End of training
Browse files- README.md +28 -7
- all_results.json +22 -22
- eval_results.json +9 -9
- predict_results.json +8 -8
- predictions.txt +0 -0
- train_results.json +6 -6
- trainer_state.json +394 -1709
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
base_model: bert-base-uncased
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- precision
|
| 9 |
- recall
|
|
@@ -11,7 +13,26 @@ metrics:
|
|
| 11 |
- accuracy
|
| 12 |
model-index:
|
| 13 |
- name: bert-base-medmentions
|
| 14 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -19,13 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# bert-base-medmentions
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 1.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
-
- Accuracy: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 4 |
base_model: bert-base-uncased
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- Ben10x/MedMentions-NER
|
| 9 |
metrics:
|
| 10 |
- precision
|
| 11 |
- recall
|
|
|
|
| 13 |
- accuracy
|
| 14 |
model-index:
|
| 15 |
- name: bert-base-medmentions
|
| 16 |
+
results:
|
| 17 |
+
- task:
|
| 18 |
+
name: Token Classification
|
| 19 |
+
type: token-classification
|
| 20 |
+
dataset:
|
| 21 |
+
name: Ben10x/MedMentions-NER
|
| 22 |
+
type: Ben10x/MedMentions-NER
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Precision
|
| 25 |
+
type: precision
|
| 26 |
+
value: 0.5820728291316527
|
| 27 |
+
- name: Recall
|
| 28 |
+
type: recall
|
| 29 |
+
value: 0.6344207955338451
|
| 30 |
+
- name: F1
|
| 31 |
+
type: f1
|
| 32 |
+
value: 0.6071204975165909
|
| 33 |
+
- name: Accuracy
|
| 34 |
+
type: accuracy
|
| 35 |
+
value: 0.8688595400463357
|
| 36 |
---
|
| 37 |
|
| 38 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 40 |
|
| 41 |
# bert-base-medmentions
|
| 42 |
|
| 43 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Ben10x/MedMentions-NER dataset.
|
| 44 |
It achieves the following results on the evaluation set:
|
| 45 |
+
- Loss: 1.5156
|
| 46 |
+
- Precision: 0.5821
|
| 47 |
+
- Recall: 0.6344
|
| 48 |
+
- F1: 0.6071
|
| 49 |
+
- Accuracy: 0.8689
|
| 50 |
|
| 51 |
## Model description
|
| 52 |
|
all_results.json
CHANGED
|
@@ -1,26 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 1.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 4.
|
| 9 |
"eval_samples": 2910,
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
-
"predict_accuracy": 0.
|
| 13 |
-
"predict_f1": 0.
|
| 14 |
-
"predict_loss": 1.
|
| 15 |
-
"predict_precision": 0.
|
| 16 |
-
"predict_recall": 0.
|
| 17 |
-
"predict_runtime": 4.
|
| 18 |
-
"predict_samples_per_second":
|
| 19 |
-
"predict_steps_per_second": 87.
|
| 20 |
-
"total_flos":
|
| 21 |
-
"train_loss": 1.
|
| 22 |
-
"train_runtime":
|
| 23 |
"train_samples": 23285,
|
| 24 |
-
"train_samples_per_second":
|
| 25 |
-
"train_steps_per_second": 18.
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.8688595400463357,
|
| 4 |
+
"eval_f1": 0.6071204975165909,
|
| 5 |
+
"eval_loss": 1.5156257152557373,
|
| 6 |
+
"eval_precision": 0.5820728291316527,
|
| 7 |
+
"eval_recall": 0.6344207955338451,
|
| 8 |
+
"eval_runtime": 4.3275,
|
| 9 |
"eval_samples": 2910,
|
| 10 |
+
"eval_samples_per_second": 672.436,
|
| 11 |
+
"eval_steps_per_second": 84.112,
|
| 12 |
+
"predict_accuracy": 0.8737973374523844,
|
| 13 |
+
"predict_f1": 0.6134236041457707,
|
| 14 |
+
"predict_loss": 1.508852243423462,
|
| 15 |
+
"predict_precision": 0.5912826297131808,
|
| 16 |
+
"predict_recall": 0.6372872525182355,
|
| 17 |
+
"predict_runtime": 4.1494,
|
| 18 |
+
"predict_samples_per_second": 701.789,
|
| 19 |
+
"predict_steps_per_second": 87.724,
|
| 20 |
+
"total_flos": 1.1901430945516224e+16,
|
| 21 |
+
"train_loss": 1.311661433704009,
|
| 22 |
+
"train_runtime": 2299.911,
|
| 23 |
"train_samples": 23285,
|
| 24 |
+
"train_samples_per_second": 151.865,
|
| 25 |
+
"train_steps_per_second": 18.986
|
| 26 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 1.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 4.
|
| 9 |
"eval_samples": 2910,
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.8688595400463357,
|
| 4 |
+
"eval_f1": 0.6071204975165909,
|
| 5 |
+
"eval_loss": 1.5156257152557373,
|
| 6 |
+
"eval_precision": 0.5820728291316527,
|
| 7 |
+
"eval_recall": 0.6344207955338451,
|
| 8 |
+
"eval_runtime": 4.3275,
|
| 9 |
"eval_samples": 2910,
|
| 10 |
+
"eval_samples_per_second": 672.436,
|
| 11 |
+
"eval_steps_per_second": 84.112
|
| 12 |
}
|
predict_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"predict_accuracy": 0.
|
| 3 |
-
"predict_f1": 0.
|
| 4 |
-
"predict_loss": 1.
|
| 5 |
-
"predict_precision": 0.
|
| 6 |
-
"predict_recall": 0.
|
| 7 |
-
"predict_runtime": 4.
|
| 8 |
-
"predict_samples_per_second":
|
| 9 |
-
"predict_steps_per_second": 87.
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_accuracy": 0.8737973374523844,
|
| 3 |
+
"predict_f1": 0.6134236041457707,
|
| 4 |
+
"predict_loss": 1.508852243423462,
|
| 5 |
+
"predict_precision": 0.5912826297131808,
|
| 6 |
+
"predict_recall": 0.6372872525182355,
|
| 7 |
+
"predict_runtime": 4.1494,
|
| 8 |
+
"predict_samples_per_second": 701.789,
|
| 9 |
+
"predict_steps_per_second": 87.724
|
| 10 |
}
|
predictions.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 23285,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second": 18.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 1.1901430945516224e+16,
|
| 4 |
+
"train_loss": 1.311661433704009,
|
| 5 |
+
"train_runtime": 2299.911,
|
| 6 |
"train_samples": 23285,
|
| 7 |
+
"train_samples_per_second": 151.865,
|
| 8 |
+
"train_steps_per_second": 18.986
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,2132 +1,817 @@
|
|
| 1 |
{
|
| 2 |
"best_global_step": 5822,
|
| 3 |
-
"best_metric": 1.
|
| 4 |
"best_model_checkpoint": "./output/bert-base-medmentions/checkpoint-5822",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.1717622810030917,
|
| 14 |
-
"grad_norm": 1.
|
| 15 |
-
"learning_rate": 4.
|
| 16 |
-
"loss":
|
| 17 |
"step": 500
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.3435245620061834,
|
| 21 |
-
"grad_norm": 1.
|
| 22 |
-
"learning_rate": 4.
|
| 23 |
-
"loss":
|
| 24 |
"step": 1000
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.5152868430092752,
|
| 28 |
-
"grad_norm": 1.
|
| 29 |
-
"learning_rate": 4.
|
| 30 |
-
"loss":
|
| 31 |
"step": 1500
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.6870491240123668,
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate": 4.
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 2000
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.8588114050154586,
|
| 42 |
-
"grad_norm": 1.
|
| 43 |
-
"learning_rate": 4.
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 2500
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 1.0,
|
| 49 |
-
"eval_accuracy": 0.
|
| 50 |
-
"eval_f1": 0.
|
| 51 |
-
"eval_loss": 1.
|
| 52 |
-
"eval_precision": 0.
|
| 53 |
-
"eval_recall": 0.
|
| 54 |
-
"eval_runtime": 4.
|
| 55 |
-
"eval_samples_per_second":
|
| 56 |
-
"eval_steps_per_second":
|
| 57 |
"step": 2911
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 1.0305736860185504,
|
| 61 |
-
"grad_norm": 1.
|
| 62 |
-
"learning_rate": 4.
|
| 63 |
-
"loss": 1.
|
| 64 |
"step": 3000
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"epoch": 1.202335967021642,
|
| 68 |
-
"grad_norm":
|
| 69 |
-
"learning_rate": 4.
|
| 70 |
-
"loss": 1.
|
| 71 |
"step": 3500
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 1.3740982480247337,
|
| 75 |
-
"grad_norm": 1.
|
| 76 |
-
"learning_rate": 4.
|
| 77 |
-
"loss": 1.
|
| 78 |
"step": 4000
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 1.5458605290278253,
|
| 82 |
-
"grad_norm":
|
| 83 |
-
"learning_rate": 4.
|
| 84 |
-
"loss": 1.
|
| 85 |
"step": 4500
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 1.7176228100309172,
|
| 89 |
-
"grad_norm":
|
| 90 |
-
"learning_rate": 4.
|
| 91 |
-
"loss": 1.
|
| 92 |
"step": 5000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 1.889385091034009,
|
| 96 |
-
"grad_norm": 2.
|
| 97 |
-
"learning_rate": 4.
