Model save
Browse files- README.md +25 -25
- all_results.json +12 -12
- config.json +12 -12
- eval_results.json +12 -12
- model.safetensors +1 -1
- train_results.json +4 -4
- trainer_state.json +206 -206
README.md
CHANGED
|
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on an unknown dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
-
- Accuracy: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
@@ -58,26 +58,26 @@ The following hyperparameters were used during training:
|
|
| 58 |
|
| 59 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 60 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 61 |
-
| 1.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on an unknown dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.4573
|
| 25 |
+
- Precision: 0.5991
|
| 26 |
+
- Recall: 0.5668
|
| 27 |
+
- F1: 0.5825
|
| 28 |
+
- Accuracy: 0.9301
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 58 |
|
| 59 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 60 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 61 |
+
| 1.0711 | 1.0 | 115 | 0.4380 | 0.2039 | 0.1800 | 0.1912 | 0.8599 |
|
| 62 |
+
| 0.2579 | 2.0 | 230 | 0.2830 | 0.4117 | 0.3991 | 0.4053 | 0.9112 |
|
| 63 |
+
| 0.1083 | 3.0 | 345 | 0.2841 | 0.5199 | 0.4894 | 0.5042 | 0.9222 |
|
| 64 |
+
| 0.0707 | 4.0 | 460 | 0.2899 | 0.5291 | 0.5481 | 0.5384 | 0.9240 |
|
| 65 |
+
| 0.0472 | 5.0 | 575 | 0.2954 | 0.5816 | 0.5354 | 0.5576 | 0.9297 |
|
| 66 |
+
| 0.0336 | 6.0 | 690 | 0.3135 | 0.5902 | 0.5354 | 0.5615 | 0.9296 |
|
| 67 |
+
| 0.0232 | 7.0 | 805 | 0.3596 | 0.6125 | 0.5419 | 0.5750 | 0.9299 |
|
| 68 |
+
| 0.0178 | 8.0 | 920 | 0.3412 | 0.5675 | 0.5903 | 0.5787 | 0.9285 |
|
| 69 |
+
| 0.0181 | 9.0 | 1035 | 0.3621 | 0.6100 | 0.5470 | 0.5768 | 0.9296 |
|
| 70 |
+
| 0.0132 | 10.0 | 1150 | 0.3638 | 0.5904 | 0.5733 | 0.5817 | 0.9302 |
|
| 71 |
+
| 0.0106 | 11.0 | 1265 | 0.4134 | 0.6078 | 0.5556 | 0.5805 | 0.9303 |
|
| 72 |
+
| 0.0088 | 12.0 | 1380 | 0.4197 | 0.6023 | 0.5579 | 0.5793 | 0.9297 |
|
| 73 |
+
| 0.0071 | 13.0 | 1495 | 0.4162 | 0.5947 | 0.5712 | 0.5828 | 0.9301 |
|
| 74 |
+
| 0.0067 | 14.0 | 1610 | 0.4196 | 0.6077 | 0.5518 | 0.5784 | 0.9305 |
|
| 75 |
+
| 0.005 | 15.0 | 1725 | 0.4391 | 0.5892 | 0.5661 | 0.5774 | 0.9295 |
|
| 76 |
+
| 0.0047 | 16.0 | 1840 | 0.4424 | 0.5872 | 0.5682 | 0.5775 | 0.9295 |
|
| 77 |
+
| 0.0042 | 17.0 | 1955 | 0.4632 | 0.5939 | 0.5539 | 0.5732 | 0.9293 |
|
| 78 |
+
| 0.0037 | 18.0 | 2070 | 0.4541 | 0.5971 | 0.5692 | 0.5828 | 0.9300 |
|
| 79 |
+
| 0.0041 | 19.0 | 2185 | 0.4611 | 0.6069 | 0.5631 | 0.5842 | 0.9307 |
|
| 80 |
+
| 0.0034 | 20.0 | 2300 | 0.4573 | 0.5991 | 0.5668 | 0.5825 | 0.9301 |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 4.
|
| 9 |
"eval_samples": 952,
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
"total_flos": 1090015519875414.0,
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
-
"train_samples_per_second": 72.
|
| 16 |
-
"train_steps_per_second": 4.
