22-35-12_modal/events.out.tfevents.1738536564.modal.2.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a84918a9fff82bd31005ba4c992bc206eec67b25ffd1bd24fbebad1626b73d9
3
+ size 921
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "total_flos": 1.0740871074163507e+18,
4
+ "train_loss": 0.5336226776871167,
5
+ "train_runtime": 850.3912,
6
+ "train_samples_per_second": 16.298,
7
+ "train_steps_per_second": 1.023
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,3627 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.160251259803772,
3
+ "best_model_checkpoint": "google/vit-base-patch16-224/checkpoint-261",
4
+ "epoch": 30.0,
5
+ "eval_steps": 500,
6
+ "global_step": 870,
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": 14.510237693786621,
14
+ "learning_rate": 2.2988505747126437e-06,
15
+ "loss": 2.1774,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.13793103448275862,
20
+ "grad_norm": 9.049612998962402,
21
+ "learning_rate": 4.5977011494252875e-06,
22
+ "loss": 2.0791,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.20689655172413793,
27
+ "grad_norm": 9.698376655578613,
28
+ "learning_rate": 6.896551724137932e-06,
29
+ "loss": 2.0987,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.27586206896551724,
34
+ "grad_norm": 7.020346641540527,
35
+ "learning_rate": 9.195402298850575e-06,
36
+ "loss": 1.8821,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.3448275862068966,
41
+ "grad_norm": 9.71212100982666,
42
+ "learning_rate": 1.1494252873563218e-05,
43
+ "loss": 1.8769,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.41379310344827586,
48
+ "grad_norm": 10.103402137756348,
49
+ "learning_rate": 1.3793103448275863e-05,
50
+ "loss": 2.0004,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.4827586206896552,
55
+ "grad_norm": 7.7244110107421875,
56
+ "learning_rate": 1.6091954022988507e-05,
57
+ "loss": 1.8686,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.5517241379310345,
62
+ "grad_norm": 7.321352481842041,
63
+ "learning_rate": 1.839080459770115e-05,
64
+ "loss": 1.9987,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.6206896551724138,
69
+ "grad_norm": 8.488332748413086,
70
+ "learning_rate": 2.0689655172413793e-05,
71
+ "loss": 1.8465,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.6896551724137931,
76
+ "grad_norm": 8.521231651306152,
77
+ "learning_rate": 2.2988505747126437e-05,
78
+ "loss": 1.7967,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.7586206896551724,
83
+ "grad_norm": 5.531124591827393,
84
+ "learning_rate": 2.5287356321839083e-05,
85
+ "loss": 1.8343,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.8275862068965517,
90
+ "grad_norm": 5.5662841796875,
91
+ "learning_rate": 2.7586206896551727e-05,
92
+ "loss": 1.9065,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.896551724137931,
97
+ "grad_norm": 9.917183876037598,
98
+ "learning_rate": 2.988505747126437e-05,
99
+ "loss": 1.8018,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.9655172413793104,
104
+ "grad_norm": 8.262176513671875,
105
+ "learning_rate": 3.218390804597701e-05,
106
+ "loss": 1.9037,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 1.0,
111
+ "eval_accuracy": 0.2196969696969697,
112
+ "eval_f1_macro": 0.12497789566755084,
113
+ "eval_f1_micro": 0.2196969696969697,
114
+ "eval_f1_weighted": 0.1591974117836187,
115
+ "eval_loss": 1.8618106842041016,
116
+ "eval_precision_macro": 0.14014863107134926,
117
+ "eval_precision_micro": 0.2196969696969697,
118
+ "eval_precision_weighted": 0.1691896059192861,
119
+ "eval_recall_macro": 0.1673922902494331,
120
+ "eval_recall_micro": 0.2196969696969697,
121
+ "eval_recall_weighted": 0.2196969696969697,
122
+ "eval_runtime": 2.316,
123
+ "eval_samples_per_second": 56.996,
124
+ "eval_steps_per_second": 7.34,
125
+ "step": 29
126
+ },
127
+ {
128
+ "epoch": 1.0344827586206897,
129
+ "grad_norm": 9.220452308654785,
130
+ "learning_rate": 3.4482758620689657e-05,
131
+ "loss": 1.8331,
132
+ "step": 30
133
+ },
134
+ {
135
+ "epoch": 1.103448275862069,
136
+ "grad_norm": 7.508858680725098,
137
+ "learning_rate": 3.67816091954023e-05,
138
+ "loss": 1.8269,
139
+ "step": 32
140
+ },
141
+ {
142
+ "epoch": 1.1724137931034484,
143
+ "grad_norm": 6.483837604522705,
144
+ "learning_rate": 3.908045977011495e-05,
145
+ "loss": 1.8778,
146
+ "step": 34
147
+ },
148
+ {
149
+ "epoch": 1.2413793103448276,
150
+ "grad_norm": 6.013676643371582,
151
+ "learning_rate": 4.1379310344827587e-05,
152
+ "loss": 1.9122,
153
+ "step": 36
154
+ },
155
+ {
156
+ "epoch": 1.3103448275862069,
157
+ "grad_norm": 6.562616348266602,
158
+ "learning_rate": 4.367816091954024e-05,
159
+ "loss": 1.7616,
160
+ "step": 38
161
+ },
162
+ {
163
+ "epoch": 1.3793103448275863,
164
+ "grad_norm": 8.177282333374023,
165
+ "learning_rate": 4.597701149425287e-05,
166
+ "loss": 1.8654,
167
+ "step": 40
168
+ },
169
+ {
170
+ "epoch": 1.4482758620689655,
171
+ "grad_norm": 6.561540126800537,
172
+ "learning_rate": 4.827586206896552e-05,
173
+ "loss": 1.8393,
174
+ "step": 42
175
+ },
176
+ {
177
+ "epoch": 1.5172413793103448,
178
+ "grad_norm": 11.305171966552734,
179
+ "learning_rate": 5.057471264367817e-05,
180
+ "loss": 1.9321,
181
+ "step": 44
182
+ },
183
+ {
184
+ "epoch": 1.5862068965517242,
185
+ "grad_norm": 7.003162384033203,
186
+ "learning_rate": 5.287356321839081e-05,
187
+ "loss": 1.9292,
188
+ "step": 46
189
+ },
190
+ {
191
+ "epoch": 1.6551724137931034,
192
+ "grad_norm": 6.365418434143066,
193
+ "learning_rate": 5.517241379310345e-05,
194
+ "loss": 1.7028,
195
+ "step": 48
196
+ },
197
+ {
198
+ "epoch": 1.7241379310344827,
199
+ "grad_norm": 10.20651626586914,
200
+ "learning_rate": 5.747126436781609e-05,
201
+ "loss": 2.0531,
202
+ "step": 50
203
+ },
204
+ {
205
+ "epoch": 1.793103448275862,
206
+ "grad_norm": 9.218647003173828,
207
+ "learning_rate": 5.977011494252874e-05,
208
+ "loss": 1.8879,
209
+ "step": 52
210
+ },
211
+ {
212
+ "epoch": 1.8620689655172413,
213
+ "grad_norm": 8.88680648803711,
214
+ "learning_rate": 6.206896551724138e-05,
215
+ "loss": 1.8247,
216
+ "step": 54
217
+ },
218
+ {
219
+ "epoch": 1.9310344827586206,
220
+ "grad_norm": 9.119765281677246,
221
+ "learning_rate": 6.436781609195403e-05,
222
+ "loss": 1.774,
223
+ "step": 56
224
+ },
225
+ {
226
+ "epoch": 2.0,
227
+ "grad_norm": 7.1343159675598145,
228
+ "learning_rate": 6.666666666666667e-05,
229
+ "loss": 1.6981,
230
+ "step": 58
231
+ },
232
+ {
233
+ "epoch": 2.0,
234
+ "eval_accuracy": 0.24242424242424243,
235
+ "eval_f1_macro": 0.1537403956438364,
236
+ "eval_f1_micro": 0.24242424242424243,
237
+ "eval_f1_weighted": 0.18962596561868278,
238
+ "eval_loss": 1.876023292541504,
239
+ "eval_precision_macro": 0.21524098687403828,
240
+ "eval_precision_micro": 0.24242424242424243,
241
+ "eval_precision_weighted": 0.2786748421101056,
242
+ "eval_recall_macro": 0.20681783824640967,
243
+ "eval_recall_micro": 0.24242424242424243,
244
+ "eval_recall_weighted": 0.24242424242424243,
245
+ "eval_runtime": 2.3142,
246
+ "eval_samples_per_second": 57.039,
247
+ "eval_steps_per_second": 7.346,
248
+ "step": 58
249
+ },
250
+ {
251
+ "epoch": 2.0689655172413794,
252
+ "grad_norm": 9.466385841369629,
253
+ "learning_rate": 6.896551724137931e-05,
254
+ "loss": 1.9208,
255
+ "step": 60
256
+ },
257
+ {
258
+ "epoch": 2.1379310344827585,
259
+ "grad_norm": 6.799683094024658,
260
+ "learning_rate": 7.126436781609196e-05,
261
+ "loss": 1.6549,
262
+ "step": 62
263
+ },
264
+ {
265
+ "epoch": 2.206896551724138,
266
+ "grad_norm": 9.33665943145752,
267
+ "learning_rate": 7.35632183908046e-05,
268
+ "loss": 1.6985,
269
+ "step": 64
270
+ },
271
+ {
272
+ "epoch": 2.2758620689655173,
273
+ "grad_norm": 13.14546012878418,
274
+ "learning_rate": 7.586206896551724e-05,
275
+ "loss": 1.81,
276
+ "step": 66
277
+ },
278
+ {
279
+ "epoch": 2.344827586206897,
280
+ "grad_norm": 7.021309852600098,
281
+ "learning_rate": 7.81609195402299e-05,
282
+ "loss": 1.5293,
283
+ "step": 68
284
+ },
285
+ {
286
+ "epoch": 2.413793103448276,
287
+ "grad_norm": 11.861666679382324,
288
+ "learning_rate": 8.045977011494253e-05,
289
+ "loss": 1.8111,
290
+ "step": 70
291
+ },
292
+ {
293
+ "epoch": 2.4827586206896552,
294
+ "grad_norm": 7.507106304168701,
295
+ "learning_rate": 8.275862068965517e-05,
296
+ "loss": 1.9034,
297
+ "step": 72
298
+ },
299
+ {
300
+ "epoch": 2.5517241379310347,
301
+ "grad_norm": 6.025614261627197,
302
+ "learning_rate": 8.505747126436782e-05,
303
+ "loss": 1.7827,
304
+ "step": 74
305
+ },
306
+ {
307
+ "epoch": 2.6206896551724137,
308
+ "grad_norm": 7.319404125213623,
309
+ "learning_rate": 8.735632183908047e-05,
310
+ "loss": 1.5888,
311
+ "step": 76
312
+ },
313
+ {
314
+ "epoch": 2.689655172413793,
315
+ "grad_norm": 9.80504322052002,
316
+ "learning_rate": 8.96551724137931e-05,
317
+ "loss": 1.7932,
318
+ "step": 78
319
+ },
320
+ {
321
+ "epoch": 2.7586206896551726,
322
+ "grad_norm": 9.417110443115234,
323
+ "learning_rate": 9.195402298850575e-05,
324
+ "loss": 1.7183,
325
+ "step": 80
326
+ },
327
+ {
328
+ "epoch": 2.8275862068965516,
329
+ "grad_norm": 8.941635131835938,
330
+ "learning_rate": 9.425287356321839e-05,
331
+ "loss": 1.5874,
332
+ "step": 82
333
+ },
334
+ {
335
+ "epoch": 2.896551724137931,
336
+ "grad_norm": 5.732688903808594,
337
+ "learning_rate": 9.655172413793105e-05,
338
+ "loss": 1.7631,
339
+ "step": 84
340
+ },
341
+ {
342
+ "epoch": 2.9655172413793105,
343
+ "grad_norm": 7.542623043060303,
344
+ "learning_rate": 9.885057471264369e-05,
345
+ "loss": 1.7426,
346
+ "step": 86
347
+ },
348
+ {
349
+ "epoch": 3.0,
350
+ "eval_accuracy": 0.3333333333333333,
351
+ "eval_f1_macro": 0.22724742891712044,
352
+ "eval_f1_micro": 0.3333333333333333,
353
+ "eval_f1_weighted": 0.26217254211809565,
354
+ "eval_loss": 1.6970728635787964,
355
+ "eval_precision_macro": 0.19590733590733594,
356
+ "eval_precision_micro": 0.3333333333333333,
357
+ "eval_precision_weighted": 0.22332104832104835,
358
+ "eval_recall_macro": 0.28462585034013604,
359
+ "eval_recall_micro": 0.3333333333333333,
360
+ "eval_recall_weighted": 0.3333333333333333,
361
+ "eval_runtime": 2.2957,
362
+ "eval_samples_per_second": 57.5,
363
+ "eval_steps_per_second": 7.405,
364
+ "step": 87
365
+ },
366
+ {
367
+ "epoch": 3.0344827586206895,
368
+ "grad_norm": 10.286172866821289,
369
+ "learning_rate": 9.987228607918264e-05,
370
+ "loss": 1.7147,
371
+ "step": 88
372
+ },
373
+ {
374
+ "epoch": 3.103448275862069,
375
+ "grad_norm": 6.141002178192139,
376
+ "learning_rate": 9.96168582375479e-05,
377
+ "loss": 1.431,
378
+ "step": 90
379
+ },
380
+ {
381
+ "epoch": 3.1724137931034484,
382
+ "grad_norm": 8.815275192260742,
383
+ "learning_rate": 9.936143039591316e-05,
384
+ "loss": 1.5841,
385
+ "step": 92
386
+ },
387
+ {
388
+ "epoch": 3.2413793103448274,
389
+ "grad_norm": 8.497651100158691,
390
+ "learning_rate": 9.910600255427843e-05,
391
+ "loss": 1.5312,
392
+ "step": 94
393
+ },
394
+ {
395
+ "epoch": 3.310344827586207,
396
+ "grad_norm": 9.317349433898926,
397
+ "learning_rate": 9.885057471264369e-05,
398
+ "loss": 1.4125,
399
+ "step": 96
400
+ },
401
+ {
402
+ "epoch": 3.3793103448275863,
403
+ "grad_norm": 7.25119686126709,
404
+ "learning_rate": 9.859514687100895e-05,
405
+ "loss": 1.5882,
406
+ "step": 98
407
+ },
408
+ {
409
+ "epoch": 3.4482758620689653,
410
+ "grad_norm": 7.394839763641357,
411
+ "learning_rate": 9.833971902937422e-05,
412
+ "loss": 1.3363,
413
+ "step": 100
414
+ },
415
+ {
416
+ "epoch": 3.5172413793103448,
417
+ "grad_norm": 12.02316665649414,
418
+ "learning_rate": 9.808429118773947e-05,
419
+ "loss": 1.7395,
420
+ "step": 102
421
+ },
422
+ {
423
+ "epoch": 3.586206896551724,
424
+ "grad_norm": 5.999875545501709,
425
+ "learning_rate": 9.782886334610473e-05,
426
+ "loss": 1.1745,
427
+ "step": 104
428
+ },
429
+ {
430
+ "epoch": 3.655172413793103,
431
+ "grad_norm": 7.852089881896973,
432
+ "learning_rate": 9.757343550446999e-05,
433
+ "loss": 1.4165,
434
+ "step": 106
435
+ },
436
+ {
437
+ "epoch": 3.7241379310344827,
438
+ "grad_norm": 10.310169219970703,
439
+ "learning_rate": 9.731800766283526e-05,
440
+ "loss": 1.2625,
441
+ "step": 108
442
+ },
443
+ {
444
+ "epoch": 3.793103448275862,
445
+ "grad_norm": 9.247345924377441,
446
+ "learning_rate": 9.706257982120052e-05,
447
+ "loss": 1.5794,
448
+ "step": 110
449
+ },
450
+ {
451
+ "epoch": 3.862068965517241,
452
+ "grad_norm": 11.231956481933594,
453
+ "learning_rate": 9.680715197956578e-05,
454
+ "loss": 1.7341,
455
+ "step": 112
456
+ },
457
+ {
458
+ "epoch": 3.9310344827586206,
459
+ "grad_norm": 9.639124870300293,
460