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 5500
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 2.0,
|
| 103 |
-
"eval_accuracy": 0.
|
| 104 |
-
"eval_f1": 0.
|
| 105 |
-
"eval_loss": 1.
|
| 106 |
-
"eval_precision": 0.
|
| 107 |
-
"eval_recall": 0.
|
| 108 |
-
"eval_runtime": 4.
|
| 109 |
-
"eval_samples_per_second":
|
| 110 |
-
"eval_steps_per_second":
|
| 111 |
"step": 5822
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 2.0611473720371007,
|
| 115 |
-
"grad_norm": 4.
|
| 116 |
-
"learning_rate": 4.
|
| 117 |
-
"loss": 1.
|
| 118 |
"step": 6000
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 2.2329096530401924,
|
| 122 |
-
"grad_norm": 1.
|
| 123 |
-
"learning_rate": 4.
|
| 124 |
-
"loss": 1.
|
| 125 |
"step": 6500
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 2.404671934043284,
|
| 129 |
-
"grad_norm": 2.
|
| 130 |
-
"learning_rate": 4.
|
| 131 |
-
"loss": 1.
|
| 132 |
"step": 7000
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.5764342150463757,
|
| 136 |
-
"grad_norm":
|
| 137 |
-
"learning_rate": 4.
|
| 138 |
-
"loss": 1.
|
| 139 |
"step": 7500
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.7481964960494674,
|
| 143 |
-
"grad_norm": 1.
|
| 144 |
-
"learning_rate": 4.
|
| 145 |
-
"loss": 1.
|
| 146 |
"step": 8000
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 2.9199587770525595,
|
| 150 |
-
"grad_norm":
|
| 151 |
-
"learning_rate": 4.
|
| 152 |
-
"loss": 1.
|
| 153 |
"step": 8500
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 3.0,
|
| 157 |
-
"eval_accuracy": 0.
|
| 158 |
-
"eval_f1": 0.
|
| 159 |
-
"eval_loss": 1.
|
| 160 |
-
"eval_precision": 0.
|
| 161 |
-
"eval_recall": 0.
|
| 162 |
-
"eval_runtime": 4.
|
| 163 |
-
"eval_samples_per_second":
|
| 164 |
-
"eval_steps_per_second":
|
| 165 |
"step": 8733
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 3.091721058055651,
|
| 169 |
-
"grad_norm": 1.
|
| 170 |
-
"learning_rate":
|
| 171 |
-
"loss": 1.
|
| 172 |
"step": 9000
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 3.2634833390587428,
|
| 176 |
-
"grad_norm": 1.
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss": 1.
|
| 179 |
"step": 9500
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 3.4352456200618344,
|
| 183 |
-
"grad_norm": 2.
|
| 184 |
-
"learning_rate":
|
| 185 |
-
"loss": 1.
|
| 186 |
"step": 10000
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 3.607007901064926,
|
| 190 |
-
"grad_norm": 2.
|
| 191 |
-
"learning_rate":
|
| 192 |
-
"loss": 1.
|
| 193 |
"step": 10500
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 3.7787701820680177,
|
| 197 |
-
"grad_norm":
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 1.
|
| 200 |
"step": 11000
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 3.9505324630711094,
|
| 204 |
-
"grad_norm":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 1.
|
| 207 |
"step": 11500
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 4.0,
|
| 211 |
-
"eval_accuracy": 0.
|
| 212 |
-
"eval_f1": 0.
|
| 213 |
-
"eval_loss": 1.
|
| 214 |
-
"eval_precision": 0.
|
| 215 |
-
"eval_recall": 0.
|
| 216 |
-
"eval_runtime": 4.
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second":
|
| 219 |
"step": 11644
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 4.1222947440742015,
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 1.
|
| 226 |
"step": 12000
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 4.294057025077293,
|
| 230 |
-
"grad_norm": 1.
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 1.
|
| 233 |
"step": 12500
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 4.465819306080385,
|
| 237 |
-
"grad_norm": 2.
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 1.
|
| 240 |
"step": 13000
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 4.637581587083476,
|
| 244 |
-
"grad_norm": 1.
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 1.
|
| 247 |
"step": 13500
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 4.809343868086568,
|
| 251 |
-
"grad_norm":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 1.
|
| 254 |
"step": 14000
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 4.98110614908966,
|
| 258 |
-
"grad_norm": 1.
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 1.
|
| 261 |
"step": 14500
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 5.0,
|
| 265 |
-
"eval_accuracy": 0.
|
| 266 |
-
"eval_f1": 0.
|
| 267 |
-
"eval_loss": 1.
|
| 268 |
-
"eval_precision": 0.
|
| 269 |
-
"eval_recall": 0.
|
| 270 |
-
"eval_runtime": 4.
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second":
|
| 273 |
"step": 14555
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 5.152868430092751,
|
| 277 |
-
"grad_norm":
|
| 278 |
-
"learning_rate":
|
| 279 |
-
"loss": 1.
|
| 280 |
"step": 15000
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 5.3246307110958435,
|
| 284 |
-
"grad_norm":
|
| 285 |
-
"learning_rate":
|
| 286 |
-
"loss": 1.
|
| 287 |
"step": 15500
|
| 288 |
},
|
| 289 |
{
|
| 290 |
"epoch": 5.496392992098935,
|
| 291 |
-
"grad_norm": 1.
|
| 292 |
-
"learning_rate":
|
| 293 |
-
"loss": 1.
|
| 294 |
"step": 16000
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 5.668155273102027,
|
| 298 |
-
"grad_norm":
|
| 299 |
-
"learning_rate":
|
| 300 |
-
"loss": 1.
|
| 301 |
"step": 16500
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 5.839917554105119,
|
| 305 |
-
"grad_norm":
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss": 1.
|
| 308 |
"step": 17000
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 6.0,
|
| 312 |
-
"eval_accuracy": 0.
|
| 313 |
-
"eval_f1": 0.
|
| 314 |
-
"eval_loss": 1.
|
| 315 |
-
"eval_precision": 0.
|
| 316 |
-
"eval_recall": 0.
|
| 317 |
-
"eval_runtime": 4.
|
| 318 |
-
"eval_samples_per_second":
|
| 319 |
-
"eval_steps_per_second":
|
| 320 |
"step": 17466
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 6.01167983510821,
|
| 324 |
-
"grad_norm": 1.
|
| 325 |
-
"learning_rate":
|
| 326 |
-
"loss": 1.
|
| 327 |
"step": 17500
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 6.183442116111302,
|
| 331 |
-
"grad_norm":
|
| 332 |
-
"learning_rate":
|
| 333 |
-
"loss": 1.
|
| 334 |
"step": 18000
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 6.3552043971143934,
|
| 338 |
-
"grad_norm":
|
| 339 |
-
"learning_rate":
|
| 340 |
-
"loss": 1.
|
| 341 |
"step": 18500
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 6.5269666781174855,
|
| 345 |
-
"grad_norm":
|
| 346 |
-
"learning_rate":
|
| 347 |
-
"loss": 1.
|
| 348 |
"step": 19000
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 6.698728959120577,
|
| 352 |
-
"grad_norm":
|
| 353 |
-
"learning_rate":
|
| 354 |
-
"loss": 1.
|
| 355 |
"step": 19500
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 6.870491240123669,
|
| 359 |
-
"grad_norm":
|
| 360 |
-
"learning_rate":
|
| 361 |
-
"loss": 1.
|
| 362 |
"step": 20000
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 7.0,
|
| 366 |
-
"eval_accuracy": 0.
|
| 367 |
-
"eval_f1": 0.
|
| 368 |
-
"eval_loss": 1.
|
| 369 |
-
"eval_precision": 0.
|
| 370 |
-
"eval_recall": 0.
|
| 371 |
-
"eval_runtime": 4.
|
| 372 |
-
"eval_samples_per_second":
|
| 373 |
-
"eval_steps_per_second":
|
| 374 |
"step": 20377
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 7.042253521126761,
|
| 378 |
-
"grad_norm":
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 1.
|
| 381 |
"step": 20500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 7.214015802129852,
|
| 385 |
-
"grad_norm": 2.
|
| 386 |
-
"learning_rate":
|
| 387 |
-
"loss": 1.
|
| 388 |
"step": 21000
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 7.385778083132944,
|
| 392 |
-
"grad_norm": 1.
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss": 1.
|
| 395 |
"step": 21500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 7.5575403641360355,
|
| 399 |
-
"grad_norm":
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss": 1.
|
| 402 |
"step": 22000
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 7.729302645139128,
|
| 406 |
-
"grad_norm":
|
| 407 |
-
"learning_rate":
|
| 408 |
-
"loss": 1.
|
| 409 |
"step": 22500
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 7.901064926142219,
|
| 413 |
-
"grad_norm": 3.
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 1.
|
| 416 |
"step": 23000
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 8.0,
|
| 420 |
-
"eval_accuracy": 0.
|
| 421 |
-
"eval_f1": 0.
|
| 422 |
-
"eval_loss": 1.
|
| 423 |
-
"eval_precision": 0.
|
| 424 |
-
"eval_recall": 0.
|
| 425 |
-
"eval_runtime": 4.
|
| 426 |
-
"eval_samples_per_second":
|
| 427 |
-
"eval_steps_per_second":
|
| 428 |
"step": 23288
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 8.07282720714531,
|
| 432 |
-
"grad_norm":
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"loss": 1.
|
| 435 |
"step": 23500
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 8.244589488148403,
|
| 439 |
-
"grad_norm":
|
| 440 |
-
"learning_rate":
|
| 441 |
-
"loss": 1.
|
| 442 |
"step": 24000
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 8.416351769151495,
|
| 446 |
-
"grad_norm": 1.
|
| 447 |
-
"learning_rate":
|
| 448 |
-
"loss": 1.
|
| 449 |
"step": 24500
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 8.588114050154585,
|
| 453 |
-
"grad_norm":
|
| 454 |
-
"learning_rate":
|
| 455 |
-
"loss": 1.
|
| 456 |
"step": 25000
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 8.759876331157677,
|
| 460 |
-
"grad_norm":
|
| 461 |
-
"learning_rate":
|
| 462 |
-
"loss": 1.
|
| 463 |
"step": 25500
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 8.93163861216077,
|
| 467 |
-
"grad_norm":
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 1.
|
| 470 |
"step": 26000
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 9.0,
|
| 474 |
-
"eval_accuracy": 0.
|
| 475 |
-
"eval_f1": 0.
|
| 476 |
-
"eval_loss": 1.
|
| 477 |
-
"eval_precision": 0.
|
| 478 |
-
"eval_recall": 0.
|
| 479 |
-
"eval_runtime": 4.
|
| 480 |
-
"eval_samples_per_second":
|
| 481 |
-
"eval_steps_per_second":
|
| 482 |
"step": 26199
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 9.103400893163862,
|
| 486 |
-
"grad_norm": 2.
|
| 487 |
-
"learning_rate":
|
| 488 |
-
"loss": 1.
|
| 489 |
"step": 26500
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 9.275163174166954,
|
| 493 |
-
"grad_norm":
|
| 494 |
-
"learning_rate":
|
| 495 |
-
"loss": 1.
|
| 496 |
"step": 27000
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 9.446925455170044,
|
| 500 |
-
"grad_norm":
|
| 501 |
-
"learning_rate":
|
| 502 |
-
"loss": 1.
|
| 503 |
"step": 27500
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 9.618687736173136,
|
| 507 |
-
"grad_norm":
|
| 508 |
-
"learning_rate":
|
| 509 |
-
"loss": 1.
|
| 510 |
"step": 28000
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 9.790450017176228,
|
| 514 |
-
"grad_norm":
|
| 515 |
-
"learning_rate":
|
| 516 |
-
"loss": 1.