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9311370980866249,
|
| 4 |
+
"eval_f1": 0.5635515913237381,
|
| 5 |
+
"eval_loss": 0.32190775871276855,
|
| 6 |
+
"eval_precision": 0.585016835016835,
|
| 7 |
+
"eval_recall": 0.543605788032851,
|
| 8 |
+
"eval_runtime": 4.6723,
|
| 9 |
"eval_samples": 952,
|
| 10 |
+
"eval_samples_per_second": 203.754,
|
| 11 |
+
"eval_steps_per_second": 12.842,
|
| 12 |
"total_flos": 1090015519875414.0,
|
| 13 |
+
"train_loss": 0.08582915891771731,
|
| 14 |
+
"train_runtime": 509.1667,
|
| 15 |
+
"train_samples_per_second": 72.157,
|
| 16 |
+
"train_steps_per_second": 4.517
|
| 17 |
}
|
config.json
CHANGED
|
@@ -9,24 +9,24 @@
|
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
"1": "B-CellType",
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "I-
|
| 18 |
-
"6": "I-
|
| 19 |
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"label2id": {
|
| 23 |
-
"B-CellLine":
|
| 24 |
"B-CellType": 1,
|
| 25 |
-
"B-Tissue":
|
| 26 |
-
"I-CellLine":
|
| 27 |
-
"I-CellType":
|
| 28 |
-
"I-Tissue":
|
| 29 |
-
"O":
|
| 30 |
},
|
| 31 |
"layer_norm_eps": 1e-12,
|
| 32 |
"max_position_embeddings": 512,
|
|
|
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "B-CellLine",
|
| 13 |
"1": "B-CellType",
|
| 14 |
+
"2": "B-Tissue",
|
| 15 |
+
"3": "I-CellLine",
|
| 16 |
+
"4": "O",
|
| 17 |
+
"5": "I-CellType",
|
| 18 |
+
"6": "I-Tissue"
|
| 19 |
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"label2id": {
|
| 23 |
+
"B-CellLine": 0,
|
| 24 |
"B-CellType": 1,
|
| 25 |
+
"B-Tissue": 2,
|
| 26 |
+
"I-CellLine": 3,
|
| 27 |
+
"I-CellType": 5,
|
| 28 |
+
"I-Tissue": 6,
|
| 29 |
+
"O": 4
|
| 30 |
},
|
| 31 |
"layer_norm_eps": 1e-12,
|
| 32 |
"max_position_embeddings": 512,
|
eval_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 4.
|
| 9 |
"eval_samples": 952,
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
"total_flos": 1090015519875414.0,
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
-
"train_samples_per_second": 72.
|
| 16 |
-
"train_steps_per_second": 4.
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9311370980866249,
|
| 4 |
+
"eval_f1": 0.5635515913237381,
|
| 5 |
+
"eval_loss": 0.32190775871276855,
|
| 6 |
+
"eval_precision": 0.585016835016835,
|
| 7 |
+
"eval_recall": 0.543605788032851,
|
| 8 |
+
"eval_runtime": 4.6723,
|
| 9 |
"eval_samples": 952,
|
| 10 |
+
"eval_samples_per_second": 203.754,
|
| 11 |
+
"eval_steps_per_second": 12.842,
|
| 12 |
"total_flos": 1090015519875414.0,
|
| 13 |
+
"train_loss": 0.08582915891771731,
|
| 14 |
+
"train_runtime": 509.1667,
|
| 15 |
+
"train_samples_per_second": 72.157,
|
| 16 |
+
"train_steps_per_second": 4.517
|
| 17 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435611468
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8681f37519c7f7232f0f8d65a1870739767260dc6529a286548ff77034525cf
|
| 3 |
size 435611468
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
"total_flos": 1090015519875414.0,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 72.
|
| 7 |
-
"train_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
"total_flos": 1090015519875414.0,
|
| 4 |
+
"train_loss": 0.08582915891771731,
|
| 5 |
+
"train_runtime": 509.1667,
|
| 6 |
+
"train_samples_per_second": 72.157,
|
| 7 |
+
"train_steps_per_second": 4.517
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/hf/CeLLaTe-AL-Test_1.0/base/BiomedNLP_BiomedBERT_base/checkpoint-
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2300,
|
|
@@ -10,392 +10,392 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 9.652173913043478e-06,
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 115
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
-
"eval_accuracy": 0.
|
| 21 |
-
"eval_f1": 0.
|
| 22 |
-
"eval_loss": 0.
|
| 23 |
-
"eval_precision": 0.
|
| 24 |
-
"eval_recall": 0.
|
| 25 |
-
"eval_runtime": 4.
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second":
|
| 28 |
"step": 115
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 2.0,
|
| 32 |
-
"grad_norm":
|
| 33 |
"learning_rate": 1.965217391304348e-05,
|
| 34 |
-
"loss": 0.
|
| 35 |
"step": 230
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 2.0,
|
| 39 |
-
"eval_accuracy": 0.
|
| 40 |
-
"eval_f1": 0.
|
| 41 |
-
"eval_loss": 0.
|
| 42 |
-
"eval_precision": 0.
|
| 43 |
-
"eval_recall": 0.
|
| 44 |
-
"eval_runtime": 4.