+ "learning_rate": 9.655172413793105e-05,
461
+ "loss": 1.5511,
462
+ "step": 114
463
+ },
464
+ {
465
+ "epoch": 4.0,
466
+ "grad_norm": 6.62493371963501,
467
+ "learning_rate": 9.62962962962963e-05,
468
+ "loss": 1.1847,
469
+ "step": 116
470
+ },
471
+ {
472
+ "epoch": 4.0,
473
+ "eval_accuracy": 0.42424242424242425,
474
+ "eval_f1_macro": 0.335973499369795,
475
+ "eval_f1_micro": 0.42424242424242425,
476
+ "eval_f1_weighted": 0.3911147510313107,
477
+ "eval_loss": 1.5082193613052368,
478
+ "eval_precision_macro": 0.3925486903558188,
479
+ "eval_precision_micro": 0.42424242424242425,
480
+ "eval_precision_weighted": 0.42806213997916476,
481
+ "eval_recall_macro": 0.35530612244897963,
482
+ "eval_recall_micro": 0.42424242424242425,
483
+ "eval_recall_weighted": 0.42424242424242425,
484
+ "eval_runtime": 2.3468,
485
+ "eval_samples_per_second": 56.247,
486
+ "eval_steps_per_second": 7.244,
487
+ "step": 116
488
+ },
489
+ {
490
+ "epoch": 4.068965517241379,
491
+ "grad_norm": 8.3433837890625,
492
+ "learning_rate": 9.604086845466156e-05,
493
+ "loss": 1.231,
494
+ "step": 118
495
+ },
496
+ {
497
+ "epoch": 4.137931034482759,
498
+ "grad_norm": 7.53312349319458,
499
+ "learning_rate": 9.578544061302682e-05,
500
+ "loss": 1.242,
501
+ "step": 120
502
+ },
503
+ {
504
+ "epoch": 4.206896551724138,
505
+ "grad_norm": 7.009676456451416,
506
+ "learning_rate": 9.553001277139209e-05,
507
+ "loss": 1.1074,
508
+ "step": 122
509
+ },
510
+ {
511
+ "epoch": 4.275862068965517,
512
+ "grad_norm": 7.956512451171875,
513
+ "learning_rate": 9.527458492975735e-05,
514
+ "loss": 1.2573,
515
+ "step": 124
516
+ },
517
+ {
518
+ "epoch": 4.344827586206897,
519
+ "grad_norm": 8.008772850036621,
520
+ "learning_rate": 9.501915708812261e-05,
521
+ "loss": 1.1739,
522
+ "step": 126
523
+ },
524
+ {
525
+ "epoch": 4.413793103448276,
526
+ "grad_norm": 6.648385524749756,
527
+ "learning_rate": 9.476372924648788e-05,
528
+ "loss": 1.257,
529
+ "step": 128
530
+ },
531
+ {
532
+ "epoch": 4.482758620689655,
533
+ "grad_norm": 10.020831108093262,
534
+ "learning_rate": 9.450830140485314e-05,
535
+ "loss": 1.6915,
536
+ "step": 130
537
+ },
538
+ {
539
+ "epoch": 4.551724137931035,
540
+ "grad_norm": 9.276317596435547,
541
+ "learning_rate": 9.425287356321839e-05,
542
+ "loss": 1.6599,
543
+ "step": 132
544
+ },
545
+ {
546
+ "epoch": 4.620689655172414,
547
+ "grad_norm": 6.358138084411621,
548
+ "learning_rate": 9.399744572158365e-05,
549
+ "loss": 1.5872,
550
+ "step": 134
551
+ },
552
+ {
553
+ "epoch": 4.689655172413794,
554
+ "grad_norm": 11.517606735229492,
555
+ "learning_rate": 9.374201787994892e-05,
556
+ "loss": 1.6351,
557
+ "step": 136
558
+ },
559
+ {
560
+ "epoch": 4.758620689655173,
561
+ "grad_norm": 8.802401542663574,
562
+ "learning_rate": 9.348659003831418e-05,
563
+ "loss": 1.6311,
564
+ "step": 138
565
+ },
566
+ {
567
+ "epoch": 4.827586206896552,
568
+ "grad_norm": 5.629919052124023,
569
+ "learning_rate": 9.323116219667944e-05,
570
+ "loss": 1.1992,
571
+ "step": 140
572
+ },
573
+ {
574
+ "epoch": 4.896551724137931,
575
+ "grad_norm": 7.886866569519043,
576
+ "learning_rate": 9.29757343550447e-05,
577
+ "loss": 1.2918,
578
+ "step": 142
579
+ },
580
+ {
581
+ "epoch": 4.9655172413793105,
582
+ "grad_norm": 7.389496326446533,
583
+ "learning_rate": 9.272030651340997e-05,
584
+ "loss": 1.3906,
585
+ "step": 144
586
+ },
587
+ {
588
+ "epoch": 5.0,
589
+ "eval_accuracy": 0.4621212121212121,
590
+ "eval_f1_macro": 0.3151982592976382,
591
+ "eval_f1_micro": 0.4621212121212121,
592
+ "eval_f1_weighted": 0.3814749150717531,
593
+ "eval_loss": 1.4062546491622925,
594
+ "eval_precision_macro": 0.2726634131913635,
595
+ "eval_precision_micro": 0.4621212121212121,
596
+ "eval_precision_weighted": 0.3278632599284773,
597
+ "eval_recall_macro": 0.3784580498866213,
598
+ "eval_recall_micro": 0.4621212121212121,
599
+ "eval_recall_weighted": 0.4621212121212121,
600
+ "eval_runtime": 2.315,
601
+ "eval_samples_per_second": 57.019,
602
+ "eval_steps_per_second": 7.343,
603
+ "step": 145
604
+ },
605
+ {
606
+ "epoch": 5.0344827586206895,
607
+ "grad_norm": 6.775806903839111,
608
+ "learning_rate": 9.246487867177522e-05,
609
+ "loss": 1.5752,
610
+ "step": 146
611
+ },
612
+ {
613
+ "epoch": 5.103448275862069,
614
+ "grad_norm": 8.185930252075195,
615
+ "learning_rate": 9.220945083014048e-05,
616
+ "loss": 1.1983,
617
+ "step": 148
618
+ },
619
+ {
620
+ "epoch": 5.172413793103448,
621
+ "grad_norm": 9.192156791687012,
622
+ "learning_rate": 9.195402298850575e-05,
623
+ "loss": 1.0037,
624
+ "step": 150
625
+ },
626
+ {
627
+ "epoch": 5.241379310344827,
628
+ "grad_norm": 8.08041000366211,
629
+ "learning_rate": 9.169859514687101e-05,
630
+ "loss": 1.0097,
631
+ "step": 152
632
+ },
633
+ {
634
+ "epoch": 5.310344827586207,
635
+ "grad_norm": 5.996678352355957,
636
+ "learning_rate": 9.144316730523627e-05,
637
+ "loss": 1.1322,
638
+ "step": 154
639
+ },
640
+ {
641
+ "epoch": 5.379310344827586,
642
+ "grad_norm": 7.907155513763428,
643
+ "learning_rate": 9.118773946360154e-05,
644
+ "loss": 0.9879,
645
+ "step": 156
646
+ },
647
+ {
648
+ "epoch": 5.448275862068965,
649
+ "grad_norm": 10.711898803710938,
650
+ "learning_rate": 9.09323116219668e-05,
651
+ "loss": 1.5501,
652
+ "step": 158
653
+ },
654
+ {
655
+ "epoch": 5.517241379310345,
656
+ "grad_norm": 7.513827323913574,
657
+ "learning_rate": 9.067688378033205e-05,
658
+ "loss": 1.1546,
659
+ "step": 160
660
+ },
661
+ {
662
+ "epoch": 5.586206896551724,
663
+ "grad_norm": 6.119425296783447,
664
+ "learning_rate": 9.042145593869731e-05,
665
+ "loss": 1.2014,
666
+ "step": 162
667
+ },
668
+ {
669
+ "epoch": 5.655172413793103,
670
+ "grad_norm": 7.023372650146484,
671
+ "learning_rate": 9.016602809706258e-05,
672
+ "loss": 1.0439,
673
+ "step": 164
674
+ },
675
+ {
676
+ "epoch": 5.724137931034483,
677
+ "grad_norm": 4.931612968444824,
678
+ "learning_rate": 8.991060025542784e-05,
679
+ "loss": 0.8718,
680
+ "step": 166
681
+ },
682
+ {
683
+ "epoch": 5.793103448275862,
684
+ "grad_norm": 8.603057861328125,
685
+ "learning_rate": 8.96551724137931e-05,
686
+ "loss": 1.3958,
687
+ "step": 168
688
+ },
689
+ {
690
+ "epoch": 5.862068965517241,
691
+ "grad_norm": 13.00936508178711,
692
+ "learning_rate": 8.939974457215837e-05,
693
+ "loss": 1.1505,
694
+ "step": 170
695
+ },
696
+ {
697
+ "epoch": 5.931034482758621,
698
+ "grad_norm": 8.384045600891113,
699
+ "learning_rate": 8.914431673052363e-05,
700
+ "loss": 1.3504,
701
+ "step": 172
702
+ },
703
+ {
704
+ "epoch": 6.0,
705
+ "grad_norm": 7.159438133239746,
706
+ "learning_rate": 8.888888888888889e-05,
707
+ "loss": 1.5575,
708
+ "step": 174
709
+ },
710
+ {
711
+ "epoch": 6.0,
712
+ "eval_accuracy": 0.4621212121212121,
713
+ "eval_f1_macro": 0.44137630583623616,
714
+ "eval_f1_micro": 0.4621212121212121,
715
+ "eval_f1_weighted": 0.45257586759804047,
716
+ "eval_loss": 1.3833413124084473,
717
+ "eval_precision_macro": 0.4850115870524033,
718
+ "eval_precision_micro": 0.4621212121212121,
719
+ "eval_precision_weighted": 0.49414276199990476,
720
+ "eval_recall_macro": 0.44020408163265307,
721
+ "eval_recall_micro": 0.4621212121212121,
722
+ "eval_recall_weighted": 0.4621212121212121,
723
+ "eval_runtime": 2.2948,
724
+ "eval_samples_per_second": 57.521,
725
+ "eval_steps_per_second": 7.408,
726
+ "step": 174
727
+ },
728
+ {
729
+ "epoch": 6.068965517241379,
730
+ "grad_norm": 9.312445640563965,
731
+ "learning_rate": 8.863346104725416e-05,
732
+ "loss": 1.2654,
733
+ "step": 176
734
+ },
735
+ {
736
+ "epoch": 6.137931034482759,
737
+ "grad_norm": 6.71382999420166,
738
+ "learning_rate": 8.837803320561942e-05,
739
+ "loss": 0.9276,
740
+ "step": 178
741
+ },
742
+ {
743
+ "epoch": 6.206896551724138,
744
+ "grad_norm": 8.297896385192871,
745
+ "learning_rate": 8.812260536398468e-05,
746
+ "loss": 1.1148,
747
+ "step": 180
748
+ },
749
+ {
750
+ "epoch": 6.275862068965517,
751
+ "grad_norm": 7.873631000518799,
752
+ "learning_rate": 8.786717752234995e-05,
753
+ "loss": 1.2827,
754
+ "step": 182
755
+ },
756
+ {
757
+ "epoch": 6.344827586206897,
758
+ "grad_norm": 6.687100887298584,
759
+ "learning_rate": 8.761174968071521e-05,
760
+ "loss": 0.9606,
761
+ "step": 184
762
+ },
763
+ {
764
+ "epoch": 6.413793103448276,
765
+ "grad_norm": 6.667215824127197,
766
+ "learning_rate": 8.735632183908047e-05,
767
+ "loss": 0.6776,
768
+ "step": 186
769
+ },
770
+ {
771
+ "epoch": 6.482758620689655,
772
+ "grad_norm": 8.208929061889648,
773
+ "learning_rate": 8.710089399744572e-05,
774
+ "loss": 0.881,
775
+ "step": 188
776
+ },
777
+ {
778
+ "epoch": 6.551724137931035,
779
+ "grad_norm": 9.478071212768555,
780
+ "learning_rate": 8.684546615581099e-05,
781
+ "loss": 1.136,
782
+ "step": 190
783
+ },
784
+ {
785
+ "epoch": 6.620689655172414,
786
+ "grad_norm": 8.301050186157227,
787
+ "learning_rate": 8.659003831417625e-05,
788
+ "loss": 0.9342,
789
+ "step": 192
790
+ },
791
+ {
792
+ "epoch": 6.689655172413794,
793
+ "grad_norm": 8.761463165283203,
794
+ "learning_rate": 8.633461047254151e-05,
795
+ "loss": 1.3543,
796
+ "step": 194
797
+ },
798
+ {
799
+ "epoch": 6.758620689655173,
800
+ "grad_norm": 7.483349323272705,
801
+ "learning_rate": 8.607918263090678e-05,
802
+ "loss": 1.2922,
803
+ "step": 196
804
+ },
805
+ {
806
+ "epoch": 6.827586206896552,
807
+ "grad_norm": 8.078042984008789,
808
+ "learning_rate": 8.582375478927204e-05,
809
+ "loss": 1.0205,
810
+ "step": 198
811
+ },
812
+ {
813
+ "epoch": 6.896551724137931,
814
+ "grad_norm": 8.326959609985352,
815
+ "learning_rate": 8.55683269476373e-05,
816
+ "loss": 0.9268,
817
+ "step": 200
818
+ },
819
+ {
820
+ "epoch": 6.9655172413793105,
821
+ "grad_norm": 6.995661735534668,
822
+ "learning_rate": 8.531289910600255e-05,
823
+ "loss": 1.1063,
824
+ "step": 202
825
+ },
826
+ {
827
+ "epoch": 7.0,
828
+ "eval_accuracy": 0.5833333333333334,
829
+ "eval_f1_macro": 0.47504441047674123,
830
+ "eval_f1_micro": 0.5833333333333334,
831
+ "eval_f1_weighted": 0.5452723811276442,
832
+ "eval_loss": 1.243076205253601,
833
+ "eval_precision_macro": 0.5897593680615791,
834
+ "eval_precision_micro": 0.5833333333333334,
835
+ "eval_precision_weighted": 0.6328941262782481,
836
+ "eval_recall_macro": 0.4889720332577476,
837
+ "eval_recall_micro": 0.5833333333333334,
838
+ "eval_recall_weighted": 0.5833333333333334,
839
+ "eval_runtime": 2.2997,
840
+ "eval_samples_per_second": 57.398,
841
+ "eval_steps_per_second": 7.392,
842
+ "step": 203
843
+ },
844
+ {
845
+ "epoch": 7.0344827586206895,
846
+ "grad_norm": 5.50567626953125,
847
+ "learning_rate": 8.505747126436782e-05,
848
+ "loss": 0.8912,
849
+ "step": 204
850
+ },
851
+ {
852
+ "epoch": 7.103448275862069,
853
+ "grad_norm": 10.640387535095215,
854
+ "learning_rate": 8.480204342273308e-05,
855
+ "loss": 1.058,
856
+ "step": 206
857
+ },
858
+ {
859
+ "epoch": 7.172413793103448,
860
+ "grad_norm": 9.858780860900879,
861
+ "learning_rate": 8.454661558109834e-05,
862
+ "loss": 1.5669,
863
+ "step": 208
864
+ },
865
+ {
866
+ "epoch": 7.241379310344827,
867
+ "grad_norm": 7.491808891296387,
868
+ "learning_rate": 8.42911877394636e-05,
869
+ "loss": 1.0278,
870
+ "step": 210
871
+ },
872
+ {
873
+ "epoch": 7.310344827586207,
874
+ "grad_norm": 6.82506799697876,
875
+ "learning_rate": 8.403575989782887e-05,
876
+ "loss": 0.8304,
877
+ "step": 212
878
+ },
879
+ {
880
+ "epoch": 7.379310344827586,
881
+ "grad_norm": 9.78387451171875,
882
+ "learning_rate": 8.378033205619413e-05,
883
+ "loss": 0.9639,
884
+ "step": 214
885
+ },
886
+ {
887
+ "epoch": 7.448275862068965,
888
+ "grad_norm": 8.452964782714844,
889
+ "learning_rate": 8.35249042145594e-05,
890
+ "loss": 1.2323,
891
+ "step": 216
892
+ },
893
+ {
894
+ "epoch": 7.517241379310345,
895
+ "grad_norm": 6.856133460998535,
896
+ "learning_rate": 8.326947637292465e-05,
897
+ "loss": 0.7968,
898
+ "step": 218
899
+ },
900
+ {
901
+ "epoch": 7.586206896551724,
902
+ "grad_norm": 5.6795268058776855,
903
+ "learning_rate": 8.301404853128991e-05,
904
+ "loss": 0.677,
905
+ "step": 220
906
+ },
907
+ {
908
+ "epoch": 7.655172413793103,
909
+ "grad_norm": 6.389831066131592,
910
+ "learning_rate": 8.275862068965517e-05,
911
+ "loss": 0.7194,
912
+ "step": 222
913
+ },
914
+ {
915
+ "epoch": 7.724137931034483,
916
+ "grad_norm": 9.00326919555664,
917
+ "learning_rate": 8.250319284802044e-05,
918
+ "loss": 0.977,
919
+ "step": 224
920
+ },
921
+ {
922
+ "epoch": 7.793103448275862,
923
+ "grad_norm": 11.774524688720703,
924
+ "learning_rate": 8.22477650063857e-05,
925
+ "loss": 1.3641,
926
+ "step": 226
927
+ },
928
+ {
929
+ "epoch": 7.862068965517241,
930