|
| 517 |
"step": 28500
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 9.96221229817932,
|
| 521 |
-
"grad_norm":
|
| 522 |
-
"learning_rate":
|
| 523 |
-
"loss": 1.
|
| 524 |
"step": 29000
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 10.0,
|
| 528 |
-
"eval_accuracy": 0.
|
| 529 |
-
"eval_f1": 0.
|
| 530 |
-
"eval_loss":
|
| 531 |
-
"eval_precision": 0.
|
| 532 |
-
"eval_recall": 0.
|
| 533 |
-
"eval_runtime": 4.
|
| 534 |
-
"eval_samples_per_second":
|
| 535 |
-
"eval_steps_per_second":
|
| 536 |
"step": 29110
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 10.13397457918241,
|
| 540 |
-
"grad_norm":
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss": 1.
|
| 543 |
"step": 29500
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 10.305736860185503,
|
| 547 |
-
"grad_norm":
|
| 548 |
-
"learning_rate":
|
| 549 |
-
"loss": 1.
|
| 550 |
"step": 30000
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 10.477499141188595,
|
| 554 |
-
"grad_norm":
|
| 555 |
-
"learning_rate":
|
| 556 |
-
"loss": 1.
|
| 557 |
"step": 30500
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 10.649261422191687,
|
| 561 |
-
"grad_norm":
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 1.
|
| 564 |
"step": 31000
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 10.82102370319478,
|
| 568 |
-
"grad_norm":
|
| 569 |
-
"learning_rate":
|
| 570 |
-
"loss": 1.
|
| 571 |
"step": 31500
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 10.99278598419787,
|
| 575 |
-
"grad_norm":
|
| 576 |
-
"learning_rate":
|
| 577 |
-
"loss": 1.
|
| 578 |
"step": 32000
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 11.0,
|
| 582 |
-
"eval_accuracy": 0.
|
| 583 |
-
"eval_f1": 0.
|
| 584 |
-
"eval_loss":
|
| 585 |
-
"eval_precision": 0.
|
| 586 |
-
"eval_recall": 0.
|
| 587 |
-
"eval_runtime": 4.
|
| 588 |
-
"eval_samples_per_second":
|
| 589 |
-
"eval_steps_per_second":
|
| 590 |
"step": 32021
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 11.164548265200962,
|
| 594 |
-
"grad_norm":
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 1.
|
| 597 |
"step": 32500
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 11.336310546204054,
|
| 601 |
-
"grad_norm":
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 1.
|
| 604 |
"step": 33000
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 11.508072827207146,
|
| 608 |
-
"grad_norm":
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 1.
|
| 611 |
"step": 33500
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 11.679835108210238,
|
| 615 |
-
"grad_norm":
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 1.
|
| 618 |
"step": 34000
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 11.851597389213328,
|
| 622 |
-
"grad_norm":
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 1.
|
| 625 |
"step": 34500
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 12.0,
|
| 629 |
-
"eval_accuracy": 0.
|
| 630 |
-
"eval_f1": 0.
|
| 631 |
-
"eval_loss":
|
| 632 |
-
"eval_precision": 0.
|
| 633 |
-
"eval_recall": 0.
|
| 634 |
-
"eval_runtime": 4.
|
| 635 |
-
"eval_samples_per_second":
|
| 636 |
-
"eval_steps_per_second":
|
| 637 |
"step": 34932
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 12.02335967021642,
|
| 641 |
-
"grad_norm": 0.
|
| 642 |
-
"learning_rate":
|
| 643 |
-
"loss": 1.
|
| 644 |
"step": 35000
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 12.195121951219512,
|
| 648 |
-
"grad_norm": 0.
|
| 649 |
-
"learning_rate":
|
| 650 |
-
"loss": 1.
|
| 651 |
"step": 35500
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 12.366884232222604,
|
| 655 |
-
"grad_norm":
|
| 656 |
-
"learning_rate":
|
| 657 |
-
"loss": 1.
|
| 658 |
"step": 36000
|
| 659 |
},
|
| 660 |
{
|
| 661 |
"epoch": 12.538646513225697,
|
| 662 |
-
"grad_norm":
|
| 663 |
-
"learning_rate":
|
| 664 |
-
"loss": 1.
|
| 665 |
"step": 36500
|
| 666 |
},
|
| 667 |
{
|
| 668 |
"epoch": 12.710408794228787,
|
| 669 |
-
"grad_norm":
|
| 670 |
-
"learning_rate":
|
| 671 |
-
"loss": 1.
|
| 672 |
"step": 37000
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 12.882171075231879,
|
| 676 |
-
"grad_norm":
|
| 677 |
-
"learning_rate":
|
| 678 |
-
"loss": 1.
|
| 679 |
"step": 37500
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 13.0,
|
| 683 |
-
"eval_accuracy": 0.
|
| 684 |
-
"eval_f1": 0.
|
| 685 |
-
"eval_loss":
|
| 686 |
-
"eval_precision": 0.
|
| 687 |
-
"eval_recall": 0.
|
| 688 |
-
"eval_runtime": 4.
|
| 689 |
-
"eval_samples_per_second": 668.
|
| 690 |
-
"eval_steps_per_second": 83.
|
| 691 |
"step": 37843
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 13.053933356234971,
|
| 695 |
-
"grad_norm":
|
| 696 |
-
"learning_rate":
|
| 697 |
-
"loss": 1.
|
| 698 |
"step": 38000
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 13.225695637238063,
|
| 702 |
-
"grad_norm":
|
| 703 |
-
"learning_rate":
|
| 704 |
-
"loss": 1.
|
| 705 |
"step": 38500
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 13.397457918241154,
|
| 709 |
-
"grad_norm":
|
| 710 |
-
"learning_rate":
|
| 711 |
-
"loss": 1.
|
| 712 |
"step": 39000
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 13.569220199244246,
|
| 716 |
-
"grad_norm": 0.
|
| 717 |
-
"learning_rate":
|
| 718 |
-
"loss": 1.
|
| 719 |
"step": 39500
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 13.740982480247338,
|
| 723 |
-
"grad_norm": 0.
|
| 724 |
-
"learning_rate":
|
| 725 |
-
"loss": 1.
|
| 726 |
"step": 40000
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 13.91274476125043,
|
| 730 |
-
"grad_norm": 0.
|
| 731 |
-
"learning_rate": 3.
|
| 732 |
-
"loss": 1.
|
| 733 |
"step": 40500
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 14.0,
|
| 737 |
-
"eval_accuracy": 0.
|
| 738 |
-
"eval_f1": 0.
|
| 739 |
-
"eval_loss":
|
| 740 |
-
"eval_precision": 0.
|
| 741 |
-
"eval_recall": 0.
|
| 742 |
-
"eval_runtime": 4.
|
| 743 |
-
"eval_samples_per_second":
|
| 744 |
-
"eval_steps_per_second": 83.
|
| 745 |
"step": 40754
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 14.084507042253522,
|
| 749 |
-
"grad_norm":
|
| 750 |
-
"learning_rate": 3.
|
| 751 |
-
"loss": 1.
|
| 752 |
"step": 41000
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 14.256269323256612,
|
| 756 |
-
"grad_norm": 0.
|
| 757 |
-
"learning_rate":
|
| 758 |
-
"loss": 1.
|
| 759 |
"step": 41500
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 14.428031604259704,
|
| 763 |
-
"grad_norm": 0.
|
| 764 |
-
"learning_rate":
|
| 765 |
-
"loss": 1.
|
| 766 |
"step": 42000
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 14.599793885262796,
|
| 770 |
-
"grad_norm": 0.
|
| 771 |
-
"learning_rate":
|
| 772 |
-
"loss": 1.
|
| 773 |
"step": 42500
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 14.771556166265889,
|
| 777 |
-
"grad_norm":
|
| 778 |
-
"learning_rate":
|
| 779 |
-
"loss": 1.
|
| 780 |
"step": 43000
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 14.943318447268979,
|
| 784 |
-
"grad_norm": 0.
|
| 785 |
-
"learning_rate":
|
| 786 |
-
"loss": 1.
|
| 787 |
"step": 43500
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 15.0,
|
| 791 |
-
"eval_accuracy": 0.
|
| 792 |
-
"eval_f1": 0.
|
| 793 |
-
"eval_loss":
|
| 794 |
-
"eval_precision": 0.
|
| 795 |
-
"eval_recall": 0.
|
| 796 |
-
"eval_runtime": 4.
|
| 797 |
-
"eval_samples_per_second":
|
| 798 |
-
"eval_steps_per_second": 83.
|
| 799 |
"step": 43665
|
| 800 |
},
|
| 801 |
{
|
| 802 |
-
"epoch": 15.