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second":
|
| 47 |
"step": 230
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 3.0,
|
| 51 |
-
"grad_norm": 1.
|
| 52 |
"learning_rate": 1.892753623188406e-05,
|
| 53 |
-
"loss": 0.
|
| 54 |
"step": 345
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 3.0,
|
| 58 |
-
"eval_accuracy": 0.
|
| 59 |
-
"eval_f1": 0.
|
| 60 |
-
"eval_loss": 0.
|
| 61 |
-
"eval_precision": 0.
|
| 62 |
-
"eval_recall": 0.
|
| 63 |
-
"eval_runtime": 4.
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second":
|
| 66 |
"step": 345
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 4.0,
|
| 70 |
-
"grad_norm":
|
| 71 |
"learning_rate": 1.781642512077295e-05,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 460
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 4.0,
|
| 77 |
-
"eval_accuracy": 0.
|
| 78 |
-
"eval_f1": 0.
|
| 79 |
-
"eval_loss": 0.
|
| 80 |
-
"eval_precision": 0.
|
| 81 |
-
"eval_recall": 0.
|
| 82 |
-
"eval_runtime": 4.
|
| 83 |
-
"eval_samples_per_second":
|
| 84 |
-
"eval_steps_per_second":
|
| 85 |
"step": 460
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 5.0,
|
| 89 |
-
"grad_norm":
|
| 90 |
"learning_rate": 1.6705314009661836e-05,
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 575
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 5.0,
|
| 96 |
-
"eval_accuracy": 0.
|
| 97 |
-
"eval_f1": 0.
|
| 98 |
-
"eval_loss": 0.
|
| 99 |
-
"eval_precision": 0.
|
| 100 |
-
"eval_recall": 0.
|
| 101 |
-
"eval_runtime": 4.
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
"step": 575
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.0,
|
| 108 |
-
"grad_norm":
|
| 109 |
"learning_rate": 1.5594202898550727e-05,
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 690
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 6.0,
|
| 115 |
-
"eval_accuracy": 0.
|
| 116 |
-
"eval_f1": 0.
|
| 117 |
-
"eval_loss": 0.
|
| 118 |
-
"eval_precision": 0.
|
| 119 |
-
"eval_recall": 0.
|
| 120 |
-
"eval_runtime":
|
| 121 |
-
"eval_samples_per_second":
|
| 122 |
-
"eval_steps_per_second":
|
| 123 |
"step": 690
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 7.0,
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
"learning_rate": 1.4483091787439615e-05,
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 805
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 7.0,
|
| 134 |
-
"eval_accuracy": 0.
|
| 135 |
-
"eval_f1": 0.
|
| 136 |
-
"eval_loss": 0.
|
| 137 |
-
"eval_precision": 0.
|
| 138 |
-
"eval_recall": 0.
|
| 139 |
-
"eval_runtime": 4.
|
| 140 |
-
"eval_samples_per_second":
|
| 141 |
-
"eval_steps_per_second":
|
| 142 |
"step": 805
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 8.0,
|
| 146 |
-
"grad_norm": 1.
|
| 147 |
"learning_rate": 1.3371980676328504e-05,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 920
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 8.0,
|
| 153 |
-
"eval_accuracy": 0.
|
| 154 |
-
"eval_f1": 0.
|
| 155 |
-
"eval_loss": 0.
|
| 156 |
-
"eval_precision": 0.
|
| 157 |
-
"eval_recall": 0.
|
| 158 |
-
"eval_runtime": 4.
|
| 159 |
-
"eval_samples_per_second":
|
| 160 |
-
"eval_steps_per_second":
|
| 161 |
"step": 920
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 9.0,
|
| 165 |
-
"grad_norm": 1.
|
| 166 |
"learning_rate": 1.2260869565217393e-05,
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 1035
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 9.0,
|
| 172 |
-
"eval_accuracy": 0.
|
| 173 |
-
"eval_f1": 0.
|
| 174 |
-
"eval_loss": 0.
|
| 175 |
-
"eval_precision": 0.
|
| 176 |
-
"eval_recall": 0.
|
| 177 |
-
"eval_runtime": 4.
|
| 178 |
-
"eval_samples_per_second":
|
| 179 |
-
"eval_steps_per_second":
|
| 180 |
"step": 1035
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 10.0,
|
| 184 |
-
"grad_norm": 0.
|
| 185 |
"learning_rate": 1.114975845410628e-05,
|
| 186 |
-
"loss": 0.