+ "grad_norm": 4.0308403968811035,
931
+ "learning_rate": 8.199233716475096e-05,
932
+ "loss": 0.6648,
933
+ "step": 228
934
+ },
935
+ {
936
+ "epoch": 7.931034482758621,
937
+ "grad_norm": 7.0713701248168945,
938
+ "learning_rate": 8.173690932311623e-05,
939
+ "loss": 1.0928,
940
+ "step": 230
941
+ },
942
+ {
943
+ "epoch": 8.0,
944
+ "grad_norm": 7.82318115234375,
945
+ "learning_rate": 8.148148148148148e-05,
946
+ "loss": 1.1503,
947
+ "step": 232
948
+ },
949
+ {
950
+ "epoch": 8.0,
951
+ "eval_accuracy": 0.49242424242424243,
952
+ "eval_f1_macro": 0.4036303722650846,
953
+ "eval_f1_micro": 0.49242424242424243,
954
+ "eval_f1_weighted": 0.45858542635408917,
955
+ "eval_loss": 1.3634601831436157,
956
+ "eval_precision_macro": 0.41447662068780083,
957
+ "eval_precision_micro": 0.49242424242424243,
958
+ "eval_precision_weighted": 0.47623097148788845,
959
+ "eval_recall_macro": 0.44362055933484507,
960
+ "eval_recall_micro": 0.49242424242424243,
961
+ "eval_recall_weighted": 0.49242424242424243,
962
+ "eval_runtime": 2.3144,
963
+ "eval_samples_per_second": 57.035,
964
+ "eval_steps_per_second": 7.345,
965
+ "step": 232
966
+ },
967
+ {
968
+ "epoch": 8.068965517241379,
969
+ "grad_norm": 9.172367095947266,
970
+ "learning_rate": 8.122605363984674e-05,
971
+ "loss": 0.5962,
972
+ "step": 234
973
+ },
974
+ {
975
+ "epoch": 8.137931034482758,
976
+ "grad_norm": 5.160254001617432,
977
+ "learning_rate": 8.0970625798212e-05,
978
+ "loss": 0.7505,
979
+ "step": 236
980
+ },
981
+ {
982
+ "epoch": 8.206896551724139,
983
+ "grad_norm": 8.052289009094238,
984
+ "learning_rate": 8.071519795657727e-05,
985
+ "loss": 0.8049,
986
+ "step": 238
987
+ },
988
+ {
989
+ "epoch": 8.275862068965518,
990
+ "grad_norm": 8.01250171661377,
991
+ "learning_rate": 8.045977011494253e-05,
992
+ "loss": 0.8478,
993
+ "step": 240
994
+ },
995
+ {
996
+ "epoch": 8.344827586206897,
997
+ "grad_norm": 6.239477634429932,
998
+ "learning_rate": 8.020434227330779e-05,
999
+ "loss": 0.5106,
1000
+ "step": 242
1001
+ },
1002
+ {
1003
+ "epoch": 8.413793103448276,
1004
+ "grad_norm": 9.426051139831543,
1005
+ "learning_rate": 7.994891443167306e-05,
1006
+ "loss": 0.9756,
1007
+ "step": 244
1008
+ },
1009
+ {
1010
+ "epoch": 8.482758620689655,
1011
+ "grad_norm": 6.412058353424072,
1012
+ "learning_rate": 7.969348659003832e-05,
1013
+ "loss": 0.8193,
1014
+ "step": 246
1015
+ },
1016
+ {
1017
+ "epoch": 8.551724137931034,
1018
+ "grad_norm": 9.318161010742188,
1019
+ "learning_rate": 7.943805874840358e-05,
1020
+ "loss": 0.7661,
1021
+ "step": 248
1022
+ },
1023
+ {
1024
+ "epoch": 8.620689655172415,
1025
+ "grad_norm": 10.047941207885742,
1026
+ "learning_rate": 7.918263090676885e-05,
1027
+ "loss": 1.046,
1028
+ "step": 250
1029
+ },
1030
+ {
1031
+ "epoch": 8.689655172413794,
1032
+ "grad_norm": 7.953283786773682,
1033
+ "learning_rate": 7.892720306513411e-05,
1034
+ "loss": 0.5181,
1035
+ "step": 252
1036
+ },
1037
+ {
1038
+ "epoch": 8.758620689655173,
1039
+ "grad_norm": 7.950782299041748,
1040
+ "learning_rate": 7.867177522349937e-05,
1041
+ "loss": 1.1763,
1042
+ "step": 254
1043
+ },
1044
+ {
1045
+ "epoch": 8.827586206896552,
1046
+ "grad_norm": 9.762330055236816,
1047
+ "learning_rate": 7.841634738186464e-05,
1048
+ "loss": 0.8871,
1049
+ "step": 256
1050
+ },
1051
+ {
1052
+ "epoch": 8.89655172413793,
1053
+ "grad_norm": 7.098607063293457,
1054
+ "learning_rate": 7.81609195402299e-05,
1055
+ "loss": 0.8989,
1056
+ "step": 258
1057
+ },
1058
+ {
1059
+ "epoch": 8.96551724137931,
1060
+ "grad_norm": 5.383296966552734,
1061
+ "learning_rate": 7.790549169859515e-05,
1062
+ "loss": 0.5124,
1063
+ "step": 260
1064
+ },
1065
+ {
1066
+ "epoch": 9.0,
1067
+ "eval_accuracy": 0.6287878787878788,
1068
+ "eval_f1_macro": 0.5462549380339138,
1069
+ "eval_f1_micro": 0.6287878787878788,
1070
+ "eval_f1_weighted": 0.613625246172416,
1071
+ "eval_loss": 1.160251259803772,
1072
+ "eval_precision_macro": 0.5487637362637362,
1073
+ "eval_precision_micro": 0.6287878787878788,
1074
+ "eval_precision_weighted": 0.6112845487845487,
1075
+ "eval_recall_macro": 0.5551398337112623,
1076
+ "eval_recall_micro": 0.6287878787878788,
1077
+ "eval_recall_weighted": 0.6287878787878788,
1078
+ "eval_runtime": 2.3163,
1079
+ "eval_samples_per_second": 56.988,
1080
+ "eval_steps_per_second": 7.339,
1081
+ "step": 261
1082
+ },
1083
+ {
1084
+ "epoch": 9.03448275862069,
1085
+ "grad_norm": 9.40657901763916,
1086
+ "learning_rate": 7.765006385696041e-05,
1087
+ "loss": 0.8737,
1088
+ "step": 262
1089
+ },
1090
+ {
1091
+ "epoch": 9.10344827586207,
1092
+ "grad_norm": 4.319129943847656,
1093
+ "learning_rate": 7.739463601532568e-05,
1094
+ "loss": 0.6403,
1095
+ "step": 264
1096
+ },
1097
+ {
1098
+ "epoch": 9.172413793103448,
1099
+ "grad_norm": 5.755863189697266,
1100
+ "learning_rate": 7.713920817369094e-05,
1101
+ "loss": 0.5969,
1102
+ "step": 266
1103
+ },
1104
+ {
1105
+ "epoch": 9.241379310344827,
1106
+ "grad_norm": 6.241076469421387,
1107
+ "learning_rate": 7.68837803320562e-05,
1108
+ "loss": 0.3827,
1109
+ "step": 268
1110
+ },
1111
+ {
1112
+ "epoch": 9.310344827586206,
1113
+ "grad_norm": 8.553583145141602,
1114
+ "learning_rate": 7.662835249042147e-05,
1115
+ "loss": 0.6394,
1116
+ "step": 270
1117
+ },
1118
+ {
1119
+ "epoch": 9.379310344827585,
1120
+ "grad_norm": 9.573847770690918,
1121
+ "learning_rate": 7.637292464878673e-05,
1122
+ "loss": 0.4346,
1123
+ "step": 272
1124
+ },
1125
+ {
1126
+ "epoch": 9.448275862068966,
1127
+ "grad_norm": 5.9898295402526855,
1128
+ "learning_rate": 7.611749680715198e-05,
1129
+ "loss": 0.7311,
1130
+ "step": 274
1131
+ },
1132
+ {
1133
+ "epoch": 9.517241379310345,
1134
+ "grad_norm": 7.574869155883789,
1135
+ "learning_rate": 7.586206896551724e-05,
1136
+ "loss": 0.5058,
1137
+ "step": 276
1138
+ },
1139
+ {
1140
+ "epoch": 9.586206896551724,
1141
+ "grad_norm": 5.771493434906006,
1142
+ "learning_rate": 7.56066411238825e-05,
1143
+ "loss": 0.4429,
1144
+ "step": 278
1145
+ },
1146
+ {
1147
+ "epoch": 9.655172413793103,
1148
+ "grad_norm": 5.4583306312561035,
1149
+ "learning_rate": 7.535121328224777e-05,
1150
+ "loss": 0.3691,
1151
+ "step": 280
1152
+ },
1153
+ {
1154
+ "epoch": 9.724137931034482,
1155
+ "grad_norm": 7.02595329284668,
1156
+ "learning_rate": 7.509578544061303e-05,
1157
+ "loss": 0.9049,
1158
+ "step": 282
1159
+ },
1160
+ {
1161
+ "epoch": 9.793103448275861,
1162
+ "grad_norm": 10.01053524017334,
1163
+ "learning_rate": 7.48403575989783e-05,
1164
+ "loss": 1.0885,
1165
+ "step": 284
1166
+ },
1167
+ {
1168
+ "epoch": 9.862068965517242,
1169
+ "grad_norm": 9.570963859558105,
1170
+ "learning_rate": 7.458492975734356e-05,
1171
+ "loss": 1.0013,
1172
+ "step": 286
1173
+ },
1174
+ {
1175
+ "epoch": 9.931034482758621,
1176
+ "grad_norm": 10.005152702331543,
1177
+ "learning_rate": 7.432950191570882e-05,
1178
+ "loss": 0.9009,
1179
+ "step": 288
1180
+ },
1181
+ {
1182
+ "epoch": 10.0,
1183
+ "grad_norm": 10.777491569519043,
1184
+ "learning_rate": 7.407407407407407e-05,
1185
+ "loss": 0.6648,
1186
+ "step": 290
1187
+ },
1188
+ {
1189
+ "epoch": 10.0,
1190
+ "eval_accuracy": 0.5,
1191
+ "eval_f1_macro": 0.4184378600485691,
1192
+ "eval_f1_micro": 0.5,
1193
+ "eval_f1_weighted": 0.47128332901854153,
1194
+ "eval_loss": 1.4135934114456177,
1195
+ "eval_precision_macro": 0.47128427128427125,
1196
+ "eval_precision_micro": 0.5,
1197
+ "eval_precision_weighted": 0.5275022956841138,
1198
+ "eval_recall_macro": 0.44126984126984137,
1199
+ "eval_recall_micro": 0.5,
1200
+ "eval_recall_weighted": 0.5,
1201
+ "eval_runtime": 2.3273,
1202
+ "eval_samples_per_second": 56.719,
1203
+ "eval_steps_per_second": 7.305,
1204
+ "step": 290
1205
+ },
1206
+ {
1207
+ "epoch": 10.068965517241379,
1208
+ "grad_norm": 11.478937149047852,
1209
+ "learning_rate": 7.381864623243934e-05,
1210
+ "loss": 0.7818,
1211
+ "step": 292
1212
+ },
1213
+ {
1214
+ "epoch": 10.137931034482758,
1215
+ "grad_norm": 4.0814738273620605,
1216
+ "learning_rate": 7.35632183908046e-05,
1217
+ "loss": 0.4467,
1218
+ "step": 294
1219
+ },
1220
+ {
1221
+ "epoch": 10.206896551724139,
1222
+ "grad_norm": 9.072375297546387,
1223
+ "learning_rate": 7.330779054916986e-05,
1224
+ "loss": 0.8457,
1225
+ "step": 296
1226
+ },
1227
+ {
1228
+ "epoch": 10.275862068965518,
1229
+ "grad_norm": 14.654154777526855,
1230
+ "learning_rate": 7.305236270753513e-05,
1231
+ "loss": 1.0091,
1232
+ "step": 298
1233
+ },
1234
+ {
1235
+ "epoch": 10.344827586206897,
1236
+ "grad_norm": 5.950021266937256,
1237
+ "learning_rate": 7.279693486590039e-05,
1238
+ "loss": 0.7003,
1239
+ "step": 300
1240
+ },
1241
+ {
1242
+ "epoch": 10.413793103448276,
1243
+ "grad_norm": 5.990440845489502,
1244
+ "learning_rate": 7.254150702426565e-05,
1245
+ "loss": 0.3965,
1246
+ "step": 302
1247
+ },
1248
+ {
1249
+ "epoch": 10.482758620689655,
1250
+ "grad_norm": 5.546842098236084,
1251
+ "learning_rate": 7.22860791826309e-05,
1252
+ "loss": 0.5934,
1253
+ "step": 304
1254
+ },
1255
+ {
1256
+ "epoch": 10.551724137931034,
1257
+ "grad_norm": 7.933053016662598,
1258
+ "learning_rate": 7.203065134099617e-05,
1259
+ "loss": 0.8553,
1260
+ "step": 306
1261
+ },
1262
+ {
1263
+ "epoch": 10.620689655172415,
1264
+ "grad_norm": 8.429969787597656,
1265
+ "learning_rate": 7.177522349936143e-05,
1266
+ "loss": 0.576,
1267
+ "step": 308
1268
+ },
1269
+ {
1270
+ "epoch": 10.689655172413794,
1271
+ "grad_norm": 10.716658592224121,
1272
+ "learning_rate": 7.151979565772669e-05,
1273
+ "loss": 0.8914,
1274
+ "step": 310
1275
+ },
1276
+ {
1277
+ "epoch": 10.758620689655173,
1278
+ "grad_norm": 6.751779556274414,
1279
+ "learning_rate": 7.126436781609196e-05,
1280
+ "loss": 0.6289,
1281
+ "step": 312
1282
+ },
1283
+ {
1284
+ "epoch": 10.827586206896552,
1285
+ "grad_norm": 9.158184051513672,
1286
+ "learning_rate": 7.100893997445722e-05,
1287
+ "loss": 0.6223,
1288
+ "step": 314
1289
+ },
1290
+ {
1291
+ "epoch": 10.89655172413793,
1292
+ "grad_norm": 7.099061965942383,
1293
+ "learning_rate": 7.075351213282248e-05,
1294
+ "loss": 0.396,
1295
+ "step": 316
1296
+ },
1297
+ {
1298
+ "epoch": 10.96551724137931,
1299
+ "grad_norm": 6.873266220092773,
1300
+ "learning_rate": 7.049808429118773e-05,
1301
+ "loss": 0.2917,
1302
+ "step": 318
1303
+ },
1304
+ {
1305
+ "epoch": 11.0,
1306
+ "eval_accuracy": 0.6060606060606061,
1307
+ "eval_f1_macro": 0.5155148119854002,
1308
+ "eval_f1_micro": 0.6060606060606061,
1309
+ "eval_f1_weighted": 0.5892264894938692,
1310
+ "eval_loss": 1.2004135847091675,
1311
+ "eval_precision_macro": 0.5179884004884004,
1312
+ "eval_precision_micro": 0.6060606060606061,
1313
+ "eval_precision_weighted": 0.5881653069153069,
1314
+ "eval_recall_macro": 0.5268253968253969,
1315
+ "eval_recall_micro": 0.6060606060606061,
1316
+ "eval_recall_weighted": 0.6060606060606061,
1317
+ "eval_runtime": 2.3355,
1318
+ "eval_samples_per_second": 56.52,
1319
+ "eval_steps_per_second": 7.279,
1320
+ "step": 319
1321
+ },
1322
+ {
1323
+ "epoch": 11.03448275862069,
1324
+ "grad_norm": 3.133075714111328,
1325
+ "learning_rate": 7.0242656449553e-05,
1326
+ "loss": 0.466,
1327
+ "step": 320
1328
+ },
1329
+ {
1330
+ "epoch": 11.10344827586207,
1331
+ "grad_norm": 4.213578701019287,
1332
+ "learning_rate": 6.998722860791826e-05,
1333
+ "loss": 0.3184,
1334
+ "step": 322
1335
+ },
1336
+ {
1337
+ "epoch": 11.172413793103448,
1338
+ "grad_norm": 6.637679576873779,
1339
+ "learning_rate": 6.973180076628352e-05,
1340
+ "loss": 0.5278,
1341
+ "step": 324
1342
+ },
1343
+ {
1344
+ "epoch": 11.241379310344827,
1345
+ "grad_norm": 7.749922752380371,
1346
+ "learning_rate": 6.947637292464879e-05,
1347
+ "loss": 0.3204,
1348
+ "step": 326
1349
+ },
1350
+ {
1351
+ "epoch": 11.310344827586206,
1352
+ "grad_norm": 4.362213611602783,
1353
+ "learning_rate": 6.922094508301405e-05,
1354
+ "loss": 0.2826,
1355
+ "step": 328
1356
+ },
1357
+ {
1358
+ "epoch": 11.379310344827585,
1359
+ "grad_norm": 3.698016881942749,
1360
+ "learning_rate": 6.896551724137931e-05,
1361
+ "loss": 0.3818,
1362
+ "step": 330
1363
+ },
1364
+ {
1365
+ "epoch": 11.448275862068966,
1366
+ "grad_norm": 8.710986137390137,
1367
+ "learning_rate": 6.871008939974458e-05,
1368
+ "loss": 0.6038,
1369
+ "step": 332
1370
+ },
1371
+ {
1372
+ "epoch": 11.517241379310345,
1373
+ "grad_norm": 7.1719536781311035,
1374
+ "learning_rate": 6.845466155810984e-05,
1375
+ "loss": 0.3225,
1376
+ "step": 334
1377
+ },
1378
+ {
1379
+ "epoch": 11.586206896551724,
1380
+ "grad_norm": 6.520328521728516,
1381
+ "learning_rate": 6.81992337164751e-05,
1382
+ "loss": 0.5006,
1383
+ "step": 336
1384
+ },
1385
+ {
1386
+ "epoch": 11.655172413793103,