|
| 803 |
-
"
|
| 804 |
-
"
|
| 805 |
-
"
|
| 806 |
-
"
|
| 807 |
-
|
| 808 |
-
|
| 809 |
-
"epoch": 15.286843009275163,
|
| 810 |
-
"grad_norm": 3.0774002075195312,
|
| 811 |
-
"learning_rate": 3.089144623840605e-05,
|
| 812 |
-
"loss": 1.7126,
|
| 813 |
-
"step": 44500
|
| 814 |
-
},
|
| 815 |
-
{
|
| 816 |
-
"epoch": 15.458605290278255,
|
| 817 |
-
"grad_norm": 0.6177487373352051,
|
| 818 |
-
"learning_rate": 3.0676743387152185e-05,
|
| 819 |
-
"loss": 1.7136,
|
| 820 |
-
"step": 45000
|
| 821 |
-
},
|
| 822 |
-
{
|
| 823 |
-
"epoch": 15.630367571281347,
|
| 824 |
-
"grad_norm": 1.545906901359558,
|
| 825 |
-
"learning_rate": 3.046204053589832e-05,
|
| 826 |
-
"loss": 1.7144,
|
| 827 |
-
"step": 45500
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 15.802129852284438,
|
| 831 |
-
"grad_norm": 0.31795910000801086,
|
| 832 |
-
"learning_rate": 3.0247337684644455e-05,
|
| 833 |
-
"loss": 1.7142,
|
| 834 |
-
"step": 46000
|
| 835 |
-
},
|
| 836 |
-
{
|
| 837 |
-
"epoch": 15.97389213328753,
|
| 838 |
-
"grad_norm": 0.0434710867702961,
|
| 839 |
-
"learning_rate": 3.0032634833390588e-05,
|
| 840 |
-
"loss": 1.7154,
|
| 841 |
-
"step": 46500
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 16.0,
|
| 845 |
-
"eval_accuracy": 0.8817523789578398,
|
| 846 |
-
"eval_f1": 0.6559375134114416,
|
| 847 |
-
"eval_loss": 2.02302885055542,
|
| 848 |
-
"eval_precision": 0.6456027709723747,
|
| 849 |
-
"eval_recall": 0.6666085136078158,
|
| 850 |
-
"eval_runtime": 4.3521,
|
| 851 |
-
"eval_samples_per_second": 668.643,
|
| 852 |
-
"eval_steps_per_second": 83.638,
|
| 853 |
-
"step": 46576
|
| 854 |
-
},
|
| 855 |
-
{
|
| 856 |
-
"epoch": 16.14565441429062,
|
| 857 |
-
"grad_norm": 0.30855801701545715,
|
| 858 |
-
"learning_rate": 2.9817931982136728e-05,
|
| 859 |
-
"loss": 1.7105,
|
| 860 |
-
"step": 47000
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 16.317416695293712,
|
| 864 |
-
"grad_norm": 0.8510277271270752,
|
| 865 |
-
"learning_rate": 2.9603229130882858e-05,
|
| 866 |
-
"loss": 1.7127,
|
| 867 |
-
"step": 47500
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 16.489178976296806,
|
| 871 |
-
"grad_norm": 1.7923400402069092,
|
| 872 |
-
"learning_rate": 2.9388526279628997e-05,
|
| 873 |
-
"loss": 1.7119,
|
| 874 |
-
"step": 48000
|
| 875 |
-
},
|
| 876 |
-
{
|
| 877 |
-
"epoch": 16.660941257299896,
|
| 878 |
-
"grad_norm": 4.354673862457275,
|
| 879 |
-
"learning_rate": 2.917382342837513e-05,
|
| 880 |
-
"loss": 1.7133,
|
| 881 |
-
"step": 48500
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 16.83270353830299,
|
| 885 |
-
"grad_norm": 0.20724855363368988,
|
| 886 |
-
"learning_rate": 2.8959120577121267e-05,
|
| 887 |
-
"loss": 1.7121,
|
| 888 |
-
"step": 49000
|
| 889 |
-
},
|
| 890 |
-
{
|
| 891 |
-
"epoch": 17.0,
|
| 892 |
-
"eval_accuracy": 0.8831136533200696,
|
| 893 |
-
"eval_f1": 0.6562859946248026,
|
| 894 |
-
"eval_loss": 2.0242502689361572,
|
| 895 |
-
"eval_precision": 0.6422309426400601,
|
| 896 |
-
"eval_recall": 0.670969993021633,
|
| 897 |
-
"eval_runtime": 4.3469,
|
| 898 |
-
"eval_samples_per_second": 669.449,
|
| 899 |
-
"eval_steps_per_second": 83.739,
|
| 900 |
-
"step": 49487
|
| 901 |
-
},
|
| 902 |
-
{
|
| 903 |
-
"epoch": 17.00446581930608,
|
| 904 |
-
"grad_norm": 5.177857398986816,
|
| 905 |
-
"learning_rate": 2.87444177258674e-05,
|
| 906 |
-
"loss": 1.7127,
|
| 907 |
-
"step": 49500
|
| 908 |
-
},
|
| 909 |
-
{
|
| 910 |
-
"epoch": 17.17622810030917,
|
| 911 |
-
"grad_norm": 3.216094732284546,
|
| 912 |
-
"learning_rate": 2.852971487461354e-05,
|
| 913 |
-
"loss": 1.7098,
|
| 914 |
-
"step": 50000
|
| 915 |
-
},
|
| 916 |
-
{
|
| 917 |
-
"epoch": 17.347990381312265,
|
| 918 |
-
"grad_norm": 2.916612148284912,
|
| 919 |
-
"learning_rate": 2.8315012023359673e-05,
|
| 920 |
-
"loss": 1.71,
|
| 921 |
-
"step": 50500
|
| 922 |
-
},
|
| 923 |
-
{
|
| 924 |
-
"epoch": 17.519752662315355,
|
| 925 |
-
"grad_norm": 0.03734961524605751,
|
| 926 |
-
"learning_rate": 2.8100309172105803e-05,
|
| 927 |
-
"loss": 1.7106,
|
| 928 |
-
"step": 51000
|
| 929 |
-
},
|
| 930 |
-
{
|
| 931 |
-
"epoch": 17.69151494331845,
|
| 932 |
-
"grad_norm": 1.543533444404602,
|
| 933 |
-
"learning_rate": 2.7885606320851943e-05,
|
| 934 |
-
"loss": 1.7104,
|
| 935 |
-
"step": 51500
|
| 936 |
-
},
|
| 937 |
-
{
|
| 938 |
-
"epoch": 17.86327722432154,
|
| 939 |
-
"grad_norm": 0.31598055362701416,
|
| 940 |
-
"learning_rate": 2.7670903469598076e-05,
|
| 941 |
-
"loss": 1.7114,
|
| 942 |
-
"step": 52000
|
| 943 |
-
},
|
| 944 |
-
{
|
| 945 |
-
"epoch": 18.0,
|
| 946 |
-
"eval_accuracy": 0.8838466472074242,
|
| 947 |
-
"eval_f1": 0.6567732444944403,
|
| 948 |
-
"eval_loss": 2.019536018371582,
|
| 949 |
-
"eval_precision": 0.6515580736543909,
|
| 950 |
-
"eval_recall": 0.6620725750174459,
|
| 951 |
-
"eval_runtime": 4.3524,
|
| 952 |
-
"eval_samples_per_second": 668.593,
|
| 953 |
-
"eval_steps_per_second": 83.632,
|
| 954 |
-
"step": 52398
|
| 955 |
-
},
|
| 956 |
-
{
|
| 957 |
-
"epoch": 18.03503950532463,
|
| 958 |
-
"grad_norm": 0.3598534166812897,
|
| 959 |
-
"learning_rate": 2.7456200618344212e-05,
|
| 960 |
-
"loss": 1.7117,
|
| 961 |
-
"step": 52500
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 18.206801786327723,
|
| 965 |
-
"grad_norm": 0.020997876301407814,
|
| 966 |
-
"learning_rate": 2.7241497767090345e-05,
|
| 967 |
-
"loss": 1.7089,
|
| 968 |
-
"step": 53000
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 18.378564067330814,
|
| 972 |
-
"grad_norm": 1.392232894897461,
|
| 973 |
-
"learning_rate": 2.7026794915836485e-05,
|
| 974 |
-
"loss": 1.7088,
|
| 975 |
-
"step": 53500
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"epoch": 18.550326348333908,
|
| 979 |
-
"grad_norm": 0.47013697028160095,
|
| 980 |
-
"learning_rate": 2.681209206458262e-05,
|
| 981 |
-
"loss": 1.7095,
|
| 982 |
-
"step": 54000
|
| 983 |
-
},
|
| 984 |
-
{
|
| 985 |
-
"epoch": 18.722088629336998,
|
| 986 |
-
"grad_norm": 1.5354187488555908,
|
| 987 |
-
"learning_rate": 2.6597389213328755e-05,
|
| 988 |
-
"loss": 1.7097,
|
| 989 |
-
"step": 54500
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"epoch": 18.89385091034009,
|
| 993 |
-
"grad_norm": 0.10534074902534485,
|
| 994 |
-
"learning_rate": 2.6382686362074888e-05,
|
| 995 |
-
"loss": 1.7105,
|
| 996 |
-
"step": 55000
|
| 997 |
-
},
|
| 998 |
-
{
|
| 999 |
-
"epoch": 19.0,
|
| 1000 |
-
"eval_accuracy": 0.8828387806123117,
|
| 1001 |
-
"eval_f1": 0.6574315789473685,
|
| 1002 |
-
"eval_loss": 2.025520086288452,
|
| 1003 |
-
"eval_precision": 0.6354387107276575,
|
| 1004 |
-
"eval_recall": 0.6810013956734124,
|
| 1005 |
-
"eval_runtime": 4.3482,
|
| 1006 |
-
"eval_samples_per_second": 669.243,
|
| 1007 |
-
"eval_steps_per_second": 83.713,
|
| 1008 |
-
"step": 55309
|
| 1009 |
-
},
|
| 1010 |
-
{
|
| 1011 |
-
"epoch": 19.065613191343182,
|
| 1012 |
-
"grad_norm": 0.2419898957014084,
|
| 1013 |
-
"learning_rate": 2.6167983510821024e-05,
|
| 1014 |
-