|
| 187 |
"step": 1150
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 10.0,
|
| 191 |
-
"eval_accuracy": 0.
|
| 192 |
-
"eval_f1": 0.
|
| 193 |
-
"eval_loss": 0.
|
| 194 |
-
"eval_precision": 0.
|
| 195 |
-
"eval_recall": 0.
|
| 196 |
-
"eval_runtime": 4.
|
| 197 |
-
"eval_samples_per_second":
|
| 198 |
-
"eval_steps_per_second":
|
| 199 |
"step": 1150
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 11.0,
|
| 203 |
-
"grad_norm":
|
| 204 |
"learning_rate": 1.003864734299517e-05,
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 1265
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 11.0,
|
| 210 |
-
"eval_accuracy": 0.
|
| 211 |
-
"eval_f1": 0.
|
| 212 |
-
"eval_loss": 0.
|
| 213 |
-
"eval_precision": 0.
|
| 214 |
-
"eval_recall": 0.
|
| 215 |
-
"eval_runtime": 4.
|
| 216 |
-
"eval_samples_per_second":
|
| 217 |
-
"eval_steps_per_second":
|
| 218 |
"step": 1265
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 12.0,
|
| 222 |
-
"grad_norm": 1.
|
| 223 |
"learning_rate": 8.927536231884059e-06,
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 1380
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 12.0,
|
| 229 |
-
"eval_accuracy": 0.
|
| 230 |
-
"eval_f1": 0.
|
| 231 |
-
"eval_loss": 0.
|
| 232 |
-
"eval_precision": 0.
|
| 233 |
-
"eval_recall": 0.
|
| 234 |
-
"eval_runtime": 4.
|
| 235 |
-
"eval_samples_per_second":
|
| 236 |
-
"eval_steps_per_second": 12.
|
| 237 |
"step": 1380
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 13.0,
|
| 241 |
-
"grad_norm": 0.
|
| 242 |
"learning_rate": 7.816425120772948e-06,
|
| 243 |
-
"loss": 0.
|
| 244 |
"step": 1495
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 13.0,
|
| 248 |
-
"eval_accuracy": 0.
|
| 249 |
-
"eval_f1": 0.
|
| 250 |
-
"eval_loss": 0.
|
| 251 |
-
"eval_precision": 0.
|
| 252 |
-
"eval_recall": 0.
|
| 253 |
-
"eval_runtime": 4.
|
| 254 |
-
"eval_samples_per_second":
|
| 255 |
-
"eval_steps_per_second":
|
| 256 |
"step": 1495
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 14.0,
|
| 260 |
-
"grad_norm":
|
| 261 |
"learning_rate": 6.705314009661836e-06,
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 1610
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 14.0,
|
| 267 |
-
"eval_accuracy": 0.
|
| 268 |
-
"eval_f1": 0.
|
| 269 |
-
"eval_loss": 0.
|
| 270 |
-
"eval_precision": 0.
|
| 271 |
-
"eval_recall": 0.
|
| 272 |
-
"eval_runtime": 4.
|
| 273 |
-
"eval_samples_per_second":
|
| 274 |
-
"eval_steps_per_second":
|
| 275 |
"step": 1610
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 15.0,
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
"learning_rate": 5.594202898550725e-06,
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 1725
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 15.0,
|
| 286 |
-
"eval_accuracy": 0.
|
| 287 |
-
"eval_f1": 0.
|
| 288 |
-
"eval_loss": 0.
|
| 289 |
-
"eval_precision": 0.
|
| 290 |
-
"eval_recall": 0.
|
| 291 |
-
"eval_runtime": 4.
|
| 292 |
-
"eval_samples_per_second":
|
| 293 |
-
"eval_steps_per_second":
|
| 294 |
"step": 1725
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 16.0,
|
| 298 |
-
"grad_norm":
|
| 299 |
"learning_rate": 4.483091787439614e-06,
|
| 300 |
-
"loss": 0.
|
| 301 |
"step": 1840
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 16.0,
|
| 305 |
-
"eval_accuracy": 0.
|
| 306 |
-
"eval_f1": 0.
|
| 307 |
-
"eval_loss": 0.
|
| 308 |
-
"eval_precision": 0.
|
| 309 |
-
"eval_recall": 0.
|
| 310 |
-
"eval_runtime": 4.
|
| 311 |
-
"eval_samples_per_second":
|
| 312 |
-
"eval_steps_per_second":
|
| 313 |
"step": 1840
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 17.0,
|
| 317 |
-
"grad_norm":
|
| 318 |
"learning_rate": 3.371980676328503e-06,
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 1955
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 17.0,
|
| 324 |
-
"eval_accuracy": 0.