1387
+ "grad_norm": 7.6063127517700195,
1388
+ "learning_rate": 6.794380587484037e-05,
1389
+ "loss": 0.5006,
1390
+ "step": 338
1391
+ },
1392
+ {
1393
+ "epoch": 11.724137931034482,
1394
+ "grad_norm": 5.628337860107422,
1395
+ "learning_rate": 6.768837803320563e-05,
1396
+ "loss": 0.3412,
1397
+ "step": 340
1398
+ },
1399
+ {
1400
+ "epoch": 11.793103448275861,
1401
+ "grad_norm": 9.223949432373047,
1402
+ "learning_rate": 6.74329501915709e-05,
1403
+ "loss": 0.4309,
1404
+ "step": 342
1405
+ },
1406
+ {
1407
+ "epoch": 11.862068965517242,
1408
+ "grad_norm": 11.727864265441895,
1409
+ "learning_rate": 6.717752234993616e-05,
1410
+ "loss": 0.6459,
1411
+ "step": 344
1412
+ },
1413
+ {
1414
+ "epoch": 11.931034482758621,
1415
+ "grad_norm": 7.271657943725586,
1416
+ "learning_rate": 6.69220945083014e-05,
1417
+ "loss": 0.2677,
1418
+ "step": 346
1419
+ },
1420
+ {
1421
+ "epoch": 12.0,
1422
+ "grad_norm": 8.708776473999023,
1423
+ "learning_rate": 6.666666666666667e-05,
1424
+ "loss": 0.4962,
1425
+ "step": 348
1426
+ },
1427
+ {
1428
+ "epoch": 12.0,
1429
+ "eval_accuracy": 0.5681818181818182,
1430
+ "eval_f1_macro": 0.4970094576905722,
1431
+ "eval_f1_micro": 0.5681818181818182,
1432
+ "eval_f1_weighted": 0.5670813823572056,
1433
+ "eval_loss": 1.3730109930038452,
1434
+ "eval_precision_macro": 0.5093805943430004,
1435
+ "eval_precision_micro": 0.5681818181818182,
1436
+ "eval_precision_weighted": 0.5908635224424699,
1437
+ "eval_recall_macro": 0.5109221466364323,
1438
+ "eval_recall_micro": 0.5681818181818182,
1439
+ "eval_recall_weighted": 0.5681818181818182,
1440
+ "eval_runtime": 2.3092,
1441
+ "eval_samples_per_second": 57.162,
1442
+ "eval_steps_per_second": 7.362,
1443
+ "step": 348
1444
+ },
1445
+ {
1446
+ "epoch": 12.068965517241379,
1447
+ "grad_norm": 5.946571350097656,
1448
+ "learning_rate": 6.641123882503193e-05,
1449
+ "loss": 0.3055,
1450
+ "step": 350
1451
+ },
1452
+ {
1453
+ "epoch": 12.137931034482758,
1454
+ "grad_norm": 8.733643531799316,
1455
+ "learning_rate": 6.61558109833972e-05,
1456
+ "loss": 0.4823,
1457
+ "step": 352
1458
+ },
1459
+ {
1460
+ "epoch": 12.206896551724139,
1461
+ "grad_norm": 5.436933994293213,
1462
+ "learning_rate": 6.590038314176246e-05,
1463
+ "loss": 0.344,
1464
+ "step": 354
1465
+ },
1466
+ {
1467
+ "epoch": 12.275862068965518,
1468
+ "grad_norm": 8.14691162109375,
1469
+ "learning_rate": 6.564495530012772e-05,
1470
+ "loss": 0.4108,
1471
+ "step": 356
1472
+ },
1473
+ {
1474
+ "epoch": 12.344827586206897,
1475
+ "grad_norm": 6.8699870109558105,
1476
+ "learning_rate": 6.538952745849299e-05,
1477
+ "loss": 0.2988,
1478
+ "step": 358
1479
+ },
1480
+ {
1481
+ "epoch": 12.413793103448276,
1482
+ "grad_norm": 5.896437168121338,
1483
+ "learning_rate": 6.513409961685824e-05,
1484
+ "loss": 0.5497,
1485
+ "step": 360
1486
+ },
1487
+ {
1488
+ "epoch": 12.482758620689655,
1489
+ "grad_norm": 4.062476634979248,
1490
+ "learning_rate": 6.48786717752235e-05,
1491
+ "loss": 0.1877,
1492
+ "step": 362
1493
+ },
1494
+ {
1495
+ "epoch": 12.551724137931034,
1496
+ "grad_norm": 6.9578046798706055,
1497
+ "learning_rate": 6.462324393358876e-05,
1498
+ "loss": 0.295,
1499
+ "step": 364
1500
+ },
1501
+ {
1502
+ "epoch": 12.620689655172415,
1503
+ "grad_norm": 7.430821895599365,
1504
+ "learning_rate": 6.436781609195403e-05,
1505
+ "loss": 0.4402,
1506
+ "step": 366
1507
+ },
1508
+ {
1509
+ "epoch": 12.689655172413794,
1510
+ "grad_norm": 7.945040225982666,
1511
+ "learning_rate": 6.411238825031929e-05,
1512
+ "loss": 0.3923,
1513
+ "step": 368
1514
+ },
1515
+ {
1516
+ "epoch": 12.758620689655173,
1517
+ "grad_norm": 5.361316680908203,
1518
+ "learning_rate": 6.385696040868455e-05,
1519
+ "loss": 0.3829,
1520
+ "step": 370
1521
+ },
1522
+ {
1523
+ "epoch": 12.827586206896552,
1524
+ "grad_norm": 3.211268901824951,
1525
+ "learning_rate": 6.360153256704982e-05,
1526
+ "loss": 0.2011,
1527
+ "step": 372
1528
+ },
1529
+ {
1530
+ "epoch": 12.89655172413793,
1531
+ "grad_norm": 12.301307678222656,
1532
+ "learning_rate": 6.334610472541508e-05,
1533
+ "loss": 0.422,
1534
+ "step": 374
1535
+ },
1536
+ {
1537
+ "epoch": 12.96551724137931,
1538
+ "grad_norm": 7.031186103820801,
1539
+ "learning_rate": 6.309067688378033e-05,
1540
+ "loss": 0.5723,
1541
+ "step": 376
1542
+ },
1543
+ {
1544
+ "epoch": 13.0,
1545
+ "eval_accuracy": 0.6136363636363636,
1546
+ "eval_f1_macro": 0.5704633000800248,
1547
+ "eval_f1_micro": 0.6136363636363636,
1548
+ "eval_f1_weighted": 0.6076619338260136,
1549
+ "eval_loss": 1.337725043296814,
1550
+ "eval_precision_macro": 0.7050316678395496,
1551
+ "eval_precision_micro": 0.6136363636363636,
1552
+ "eval_precision_weighted": 0.6878949594466836,
1553
+ "eval_recall_macro": 0.5756311413454271,
1554
+ "eval_recall_micro": 0.6136363636363636,
1555
+ "eval_recall_weighted": 0.6136363636363636,
1556
+ "eval_runtime": 2.3083,
1557
+ "eval_samples_per_second": 57.184,
1558
+ "eval_steps_per_second": 7.365,
1559
+ "step": 377
1560
+ },
1561
+ {
1562
+ "epoch": 13.03448275862069,
1563
+ "grad_norm": 9.725719451904297,
1564
+ "learning_rate": 6.283524904214559e-05,
1565
+ "loss": 0.5555,
1566
+ "step": 378
1567
+ },
1568
+ {
1569
+ "epoch": 13.10344827586207,
1570
+ "grad_norm": 2.5052599906921387,
1571
+ "learning_rate": 6.257982120051086e-05,
1572
+ "loss": 0.1335,
1573
+ "step": 380
1574
+ },
1575
+ {
1576
+ "epoch": 13.172413793103448,
1577
+ "grad_norm": 5.450864315032959,
1578
+ "learning_rate": 6.232439335887612e-05,
1579
+ "loss": 0.3542,
1580
+ "step": 382
1581
+ },
1582
+ {
1583
+ "epoch": 13.241379310344827,
1584
+ "grad_norm": 6.038177967071533,
1585
+ "learning_rate": 6.206896551724138e-05,
1586
+ "loss": 0.3631,
1587
+ "step": 384
1588
+ },
1589
+ {
1590
+ "epoch": 13.310344827586206,
1591
+ "grad_norm": 2.067920207977295,
1592
+ "learning_rate": 6.181353767560665e-05,
1593
+ "loss": 0.2047,
1594
+ "step": 386
1595
+ },
1596
+ {
1597
+ "epoch": 13.379310344827585,
1598
+ "grad_norm": 3.663801908493042,
1599
+ "learning_rate": 6.155810983397191e-05,
1600
+ "loss": 0.2643,
1601
+ "step": 388
1602
+ },
1603
+ {
1604
+ "epoch": 13.448275862068966,
1605
+ "grad_norm": 6.576447010040283,
1606
+ "learning_rate": 6.130268199233716e-05,
1607
+ "loss": 0.5131,
1608
+ "step": 390
1609
+ },
1610
+ {
1611
+ "epoch": 13.517241379310345,
1612
+ "grad_norm": 2.8306472301483154,
1613
+ "learning_rate": 6.104725415070242e-05,
1614
+ "loss": 0.09,
1615
+ "step": 392
1616
+ },
1617
+ {
1618
+ "epoch": 13.586206896551724,
1619
+ "grad_norm": 4.799499988555908,
1620
+ "learning_rate": 6.0791826309067686e-05,
1621
+ "loss": 0.213,
1622
+ "step": 394
1623
+ },
1624
+ {
1625
+ "epoch": 13.655172413793103,
1626
+ "grad_norm": 5.044408321380615,
1627
+ "learning_rate": 6.053639846743295e-05,
1628
+ "loss": 0.4801,
1629
+ "step": 396
1630
+ },
1631
+ {
1632
+ "epoch": 13.724137931034482,
1633
+ "grad_norm": 2.9088187217712402,
1634
+ "learning_rate": 6.028097062579821e-05,
1635
+ "loss": 0.125,
1636
+ "step": 398
1637
+ },
1638
+ {
1639
+ "epoch": 13.793103448275861,
1640
+ "grad_norm": 5.007681369781494,
1641
+ "learning_rate": 6.0025542784163477e-05,
1642
+ "loss": 0.3982,
1643
+ "step": 400
1644
+ },
1645
+ {
1646
+ "epoch": 13.862068965517242,
1647
+ "grad_norm": 4.744725227355957,
1648
+ "learning_rate": 5.977011494252874e-05,
1649
+ "loss": 0.4611,
1650
+ "step": 402
1651
+ },
1652
+ {
1653
+ "epoch": 13.931034482758621,
1654
+ "grad_norm": 8.447021484375,
1655
+ "learning_rate": 5.9514687100893996e-05,
1656
+ "loss": 0.62,
1657
+ "step": 404
1658
+ },
1659
+ {
1660
+ "epoch": 14.0,
1661
+ "grad_norm": 8.788926124572754,
1662
+ "learning_rate": 5.925925925925926e-05,
1663
+ "loss": 0.4589,
1664
+ "step": 406
1665
+ },
1666
+ {
1667
+ "epoch": 14.0,
1668
+ "eval_accuracy": 0.6136363636363636,
1669
+ "eval_f1_macro": 0.5648011794500899,
1670
+ "eval_f1_micro": 0.6136363636363636,
1671
+ "eval_f1_weighted": 0.6094460111024054,
1672
+ "eval_loss": 1.371690273284912,
1673
+ "eval_precision_macro": 0.6239191729323308,
1674
+ "eval_precision_micro": 0.6136363636363636,
1675
+ "eval_precision_weighted": 0.6458109051036682,
1676
+ "eval_recall_macro": 0.5608919123204837,
1677
+ "eval_recall_micro": 0.6136363636363636,
1678
+ "eval_recall_weighted": 0.6136363636363636,
1679
+ "eval_runtime": 2.3086,
1680
+ "eval_samples_per_second": 57.179,
1681
+ "eval_steps_per_second": 7.364,
1682
+ "step": 406
1683
+ },
1684
+ {
1685
+ "epoch": 14.068965517241379,
1686
+ "grad_norm": 2.962904453277588,
1687
+ "learning_rate": 5.900383141762452e-05,
1688
+ "loss": 0.1153,
1689
+ "step": 408
1690
+ },
1691
+ {
1692
+ "epoch": 14.137931034482758,
1693
+ "grad_norm": 1.518691897392273,
1694
+ "learning_rate": 5.8748403575989787e-05,
1695
+ "loss": 0.1856,
1696
+ "step": 410
1697
+ },
1698
+ {
1699
+ "epoch": 14.206896551724139,
1700
+ "grad_norm": 5.813935279846191,
1701
+ "learning_rate": 5.849297573435505e-05,
1702
+ "loss": 0.1939,
1703
+ "step": 412
1704
+ },
1705
+ {
1706
+ "epoch": 14.275862068965518,
1707
+ "grad_norm": 8.985111236572266,
1708
+ "learning_rate": 5.823754789272031e-05,
1709
+ "loss": 0.4468,
1710
+ "step": 414
1711
+ },
1712
+ {
1713
+ "epoch": 14.344827586206897,
1714
+ "grad_norm": 9.152397155761719,
1715
+ "learning_rate": 5.798212005108558e-05,
1716
+ "loss": 0.2363,
1717
+ "step": 416
1718
+ },
1719
+ {
1720
+ "epoch": 14.413793103448276,
1721
+ "grad_norm": 5.893610954284668,
1722
+ "learning_rate": 5.7726692209450826e-05,
1723
+ "loss": 0.3035,
1724
+ "step": 418
1725
+ },
1726
+ {
1727
+ "epoch": 14.482758620689655,
1728
+ "grad_norm": 3.14355206489563,
1729
+ "learning_rate": 5.747126436781609e-05,
1730
+ "loss": 0.0909,
1731
+ "step": 420
1732
+ },
1733
+ {
1734
+ "epoch": 14.551724137931034,
1735
+ "grad_norm": 5.298672676086426,
1736
+ "learning_rate": 5.721583652618135e-05,
1737
+ "loss": 0.2343,
1738
+ "step": 422
1739
+ },
1740
+ {
1741
+ "epoch": 14.620689655172415,
1742
+ "grad_norm": 6.373053550720215,
1743
+ "learning_rate": 5.6960408684546617e-05,
1744
+ "loss": 0.183,
1745
+ "step": 424
1746
+ },
1747
+ {
1748
+ "epoch": 14.689655172413794,
1749
+ "grad_norm": 2.314725637435913,
1750
+ "learning_rate": 5.670498084291188e-05,
1751
+ "loss": 0.1293,
1752
+ "step": 426
1753
+ },
1754
+ {
1755
+ "epoch": 14.758620689655173,
1756
+ "grad_norm": 3.448334217071533,
1757
+ "learning_rate": 5.644955300127714e-05,
1758
+ "loss": 0.1733,
1759
+ "step": 428
1760
+ },
1761
+ {
1762
+ "epoch": 14.827586206896552,
1763
+ "grad_norm": 1.1106864213943481,
1764
+ "learning_rate": 5.6194125159642407e-05,
1765
+ "loss": 0.1687,
1766
+ "step": 430
1767
+ },
1768
+ {
1769
+ "epoch": 14.89655172413793,
1770
+ "grad_norm": 8.680233001708984,
1771
+ "learning_rate": 5.593869731800766e-05,
1772
+ "loss": 0.235,
1773
+ "step": 432
1774
+ },
1775
+ {
1776
+ "epoch": 14.96551724137931,
1777
+ "grad_norm": 6.511703014373779,
1778
+ "learning_rate": 5.5683269476372927e-05,
1779
+ "loss": 0.2544,
1780
+ "step": 434
1781
+ },
1782
+ {
1783
+ "epoch": 15.0,
1784
+ "eval_accuracy": 0.5984848484848485,
1785
+ "eval_f1_macro": 0.5086132463535884,
1786
+ "eval_f1_micro": 0.5984848484848485,
1787
+ "eval_f1_weighted": 0.5792803276453666,
1788
+ "eval_loss": 1.4129072427749634,
1789
+ "eval_precision_macro": 0.5139594299258164,
1790
+ "eval_precision_micro": 0.5984848484848485,
1791
+ "eval_precision_weighted": 0.5772144522144522,
1792
+ "eval_recall_macro": 0.5187150415721845,
1793
+ "eval_recall_micro": 0.5984848484848485,
1794
+ "eval_recall_weighted": 0.5984848484848485,
1795
+ "eval_runtime": 2.3923,
1796
+ "eval_samples_per_second": 55.177,
1797
+ "eval_steps_per_second": 7.106,
1798
+ "step": 435
1799
+ },
1800
+ {
1801
+ "epoch": 15.03448275862069,
1802
+ "grad_norm": 4.20862340927124,
1803
+ "learning_rate": 5.542784163473819e-05,
1804
+ "loss": 0.1926,
1805
+ "step": 436
1806
+ },
1807
+ {
1808
+ "epoch": 15.10344827586207,
1809
+ "grad_norm": 3.021908760070801,
1810
+ "learning_rate": 5.517241379310345e-05,
1811
+ "loss": 0.1026,
1812
+ "step": 438
1813
+ },
1814
+ {
1815
+ "epoch": 15.172413793103448,
1816
+ "grad_norm": 2.936843156814575,
1817
+ "learning_rate": 5.491698595146872e-05,
1818
+ "loss": 0.0991,
1819
+ "step": 440
1820
+ },
1821
+ {
1822
+ "epoch": 15.241379310344827,
1823
+ "grad_norm": 5.583840370178223,
1824
+ "learning_rate": 5.466155810983398e-05,
1825
+ "loss": 0.2134,
1826
+ "step": 442
1827
+ },
1828
+ {
1829
+ "epoch": 15.310344827586206,
1830
+ "grad_norm": 3.211482524871826,
1831
+ "learning_rate": 5.440613026819924e-05,
1832
+ "loss": 0.2029,
1833
+ "step": 444
1834
+ },
1835
+ {
1836