"loss": 1.7098,
|
| 1015 |
-
"step": 55500
|
| 1016 |
-
},
|
| 1017 |
-
{
|
| 1018 |
-
"epoch": 19.237375472346272,
|
| 1019 |
-
"grad_norm": 0.1751754730939865,
|
| 1020 |
-
"learning_rate": 2.5953280659567158e-05,
|
| 1021 |
-
"loss": 1.7086,
|
| 1022 |
-
"step": 56000
|
| 1023 |
-
},
|
| 1024 |
-
{
|
| 1025 |
-
"epoch": 19.409137753349363,
|
| 1026 |
-
"grad_norm": 4.463948726654053,
|
| 1027 |
-
"learning_rate": 2.5738577808313297e-05,
|
| 1028 |
-
"loss": 1.7073,
|
| 1029 |
-
"step": 56500
|
| 1030 |
-
},
|
| 1031 |
-
{
|
| 1032 |
-
"epoch": 19.580900034352457,
|
| 1033 |
-
"grad_norm": 3.6637113094329834,
|
| 1034 |
-
"learning_rate": 2.552387495705943e-05,
|
| 1035 |
-
"loss": 1.7085,
|
| 1036 |
-
"step": 57000
|
| 1037 |
-
},
|
| 1038 |
-
{
|
| 1039 |
-
"epoch": 19.752662315355547,
|
| 1040 |
-
"grad_norm": 2.393986940383911,
|
| 1041 |
-
"learning_rate": 2.5309172105805567e-05,
|
| 1042 |
-
"loss": 1.7084,
|
| 1043 |
-
"step": 57500
|
| 1044 |
-
},
|
| 1045 |
-
{
|
| 1046 |
-
"epoch": 19.92442459635864,
|
| 1047 |
-
"grad_norm": 2.718120574951172,
|
| 1048 |
-
"learning_rate": 2.50944692545517e-05,
|
| 1049 |
-
"loss": 1.7086,
|
| 1050 |
-
"step": 58000
|
| 1051 |
-
},
|
| 1052 |
-
{
|
| 1053 |
-
"epoch": 20.0,
|
| 1054 |
-
"eval_accuracy": 0.8840691632089426,
|
| 1055 |
-
"eval_f1": 0.6621772325641245,
|
| 1056 |
-
"eval_loss": 2.0267066955566406,
|
| 1057 |
-
"eval_precision": 0.6513924050632911,
|
| 1058 |
-
"eval_recall": 0.6733251919050942,
|
| 1059 |
-
"eval_runtime": 4.3383,
|
| 1060 |
-
"eval_samples_per_second": 670.771,
|
| 1061 |
-
"eval_steps_per_second": 83.904,
|
| 1062 |
-
"step": 58220
|
| 1063 |
-
},
|
| 1064 |
-
{
|
| 1065 |
-
"epoch": 20.09618687736173,
|
| 1066 |
-
"grad_norm": 0.07868649810552597,
|
| 1067 |
-
"learning_rate": 2.4879766403297837e-05,
|
| 1068 |
-
"loss": 1.7079,
|
| 1069 |
-
"step": 58500
|
| 1070 |
-
},
|
| 1071 |
-
{
|
| 1072 |
-
"epoch": 20.26794915836482,
|
| 1073 |
-
"grad_norm": 1.5867220163345337,
|
| 1074 |
-
"learning_rate": 2.466506355204397e-05,
|
| 1075 |
-
"loss": 1.708,
|
| 1076 |
-
"step": 59000
|
| 1077 |
-
},
|
| 1078 |
-
{
|
| 1079 |
-
"epoch": 20.439711439367915,
|
| 1080 |
-
"grad_norm": 2.7590816020965576,
|
| 1081 |
-
"learning_rate": 2.4450360700790106e-05,
|
| 1082 |
-
"loss": 1.7076,
|
| 1083 |
-
"step": 59500
|
| 1084 |
-
},
|
| 1085 |
-
{
|
| 1086 |
-
"epoch": 20.611473720371006,
|
| 1087 |
-
"grad_norm": 0.02333156019449234,
|
| 1088 |
-
"learning_rate": 2.4235657849536243e-05,
|
| 1089 |
-
"loss": 1.708,
|
| 1090 |
-
"step": 60000
|
| 1091 |
-
},
|
| 1092 |
-
{
|
| 1093 |
-
"epoch": 20.7832360013741,
|
| 1094 |
-
"grad_norm": 1.262069821357727,
|
| 1095 |
-
"learning_rate": 2.4020954998282376e-05,
|
| 1096 |
-
"loss": 1.7083,
|
| 1097 |
-
"step": 60500
|
| 1098 |
-
},
|
| 1099 |
-
{
|
| 1100 |
-
"epoch": 20.95499828237719,
|
| 1101 |
-
"grad_norm": 1.6238000392913818,
|
| 1102 |
-
"learning_rate": 2.3806252147028512e-05,
|
| 1103 |
-
"loss": 1.7077,
|
| 1104 |
-
"step": 61000
|
| 1105 |
-
},
|
| 1106 |
-
{
|
| 1107 |
-
"epoch": 21.0,
|
| 1108 |
-
"eval_accuracy": 0.8828387806123117,
|
| 1109 |
-
"eval_f1": 0.6590735879414006,
|
| 1110 |
-
"eval_loss": 2.0343477725982666,
|
| 1111 |
-
"eval_precision": 0.6403653118314958,
|
| 1112 |
-
"eval_recall": 0.6789078855547802,
|
| 1113 |
-
"eval_runtime": 4.3449,
|
| 1114 |
-
"eval_samples_per_second": 669.757,
|
| 1115 |
-
"eval_steps_per_second": 83.777,
|
| 1116 |
-
"step": 61131
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 21.12676056338028,
|
| 1120 |
-
"grad_norm": 0.6878411173820496,
|
| 1121 |
-
"learning_rate": 2.359154929577465e-05,
|
| 1122 |
-
"loss": 1.7075,
|
| 1123 |
-
"step": 61500
|
| 1124 |
-
},
|
| 1125 |
-
{
|
| 1126 |
-
"epoch": 21.298522844383374,
|
| 1127 |
-
"grad_norm": 0.2594795227050781,
|
| 1128 |
-
"learning_rate": 2.3376846444520782e-05,
|
| 1129 |
-
"loss": 1.7066,
|
| 1130 |
-
"step": 62000
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 21.470285125386464,
|
| 1134 |
-
"grad_norm": 0.14187024533748627,
|
| 1135 |
-
"learning_rate": 2.316214359326692e-05,
|
| 1136 |
-
"loss": 1.7067,
|
| 1137 |
-
"step": 62500
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 21.64204740638956,
|
| 1141 |
-
"grad_norm": 1.2114301919937134,
|
| 1142 |
-
"learning_rate": 2.2947440742013055e-05,
|
| 1143 |
-
"loss": 1.7066,
|
| 1144 |
-
"step": 63000
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 21.81380968739265,
|
| 1148 |
-
"grad_norm": 0.41020047664642334,
|
| 1149 |
-
"learning_rate": 2.273273789075919e-05,
|
| 1150 |
-
"loss": 1.7069,
|
| 1151 |
-
"step": 63500
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 21.98557196839574,
|
| 1155 |
-
"grad_norm": 1.944765567779541,
|
| 1156 |
-
"learning_rate": 2.2518035039505325e-05,
|
| 1157 |
-
"loss": 1.7075,
|
| 1158 |
-
"step": 64000
|
| 1159 |
-
},
|
| 1160 |
-
{
|
| 1161 |
-
"epoch": 22.0,
|
| 1162 |
-
"eval_accuracy": 0.886019450516368,
|
| 1163 |
-
"eval_f1": 0.6647068995331143,
|
| 1164 |
-
"eval_loss": 2.025860548019409,
|
| 1165 |
-
"eval_precision": 0.6588961261570107,
|
| 1166 |
-
"eval_recall": 0.6706210746685276,
|
| 1167 |
-
"eval_runtime": 4.3463,
|
| 1168 |
-
"eval_samples_per_second": 669.53,
|
| 1169 |
-
"eval_steps_per_second": 83.749,
|
| 1170 |
-
"step": 64042
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"epoch": 22.157334249398833,
|
| 1174 |
-
"grad_norm": 0.3925967216491699,
|
| 1175 |
-
"learning_rate": 2.230333218825146e-05,
|
| 1176 |
-
"loss": 1.7058,
|
| 1177 |
-
"step": 64500
|
| 1178 |
-
},
|
| 1179 |
-
{
|
| 1180 |
-
"epoch": 22.329096530401923,
|
| 1181 |
-
"grad_norm": 2.5894014835357666,
|
| 1182 |
-
"learning_rate": 2.2088629336997598e-05,
|
| 1183 |
-
"loss": 1.707,
|
| 1184 |
-
"step": 65000
|
| 1185 |
-
},
|
| 1186 |
-
{
|
| 1187 |
-
"epoch": 22.500858811405017,
|
| 1188 |
-
"grad_norm": 2.7716064453125,
|
| 1189 |
-
"learning_rate": 2.187392648574373e-05,
|
| 1190 |
-
"loss": 1.7063,
|
| 1191 |
-
"step": 65500
|
| 1192 |
-
},
|
| 1193 |
-
{
|
| 1194 |
-
"epoch": 22.672621092408107,
|
| 1195 |
-
"grad_norm": 0.03647352755069733,
|
| 1196 |
-
"learning_rate": 2.1659223634489867e-05,
|
| 1197 |
-
"loss": 1.7067,
|
| 1198 |
-
"step": 66000
|
| 1199 |
-
},
|
| 1200 |
-
{
|
| 1201 |
-
"epoch": 22.844383373411198,
|
| 1202 |
-
"grad_norm": 0.1577221304178238,
|
| 1203 |
-
"learning_rate": 2.1444520783236004e-05,
|
| 1204 |
-
"loss": 1.706,
|
| 1205 |
-
"step": 66500
|
| 1206 |
-
},
|
| 1207 |
-
{
|
| 1208 |
-
"epoch": 23.0,
|
| 1209 |
-
"eval_accuracy": 0.8844618385057396,
|
| 1210 |
-
"eval_f1": 0.662218230035502,
|
| 1211 |
-
"eval_loss": 2.02994441986084,
|
| 1212 |
-
"eval_precision": 0.6496852706672261,
|
| 1213 |
-
"eval_recall": 0.6752442428471738,
|
| 1214 |
-
"eval_runtime": 4.5456,
|
| 1215 |
-
"eval_samples_per_second": 640.185,
|
| 1216 |
-
"eval_steps_per_second": 80.078,
|
| 1217 |
-
"step": 66953
|
| 1218 |
-
},
|
| 1219 |
-
{
|
| 1220 |
-
"epoch": 23.01614565441429,