|
| 325 |
-
"eval_f1": 0.
|
| 326 |
-
"eval_loss": 0.
|
| 327 |
-
"eval_precision": 0.
|
| 328 |
-
"eval_recall": 0.
|
| 329 |
-
"eval_runtime": 4.
|
| 330 |
-
"eval_samples_per_second":
|
| 331 |
-
"eval_steps_per_second":
|
| 332 |
"step": 1955
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 18.0,
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
"learning_rate": 2.2608695652173913e-06,
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 2070
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 18.0,
|
| 343 |
-
"eval_accuracy": 0.
|
| 344 |
-
"eval_f1": 0.
|
| 345 |
-
"eval_loss": 0.
|
| 346 |
-
"eval_precision": 0.
|
| 347 |
-
"eval_recall": 0.
|
| 348 |
-
"eval_runtime": 4.
|
| 349 |
-
"eval_samples_per_second":
|
| 350 |
-
"eval_steps_per_second": 12.
|
| 351 |
"step": 2070
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 19.0,
|
| 355 |
-
"grad_norm":
|
| 356 |
"learning_rate": 1.1497584541062802e-06,
|
| 357 |
-
"loss": 0.
|
| 358 |
"step": 2185
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 19.0,
|
| 362 |
-
"eval_accuracy": 0.
|
| 363 |
-
"eval_f1": 0.
|
| 364 |
-
"eval_loss": 0.
|
| 365 |
-
"eval_precision": 0.
|
| 366 |
-
"eval_recall": 0.
|
| 367 |
-
"eval_runtime": 4.
|
| 368 |
-
"eval_samples_per_second":
|
| 369 |
-
"eval_steps_per_second":
|
| 370 |
"step": 2185
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 20.0,
|
| 374 |
-
"grad_norm": 0.
|
| 375 |
"learning_rate": 3.864734299516908e-08,
|
| 376 |
-
"loss": 0.
|
| 377 |
"step": 2300
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 20.0,
|
| 381 |
-
"eval_accuracy": 0.
|
| 382 |
-
"eval_f1": 0.
|
| 383 |
-
"eval_loss": 0.
|
| 384 |
-
"eval_precision": 0.
|
| 385 |
-
"eval_recall": 0.
|
| 386 |
-
"eval_runtime": 4.
|
| 387 |
-
"eval_samples_per_second":
|
| 388 |
-
"eval_steps_per_second":
|
| 389 |
"step": 2300
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 20.0,
|
| 393 |
"step": 2300,
|
| 394 |
"total_flos": 1090015519875414.0,
|
| 395 |
-
"train_loss": 0.
|
| 396 |
-
"train_runtime":
|
| 397 |
-
"train_samples_per_second": 72.
|
| 398 |
-
"train_steps_per_second": 4.
|
| 399 |
}
|
| 400 |
],
|
| 401 |
"logging_steps": 500,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5637284701114489,
|
| 3 |
+
"best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/hf/CeLLaTe-AL-Test_1.0/base/BiomedNLP_BiomedBERT_base/checkpoint-690",
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2300,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 3.141930341720581,
|
| 14 |
"learning_rate": 9.652173913043478e-06,
|
| 15 |
+
"loss": 1.0965,
|
| 16 |
"step": 115
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.8700857880175761,
|
| 21 |
+
"eval_f1": 0.2011861313868613,
|
| 22 |
+
"eval_loss": 0.4151777923107147,
|
| 23 |
+
"eval_precision": 0.2413793103448276,
|
| 24 |
+
"eval_recall": 0.1724677356276887,
|
| 25 |
+
"eval_runtime": 4.6552,
|
| 26 |
+
"eval_samples_per_second": 204.501,
|
| 27 |
+
"eval_steps_per_second": 12.889,
|
| 28 |
"step": 115
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 5.598133563995361,
|
| 33 |
"learning_rate": 1.965217391304348e-05,
|
| 34 |
+
"loss": 0.2292,
|
| 35 |
"step": 230
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9119103526840723,
|
| 40 |
+
"eval_f1": 0.46394984326018807,
|
| 41 |
+
"eval_loss": 0.2859836220741272,
|
| 42 |
+
"eval_precision": 0.43893928820655964,
|
| 43 |
+
"eval_recall": 0.4919827923347673,
|
| 44 |
+
"eval_runtime": 4.7635,
|
| 45 |
+
"eval_samples_per_second": 199.851,
|
| 46 |
+
"eval_steps_per_second": 12.596,
|
| 47 |
"step": 230
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 1.903611183166504,
|
| 52 |