+ "epoch": 15.379310344827585,
1837
+ "grad_norm": 1.41876220703125,
1838
+ "learning_rate": 5.415070242656451e-05,
1839
+ "loss": 0.2023,
1840
+ "step": 446
1841
+ },
1842
+ {
1843
+ "epoch": 15.448275862068966,
1844
+ "grad_norm": 7.651742458343506,
1845
+ "learning_rate": 5.3895274584929756e-05,
1846
+ "loss": 0.2089,
1847
+ "step": 448
1848
+ },
1849
+ {
1850
+ "epoch": 15.517241379310345,
1851
+ "grad_norm": 6.275810241699219,
1852
+ "learning_rate": 5.363984674329502e-05,
1853
+ "loss": 0.1875,
1854
+ "step": 450
1855
+ },
1856
+ {
1857
+ "epoch": 15.586206896551724,
1858
+ "grad_norm": 3.7232401371002197,
1859
+ "learning_rate": 5.338441890166028e-05,
1860
+ "loss": 0.0971,
1861
+ "step": 452
1862
+ },
1863
+ {
1864
+ "epoch": 15.655172413793103,
1865
+ "grad_norm": 4.189459800720215,
1866
+ "learning_rate": 5.3128991060025547e-05,
1867
+ "loss": 0.3281,
1868
+ "step": 454
1869
+ },
1870
+ {
1871
+ "epoch": 15.724137931034482,
1872
+ "grad_norm": 8.769723892211914,
1873
+ "learning_rate": 5.287356321839081e-05,
1874
+ "loss": 0.2751,
1875
+ "step": 456
1876
+ },
1877
+ {
1878
+ "epoch": 15.793103448275861,
1879
+ "grad_norm": 6.462566375732422,
1880
+ "learning_rate": 5.261813537675607e-05,
1881
+ "loss": 0.0904,
1882
+ "step": 458
1883
+ },
1884
+ {
1885
+ "epoch": 15.862068965517242,
1886
+ "grad_norm": 9.79684066772461,
1887
+ "learning_rate": 5.236270753512134e-05,
1888
+ "loss": 0.6062,
1889
+ "step": 460
1890
+ },
1891
+ {
1892
+ "epoch": 15.931034482758621,
1893
+ "grad_norm": 1.4883109331130981,
1894
+ "learning_rate": 5.2107279693486586e-05,
1895
+ "loss": 0.1717,
1896
+ "step": 462
1897
+ },
1898
+ {
1899
+ "epoch": 16.0,
1900
+ "grad_norm": 6.8840413093566895,
1901
+ "learning_rate": 5.185185185185185e-05,
1902
+ "loss": 0.3179,
1903
+ "step": 464
1904
+ },
1905
+ {
1906
+ "epoch": 16.0,
1907
+ "eval_accuracy": 0.6439393939393939,
1908
+ "eval_f1_macro": 0.5881714359157968,
1909
+ "eval_f1_micro": 0.6439393939393939,
1910
+ "eval_f1_weighted": 0.634653723469513,
1911
+ "eval_loss": 1.3588663339614868,
1912
+ "eval_precision_macro": 0.6912393397962158,
1913
+ "eval_precision_micro": 0.6439393939393939,
1914
+ "eval_precision_weighted": 0.6603221597047805,
1915
+ "eval_recall_macro": 0.5777021919879062,
1916
+ "eval_recall_micro": 0.6439393939393939,
1917
+ "eval_recall_weighted": 0.6439393939393939,
1918
+ "eval_runtime": 2.3227,
1919
+ "eval_samples_per_second": 56.83,
1920
+ "eval_steps_per_second": 7.319,
1921
+ "step": 464
1922
+ },
1923
+ {
1924
+ "epoch": 16.06896551724138,
1925
+ "grad_norm": 7.6531081199646,
1926
+ "learning_rate": 5.159642401021711e-05,
1927
+ "loss": 0.264,
1928
+ "step": 466
1929
+ },
1930
+ {
1931
+ "epoch": 16.137931034482758,
1932
+ "grad_norm": 2.896730422973633,
1933
+ "learning_rate": 5.1340996168582377e-05,
1934
+ "loss": 0.1107,
1935
+ "step": 468
1936
+ },
1937
+ {
1938
+ "epoch": 16.20689655172414,
1939
+ "grad_norm": 1.4611581563949585,
1940
+ "learning_rate": 5.108556832694764e-05,
1941
+ "loss": 0.0496,
1942
+ "step": 470
1943
+ },
1944
+ {
1945
+ "epoch": 16.275862068965516,
1946
+ "grad_norm": 4.168929100036621,
1947
+ "learning_rate": 5.08301404853129e-05,
1948
+ "loss": 0.0983,
1949
+ "step": 472
1950
+ },
1951
+ {
1952
+ "epoch": 16.344827586206897,
1953
+ "grad_norm": 2.321575880050659,
1954
+ "learning_rate": 5.057471264367817e-05,
1955
+ "loss": 0.1663,
1956
+ "step": 474
1957
+ },
1958
+ {
1959
+ "epoch": 16.413793103448278,
1960
+ "grad_norm": 4.329580783843994,
1961
+ "learning_rate": 5.031928480204342e-05,
1962
+ "loss": 0.1443,
1963
+ "step": 476
1964
+ },
1965
+ {
1966
+ "epoch": 16.482758620689655,
1967
+ "grad_norm": 2.386385917663574,
1968
+ "learning_rate": 5.0063856960408687e-05,
1969
+ "loss": 0.0896,
1970
+ "step": 478
1971
+ },
1972
+ {
1973
+ "epoch": 16.551724137931036,
1974
+ "grad_norm": 3.150066375732422,
1975
+ "learning_rate": 4.980842911877395e-05,
1976
+ "loss": 0.0847,
1977
+ "step": 480
1978
+ },
1979
+ {
1980
+ "epoch": 16.620689655172413,
1981
+ "grad_norm": 5.366412162780762,
1982
+ "learning_rate": 4.955300127713921e-05,
1983
+ "loss": 0.1571,
1984
+ "step": 482
1985
+ },
1986
+ {
1987
+ "epoch": 16.689655172413794,
1988
+ "grad_norm": 3.45316743850708,
1989
+ "learning_rate": 4.929757343550448e-05,
1990
+ "loss": 0.0969,
1991
+ "step": 484
1992
+ },
1993
+ {
1994
+ "epoch": 16.75862068965517,
1995
+ "grad_norm": 5.476890563964844,
1996
+ "learning_rate": 4.904214559386973e-05,
1997
+ "loss": 0.1459,
1998
+ "step": 486
1999
+ },
2000
+ {
2001
+ "epoch": 16.82758620689655,
2002
+ "grad_norm": 8.211587905883789,
2003
+ "learning_rate": 4.8786717752234997e-05,
2004
+ "loss": 0.1792,
2005
+ "step": 488
2006
+ },
2007
+ {
2008
+ "epoch": 16.896551724137932,
2009
+ "grad_norm": 2.131403684616089,
2010
+ "learning_rate": 4.853128991060026e-05,
2011
+ "loss": 0.0605,
2012
+ "step": 490
2013
+ },
2014
+ {
2015
+ "epoch": 16.96551724137931,
2016
+ "grad_norm": 2.498298168182373,
2017
+ "learning_rate": 4.827586206896552e-05,
2018
+ "loss": 0.1304,
2019
+ "step": 492
2020
+ },
2021
+ {
2022
+ "epoch": 17.0,
2023
+ "eval_accuracy": 0.5757575757575758,
2024
+ "eval_f1_macro": 0.5009666653370032,
2025
+ "eval_f1_micro": 0.5757575757575758,
2026
+ "eval_f1_weighted": 0.5605685796379482,
2027
+ "eval_loss": 1.5604240894317627,
2028
+ "eval_precision_macro": 0.512285419028604,
2029
+ "eval_precision_micro": 0.5757575757575758,
2030
+ "eval_precision_weighted": 0.5669229036256557,
2031
+ "eval_recall_macro": 0.507588813303099,
2032
+ "eval_recall_micro": 0.5757575757575758,
2033
+ "eval_recall_weighted": 0.5757575757575758,
2034
+ "eval_runtime": 2.3178,
2035
+ "eval_samples_per_second": 56.95,
2036
+ "eval_steps_per_second": 7.334,
2037
+ "step": 493
2038
+ },
2039
+ {
2040
+ "epoch": 17.03448275862069,
2041
+ "grad_norm": 6.805662155151367,
2042
+ "learning_rate": 4.802043422733078e-05,
2043
+ "loss": 0.2056,
2044
+ "step": 494
2045
+ },
2046
+ {
2047
+ "epoch": 17.103448275862068,
2048
+ "grad_norm": 0.6827877163887024,
2049
+ "learning_rate": 4.776500638569604e-05,
2050
+ "loss": 0.0298,
2051
+ "step": 496
2052
+ },
2053
+ {
2054
+ "epoch": 17.17241379310345,
2055
+ "grad_norm": 4.717907905578613,
2056
+ "learning_rate": 4.7509578544061307e-05,
2057
+ "loss": 0.051,
2058
+ "step": 498
2059
+ },
2060
+ {
2061
+ "epoch": 17.24137931034483,
2062
+ "grad_norm": 2.6737117767333984,
2063
+ "learning_rate": 4.725415070242657e-05,
2064
+ "loss": 0.0294,
2065
+ "step": 500
2066
+ },
2067
+ {
2068
+ "epoch": 17.310344827586206,
2069
+ "grad_norm": 6.83554220199585,
2070
+ "learning_rate": 4.6998722860791827e-05,
2071
+ "loss": 0.3266,
2072
+ "step": 502
2073
+ },
2074
+ {
2075
+ "epoch": 17.379310344827587,
2076
+ "grad_norm": 4.863897800445557,
2077
+ "learning_rate": 4.674329501915709e-05,
2078
+ "loss": 0.1338,
2079
+ "step": 504
2080
+ },
2081
+ {
2082
+ "epoch": 17.448275862068964,
2083
+ "grad_norm": 3.4082953929901123,
2084
+ "learning_rate": 4.648786717752235e-05,
2085
+ "loss": 0.1397,
2086
+ "step": 506
2087
+ },
2088
+ {
2089
+ "epoch": 17.517241379310345,
2090
+ "grad_norm": 2.798154592514038,
2091
+ "learning_rate": 4.623243933588761e-05,
2092
+ "loss": 0.0626,
2093
+ "step": 508
2094
+ },
2095
+ {
2096
+ "epoch": 17.586206896551722,
2097
+ "grad_norm": 7.175295829772949,
2098
+ "learning_rate": 4.597701149425287e-05,
2099
+ "loss": 0.0881,
2100
+ "step": 510
2101
+ },
2102
+ {
2103
+ "epoch": 17.655172413793103,
2104
+ "grad_norm": 1.9316564798355103,
2105
+ "learning_rate": 4.5721583652618137e-05,
2106
+ "loss": 0.0838,
2107
+ "step": 512
2108
+ },
2109
+ {
2110
+ "epoch": 17.724137931034484,
2111
+ "grad_norm": 7.5723161697387695,
2112
+ "learning_rate": 4.54661558109834e-05,
2113
+ "loss": 0.1712,
2114
+ "step": 514
2115
+ },
2116
+ {
2117
+ "epoch": 17.79310344827586,
2118
+ "grad_norm": 0.6257821917533875,
2119
+ "learning_rate": 4.5210727969348656e-05,
2120
+ "loss": 0.0811,
2121
+ "step": 516
2122
+ },
2123
+ {
2124
+ "epoch": 17.862068965517242,
2125
+ "grad_norm": 0.7635870575904846,
2126
+ "learning_rate": 4.495530012771392e-05,
2127
+ "loss": 0.0376,
2128
+ "step": 518
2129
+ },
2130
+ {
2131
+ "epoch": 17.93103448275862,
2132
+ "grad_norm": 8.914319038391113,
2133
+ "learning_rate": 4.469987228607918e-05,
2134
+ "loss": 0.3516,
2135
+ "step": 520
2136
+ },
2137
+ {
2138
+ "epoch": 18.0,
2139
+ "grad_norm": 4.3583478927612305,
2140
+ "learning_rate": 4.4444444444444447e-05,
2141
+ "loss": 0.0887,
2142
+ "step": 522
2143
+ },
2144
+ {
2145
+ "epoch": 18.0,
2146
+ "eval_accuracy": 0.6060606060606061,
2147
+ "eval_f1_macro": 0.5091139158366049,
2148
+ "eval_f1_micro": 0.6060606060606061,
2149
+ "eval_f1_weighted": 0.5799565723095135,
2150
+ "eval_loss": 1.6230822801589966,
2151
+ "eval_precision_macro": 0.5344263592737348,
2152
+ "eval_precision_micro": 0.6060606060606061,
2153
+ "eval_precision_weighted": 0.5916928649279117,
2154
+ "eval_recall_macro": 0.5189795918367347,
2155
+ "eval_recall_micro": 0.6060606060606061,
2156
+ "eval_recall_weighted": 0.6060606060606061,
2157
+ "eval_runtime": 2.3176,
2158
+ "eval_samples_per_second": 56.956,
2159
+ "eval_steps_per_second": 7.335,
2160
+ "step": 522
2161
+ },
2162
+ {
2163
+ "epoch": 18.06896551724138,
2164
+ "grad_norm": 0.7991401553153992,
2165
+ "learning_rate": 4.418901660280971e-05,
2166
+ "loss": 0.0268,
2167
+ "step": 524
2168
+ },
2169
+ {
2170
+ "epoch": 18.137931034482758,
2171
+ "grad_norm": 5.092419624328613,
2172
+ "learning_rate": 4.393358876117497e-05,
2173
+ "loss": 0.2074,
2174
+ "step": 526
2175
+ },
2176
+ {
2177
+ "epoch": 18.20689655172414,
2178
+ "grad_norm": 7.083487510681152,
2179
+ "learning_rate": 4.367816091954024e-05,
2180
+ "loss": 0.0535,
2181
+ "step": 528
2182
+ },
2183
+ {
2184
+ "epoch": 18.275862068965516,
2185
+ "grad_norm": 3.665398597717285,
2186
+ "learning_rate": 4.342273307790549e-05,
2187
+ "loss": 0.1522,
2188
+ "step": 530
2189
+ },
2190
+ {
2191
+ "epoch": 18.344827586206897,
2192
+ "grad_norm": 3.8143649101257324,
2193
+ "learning_rate": 4.3167305236270757e-05,
2194
+ "loss": 0.0704,
2195
+ "step": 532
2196
+ },
2197
+ {
2198
+ "epoch": 18.413793103448278,
2199
+ "grad_norm": 1.7281546592712402,
2200
+ "learning_rate": 4.291187739463602e-05,
2201
+ "loss": 0.0498,
2202
+ "step": 534
2203
+ },
2204
+ {
2205
+ "epoch": 18.482758620689655,
2206
+ "grad_norm": 5.076626777648926,
2207
+ "learning_rate": 4.2656449553001277e-05,
2208
+ "loss": 0.0954,
2209
+ "step": 536
2210
+ },
2211
+ {
2212
+ "epoch": 18.551724137931036,
2213
+ "grad_norm": 1.358458161354065,
2214
+ "learning_rate": 4.240102171136654e-05,
2215
+ "loss": 0.0325,
2216
+ "step": 538
2217
+ },
2218
+ {
2219
+ "epoch": 18.620689655172413,
2220
+ "grad_norm": 5.167296886444092,
2221
+ "learning_rate": 4.21455938697318e-05,
2222
+ "loss": 0.0966,
2223
+ "step": 540
2224
+ },
2225
+ {
2226
+ "epoch": 18.689655172413794,
2227
+ "grad_norm": 1.9453201293945312,
2228
+ "learning_rate": 4.189016602809707e-05,
2229
+ "loss": 0.0576,
2230
+ "step": 542
2231
+ },
2232
+ {
2233
+ "epoch": 18.75862068965517,
2234
+ "grad_norm": 0.7826907634735107,
2235
+ "learning_rate": 4.163473818646232e-05,
2236
+ "loss": 0.1441,
2237
+ "step": 544
2238
+ },
2239
+ {
2240
+ "epoch": 18.82758620689655,
2241
+ "grad_norm": 1.4397317171096802,
2242
+ "learning_rate": 4.1379310344827587e-05,
2243
+ "loss": 0.0744,
2244
+ "step": 546
2245
+ },
2246
+ {
2247
+ "epoch": 18.896551724137932,
2248
+ "grad_norm": 3.9290759563446045,
2249
+ "learning_rate": 4.112388250319285e-05,
2250
+ "loss": 0.1042,
2251
+ "step": 548
2252
+ },
2253
+ {
2254
+ "epoch": 18.96551724137931,
2255
+ "grad_norm": 0.7687857747077942,
2256
+ "learning_rate": 4.086845466155811e-05,
2257
+ "loss": 0.0254,
2258
+ "step": 550
2259
+ },
2260
+ {
2261
+ "epoch": 19.0,
2262
+ "eval_accuracy": 0.6136363636363636,
2263
+ "eval_f1_macro": 0.5625326265517395,
2264
+ "eval_f1_micro": 0.6136363636363636,
2265
+ "eval_f1_weighted": 0.6070491578999321,
2266
+ "eval_loss": 1.6095294952392578,
2267
+ "eval_precision_macro": 0.6642268445839873,
2268
+ "eval_precision_micro": 0.6136363636363636,
2269
+ "eval_precision_weighted": 0.6353459040959041,
2270
+ "eval_recall_macro": 0.5520332577475434,
2271
+ "eval_recall_micro": 0.6136363636363636,
2272
+ "eval_recall_weighted": 0.6136363636363636,
2273
+ "eval_runtime": 2.3103,
2274
+ "eval_samples_per_second": 57.134,
2275
+ "eval_steps_per_second": 7.358,
2276
+ "step": 551
2277
+ },
2278
+ {
2279
+ "epoch": 19.03448275862069,
2280
+ "grad_norm": 0.8335579037666321,
2281
+ "learning_rate": 4.061302681992337e-05,
2282
+ "loss": 0.0143,
2283
+ "step": 552