|
| 1221 |
-
"grad_norm": 2.8254947662353516,
|
| 1222 |
-
"learning_rate": 2.1229817931982137e-05,
|
| 1223 |
-
"loss": 1.7066,
|
| 1224 |
-
"step": 67000
|
| 1225 |
-
},
|
| 1226 |
-
{
|
| 1227 |
-
"epoch": 23.187907935417382,
|
| 1228 |
-
"grad_norm": 0.07582961767911911,
|
| 1229 |
-
"learning_rate": 2.1015115080728273e-05,
|
| 1230 |
-
"loss": 1.7055,
|
| 1231 |
-
"step": 67500
|
| 1232 |
-
},
|
| 1233 |
-
{
|
| 1234 |
-
"epoch": 23.359670216420476,
|
| 1235 |
-
"grad_norm": 0.11683762818574905,
|
| 1236 |
-
"learning_rate": 2.080041222947441e-05,
|
| 1237 |
-
"loss": 1.7052,
|
| 1238 |
-
"step": 68000
|
| 1239 |
-
},
|
| 1240 |
-
{
|
| 1241 |
-
"epoch": 23.531432497423566,
|
| 1242 |
-
"grad_norm": 0.6018902063369751,
|
| 1243 |
-
"learning_rate": 2.0585709378220543e-05,
|
| 1244 |
-
"loss": 1.7053,
|
| 1245 |
-
"step": 68500
|
| 1246 |
-
},
|
| 1247 |
-
{
|
| 1248 |
-
"epoch": 23.703194778426656,
|
| 1249 |
-
"grad_norm": 0.0493299625813961,
|
| 1250 |
-
"learning_rate": 2.037100652696668e-05,
|
| 1251 |
-
"loss": 1.7052,
|
| 1252 |
-
"step": 69000
|
| 1253 |
-
},
|
| 1254 |
-
{
|
| 1255 |
-
"epoch": 23.87495705942975,
|
| 1256 |
-
"grad_norm": 0.7263774275779724,
|
| 1257 |
-
"learning_rate": 2.0156303675712816e-05,
|
| 1258 |
-
"loss": 1.7062,
|
| 1259 |
-
"step": 69500
|
| 1260 |
-
},
|
| 1261 |
-
{
|
| 1262 |
-
"epoch": 24.0,
|
| 1263 |
-
"eval_accuracy": 0.8855613293367715,
|
| 1264 |
-
"eval_f1": 0.6654007164127573,
|
| 1265 |
-
"eval_loss": 2.0291478633880615,
|
| 1266 |
-
"eval_precision": 0.6584949175706842,
|
| 1267 |
-
"eval_recall": 0.6724528960223308,
|
| 1268 |
-
"eval_runtime": 4.425,
|
| 1269 |
-
"eval_samples_per_second": 657.631,
|
| 1270 |
-
"eval_steps_per_second": 82.26,
|
| 1271 |
-
"step": 69864
|
| 1272 |
-
},
|
| 1273 |
-
{
|
| 1274 |
-
"epoch": 24.04671934043284,
|
| 1275 |
-
"grad_norm": 0.22631505131721497,
|
| 1276 |
-
"learning_rate": 1.994160082445895e-05,
|
| 1277 |
-
"loss": 1.7058,
|
| 1278 |
-
"step": 70000
|
| 1279 |
-
},
|
| 1280 |
-
{
|
| 1281 |
-
"epoch": 24.218481621435934,
|
| 1282 |
-
"grad_norm": 0.08843923360109329,
|
| 1283 |
-
"learning_rate": 1.9726897973205085e-05,
|
| 1284 |
-
"loss": 1.7051,
|
| 1285 |
-
"step": 70500
|
| 1286 |
-
},
|
| 1287 |
-
{
|
| 1288 |
-
"epoch": 24.390243902439025,
|
| 1289 |
-
"grad_norm": 0.615134060382843,
|
| 1290 |
-
"learning_rate": 1.9512195121951222e-05,
|
| 1291 |
-
"loss": 1.7052,
|
| 1292 |
-
"step": 71000
|
| 1293 |
-
},
|
| 1294 |
-
{
|
| 1295 |
-
"epoch": 24.562006183442115,
|
| 1296 |
-
"grad_norm": 0.013932738453149796,
|
| 1297 |
-
"learning_rate": 1.9297492270697355e-05,
|
| 1298 |
-
"loss": 1.7051,
|
| 1299 |
-
"step": 71500
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 24.73376846444521,
|
| 1303 |
-
"grad_norm": 3.4743807315826416,
|
| 1304 |
-
"learning_rate": 1.908278941944349e-05,
|
| 1305 |
-
"loss": 1.7058,
|
| 1306 |
-
"step": 72000
|
| 1307 |
-
},
|
| 1308 |
-
{
|
| 1309 |
-
"epoch": 24.9055307454483,
|
| 1310 |
-
"grad_norm": 0.03590023145079613,
|
| 1311 |
-
"learning_rate": 1.8868086568189628e-05,
|
| 1312 |
-
"loss": 1.7051,
|
| 1313 |
-
"step": 72500
|
| 1314 |
-
},
|
| 1315 |
-
{
|
| 1316 |
-
"epoch": 25.0,
|
| 1317 |
-
"eval_accuracy": 0.8849592272150159,
|
| 1318 |
-
"eval_f1": 0.6664947124064998,
|
| 1319 |
-
"eval_loss": 2.032705783843994,
|
| 1320 |
-
"eval_precision": 0.6570605187319885,
|
| 1321 |
-
"eval_recall": 0.6762037683182135,
|
| 1322 |
-
"eval_runtime": 4.3381,
|
| 1323 |
-
"eval_samples_per_second": 670.805,
|
| 1324 |
-
"eval_steps_per_second": 83.908,
|
| 1325 |
-
"step": 72775
|
| 1326 |
-
},
|
| 1327 |
-
{
|
| 1328 |
-
"epoch": 25.07729302645139,
|
| 1329 |
-
"grad_norm": 2.080662250518799,
|
| 1330 |
-
"learning_rate": 1.865338371693576e-05,
|
| 1331 |
-
"loss": 1.7049,
|
| 1332 |
-
"step": 73000
|
| 1333 |
-
},
|
| 1334 |
-
{
|
| 1335 |
-
"epoch": 25.249055307454483,
|
| 1336 |
-
"grad_norm": 0.029195208102464676,
|
| 1337 |
-
"learning_rate": 1.8438680865681898e-05,
|
| 1338 |
-
"loss": 1.7053,
|
| 1339 |
-
"step": 73500
|
| 1340 |
-
},
|
| 1341 |
-
{
|
| 1342 |
-
"epoch": 25.420817588457574,
|
| 1343 |
-
"grad_norm": 0.31326115131378174,
|
| 1344 |
-
"learning_rate": 1.8223978014428034e-05,
|
| 1345 |
-
"loss": 1.7049,
|
| 1346 |
-
"step": 74000
|
| 1347 |
-
},
|
| 1348 |
-
{
|
| 1349 |
-
"epoch": 25.592579869460668,
|
| 1350 |
-
"grad_norm": 0.01428903266787529,
|
| 1351 |
-
"learning_rate": 1.800927516317417e-05,
|
| 1352 |
-
"loss": 1.7047,
|
| 1353 |
-
"step": 74500
|
| 1354 |
-
},
|
| 1355 |
-
{
|
| 1356 |
-
"epoch": 25.764342150463758,
|
| 1357 |
-
"grad_norm": 1.265703797340393,
|
| 1358 |
-
"learning_rate": 1.7794572311920304e-05,
|
| 1359 |
-
"loss": 1.7049,
|
| 1360 |
-
"step": 75000
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"epoch": 25.93610443146685,
|
| 1364 |
-
"grad_norm": 0.12370016425848007,
|
| 1365 |
-
"learning_rate": 1.7579869460666437e-05,
|
| 1366 |
-
"loss": 1.7044,
|
| 1367 |
-
"step": 75500
|
| 1368 |
-
},
|
| 1369 |
-
{
|
| 1370 |
-
"epoch": 26.0,
|
| 1371 |
-
"eval_accuracy": 0.8851293865102946,
|
| 1372 |
-
"eval_f1": 0.6667517223781576,
|
| 1373 |
-
"eval_loss": 2.034836530685425,
|
| 1374 |
-
"eval_precision": 0.650539419087137,
|
| 1375 |
-
"eval_recall": 0.6837927424982554,
|
| 1376 |
-
"eval_runtime": 4.3502,
|
| 1377 |
-
"eval_samples_per_second": 668.933,
|
| 1378 |
-
"eval_steps_per_second": 83.674,
|
| 1379 |
-
"step": 75686
|
| 1380 |
-
},
|
| 1381 |
-
{
|
| 1382 |
-
"epoch": 26.107866712469942,
|
| 1383 |
-
"grad_norm": 0.7563213109970093,
|
| 1384 |
-
"learning_rate": 1.7365166609412573e-05,
|
| 1385 |
-
"loss": 1.7049,
|
| 1386 |
-
"step": 76000
|
| 1387 |
-
},
|
| 1388 |
-
{
|
| 1389 |
-
"epoch": 26.279628993473032,
|
| 1390 |
-
"grad_norm": 0.0820002630352974,
|
| 1391 |
-
"learning_rate": 1.7150463758158706e-05,
|
| 1392 |
-
"loss": 1.7043,
|
| 1393 |
-
"step": 76500
|
| 1394 |
-
},
|
| 1395 |
-
{
|
| 1396 |
-
"epoch": 26.451391274476126,
|
| 1397 |
-
"grad_norm": 0.0947314128279686,
|
| 1398 |
-
"learning_rate": 1.6935760906904843e-05,
|
| 1399 |
-
"loss": 1.7039,
|
| 1400 |
-
"step": 77000
|
| 1401 |
-
},
|
| 1402 |
-
{
|
| 1403 |
-
"epoch": 26.623153555479217,
|
| 1404 |
-
"grad_norm": 0.03729939088225365,
|
| 1405 |
-
"learning_rate": 1.672105805565098e-05,
|
| 1406 |
-
"loss": 1.7045,
|
| 1407 |
-
"step": 77500
|
| 1408 |
-
},
|
| 1409 |
-
{
|
| 1410 |
-
"epoch": 26.794915836482307,
|
| 1411 |
-
"grad_norm": 0.022032542154192924,
|
| 1412 |
-
"learning_rate": 1.6506355204397116e-05,
|
| 1413 |
-
"loss": 1.7046,
|
| 1414 |
-
"step": 78000
|
| 1415 |
-
},
|
| 1416 |
-
{
|
| 1417 |
-
"epoch": 26.9666781174854,
|
| 1418 |
-
"grad_norm": 0.01787804253399372,
|
| 1419 |
-
"learning_rate": 1.629165235314325e-05,
|
| 1420 |
-
"loss": 1.704,
|
| 1421 |
-
"step": 78500
|
| 1422 |
-
},
|
| 1423 |
-
{
|
| 1424 |
-
"epoch": 27.0,
|
| 1425 |
-
"eval_accuracy": 0.885482794277412,
|
| 1426 |
-
"eval_f1": 0.6641411967283685,