"learning_rate": 1.892753623188406e-05,
|
| 53 |
+
"loss": 0.1037,
|
| 54 |
"step": 345
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9199544323809081,
|
| 59 |
+
"eval_f1": 0.5066666666666667,
|
| 60 |
+
"eval_loss": 0.2779094874858856,
|
| 61 |
+
"eval_precision": 0.49387300408466395,
|
| 62 |
+
"eval_recall": 0.5201407899882675,
|
| 63 |
+
"eval_runtime": 4.7455,
|
| 64 |
+
"eval_samples_per_second": 200.612,
|
| 65 |
+
"eval_steps_per_second": 12.644,
|
| 66 |
"step": 345
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 1.9366143941879272,
|
| 71 |
"learning_rate": 1.781642512077295e-05,
|
| 72 |
+
"loss": 0.0684,
|
| 73 |
"step": 460
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9274405412317206,
|
| 78 |
+
"eval_f1": 0.5361736334405145,
|
| 79 |
+
"eval_loss": 0.29712674021720886,
|
| 80 |
+
"eval_precision": 0.5514675485737909,
|
| 81 |
+
"eval_recall": 0.5217051231912397,
|
| 82 |
+
"eval_runtime": 4.733,
|
| 83 |
+
"eval_samples_per_second": 201.143,
|
| 84 |
+
"eval_steps_per_second": 12.677,
|
| 85 |
"step": 460
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 1.2101763486862183,
|
| 90 |
"learning_rate": 1.6705314009661836e-05,
|
| 91 |
+
"loss": 0.0463,
|
| 92 |
"step": 575
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9276265315137284,
|
| 97 |
+
"eval_f1": 0.5296671490593343,
|
| 98 |
+
"eval_loss": 0.3128739893436432,
|
| 99 |
+
"eval_precision": 0.5618421052631579,
|
| 100 |
+
"eval_recall": 0.5009777082518576,
|
| 101 |
+
"eval_runtime": 4.7226,
|
| 102 |
+
"eval_samples_per_second": 201.582,
|
| 103 |
+
"eval_steps_per_second": 12.705,
|
| 104 |
"step": 575
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 2.3417909145355225,
|
| 109 |
"learning_rate": 1.5594202898550727e-05,
|
| 110 |
+
"loss": 0.0319,
|
| 111 |
"step": 690
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.931113849301374,
|
| 116 |
+
"eval_f1": 0.5637284701114489,
|
| 117 |
+
"eval_loss": 0.3199135661125183,
|
| 118 |
+
"eval_precision": 0.5849453322119428,
|
| 119 |
+
"eval_recall": 0.5439968713335941,
|
| 120 |
+
"eval_runtime": 5.02,
|
| 121 |
+
"eval_samples_per_second": 189.643,
|
| 122 |
+
"eval_steps_per_second": 11.952,
|
| 123 |
"step": 690
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 0.4602757394313812,
|
| 128 |
"learning_rate": 1.4483091787439615e-05,
|
| 129 |
+
"loss": 0.0257,
|
| 130 |
"step": 805
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9257201311231488,
|
| 135 |
+
"eval_f1": 0.525974025974026,
|
| 136 |
+
"eval_loss": 0.37688568234443665,
|
| 137 |
+
"eval_precision": 0.5466048080978491,
|
| 138 |
+
"eval_recall": 0.5068439577630035,
|
| 139 |
+
"eval_runtime": 4.7781,
|
| 140 |
+
"eval_samples_per_second": 199.241,
|
| 141 |
+
"eval_steps_per_second": 12.557,
|
| 142 |
"step": 805
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 1.866155743598938,
|
| 147 |
"learning_rate": 1.3371980676328504e-05,
|
| 148 |
+
"loss": 0.0223,
|
| 149 |
"step": 920
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9242089600818357,
|
| 154 |
+
"eval_f1": 0.5371711780404118,
|
| 155 |
+
"eval_loss": 0.356906533241272,
|
| 156 |
+
"eval_precision": 0.523986612123466,
|
| 157 |
+
"eval_recall": 0.5510363707469691,
|
| 158 |
+
"eval_runtime": 4.6714,
|
| 159 |
+
"eval_samples_per_second": 203.793,
|
| 160 |
+
"eval_steps_per_second": 12.844,
|
| 161 |
"step": 920
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 1.9551316499710083,
|
| 166 |
"learning_rate": 1.2260869565217393e-05,
|
| 167 |
+
"loss": 0.0176,
|
| 168 |
"step": 1035
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9249529212098668,
|
| 173 |
+
"eval_f1": 0.549402390438247,
|
| 174 |
+