2284
+ },
2285
+ {
2286
+ "epoch": 19.103448275862068,
2287
+ "grad_norm": 2.744795083999634,
2288
+ "learning_rate": 4.035759897828863e-05,
2289
+ "loss": 0.0357,
2290
+ "step": 554
2291
+ },
2292
+ {
2293
+ "epoch": 19.17241379310345,
2294
+ "grad_norm": 11.362982749938965,
2295
+ "learning_rate": 4.0102171136653897e-05,
2296
+ "loss": 0.1115,
2297
+ "step": 556
2298
+ },
2299
+ {
2300
+ "epoch": 19.24137931034483,
2301
+ "grad_norm": 9.07187557220459,
2302
+ "learning_rate": 3.984674329501916e-05,
2303
+ "loss": 0.0925,
2304
+ "step": 558
2305
+ },
2306
+ {
2307
+ "epoch": 19.310344827586206,
2308
+ "grad_norm": 0.26310238242149353,
2309
+ "learning_rate": 3.959131545338442e-05,
2310
+ "loss": 0.0123,
2311
+ "step": 560
2312
+ },
2313
+ {
2314
+ "epoch": 19.379310344827587,
2315
+ "grad_norm": 1.043347954750061,
2316
+ "learning_rate": 3.933588761174969e-05,
2317
+ "loss": 0.0295,
2318
+ "step": 562
2319
+ },
2320
+ {
2321
+ "epoch": 19.448275862068964,
2322
+ "grad_norm": 0.23652300238609314,
2323
+ "learning_rate": 3.908045977011495e-05,
2324
+ "loss": 0.0058,
2325
+ "step": 564
2326
+ },
2327
+ {
2328
+ "epoch": 19.517241379310345,
2329
+ "grad_norm": 2.8097283840179443,
2330
+ "learning_rate": 3.8825031928480207e-05,
2331
+ "loss": 0.0406,
2332
+ "step": 566
2333
+ },
2334
+ {
2335
+ "epoch": 19.586206896551722,
2336
+ "grad_norm": 0.406757652759552,
2337
+ "learning_rate": 3.856960408684547e-05,
2338
+ "loss": 0.0079,
2339
+ "step": 568
2340
+ },
2341
+ {
2342
+ "epoch": 19.655172413793103,
2343
+ "grad_norm": 3.588495969772339,
2344
+ "learning_rate": 3.831417624521073e-05,
2345
+ "loss": 0.2604,
2346
+ "step": 570
2347
+ },
2348
+ {
2349
+ "epoch": 19.724137931034484,
2350
+ "grad_norm": 11.747899055480957,
2351
+ "learning_rate": 3.805874840357599e-05,
2352
+ "loss": 0.1278,
2353
+ "step": 572
2354
+ },
2355
+ {
2356
+ "epoch": 19.79310344827586,
2357
+ "grad_norm": 2.0980422496795654,
2358
+ "learning_rate": 3.780332056194125e-05,
2359
+ "loss": 0.1029,
2360
+ "step": 574
2361
+ },
2362
+ {
2363
+ "epoch": 19.862068965517242,
2364
+ "grad_norm": 0.777961015701294,
2365
+ "learning_rate": 3.7547892720306517e-05,
2366
+ "loss": 0.0893,
2367
+ "step": 576
2368
+ },
2369
+ {
2370
+ "epoch": 19.93103448275862,
2371
+ "grad_norm": 1.2306005954742432,
2372
+ "learning_rate": 3.729246487867178e-05,
2373
+ "loss": 0.0202,
2374
+ "step": 578
2375
+ },
2376
+ {
2377
+ "epoch": 20.0,
2378
+ "grad_norm": 4.3356451988220215,
2379
+ "learning_rate": 3.7037037037037037e-05,
2380
+ "loss": 0.0908,
2381
+ "step": 580
2382
+ },
2383
+ {
2384
+ "epoch": 20.0,
2385
+ "eval_accuracy": 0.6136363636363636,
2386
+ "eval_f1_macro": 0.5269679578540161,
2387
+ "eval_f1_micro": 0.6136363636363636,
2388
+ "eval_f1_weighted": 0.5961527319540719,
2389
+ "eval_loss": 1.6940934658050537,
2390
+ "eval_precision_macro": 0.5331414617128902,
2391
+ "eval_precision_micro": 0.6136363636363636,
2392
+ "eval_precision_weighted": 0.6004181004181004,
2393
+ "eval_recall_macro": 0.5381027966742253,
2394
+ "eval_recall_micro": 0.6136363636363636,
2395
+ "eval_recall_weighted": 0.6136363636363636,
2396
+ "eval_runtime": 2.3346,
2397
+ "eval_samples_per_second": 56.541,
2398
+ "eval_steps_per_second": 7.282,
2399
+ "step": 580
2400
+ },
2401
+ {
2402
+ "epoch": 20.06896551724138,
2403
+ "grad_norm": 0.9854629635810852,
2404
+ "learning_rate": 3.67816091954023e-05,
2405
+ "loss": 0.0315,
2406
+ "step": 582
2407
+ },
2408
+ {
2409
+ "epoch": 20.137931034482758,
2410
+ "grad_norm": 8.160626411437988,
2411
+ "learning_rate": 3.652618135376756e-05,
2412
+ "loss": 0.195,
2413
+ "step": 584
2414
+ },
2415
+ {
2416
+ "epoch": 20.20689655172414,
2417
+ "grad_norm": 9.696558952331543,
2418
+ "learning_rate": 3.627075351213283e-05,
2419
+ "loss": 0.1459,
2420
+ "step": 586
2421
+ },
2422
+ {
2423
+ "epoch": 20.275862068965516,
2424
+ "grad_norm": 2.334758758544922,
2425
+ "learning_rate": 3.601532567049808e-05,
2426
+ "loss": 0.0256,
2427
+ "step": 588
2428
+ },
2429
+ {
2430
+ "epoch": 20.344827586206897,
2431
+ "grad_norm": 0.862045407295227,
2432
+ "learning_rate": 3.5759897828863347e-05,
2433
+ "loss": 0.0133,
2434
+ "step": 590
2435
+ },
2436
+ {
2437
+ "epoch": 20.413793103448278,
2438
+ "grad_norm": 0.4637574553489685,
2439
+ "learning_rate": 3.550446998722861e-05,
2440
+ "loss": 0.025,
2441
+ "step": 592
2442
+ },
2443
+ {
2444
+ "epoch": 20.482758620689655,
2445
+ "grad_norm": 2.358105182647705,
2446
+ "learning_rate": 3.5249042145593867e-05,
2447
+ "loss": 0.0418,
2448
+ "step": 594
2449
+ },
2450
+ {
2451
+ "epoch": 20.551724137931036,
2452
+ "grad_norm": 3.2894065380096436,
2453
+ "learning_rate": 3.499361430395913e-05,
2454
+ "loss": 0.0155,
2455
+ "step": 596
2456
+ },
2457
+ {
2458
+ "epoch": 20.620689655172413,
2459
+ "grad_norm": 1.3686822652816772,
2460
+ "learning_rate": 3.473818646232439e-05,
2461
+ "loss": 0.0186,
2462
+ "step": 598
2463
+ },
2464
+ {
2465
+ "epoch": 20.689655172413794,
2466
+ "grad_norm": 0.2436424344778061,
2467
+ "learning_rate": 3.4482758620689657e-05,
2468
+ "loss": 0.1607,
2469
+ "step": 600
2470
+ },
2471
+ {
2472
+ "epoch": 20.75862068965517,
2473
+ "grad_norm": 0.6559809446334839,
2474
+ "learning_rate": 3.422733077905492e-05,
2475
+ "loss": 0.0645,
2476
+ "step": 602
2477
+ },
2478
+ {
2479
+ "epoch": 20.82758620689655,
2480
+ "grad_norm": 0.6616806387901306,
2481
+ "learning_rate": 3.397190293742018e-05,
2482
+ "loss": 0.1066,
2483
+ "step": 604
2484
+ },
2485
+ {
2486
+ "epoch": 20.896551724137932,
2487
+ "grad_norm": 5.0346150398254395,
2488
+ "learning_rate": 3.371647509578545e-05,
2489
+ "loss": 0.0505,
2490
+ "step": 606
2491
+ },
2492
+ {
2493
+ "epoch": 20.96551724137931,
2494
+ "grad_norm": 6.462579727172852,
2495
+ "learning_rate": 3.34610472541507e-05,
2496
+ "loss": 0.0913,
2497
+ "step": 608
2498
+ },
2499
+ {
2500
+ "epoch": 21.0,
2501
+ "eval_accuracy": 0.6136363636363636,
2502
+ "eval_f1_macro": 0.5536764705882352,
2503
+ "eval_f1_micro": 0.6136363636363636,
2504
+ "eval_f1_weighted": 0.6018196672608437,
2505
+ "eval_loss": 1.6917121410369873,
2506
+ "eval_precision_macro": 0.5908806106174527,
2507
+ "eval_precision_micro": 0.6136363636363636,
2508
+ "eval_precision_weighted": 0.6169424508240299,
2509
+ "eval_recall_macro": 0.5578609221466364,
2510
+ "eval_recall_micro": 0.6136363636363636,
2511
+ "eval_recall_weighted": 0.6136363636363636,
2512
+ "eval_runtime": 2.3118,
2513
+ "eval_samples_per_second": 57.098,
2514
+ "eval_steps_per_second": 7.354,
2515
+ "step": 609
2516
+ },
2517
+ {
2518
+ "epoch": 21.03448275862069,
2519
+ "grad_norm": 3.8986473083496094,
2520
+ "learning_rate": 3.3205619412515967e-05,
2521
+ "loss": 0.0349,
2522
+ "step": 610
2523
+ },
2524
+ {
2525
+ "epoch": 21.103448275862068,
2526
+ "grad_norm": 0.6565538048744202,
2527
+ "learning_rate": 3.295019157088123e-05,
2528
+ "loss": 0.0116,
2529
+ "step": 612
2530
+ },
2531
+ {
2532
+ "epoch": 21.17241379310345,
2533
+ "grad_norm": 0.6683332324028015,
2534
+ "learning_rate": 3.269476372924649e-05,
2535
+ "loss": 0.0099,
2536
+ "step": 614
2537
+ },
2538
+ {
2539
+ "epoch": 21.24137931034483,
2540
+ "grad_norm": 10.452178001403809,
2541
+ "learning_rate": 3.243933588761175e-05,
2542
+ "loss": 0.1153,
2543
+ "step": 616
2544
+ },
2545
+ {
2546
+ "epoch": 21.310344827586206,
2547
+ "grad_norm": 2.8734970092773438,
2548
+ "learning_rate": 3.218390804597701e-05,
2549
+ "loss": 0.0294,
2550
+ "step": 618
2551
+ },
2552
+ {
2553
+ "epoch": 21.379310344827587,
2554
+ "grad_norm": 4.400616645812988,
2555
+ "learning_rate": 3.192848020434228e-05,
2556
+ "loss": 0.0362,
2557
+ "step": 620
2558
+ },
2559
+ {
2560
+ "epoch": 21.448275862068964,
2561
+ "grad_norm": 11.646851539611816,
2562
+ "learning_rate": 3.167305236270754e-05,
2563
+ "loss": 0.229,
2564
+ "step": 622
2565
+ },
2566
+ {
2567
+ "epoch": 21.517241379310345,
2568
+ "grad_norm": 3.486697196960449,
2569
+ "learning_rate": 3.1417624521072797e-05,
2570
+ "loss": 0.0364,
2571
+ "step": 624
2572
+ },
2573
+ {
2574
+ "epoch": 21.586206896551722,
2575
+ "grad_norm": 1.5919147729873657,
2576
+ "learning_rate": 3.116219667943806e-05,
2577
+ "loss": 0.0673,
2578
+ "step": 626
2579
+ },
2580
+ {
2581
+ "epoch": 21.655172413793103,
2582
+ "grad_norm": 0.1539590209722519,
2583
+ "learning_rate": 3.090676883780332e-05,
2584
+ "loss": 0.0153,
2585
+ "step": 628
2586
+ },
2587
+ {
2588
+ "epoch": 21.724137931034484,
2589
+ "grad_norm": 1.7349178791046143,
2590
+ "learning_rate": 3.065134099616858e-05,
2591
+ "loss": 0.0414,
2592
+ "step": 630
2593
+ },
2594
+ {
2595
+ "epoch": 21.79310344827586,
2596
+ "grad_norm": 7.606224060058594,
2597
+ "learning_rate": 3.0395913154533843e-05,
2598
+ "loss": 0.0653,
2599
+ "step": 632
2600
+ },
2601
+ {
2602
+ "epoch": 21.862068965517242,
2603
+ "grad_norm": 1.45542311668396,
2604
+ "learning_rate": 3.0140485312899107e-05,
2605
+ "loss": 0.0252,
2606
+ "step": 634
2607
+ },
2608
+ {
2609
+ "epoch": 21.93103448275862,
2610
+ "grad_norm": 0.78499835729599,
2611
+ "learning_rate": 2.988505747126437e-05,
2612
+ "loss": 0.013,
2613
+ "step": 636
2614
+ },
2615
+ {
2616
+ "epoch": 22.0,
2617
+ "grad_norm": 1.3190522193908691,
2618
+ "learning_rate": 2.962962962962963e-05,
2619
+ "loss": 0.015,
2620
+ "step": 638
2621
+ },
2622
+ {
2623
+ "epoch": 22.0,
2624
+ "eval_accuracy": 0.5681818181818182,
2625
+ "eval_f1_macro": 0.4866218709706104,
2626
+ "eval_f1_micro": 0.5681818181818182,
2627
+ "eval_f1_weighted": 0.5512056253477822,
2628
+ "eval_loss": 1.8274449110031128,
2629
+ "eval_precision_macro": 0.48550040705937547,
2630
+ "eval_precision_micro": 0.5681818181818182,
2631
+ "eval_precision_weighted": 0.5476516834529005,
2632
+ "eval_recall_macro": 0.5002721088435373,
2633
+ "eval_recall_micro": 0.5681818181818182,
2634
+ "eval_recall_weighted": 0.5681818181818182,
2635
+ "eval_runtime": 2.3183,
2636
+ "eval_samples_per_second": 56.939,
2637
+ "eval_steps_per_second": 7.333,
2638
+ "step": 638
2639
+ },
2640
+ {
2641
+ "epoch": 22.06896551724138,
2642
+ "grad_norm": 0.5085828900337219,
2643
+ "learning_rate": 2.9374201787994893e-05,
2644
+ "loss": 0.0224,
2645
+ "step": 640
2646
+ },
2647
+ {
2648
+ "epoch": 22.137931034482758,
2649
+ "grad_norm": 9.176717758178711,
2650
+ "learning_rate": 2.9118773946360157e-05,
2651
+ "loss": 0.1208,
2652
+ "step": 642
2653
+ },
2654
+ {
2655
+ "epoch": 22.20689655172414,
2656
+ "grad_norm": 0.0806804820895195,
2657
+ "learning_rate": 2.8863346104725413e-05,
2658
+ "loss": 0.0058,
2659
+ "step": 644
2660
+ },
2661
+ {
2662
+ "epoch": 22.275862068965516,
2663
+ "grad_norm": 0.9548521041870117,
2664
+ "learning_rate": 2.8607918263090677e-05,
2665
+ "loss": 0.0117,
2666
+ "step": 646
2667
+ },
2668
+ {
2669
+ "epoch": 22.344827586206897,
2670
+ "grad_norm": 1.6547935009002686,
2671
+ "learning_rate": 2.835249042145594e-05,
2672
+ "loss": 0.0424,
2673
+ "step": 648
2674
+ },
2675
+ {
2676
+ "epoch": 22.413793103448278,
2677
+ "grad_norm": 6.715394973754883,
2678
+ "learning_rate": 2.8097062579821203e-05,
2679
+ "loss": 0.0423,
2680
+ "step": 650
2681
+ },
2682
+ {
2683
+ "epoch": 22.482758620689655,
2684
+ "grad_norm": 10.177534103393555,
2685
+ "learning_rate": 2.7841634738186463e-05,
2686
+ "loss": 0.2377,
2687
+ "step": 652
2688
+ },
2689
+ {
2690
+ "epoch": 22.551724137931036,
2691
+ "grad_norm": 0.11357463151216507,
2692
+ "learning_rate": 2.7586206896551727e-05,
2693
+ "loss": 0.0051,
2694
+ "step": 654
2695
+ },
2696
+ {
2697
+ "epoch": 22.620689655172413,
2698
+ "grad_norm": 7.2798027992248535,
2699
+ "learning_rate": 2.733077905491699e-05,
2700
+ "loss": 0.0687,
2701
+ "step": 656
2702
+ },
2703
+ {
2704
+ "epoch": 22.689655172413794,
2705
+ "grad_norm": 2.2690324783325195,
2706
+ "learning_rate": 2.7075351213282253e-05,
2707
+ "loss": 0.0163,
2708
+ "step": 658
2709
+ },
2710
+ {
2711
+ "epoch": 22.75862068965517,
2712
+ "grad_norm": 0.6616243720054626,
2713
+ "learning_rate": 2.681992337164751e-05,
2714
+ "loss": 0.0126,
2715
+ "step": 660
2716
+ },
2717
+ {
2718
+ "epoch": 22.82758620689655,
2719
+ "grad_norm": 0.5030643939971924,
2720
+ "learning_rate": 2.6564495530012773e-05,
2721
+ "loss": 0.0317,
2722
+ "step": 662
2723
+ },
2724
+ {
2725
+ "epoch": 22.896551724137932,
2726
+ "grad_norm": 0.4334893524646759,
2727
+ "learning_rate": 2.6309067688378037e-05,
2728
+ "loss": 0.0096,
2729
+ "step": 664
2730
+ },
2731
+ {
2732
+ "epoch": 22.96551724137931,
2733
+ "grad_norm": 1.307210087776184,
2734
+ "learning_rate": 2.6053639846743293e-05,
2735
+ "loss": 0.0156,
2736
+ "step": 666
2737
+ },
2738
+ {
2739
+ "epoch": 23.0,
2740
+ "eval_accuracy": 0.6439393939393939,