|
| 1427 |
-
"eval_loss": 2.0346953868865967,
|
| 1428 |
-
"eval_precision": 0.6556178820329763,
|
| 1429 |
-
"eval_recall": 0.6728890439637125,
|
| 1430 |
-
"eval_runtime": 4.3364,
|
| 1431 |
-
"eval_samples_per_second": 671.067,
|
| 1432 |
-
"eval_steps_per_second": 83.941,
|
| 1433 |
-
"step": 78597
|
| 1434 |
-
},
|
| 1435 |
-
{
|
| 1436 |
-
"epoch": 27.13844039848849,
|
| 1437 |
-
"grad_norm": 0.04579576849937439,
|
| 1438 |
-
"learning_rate": 1.6076949501889386e-05,
|
| 1439 |
-
"loss": 1.7036,
|
| 1440 |
-
"step": 79000
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"epoch": 27.310202679491585,
|
| 1444 |
-
"grad_norm": 0.01315494254231453,
|
| 1445 |
-
"learning_rate": 1.5862246650635522e-05,
|
| 1446 |
-
"loss": 1.704,
|
| 1447 |
-
"step": 79500
|
| 1448 |
-
},
|
| 1449 |
-
{
|
| 1450 |
-
"epoch": 27.481964960494675,
|
| 1451 |
-
"grad_norm": 0.014564316719770432,
|
| 1452 |
-
"learning_rate": 1.5647543799381655e-05,
|
| 1453 |
-
"loss": 1.7038,
|
| 1454 |
-
"step": 80000
|
| 1455 |
-
},
|
| 1456 |
-
{
|
| 1457 |
-
"epoch": 27.653727241497766,
|
| 1458 |
-
"grad_norm": 0.027286505326628685,
|
| 1459 |
-
"learning_rate": 1.543284094812779e-05,
|
| 1460 |
-
"loss": 1.7042,
|
| 1461 |
-
"step": 80500
|
| 1462 |
-
},
|
| 1463 |
-
{
|
| 1464 |
-
"epoch": 27.82548952250086,
|
| 1465 |
-
"grad_norm": 0.012170245870947838,
|
| 1466 |
-
"learning_rate": 1.5218138096873926e-05,
|
| 1467 |
-
"loss": 1.7041,
|
| 1468 |
-
"step": 81000
|
| 1469 |
-
},
|
| 1470 |
-
{
|
| 1471 |
-
"epoch": 27.99725180350395,
|
| 1472 |
-
"grad_norm": 0.10445314645767212,
|
| 1473 |
-
"learning_rate": 1.5003435245620063e-05,
|
| 1474 |
-
"loss": 1.7041,
|
| 1475 |
-
"step": 81500
|
| 1476 |
-
},
|
| 1477 |
-
{
|
| 1478 |
-
"epoch": 28.0,
|
| 1479 |
-
"eval_accuracy": 0.8848414246259768,
|
| 1480 |
-
"eval_f1": 0.665781243305771,
|
| 1481 |
-
"eval_loss": 2.039051055908203,
|
| 1482 |
-
"eval_precision": 0.6542056074766355,
|
| 1483 |
-
"eval_recall": 0.6777739009071877,
|
| 1484 |
-
"eval_runtime": 4.3543,
|
| 1485 |
-
"eval_samples_per_second": 668.309,
|
| 1486 |
-
"eval_steps_per_second": 83.596,
|
| 1487 |
-
"step": 81508
|
| 1488 |
-
},
|
| 1489 |
-
{
|
| 1490 |
-
"epoch": 28.169014084507044,
|
| 1491 |
-
"grad_norm": 0.03070581518113613,
|
| 1492 |
-
"learning_rate": 1.4788732394366198e-05,
|
| 1493 |
-
"loss": 1.7034,
|
| 1494 |
-
"step": 82000
|
| 1495 |
-
},
|
| 1496 |
-
{
|
| 1497 |
-
"epoch": 28.340776365510134,
|
| 1498 |
-
"grad_norm": 0.028482601046562195,
|
| 1499 |
-
"learning_rate": 1.4574029543112333e-05,
|
| 1500 |
-
"loss": 1.7034,
|
| 1501 |
-
"step": 82500
|
| 1502 |
-
},
|
| 1503 |
-
{
|
| 1504 |
-
"epoch": 28.512538646513224,
|
| 1505 |
-
"grad_norm": 0.020483843982219696,
|
| 1506 |
-
"learning_rate": 1.4359326691858469e-05,
|
| 1507 |
-
"loss": 1.7037,
|
| 1508 |
-
"step": 83000
|
| 1509 |
-
},
|
| 1510 |
-
{
|
| 1511 |
-
"epoch": 28.68430092751632,
|
| 1512 |
-
"grad_norm": 0.04633668065071106,
|
| 1513 |
-
"learning_rate": 1.4144623840604604e-05,
|
| 1514 |
-
"loss": 1.7038,
|
| 1515 |
-
"step": 83500
|
| 1516 |
-
},
|
| 1517 |
-
{
|
| 1518 |
-
"epoch": 28.85606320851941,
|
| 1519 |
-
"grad_norm": 0.013343285769224167,
|
| 1520 |
-
"learning_rate": 1.3929920989350739e-05,
|
| 1521 |
-
"loss": 1.7044,
|
| 1522 |
-
"step": 84000
|
| 1523 |
-
},
|
| 1524 |
-
{
|
| 1525 |
-
"epoch": 29.0,
|
| 1526 |
-
"eval_accuracy": 0.8849592272150159,
|
| 1527 |
-
"eval_f1": 0.6683048801517503,
|
| 1528 |
-
"eval_loss": 2.0383501052856445,
|
| 1529 |
-
"eval_precision": 0.6606716672349131,
|
| 1530 |
-
"eval_recall": 0.6761165387299372,
|
| 1531 |
-
"eval_runtime": 4.5322,
|
| 1532 |
-
"eval_samples_per_second": 642.076,
|
| 1533 |
-
"eval_steps_per_second": 80.315,
|
| 1534 |
-
"step": 84419
|
| 1535 |
-
},
|
| 1536 |
-
{
|
| 1537 |
-
"epoch": 29.027825489522503,
|
| 1538 |
-
"grad_norm": 0.012182236649096012,
|
| 1539 |
-
"learning_rate": 1.3715218138096875e-05,
|
| 1540 |
-
"loss": 1.7031,
|
| 1541 |
-
"step": 84500
|
| 1542 |
-
},
|
| 1543 |
-
{
|
| 1544 |
-
"epoch": 29.199587770525593,
|
| 1545 |
-
"grad_norm": 0.022931888699531555,
|
| 1546 |
-
"learning_rate": 1.350051528684301e-05,
|
| 1547 |
-
"loss": 1.7034,
|
| 1548 |
-
"step": 85000
|
| 1549 |
-
},
|
| 1550 |
-
{
|
| 1551 |
-
"epoch": 29.371350051528683,
|
| 1552 |
-
"grad_norm": 0.03491847962141037,
|
| 1553 |
-
"learning_rate": 1.3285812435589146e-05,
|
| 1554 |
-
"loss": 1.7031,
|
| 1555 |
-
"step": 85500
|
| 1556 |
-
},
|
| 1557 |
-
{
|
| 1558 |
-
"epoch": 29.543112332531777,
|
| 1559 |
-
"grad_norm": 0.7195144295692444,
|
| 1560 |
-
"learning_rate": 1.3071109584335281e-05,
|
| 1561 |
-
"loss": 1.703,
|
| 1562 |
-
"step": 86000
|
| 1563 |
-
},
|
| 1564 |
-
{
|
| 1565 |
-
"epoch": 29.714874613534867,
|
| 1566 |
-
"grad_norm": 0.06322001665830612,
|
| 1567 |
-
"learning_rate": 1.2856406733081416e-05,
|
| 1568 |
-
"loss": 1.7038,
|
| 1569 |
-
"step": 86500
|
| 1570 |
-
},
|
| 1571 |
-
{
|
| 1572 |
-
"epoch": 29.886636894537958,
|
| 1573 |
-
"grad_norm": 2.88450288772583,
|
| 1574 |
-
"learning_rate": 1.2641703881827552e-05,
|
| 1575 |
-
"loss": 1.7038,
|
| 1576 |
-
"step": 87000
|
| 1577 |
-
},
|
| 1578 |
-
{
|
| 1579 |
-
"epoch": 30.0,
|
| 1580 |
-
"eval_accuracy": 0.8862157881647665,
|
| 1581 |
-
"eval_f1": 0.6689958592132506,
|
| 1582 |
-
"eval_loss": 2.036111354827881,
|
| 1583 |
-
"eval_precision": 0.6616894197952219,
|
| 1584 |
-
"eval_recall": 0.6764654570830426,
|
| 1585 |
-
"eval_runtime": 4.3577,
|
| 1586 |
-
"eval_samples_per_second": 667.782,
|
| 1587 |
-
"eval_steps_per_second": 83.53,
|
| 1588 |
-
"step": 87330
|
| 1589 |
-
},
|
| 1590 |
-
{
|
| 1591 |
-
"epoch": 30.05839917554105,
|
| 1592 |
-
"grad_norm": 0.045289408415555954,
|
| 1593 |
-
"learning_rate": 1.2427001030573687e-05,
|
| 1594 |
-
"loss": 1.7034,
|
| 1595 |
-
"step": 87500
|
| 1596 |
-
},
|
| 1597 |
-
{
|
| 1598 |
-
"epoch": 30.230161456544142,
|
| 1599 |
-
"grad_norm": 0.08461955934762955,
|
| 1600 |
-
"learning_rate": 1.2212298179319822e-05,
|
| 1601 |
-
"loss": 1.703,
|
| 1602 |
-
"step": 88000
|
| 1603 |
-
},
|
| 1604 |
-
{
|
| 1605 |
-
"epoch": 30.401923737547236,
|
| 1606 |
-
"grad_norm": 0.019219454377889633,
|
| 1607 |
-
"learning_rate": 1.1997595328065957e-05,
|
| 1608 |
-
"loss": 1.7028,
|
| 1609 |
-
"step": 88500
|
| 1610 |
-
},
|
| 1611 |
-
{
|
| 1612 |
-
"epoch": 30.573686018550326,
|
| 1613 |
-
"grad_norm": 0.08018019050359726,
|
| 1614 |
-
"learning_rate": 1.1782892476812092e-05,
|
| 1615 |
-
"loss": 1.7035,
|
| 1616 |
-
"step": 89000
|
| 1617 |
-
},
|
| 1618 |
-
{
|
| 1619 |
-
"epoch": 30.745448299553416,
|
| 1620 |
-
"grad_norm": 0.022569868713617325,
|
| 1621 |
-
"learning_rate": 1.1568189625558228e-05,
|
| 1622 |
-
"loss": 1.7029,
|
| 1623 |
-
"step": 89500
|
| 1624 |
-
},
|
| 1625 |
-
{
|
| 1626 |
-
"epoch": 30.91721058055651,
|
| 1627 |
-
"grad_norm": 0.01143190823495388,
|
| 1628 |
-
"learning_rate": 1.1353486774304363e-05,
|
| 1629 |
-
"loss": 1.7043,
|