"eval_loss": 0.3771890699863434,
|
| 175 |
+
"eval_precision": 0.559886317498985,
|
| 176 |
+
"eval_recall": 0.5393038717246773,
|
| 177 |
+
"eval_runtime": 4.7822,
|
| 178 |
+
"eval_samples_per_second": 199.072,
|
| 179 |
+
"eval_steps_per_second": 12.547,
|
| 180 |
"step": 1035
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 0.21579106152057648,
|
| 185 |
"learning_rate": 1.114975845410628e-05,
|
| 186 |
+
"loss": 0.0129,
|
| 187 |
"step": 1150
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9298119173273196,
|
| 192 |
+
"eval_f1": 0.5549613784907903,
|
| 193 |
+
"eval_loss": 0.3583073616027832,
|
| 194 |
+
"eval_precision": 0.562199036918138,
|
| 195 |
+
"eval_recall": 0.5479077043410246,
|
| 196 |
+
"eval_runtime": 4.7887,
|
| 197 |
+
"eval_samples_per_second": 198.801,
|
| 198 |
+
"eval_steps_per_second": 12.529,
|
| 199 |
"step": 1150
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 0.4364924728870392,
|
| 204 |
"learning_rate": 1.003864734299517e-05,
|
| 205 |
+
"loss": 0.0112,
|
| 206 |
"step": 1265
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9262316043986701,
|
| 211 |
+
"eval_f1": 0.5348368908578334,
|
| 212 |
+
"eval_loss": 0.39430442452430725,
|
| 213 |
+
"eval_precision": 0.5512660855126609,
|
| 214 |
+
"eval_recall": 0.5193586233867814,
|
| 215 |
+
"eval_runtime": 4.6852,
|
| 216 |
+
"eval_samples_per_second": 203.191,
|
| 217 |
+
"eval_steps_per_second": 12.806,
|
| 218 |
"step": 1265
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 1.8533910512924194,
|
| 223 |
"learning_rate": 8.927536231884059e-06,
|
| 224 |
+
"loss": 0.0096,
|
| 225 |
"step": 1380
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.9285099853532653,
|
| 230 |
+
"eval_f1": 0.5507480792559645,
|
| 231 |
+
"eval_loss": 0.4048748314380646,
|
| 232 |
+
"eval_precision": 0.5701130179991628,
|
| 233 |
+
"eval_recall": 0.5326554556120454,
|
| 234 |
+
"eval_runtime": 4.9847,
|
| 235 |
+
"eval_samples_per_second": 190.986,
|
| 236 |
+
"eval_steps_per_second": 12.037,
|
| 237 |
"step": 1380
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 0.022831812500953674,
|
| 242 |
"learning_rate": 7.816425120772948e-06,
|
| 243 |
+
"loss": 0.0078,
|
| 244 |
"step": 1495
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.927138307023458,
|
| 249 |
+
"eval_f1": 0.5415120140652471,
|
| 250 |
+
"eval_loss": 0.42278555035591125,
|
| 251 |
+
"eval_precision": 0.5409836065573771,
|
| 252 |
+
"eval_recall": 0.5420414548298788,
|
| 253 |
+
"eval_runtime": 4.7419,
|
| 254 |
+
"eval_samples_per_second": 200.765,
|
| 255 |
+
"eval_steps_per_second": 12.653,
|
| 256 |
"step": 1495
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 2.755345582962036,
|
| 261 |
"learning_rate": 6.705314009661836e-06,
|
| 262 |
+
"loss": 0.0068,
|
| 263 |
"step": 1610
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.9264408434659289,
|
| 268 |
+
"eval_f1": 0.541335453100159,
|
| 269 |
+
"eval_loss": 0.41575905680656433,
|
| 270 |
+
"eval_precision": 0.5503030303030303,
|
| 271 |
+
"eval_recall": 0.5326554556120454,
|
| 272 |
+
"eval_runtime": 4.73,
|
| 273 |
+
"eval_samples_per_second": 201.268,
|
| 274 |
+
"eval_steps_per_second": 12.685,
|
| 275 |
"step": 1610
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 0.009739220142364502,
|
| 280 |
"learning_rate": 5.594202898550725e-06,
|
| 281 |
+
"loss": 0.0057,
|
| 282 |
"step": 1725
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9306256248111037,
|
| 287 |
+
"eval_f1": 0.5625126646403241,
|
| 288 |
+
"eval_loss": 0.41495904326438904,
|
| 289 |
+
"eval_precision": 0.5836837678721615,
|
| 290 |
+
"eval_recall": 0.5428236214313649,
|
| 291 |
+
"eval_runtime": 4.7302,
|