2741
+ "eval_f1_macro": 0.5772056256881202,
2742
+ "eval_f1_micro": 0.6439393939393939,
2743
+ "eval_f1_weighted": 0.6233499854025143,
2744
+ "eval_loss": 1.732154369354248,
2745
+ "eval_precision_macro": 0.6869692704668073,
2746
+ "eval_precision_micro": 0.6439393939393939,
2747
+ "eval_precision_weighted": 0.6597670050256258,
2748
+ "eval_recall_macro": 0.5802267573696145,
2749
+ "eval_recall_micro": 0.6439393939393939,
2750
+ "eval_recall_weighted": 0.6439393939393939,
2751
+ "eval_runtime": 2.3163,
2752
+ "eval_samples_per_second": 56.988,
2753
+ "eval_steps_per_second": 7.339,
2754
+ "step": 667
2755
+ },
2756
+ {
2757
+ "epoch": 23.03448275862069,
2758
+ "grad_norm": 9.869407653808594,
2759
+ "learning_rate": 2.5798212005108557e-05,
2760
+ "loss": 0.0452,
2761
+ "step": 668
2762
+ },
2763
+ {
2764
+ "epoch": 23.103448275862068,
2765
+ "grad_norm": 0.35701480507850647,
2766
+ "learning_rate": 2.554278416347382e-05,
2767
+ "loss": 0.0106,
2768
+ "step": 670
2769
+ },
2770
+ {
2771
+ "epoch": 23.17241379310345,
2772
+ "grad_norm": 0.22175803780555725,
2773
+ "learning_rate": 2.5287356321839083e-05,
2774
+ "loss": 0.0674,
2775
+ "step": 672
2776
+ },
2777
+ {
2778
+ "epoch": 23.24137931034483,
2779
+ "grad_norm": 0.5231541395187378,
2780
+ "learning_rate": 2.5031928480204343e-05,
2781
+ "loss": 0.022,
2782
+ "step": 674
2783
+ },
2784
+ {
2785
+ "epoch": 23.310344827586206,
2786
+ "grad_norm": 5.801222324371338,
2787
+ "learning_rate": 2.4776500638569607e-05,
2788
+ "loss": 0.0374,
2789
+ "step": 676
2790
+ },
2791
+ {
2792
+ "epoch": 23.379310344827587,
2793
+ "grad_norm": 0.288379967212677,
2794
+ "learning_rate": 2.4521072796934867e-05,
2795
+ "loss": 0.0079,
2796
+ "step": 678
2797
+ },
2798
+ {
2799
+ "epoch": 23.448275862068964,
2800
+ "grad_norm": 0.34467244148254395,
2801
+ "learning_rate": 2.426564495530013e-05,
2802
+ "loss": 0.0058,
2803
+ "step": 680
2804
+ },
2805
+ {
2806
+ "epoch": 23.517241379310345,
2807
+ "grad_norm": 2.5069077014923096,
2808
+ "learning_rate": 2.401021711366539e-05,
2809
+ "loss": 0.0169,
2810
+ "step": 682
2811
+ },
2812
+ {
2813
+ "epoch": 23.586206896551722,
2814
+ "grad_norm": 0.22579370439052582,
2815
+ "learning_rate": 2.3754789272030653e-05,
2816
+ "loss": 0.0077,
2817
+ "step": 684
2818
+ },
2819
+ {
2820
+ "epoch": 23.655172413793103,
2821
+ "grad_norm": 0.15394940972328186,
2822
+ "learning_rate": 2.3499361430395913e-05,
2823
+ "loss": 0.0648,
2824
+ "step": 686
2825
+ },
2826
+ {
2827
+ "epoch": 23.724137931034484,
2828
+ "grad_norm": 0.045006781816482544,
2829
+ "learning_rate": 2.3243933588761177e-05,
2830
+ "loss": 0.087,
2831
+ "step": 688
2832
+ },
2833
+ {
2834
+ "epoch": 23.79310344827586,
2835
+ "grad_norm": 0.6705069541931152,
2836
+ "learning_rate": 2.2988505747126437e-05,
2837
+ "loss": 0.0168,
2838
+ "step": 690
2839
+ },
2840
+ {
2841
+ "epoch": 23.862068965517242,
2842
+ "grad_norm": 0.20562146604061127,
2843
+ "learning_rate": 2.27330779054917e-05,
2844
+ "loss": 0.0059,
2845
+ "step": 692
2846
+ },
2847
+ {
2848
+ "epoch": 23.93103448275862,
2849
+ "grad_norm": 0.12316538393497467,
2850
+ "learning_rate": 2.247765006385696e-05,
2851
+ "loss": 0.005,
2852
+ "step": 694
2853
+ },
2854
+ {
2855
+ "epoch": 24.0,
2856
+ "grad_norm": 3.606569528579712,
2857
+ "learning_rate": 2.2222222222222223e-05,
2858
+ "loss": 0.0275,
2859
+ "step": 696
2860
+ },
2861
+ {
2862
+ "epoch": 24.0,
2863
+ "eval_accuracy": 0.6212121212121212,
2864
+ "eval_f1_macro": 0.5293264604717091,
2865
+ "eval_f1_micro": 0.6212121212121212,
2866
+ "eval_f1_weighted": 0.6006327806228502,
2867
+ "eval_loss": 1.6261619329452515,
2868
+ "eval_precision_macro": 0.527442388438629,
2869
+ "eval_precision_micro": 0.6212121212121212,
2870
+ "eval_precision_weighted": 0.591250595497007,
2871
+ "eval_recall_macro": 0.5421541950113379,
2872
+ "eval_recall_micro": 0.6212121212121212,
2873
+ "eval_recall_weighted": 0.6212121212121212,
2874
+ "eval_runtime": 2.315,
2875
+ "eval_samples_per_second": 57.021,
2876
+ "eval_steps_per_second": 7.344,
2877
+ "step": 696
2878
+ },
2879
+ {
2880
+ "epoch": 24.06896551724138,
2881
+ "grad_norm": 0.13560178875923157,
2882
+ "learning_rate": 2.1966794380587487e-05,
2883
+ "loss": 0.0063,
2884
+ "step": 698
2885
+ },
2886
+ {
2887
+ "epoch": 24.137931034482758,
2888
+ "grad_norm": 0.858462929725647,
2889
+ "learning_rate": 2.1711366538952747e-05,
2890
+ "loss": 0.0073,
2891
+ "step": 700
2892
+ },
2893
+ {
2894
+ "epoch": 24.20689655172414,
2895
+ "grad_norm": 2.4385788440704346,
2896
+ "learning_rate": 2.145593869731801e-05,
2897
+ "loss": 0.0149,
2898
+ "step": 702
2899
+ },
2900
+ {
2901
+ "epoch": 24.275862068965516,
2902
+ "grad_norm": 0.1377100646495819,
2903
+ "learning_rate": 2.120051085568327e-05,
2904
+ "loss": 0.0034,
2905
+ "step": 704
2906
+ },
2907
+ {
2908
+ "epoch": 24.344827586206897,
2909
+ "grad_norm": 1.9415969848632812,
2910
+ "learning_rate": 2.0945083014048533e-05,
2911
+ "loss": 0.0675,
2912
+ "step": 706
2913
+ },
2914
+ {
2915
+ "epoch": 24.413793103448278,
2916
+ "grad_norm": 0.028621500357985497,
2917
+ "learning_rate": 2.0689655172413793e-05,
2918
+ "loss": 0.0062,
2919
+ "step": 708
2920
+ },
2921
+ {
2922
+ "epoch": 24.482758620689655,
2923
+ "grad_norm": 0.3451801538467407,
2924
+ "learning_rate": 2.0434227330779057e-05,
2925
+ "loss": 0.004,
2926
+ "step": 710
2927
+ },
2928
+ {
2929
+ "epoch": 24.551724137931036,
2930
+ "grad_norm": 0.7758638262748718,
2931
+ "learning_rate": 2.0178799489144317e-05,
2932
+ "loss": 0.0182,
2933
+ "step": 712
2934
+ },
2935
+ {
2936
+ "epoch": 24.620689655172413,
2937
+ "grad_norm": 9.42198371887207,
2938
+ "learning_rate": 1.992337164750958e-05,
2939
+ "loss": 0.0647,
2940
+ "step": 714
2941
+ },
2942
+ {
2943
+ "epoch": 24.689655172413794,
2944
+ "grad_norm": 0.6298714280128479,
2945
+ "learning_rate": 1.9667943805874843e-05,
2946
+ "loss": 0.0108,
2947
+ "step": 716
2948
+ },
2949
+ {
2950
+ "epoch": 24.75862068965517,
2951
+ "grad_norm": 0.5104489326477051,
2952
+ "learning_rate": 1.9412515964240103e-05,
2953
+ "loss": 0.009,
2954
+ "step": 718
2955
+ },
2956
+ {
2957
+ "epoch": 24.82758620689655,
2958
+ "grad_norm": 0.20583294332027435,
2959
+ "learning_rate": 1.9157088122605367e-05,
2960
+ "loss": 0.0044,
2961
+ "step": 720
2962
+ },
2963
+ {
2964
+ "epoch": 24.896551724137932,
2965
+ "grad_norm": 0.09636816382408142,
2966
+ "learning_rate": 1.8901660280970627e-05,
2967
+ "loss": 0.0073,
2968
+ "step": 722
2969
+ },
2970
+ {
2971
+ "epoch": 24.96551724137931,
2972
+ "grad_norm": 0.13066060841083527,
2973
+ "learning_rate": 1.864623243933589e-05,
2974
+ "loss": 0.0034,
2975
+ "step": 724
2976
+ },
2977
+ {
2978
+ "epoch": 25.0,
2979
+ "eval_accuracy": 0.6590909090909091,
2980
+ "eval_f1_macro": 0.5680281748326861,
2981
+ "eval_f1_micro": 0.6590909090909091,
2982
+ "eval_f1_weighted": 0.6409447423921109,
2983
+ "eval_loss": 1.7278190851211548,
2984
+ "eval_precision_macro": 0.5673925245094548,
2985
+ "eval_precision_micro": 0.6590909090909091,
2986
+ "eval_precision_weighted": 0.6333160386699408,
2987
+ "eval_recall_macro": 0.5785563114134543,
2988
+ "eval_recall_micro": 0.6590909090909091,
2989
+ "eval_recall_weighted": 0.6590909090909091,
2990
+ "eval_runtime": 2.3069,
2991
+ "eval_samples_per_second": 57.219,
2992
+ "eval_steps_per_second": 7.369,
2993
+ "step": 725
2994
+ },
2995
+ {
2996
+ "epoch": 25.03448275862069,
2997
+ "grad_norm": 0.1809925138950348,
2998
+ "learning_rate": 1.839080459770115e-05,
2999
+ "loss": 0.0291,
3000
+ "step": 726
3001
+ },
3002
+ {
3003
+ "epoch": 25.103448275862068,
3004
+ "grad_norm": 0.24622710049152374,
3005
+ "learning_rate": 1.8135376756066413e-05,
3006
+ "loss": 0.0196,
3007
+ "step": 728
3008
+ },
3009
+ {
3010
+ "epoch": 25.17241379310345,
3011
+ "grad_norm": 0.8039155006408691,
3012
+ "learning_rate": 1.7879948914431673e-05,
3013
+ "loss": 0.0187,
3014
+ "step": 730
3015
+ },
3016
+ {
3017
+ "epoch": 25.24137931034483,
3018
+ "grad_norm": 0.09927386790513992,
3019
+ "learning_rate": 1.7624521072796933e-05,
3020
+ "loss": 0.0444,
3021
+ "step": 732
3022
+ },
3023
+ {
3024
+ "epoch": 25.310344827586206,
3025
+ "grad_norm": 0.25122836232185364,
3026
+ "learning_rate": 1.7369093231162197e-05,
3027
+ "loss": 0.0032,
3028
+ "step": 734
3029
+ },
3030
+ {
3031
+ "epoch": 25.379310344827587,
3032
+ "grad_norm": 0.5785457491874695,
3033
+ "learning_rate": 1.711366538952746e-05,
3034
+ "loss": 0.0054,
3035
+ "step": 736
3036
+ },
3037
+ {
3038
+ "epoch": 25.448275862068964,
3039
+ "grad_norm": 0.3383479714393616,
3040
+ "learning_rate": 1.6858237547892723e-05,
3041
+ "loss": 0.0079,
3042
+ "step": 738
3043
+ },
3044
+ {
3045
+ "epoch": 25.517241379310345,
3046
+ "grad_norm": 0.07435264438390732,
3047
+ "learning_rate": 1.6602809706257983e-05,
3048
+ "loss": 0.0021,
3049
+ "step": 740
3050
+ },
3051
+ {
3052
+ "epoch": 25.586206896551722,
3053
+ "grad_norm": 0.10871023684740067,
3054
+ "learning_rate": 1.6347381864623247e-05,
3055
+ "loss": 0.0027,
3056
+ "step": 742
3057
+ },
3058
+ {
3059
+ "epoch": 25.655172413793103,
3060
+ "grad_norm": 0.22888857126235962,
3061
+ "learning_rate": 1.6091954022988507e-05,
3062
+ "loss": 0.0031,
3063
+ "step": 744
3064
+ },
3065
+ {
3066
+ "epoch": 25.724137931034484,
3067
+ "grad_norm": 4.243800640106201,
3068
+ "learning_rate": 1.583652618135377e-05,
3069
+ "loss": 0.0211,
3070
+ "step": 746
3071
+ },
3072
+ {
3073
+ "epoch": 25.79310344827586,
3074
+ "grad_norm": 0.25736576318740845,
3075
+ "learning_rate": 1.558109833971903e-05,
3076
+ "loss": 0.0033,
3077
+ "step": 748
3078
+ },
3079
+ {
3080
+ "epoch": 25.862068965517242,
3081
+ "grad_norm": 0.03959902003407478,
3082
+ "learning_rate": 1.532567049808429e-05,
3083
+ "loss": 0.0133,
3084
+ "step": 750
3085
+ },
3086
+ {
3087
+ "epoch": 25.93103448275862,
3088
+ "grad_norm": 0.07808686792850494,
3089
+ "learning_rate": 1.5070242656449553e-05,
3090
+ "loss": 0.0022,
3091
+ "step": 752
3092
+ },
3093
+ {
3094
+ "epoch": 26.0,
3095
+ "grad_norm": 0.05853148549795151,
3096
+ "learning_rate": 1.4814814814814815e-05,
3097
+ "loss": 0.0021,
3098
+ "step": 754
3099
+ },
3100
+ {
3101
+ "epoch": 26.0,
3102
+ "eval_accuracy": 0.6439393939393939,
3103
+ "eval_f1_macro": 0.554181839979619,
3104
+ "eval_f1_micro": 0.6439393939393939,
3105
+ "eval_f1_weighted": 0.6249546588712281,
3106
+ "eval_loss": 1.7111490964889526,
3107
+ "eval_precision_macro": 0.5506334900131893,
3108
+ "eval_precision_micro": 0.6439393939393939,
3109
+ "eval_precision_weighted": 0.6148272110443164,
3110
+ "eval_recall_macro": 0.5656991685563114,
3111
+ "eval_recall_micro": 0.6439393939393939,
3112
+ "eval_recall_weighted": 0.6439393939393939,
3113
+ "eval_runtime": 2.3159,
3114
+ "eval_samples_per_second": 56.997,
3115
+ "eval_steps_per_second": 7.341,
3116
+ "step": 754
3117
+ },
3118
+ {
3119
+ "epoch": 26.06896551724138,
3120
+ "grad_norm": 1.2636756896972656,
3121
+ "learning_rate": 1.4559386973180078e-05,
3122
+ "loss": 0.008,
3123
+ "step": 756
3124
+ },
3125
+ {
3126
+ "epoch": 26.137931034482758,
3127
+ "grad_norm": 0.132855623960495,
3128
+ "learning_rate": 1.4303959131545338e-05,
3129
+ "loss": 0.0042,
3130
+ "step": 758
3131
+ },
3132
+ {
3133
+ "epoch": 26.20689655172414,
3134
+ "grad_norm": 0.33450737595558167,
3135
+ "learning_rate": 1.4048531289910602e-05,
3136
+ "loss": 0.0072,
3137
+ "step": 760
3138
+ },
3139
+ {
3140
+ "epoch": 26.275862068965516,
3141
+ "grad_norm": 0.05951528623700142,
3142
+ "learning_rate": 1.3793103448275863e-05,
3143
+ "loss": 0.0014,
3144
+ "step": 762
3145
+ },
3146
+ {
3147
+ "epoch": 26.344827586206897,
3148
+ "grad_norm": 0.046173300594091415,
3149
+ "learning_rate": 1.3537675606641127e-05,
3150
+ "loss": 0.0046,
3151
+ "step": 764
3152
+ },
3153
+ {
3154
+ "epoch": 26.413793103448278,
3155
+ "grad_norm": 0.030656151473522186,
3156
+ "learning_rate": 1.3282247765006387e-05,
3157
+ "loss": 0.0019,
3158
+ "step": 766
3159
+ },
3160
+ {
3161
+ "epoch": 26.482758620689655,
3162
+ "grad_norm": 8.779583930969238,
3163
+ "learning_rate": 1.3026819923371647e-05,
3164
+ "loss": 0.0493,
3165
+ "step": 768
3166
+ },
3167
+ {
3168
+ "epoch": 26.551724137931036,
3169
+ "grad_norm": 0.07112403959035873,
3170
+ "learning_rate": 1.277139208173691e-05,
3171
+ "loss": 0.0019,
3172
+ "step": 770
3173
+ },
3174
+ {
3175
+ "epoch": 26.620689655172413,
3176
+ "grad_norm": 0.10120349377393723,
3177
+ "learning_rate": 1.2515964240102172e-05,
3178
+ "loss": 0.0039,
3179
+ "step": 772
3180
+ },
3181
+ {
3182
+ "epoch": 26.689655172413794,
3183
+ "grad_norm": 0.1142292320728302,
3184
+ "learning_rate": 1.2260536398467433e-05,