| 292 |
+
"eval_samples_per_second": 201.262,
|
| 293 |
+
"eval_steps_per_second": 12.685,
|
| 294 |
"step": 1725
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 0.20581257343292236,
|
| 299 |
"learning_rate": 4.483091787439614e-06,
|
| 300 |
+
"loss": 0.0051,
|
| 301 |
"step": 1840
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.929509683119057,
|
| 306 |
+
"eval_f1": 0.5591397849462366,
|
| 307 |
+
"eval_loss": 0.427743524312973,
|
| 308 |
+
"eval_precision": 0.5695740365111562,
|
| 309 |
+
"eval_recall": 0.5490809542432538,
|
| 310 |
+
"eval_runtime": 4.7523,
|
| 311 |
+
"eval_samples_per_second": 200.322,
|
| 312 |
+
"eval_steps_per_second": 12.625,
|
| 313 |
"step": 1840
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 17.0,
|
| 317 |
+
"grad_norm": 1.4635635614395142,
|
| 318 |
"learning_rate": 3.371980676328503e-06,
|
| 319 |
+
"loss": 0.0048,
|
| 320 |
"step": 1955
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 17.0,
|
| 324 |
+
"eval_accuracy": 0.9296026782600609,
|
| 325 |
+
"eval_f1": 0.5549841772151899,
|
| 326 |
+
"eval_loss": 0.4313228130340576,
|
| 327 |
+
"eval_precision": 0.5614245698279312,
|
| 328 |
+
"eval_recall": 0.5486898709425108,
|
| 329 |
+
"eval_runtime": 4.9134,
|
| 330 |
+
"eval_samples_per_second": 193.757,
|
| 331 |
+
"eval_steps_per_second": 12.212,
|
| 332 |
"step": 1955
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 18.0,
|
| 336 |
+
"grad_norm": 0.020520634949207306,
|
| 337 |
"learning_rate": 2.2608695652173913e-06,
|
| 338 |
+
"loss": 0.004,
|
| 339 |
"step": 2070
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 18.0,
|
| 343 |
+
"eval_accuracy": 0.9297421709715668,
|
| 344 |
+
"eval_f1": 0.5621019108280255,
|
| 345 |
+
"eval_loss": 0.4391424357891083,
|
| 346 |
+
"eval_precision": 0.5723550871503851,
|
| 347 |
+
"eval_recall": 0.5522096206491983,
|
| 348 |
+
"eval_runtime": 4.7507,
|
| 349 |
+
"eval_samples_per_second": 200.39,
|
| 350 |
+
"eval_steps_per_second": 12.63,
|
| 351 |
"step": 2070
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 19.0,
|
| 355 |
+
"grad_norm": 1.6688083410263062,
|
| 356 |
"learning_rate": 1.1497584541062802e-06,
|
| 357 |
+
"loss": 0.0036,
|
| 358 |
"step": 2185
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 19.0,
|
| 362 |
+
"eval_accuracy": 0.9293236928370493,
|
| 363 |
+
"eval_f1": 0.5589764094362255,
|
| 364 |
+
"eval_loss": 0.44707345962524414,
|
| 365 |
+
"eval_precision": 0.5717791411042945,
|
| 366 |
+
"eval_recall": 0.5467344544387954,
|
| 367 |
+
"eval_runtime": 4.7037,
|
| 368 |
+
"eval_samples_per_second": 202.393,
|
| 369 |
+
"eval_steps_per_second": 12.756,
|
| 370 |
"step": 2185
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 20.0,
|
| 374 |
+
"grad_norm": 0.006341221742331982,
|
| 375 |
"learning_rate": 3.864734299516908e-08,
|
| 376 |
+
"loss": 0.0035,
|
| 377 |
"step": 2300
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 20.0,
|
| 381 |
+
"eval_accuracy": 0.9296956734010648,
|
| 382 |
+
"eval_f1": 0.5620888977476579,
|
| 383 |
+
"eval_loss": 0.4408387243747711,
|
| 384 |
+
"eval_precision": 0.573170731707317,
|
| 385 |
+
"eval_recall": 0.5514274540477122,
|
| 386 |
+
"eval_runtime": 4.7859,
|
| 387 |
+
"eval_samples_per_second": 198.919,
|
| 388 |
+
"eval_steps_per_second": 12.537,
|
| 389 |
"step": 2300
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 20.0,
|
| 393 |
"step": 2300,
|
| 394 |
"total_flos": 1090015519875414.0,
|
| 395 |
+
"train_loss": 0.08582915891771731,
|
| 396 |
+
"train_runtime": 509.1667,
|
| 397 |
+
"train_samples_per_second": 72.157,
|
| 398 |
+
"train_steps_per_second": 4.517
|
| 399 |
}
|
| 400 |
],
|
| 401 |
"logging_steps": 500,
|