3185
+ "loss": 0.0036,
3186
+ "step": 774
3187
+ },
3188
+ {
3189
+ "epoch": 26.75862068965517,
3190
+ "grad_norm": 0.6233051419258118,
3191
+ "learning_rate": 1.2005108556832695e-05,
3192
+ "loss": 0.0043,
3193
+ "step": 776
3194
+ },
3195
+ {
3196
+ "epoch": 26.82758620689655,
3197
+ "grad_norm": 0.03758774697780609,
3198
+ "learning_rate": 1.1749680715197957e-05,
3199
+ "loss": 0.0106,
3200
+ "step": 778
3201
+ },
3202
+ {
3203
+ "epoch": 26.896551724137932,
3204
+ "grad_norm": 1.8201748132705688,
3205
+ "learning_rate": 1.1494252873563218e-05,
3206
+ "loss": 0.0569,
3207
+ "step": 780
3208
+ },
3209
+ {
3210
+ "epoch": 26.96551724137931,
3211
+ "grad_norm": 0.15079987049102783,
3212
+ "learning_rate": 1.123882503192848e-05,
3213
+ "loss": 0.0021,
3214
+ "step": 782
3215
+ },
3216
+ {
3217
+ "epoch": 27.0,
3218
+ "eval_accuracy": 0.6439393939393939,
3219
+ "eval_f1_macro": 0.555558065475334,
3220
+ "eval_f1_micro": 0.6439393939393939,
3221
+ "eval_f1_weighted": 0.6256767300352377,
3222
+ "eval_loss": 1.7411731481552124,
3223
+ "eval_precision_macro": 0.5507048374905518,
3224
+ "eval_precision_micro": 0.6439393939393939,
3225
+ "eval_precision_weighted": 0.616289381914382,
3226
+ "eval_recall_macro": 0.5684202569916855,
3227
+ "eval_recall_micro": 0.6439393939393939,
3228
+ "eval_recall_weighted": 0.6439393939393939,
3229
+ "eval_runtime": 2.4493,
3230
+ "eval_samples_per_second": 53.894,
3231
+ "eval_steps_per_second": 6.941,
3232
+ "step": 783
3233
+ },
3234
+ {
3235
+ "epoch": 27.03448275862069,
3236
+ "grad_norm": 0.30042076110839844,
3237
+ "learning_rate": 1.0983397190293743e-05,
3238
+ "loss": 0.023,
3239
+ "step": 784
3240
+ },
3241
+ {
3242
+ "epoch": 27.103448275862068,
3243
+ "grad_norm": 0.06235335394740105,
3244
+ "learning_rate": 1.0727969348659005e-05,
3245
+ "loss": 0.0051,
3246
+ "step": 786
3247
+ },
3248
+ {
3249
+ "epoch": 27.17241379310345,
3250
+ "grad_norm": 1.5789542198181152,
3251
+ "learning_rate": 1.0472541507024267e-05,
3252
+ "loss": 0.0104,
3253
+ "step": 788
3254
+ },
3255
+ {
3256
+ "epoch": 27.24137931034483,
3257
+ "grad_norm": 0.17915375530719757,
3258
+ "learning_rate": 1.0217113665389528e-05,
3259
+ "loss": 0.002,
3260
+ "step": 790
3261
+ },
3262
+ {
3263
+ "epoch": 27.310344827586206,
3264
+ "grad_norm": 0.71551513671875,
3265
+ "learning_rate": 9.96168582375479e-06,
3266
+ "loss": 0.0114,
3267
+ "step": 792
3268
+ },
3269
+ {
3270
+ "epoch": 27.379310344827587,
3271
+ "grad_norm": 0.043835002928972244,
3272
+ "learning_rate": 9.706257982120052e-06,
3273
+ "loss": 0.0029,
3274
+ "step": 794
3275
+ },
3276
+ {
3277
+ "epoch": 27.448275862068964,
3278
+ "grad_norm": 1.4578912258148193,
3279
+ "learning_rate": 9.450830140485313e-06,
3280
+ "loss": 0.0388,
3281
+ "step": 796
3282
+ },
3283
+ {
3284
+ "epoch": 27.517241379310345,
3285
+ "grad_norm": 0.7825492024421692,
3286
+ "learning_rate": 9.195402298850575e-06,
3287
+ "loss": 0.0168,
3288
+ "step": 798
3289
+ },
3290
+ {
3291
+ "epoch": 27.586206896551722,
3292
+ "grad_norm": 0.5712390542030334,
3293
+ "learning_rate": 8.939974457215837e-06,
3294
+ "loss": 0.0036,
3295
+ "step": 800
3296
+ },
3297
+ {
3298
+ "epoch": 27.655172413793103,
3299
+ "grad_norm": 0.05121476203203201,
3300
+ "learning_rate": 8.684546615581098e-06,
3301
+ "loss": 0.0019,
3302
+ "step": 802
3303
+ },
3304
+ {
3305
+ "epoch": 27.724137931034484,
3306
+ "grad_norm": 0.02635987475514412,
3307
+ "learning_rate": 8.429118773946362e-06,
3308
+ "loss": 0.0015,
3309
+ "step": 804
3310
+ },
3311
+ {
3312
+ "epoch": 27.79310344827586,
3313
+ "grad_norm": 0.09528487920761108,
3314
+ "learning_rate": 8.173690932311623e-06,
3315
+ "loss": 0.0021,
3316
+ "step": 806
3317
+ },
3318
+ {
3319
+ "epoch": 27.862068965517242,
3320
+ "grad_norm": 12.712857246398926,
3321
+ "learning_rate": 7.918263090676885e-06,
3322
+ "loss": 0.0664,
3323
+ "step": 808
3324
+ },
3325
+ {
3326
+ "epoch": 27.93103448275862,
3327
+ "grad_norm": 0.25220927596092224,
3328
+ "learning_rate": 7.662835249042145e-06,
3329
+ "loss": 0.0093,
3330
+ "step": 810
3331
+ },
3332
+ {
3333
+ "epoch": 28.0,
3334
+ "grad_norm": 0.45354342460632324,
3335
+ "learning_rate": 7.4074074074074075e-06,
3336
+ "loss": 0.0079,
3337
+ "step": 812
3338
+ },
3339
+ {
3340
+ "epoch": 28.0,
3341
+ "eval_accuracy": 0.6363636363636364,
3342
+ "eval_f1_macro": 0.5506189724046867,
3343
+ "eval_f1_micro": 0.6363636363636364,
3344
+ "eval_f1_weighted": 0.6175532948828404,
3345
+ "eval_loss": 1.8650879859924316,
3346
+ "eval_precision_macro": 0.5427141891239254,
3347
+ "eval_precision_micro": 0.6363636363636364,
3348
+ "eval_precision_weighted": 0.6077663040137685,
3349
+ "eval_recall_macro": 0.5670219198790628,
3350
+ "eval_recall_micro": 0.6363636363636364,
3351
+ "eval_recall_weighted": 0.6363636363636364,
3352
+ "eval_runtime": 2.3148,
3353
+ "eval_samples_per_second": 57.023,
3354
+ "eval_steps_per_second": 7.344,
3355
+ "step": 812
3356
+ },
3357
+ {
3358
+ "epoch": 28.06896551724138,
3359
+ "grad_norm": 1.3216640949249268,
3360
+ "learning_rate": 7.151979565772669e-06,
3361
+ "loss": 0.0333,
3362
+ "step": 814
3363
+ },
3364
+ {
3365
+ "epoch": 28.137931034482758,
3366
+ "grad_norm": 9.799240112304688,
3367
+ "learning_rate": 6.896551724137932e-06,
3368
+ "loss": 0.1634,
3369
+ "step": 816
3370
+ },
3371
+ {
3372
+ "epoch": 28.20689655172414,
3373
+ "grad_norm": 0.052395276725292206,
3374
+ "learning_rate": 6.641123882503193e-06,
3375
+ "loss": 0.0016,
3376
+ "step": 818
3377
+ },
3378
+ {
3379
+ "epoch": 28.275862068965516,
3380
+ "grad_norm": 4.465813159942627,
3381
+ "learning_rate": 6.385696040868455e-06,
3382
+ "loss": 0.0404,
3383
+ "step": 820
3384
+ },
3385
+ {
3386
+ "epoch": 28.344827586206897,
3387
+ "grad_norm": 2.288407564163208,
3388
+ "learning_rate": 6.130268199233717e-06,
3389
+ "loss": 0.0091,
3390
+ "step": 822
3391
+ },
3392
+ {
3393
+ "epoch": 28.413793103448278,
3394
+ "grad_norm": 0.025375355035066605,
3395
+ "learning_rate": 5.874840357598978e-06,
3396
+ "loss": 0.0011,
3397
+ "step": 824
3398
+ },
3399
+ {
3400
+ "epoch": 28.482758620689655,
3401
+ "grad_norm": 0.16025374829769135,
3402
+ "learning_rate": 5.61941251596424e-06,
3403
+ "loss": 0.003,
3404
+ "step": 826
3405
+ },
3406
+ {
3407
+ "epoch": 28.551724137931036,
3408
+ "grad_norm": 0.03463875502347946,
3409
+ "learning_rate": 5.3639846743295025e-06,
3410
+ "loss": 0.0093,
3411
+ "step": 828
3412
+ },
3413
+ {
3414
+ "epoch": 28.620689655172413,
3415
+ "grad_norm": 0.12321082502603531,
3416
+ "learning_rate": 5.108556832694764e-06,
3417
+ "loss": 0.0103,
3418
+ "step": 830
3419
+ },
3420
+ {
3421
+ "epoch": 28.689655172413794,
3422
+ "grad_norm": 0.22069355845451355,
3423
+ "learning_rate": 4.853128991060026e-06,
3424
+ "loss": 0.0025,
3425
+ "step": 832
3426
+ },
3427
+ {
3428
+ "epoch": 28.75862068965517,
3429
+ "grad_norm": 0.04350389167666435,
3430
+ "learning_rate": 4.5977011494252875e-06,
3431
+ "loss": 0.0024,
3432
+ "step": 834
3433
+ },
3434
+ {
3435
+ "epoch": 28.82758620689655,
3436
+ "grad_norm": 0.0725034549832344,
3437
+ "learning_rate": 4.342273307790549e-06,
3438
+ "loss": 0.0025,
3439
+ "step": 836
3440
+ },
3441
+ {
3442
+ "epoch": 28.896551724137932,
3443
+ "grad_norm": 0.0820830762386322,
3444
+ "learning_rate": 4.086845466155812e-06,
3445
+ "loss": 0.0044,
3446
+ "step": 838
3447
+ },
3448
+ {
3449
+ "epoch": 28.96551724137931,
3450
+ "grad_norm": 0.12842264771461487,
3451
+ "learning_rate": 3.8314176245210725e-06,
3452
+ "loss": 0.0018,
3453
+ "step": 840
3454
+ },
3455
+ {
3456
+ "epoch": 29.0,
3457
+ "eval_accuracy": 0.6363636363636364,
3458
+ "eval_f1_macro": 0.550809139380568,
3459
+ "eval_f1_micro": 0.6363636363636364,
3460
+ "eval_f1_weighted": 0.6183867102048921,
3461
+ "eval_loss": 1.8015811443328857,
3462
+ "eval_precision_macro": 0.5424965742265075,
3463
+ "eval_precision_micro": 0.6363636363636364,
3464
+ "eval_precision_weighted": 0.6074053566447076,
3465
+ "eval_recall_macro": 0.5654346182917611,
3466
+ "eval_recall_micro": 0.6363636363636364,
3467
+ "eval_recall_weighted": 0.6363636363636364,
3468
+ "eval_runtime": 2.3209,
3469
+ "eval_samples_per_second": 56.875,
3470
+ "eval_steps_per_second": 7.325,
3471
+ "step": 841
3472
+ },
3473
+ {
3474
+ "epoch": 29.03448275862069,
3475
+ "grad_norm": 0.04786275699734688,
3476
+ "learning_rate": 3.5759897828863346e-06,
3477
+ "loss": 0.0016,
3478
+ "step": 842
3479
+ },
3480
+ {
3481
+ "epoch": 29.103448275862068,
3482
+ "grad_norm": 0.12234374135732651,
3483
+ "learning_rate": 3.3205619412515967e-06,
3484
+ "loss": 0.0024,
3485
+ "step": 844
3486
+ },
3487
+ {
3488
+ "epoch": 29.17241379310345,
3489
+ "grad_norm": 1.1938027143478394,
3490
+ "learning_rate": 3.0651340996168583e-06,
3491
+ "loss": 0.0247,
3492
+ "step": 846
3493
+ },
3494
+ {
3495
+ "epoch": 29.24137931034483,
3496
+ "grad_norm": 0.06169275566935539,
3497
+ "learning_rate": 2.80970625798212e-06,
3498
+ "loss": 0.0019,
3499
+ "step": 848
3500
+ },
3501
+ {
3502
+ "epoch": 29.310344827586206,
3503
+ "grad_norm": 0.05622587725520134,
3504
+ "learning_rate": 2.554278416347382e-06,
3505
+ "loss": 0.0048,
3506
+ "step": 850
3507
+ },
3508
+ {
3509
+ "epoch": 29.379310344827587,
3510
+ "grad_norm": 1.4125478267669678,
3511
+ "learning_rate": 2.2988505747126437e-06,
3512
+ "loss": 0.0341,
3513
+ "step": 852
3514
+ },
3515
+ {
3516
+ "epoch": 29.448275862068964,
3517
+ "grad_norm": 0.7389807105064392,
3518
+ "learning_rate": 2.043422733077906e-06,
3519
+ "loss": 0.0063,
3520
+ "step": 854
3521
+ },
3522
+ {
3523
+ "epoch": 29.517241379310345,
3524
+ "grad_norm": 0.1219203844666481,
3525
+ "learning_rate": 1.7879948914431673e-06,
3526
+ "loss": 0.0024,
3527
+ "step": 856
3528
+ },
3529
+ {
3530
+ "epoch": 29.586206896551722,
3531
+ "grad_norm": 0.02140001207590103,
3532
+ "learning_rate": 1.5325670498084292e-06,
3533
+ "loss": 0.001,
3534
+ "step": 858
3535
+ },
3536
+ {
3537
+ "epoch": 29.655172413793103,
3538
+ "grad_norm": 0.16312941908836365,
3539
+ "learning_rate": 1.277139208173691e-06,
3540
+ "loss": 0.0051,
3541
+ "step": 860
3542
+ },
3543
+ {
3544
+ "epoch": 29.724137931034484,
3545
+ "grad_norm": 0.09436585009098053,
3546
+ "learning_rate": 1.021711366538953e-06,
3547
+ "loss": 0.0027,
3548
+ "step": 862
3549
+ },
3550
+ {
3551
+ "epoch": 29.79310344827586,
3552
+ "grad_norm": 0.05503632500767708,
3553
+ "learning_rate": 7.662835249042146e-07,
3554
+ "loss": 0.0013,
3555
+ "step": 864
3556
+ },
3557
+ {
3558
+ "epoch": 29.862068965517242,
3559
+ "grad_norm": 0.17716890573501587,
3560
+ "learning_rate": 5.108556832694765e-07,
3561
+ "loss": 0.0038,
3562
+ "step": 866
3563
+ },
3564
+ {
3565
+ "epoch": 29.93103448275862,
3566
+ "grad_norm": 0.061406251043081284,
3567
+ "learning_rate": 2.5542784163473823e-07,
3568
+ "loss": 0.0235,
3569
+ "step": 868
3570
+ },
3571
+ {
3572
+ "epoch": 30.0,
3573
+ "grad_norm": 0.027203461155295372,
3574
+ "learning_rate": 0.0,
3575
+ "loss": 0.0068,
3576
+ "step": 870
3577
+ },
3578
+ {
3579
+ "epoch": 30.0,
3580
+ "eval_accuracy": 0.6363636363636364,
3581
+ "eval_f1_macro": 0.5510361100016273,
3582
+ "eval_f1_micro": 0.6363636363636364,
3583
+ "eval_f1_weighted": 0.6182163433025503,
3584
+ "eval_loss": 1.793615460395813,
3585
+ "eval_precision_macro": 0.5435933453841307,
3586
+ "eval_precision_micro": 0.6363636363636364,
3587
+ "eval_precision_weighted": 0.6073074998024288,
3588
+ "eval_recall_macro": 0.5650113378684807,
3589
+ "eval_recall_micro": 0.6363636363636364,
3590
+ "eval_recall_weighted": 0.6363636363636364,
3591
+ "eval_runtime": 2.3235,
3592
+ "eval_samples_per_second": 56.811,
3593
+ "eval_steps_per_second": 7.317,
3594
+ "step": 870
3595
+ },
3596
+ {
3597
+ "epoch": 30.0,
3598
+ "step": 870,
3599
+ "total_flos": 1.0740871074163507e+18,
3600
+ "train_loss": 0.5336226776871167,
3601
+ "train_runtime": 850.3912,
3602
+ "train_samples_per_second": 16.298,
3603
+ "train_steps_per_second": 1.023
3604
+ }
3605
+ ],
3606
+ "logging_steps": 2,
3607
+ "max_steps": 870,
3608
+ "num_input_tokens_seen": 0,
3609
+ "num_train_epochs": 30,
3610
+ "save_steps": 500,
3611
+ "stateful_callbacks": {
3612
+ "TrainerControl": {
3613
+ "args": {
3614
+ "should_epoch_stop": false,
3615
+ "should_evaluate": false,
3616
+ "should_log": false,
3617
+ "should_save": true,
3618
+ "should_training_stop": true
3619
+ },
3620
+ "attributes": {}
3621
+ }
3622
+ },
3623
+ "total_flos": 1.0740871074163507e+18,
3624
+ "train_batch_size": 8,
3625
+ "trial_name": null,
3626
+ "trial_params": null
3627
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bcce94f9c810b71a0159e2a97379910bf4afe0063ea6a80d0d352ba194c2d0
3
+ size 5368