| 1630 |
-
"step": 90000
|
| 1631 |
-
},
|
| 1632 |
-
{
|
| 1633 |
-
"epoch": 31.0,
|
| 1634 |
-
"eval_accuracy": 0.8862157881647665,
|
| 1635 |
-
"eval_f1": 0.6686131386861313,
|
| 1636 |
-
"eval_loss": 2.036999225616455,
|
| 1637 |
-
"eval_precision": 0.6583798410282429,
|
| 1638 |
-
"eval_recall": 0.6791695743196092,
|
| 1639 |
-
"eval_runtime": 4.3764,
|
| 1640 |
-
"eval_samples_per_second": 664.936,
|
| 1641 |
-
"eval_steps_per_second": 83.174,
|
| 1642 |
-
"step": 90241
|
| 1643 |
-
},
|
| 1644 |
-
{
|
| 1645 |
-
"epoch": 31.0889728615596,
|
| 1646 |
-
"grad_norm": 0.020288735628128052,
|
| 1647 |
-
"learning_rate": 1.1138783923050498e-05,
|
| 1648 |
-
"loss": 1.7027,
|
| 1649 |
-
"step": 90500
|
| 1650 |
-
},
|
| 1651 |
-
{
|
| 1652 |
-
"epoch": 31.260735142562694,
|
| 1653 |
-
"grad_norm": 1.4007924795150757,
|
| 1654 |
-
"learning_rate": 1.0924081071796634e-05,
|
| 1655 |
-
"loss": 1.7031,
|
| 1656 |
-
"step": 91000
|
| 1657 |
-
},
|
| 1658 |
-
{
|
| 1659 |
-
"epoch": 31.432497423565785,
|
| 1660 |
-
"grad_norm": 0.026297271251678467,
|
| 1661 |
-
"learning_rate": 1.0709378220542769e-05,
|
| 1662 |
-
"loss": 1.7033,
|
| 1663 |
-
"step": 91500
|
| 1664 |
-
},
|
| 1665 |
-
{
|
| 1666 |
-
"epoch": 31.604259704568875,
|
| 1667 |
-
"grad_norm": 0.01724054105579853,
|
| 1668 |
-
"learning_rate": 1.0494675369288904e-05,
|
| 1669 |
-
"loss": 1.7033,
|
| 1670 |
-
"step": 92000
|
| 1671 |
-
},
|
| 1672 |
-
{
|
| 1673 |
-
"epoch": 31.77602198557197,
|
| 1674 |
-
"grad_norm": 0.022584540769457817,
|
| 1675 |
-
"learning_rate": 1.027997251803504e-05,
|
| 1676 |
-
"loss": 1.7029,
|
| 1677 |
-
"step": 92500
|
| 1678 |
-
},
|
| 1679 |
-
{
|
| 1680 |
-
"epoch": 31.94778426657506,
|
| 1681 |
-
"grad_norm": 0.020957598462700844,
|
| 1682 |
-
"learning_rate": 1.0065269666781175e-05,
|
| 1683 |
-
"loss": 1.7027,
|
| 1684 |
-
"step": 93000
|
| 1685 |
-
},
|
| 1686 |
-
{
|
| 1687 |
-
"epoch": 32.0,
|
| 1688 |
-
"eval_accuracy": 0.887498527467637,
|
| 1689 |
-
"eval_f1": 0.6720918279938325,
|
| 1690 |
-
"eval_loss": 2.0346181392669678,
|
| 1691 |
-
"eval_precision": 0.6602154156849546,
|
| 1692 |
-
"eval_recall": 0.6844033496161898,
|
| 1693 |
-
"eval_runtime": 4.3442,
|
| 1694 |
-
"eval_samples_per_second": 669.861,
|
| 1695 |
-
"eval_steps_per_second": 83.79,
|
| 1696 |
-
"step": 93152
|
| 1697 |
-
},
|
| 1698 |
-
{
|
| 1699 |
-
"epoch": 32.11954654757815,
|
| 1700 |
-
"grad_norm": 0.034752070903778076,
|
| 1701 |
-
"learning_rate": 9.850566815527312e-06,
|
| 1702 |
-
"loss": 1.7029,
|
| 1703 |
-
"step": 93500
|
| 1704 |
-
},
|
| 1705 |
-
{
|
| 1706 |
-
"epoch": 32.29130882858124,
|
| 1707 |
-
"grad_norm": 0.029328178614377975,
|
| 1708 |
-
"learning_rate": 9.635863964273446e-06,
|
| 1709 |
-
"loss": 1.7028,
|
| 1710 |
-
"step": 94000
|
| 1711 |
-
},
|
| 1712 |
-
{
|
| 1713 |
-
"epoch": 32.463071109584334,
|
| 1714 |
-
"grad_norm": 0.012389196082949638,
|
| 1715 |
-
"learning_rate": 9.421161113019581e-06,
|
| 1716 |
-
"loss": 1.7029,
|
| 1717 |
-
"step": 94500
|
| 1718 |
-
},
|
| 1719 |
-
{
|
| 1720 |
-
"epoch": 32.634833390587424,
|
| 1721 |
-
"grad_norm": 0.3913457989692688,
|
| 1722 |
-
"learning_rate": 9.206458261765718e-06,
|
| 1723 |
-
"loss": 1.703,
|
| 1724 |
-
"step": 95000
|
| 1725 |
-
},
|
| 1726 |
-
{
|
| 1727 |
-
"epoch": 32.80659567159052,
|
| 1728 |
-
"grad_norm": 0.018091492354869843,
|
| 1729 |
-
"learning_rate": 8.991755410511853e-06,
|
| 1730 |
-
"loss": 1.703,
|
| 1731 |
-
"step": 95500
|
| 1732 |
-
},
|
| 1733 |
-
{
|
| 1734 |
-
"epoch": 32.97835795259361,
|
| 1735 |
-
"grad_norm": 0.0414559505879879,
|
| 1736 |
-
"learning_rate": 8.777052559257987e-06,
|
| 1737 |
-
"loss": 1.7026,
|
| 1738 |
-
"step": 96000
|
| 1739 |
-
},
|
| 1740 |
-
{
|
| 1741 |
-
"epoch": 33.0,
|
| 1742 |
-
"eval_accuracy": 0.8870796738177201,
|
| 1743 |
-
"eval_f1": 0.6719724671972467,
|
| 1744 |
-
"eval_loss": 2.0373663902282715,
|
| 1745 |
-
"eval_precision": 0.6629318394024276,
|
| 1746 |
-
"eval_recall": 0.6812630844382415,
|
| 1747 |
-
"eval_runtime": 4.3395,
|
| 1748 |
-
"eval_samples_per_second": 670.591,
|
| 1749 |
-
"eval_steps_per_second": 83.881,
|
| 1750 |
-
"step": 96063
|
| 1751 |
-
},
|
| 1752 |
-
{
|
| 1753 |
-
"epoch": 33.1501202335967,
|
| 1754 |
-
"grad_norm": 1.3967928886413574,
|
| 1755 |
-
"learning_rate": 8.562349708004122e-06,
|
| 1756 |
-
"loss": 1.7026,
|
| 1757 |
-
"step": 96500
|
| 1758 |
-
},
|
| 1759 |
-
{
|
| 1760 |
-
"epoch": 33.32188251459979,
|
| 1761 |
-
"grad_norm": 0.0278925858438015,
|
| 1762 |
-
"learning_rate": 8.347646856750257e-06,
|
| 1763 |
-
"loss": 1.7029,
|
| 1764 |
-
"step": 97000
|
| 1765 |
-
},
|
| 1766 |
-
{
|
| 1767 |
-
"epoch": 33.49364479560288,
|
| 1768 |
-
"grad_norm": 0.0145077770575881,
|
| 1769 |
-
"learning_rate": 8.132944005496393e-06,
|
| 1770 |
-
"loss": 1.7026,
|
| 1771 |
-
"step": 97500
|
| 1772 |
-
},
|
| 1773 |
-
{
|
| 1774 |
-
"epoch": 33.66540707660598,
|
| 1775 |
-
"grad_norm": 0.025042984634637833,
|
| 1776 |
-
"learning_rate": 7.918241154242528e-06,
|
| 1777 |
-
"loss": 1.7027,
|
| 1778 |
-
"step": 98000
|
| 1779 |
-
},
|
| 1780 |
-
{
|
| 1781 |
-
"epoch": 33.83716935760907,
|
| 1782 |
-
"grad_norm": 0.01291943620890379,
|
| 1783 |
-
"learning_rate": 7.703538302988663e-06,
|
| 1784 |
-
"loss": 1.7025,
|
| 1785 |
-
"step": 98500
|
| 1786 |
-
},
|
| 1787 |
-
{
|
| 1788 |
-
"epoch": 34.0,
|
| 1789 |
-
"eval_accuracy": 0.8862026989882067,
|
| 1790 |
-
"eval_f1": 0.6707671279685631,
|
| 1791 |
-
"eval_loss": 2.038774251937866,
|
| 1792 |
-
"eval_precision": 0.6571811181787747,
|
| 1793 |
-
"eval_recall": 0.6849267271458479,
|
| 1794 |
-
"eval_runtime": 4.3422,
|
| 1795 |
-
"eval_samples_per_second": 670.172,
|
| 1796 |
-
"eval_steps_per_second": 83.829,
|
| 1797 |
-
"step": 98974
|
| 1798 |
-
},
|
| 1799 |
-
{
|
| 1800 |
-
"epoch": 34.00893163861216,
|
| 1801 |
-
"grad_norm": 0.014937439002096653,
|
| 1802 |
-
"learning_rate": 7.4888354517347995e-06,
|
| 1803 |
-
"loss": 1.7027,
|
| 1804 |
-
"step": 99000
|
| 1805 |
-
},
|
| 1806 |
-
{
|
| 1807 |
-
"epoch": 34.18069391961525,
|
| 1808 |
-
"grad_norm": 0.05787663906812668,
|
| 1809 |
-
"learning_rate": 7.274132600480934e-06,
|
| 1810 |
-
"loss": 1.7029,
|
| 1811 |
-
"step": 99500
|
| 1812 |
-
},
|
| 1813 |
-
{
|
| 1814 |
-
"epoch": 34.35245620061834,
|
| 1815 |
-
"grad_norm": 0.12616612017154694,
|
| 1816 |
-
"learning_rate": 7.05942974922707e-06,
|
| 1817 |
-
"loss": 1.7025,
|
| 1818 |
-
"step": 100000
|
| 1819 |
-
},
|
| 1820 |
-
{
|
| 1821 |
-
"epoch": 34.52421848162144,
|
| 1822 |
-
"grad_norm": 1.7043280601501465,
|
| 1823 |
-
"learning_rate": 6.844726897973206e-06,
|
| 1824 |
-
"loss": 1.7026,
|
| 1825 |
-
"step": 100500
|
| 1826 |
-
},
|
| 1827 |
-
{
|
| 1828 |
-
"epoch": 34.69598076262453,
|
| 1829 |
-
"grad_norm": 0.2174743413925171,
|
| 1830 |
-
"learning_rate": 6.6300240467193404e-06,
|
| 1831 |
-
"loss": 1.7026,
|
| 1832 |
-
"step": 101000
|
| 1833 |
-
},
|
| 1834 |
-
{
|
| 1835 |
-
"epoch": 34.86774304362762,
|
| 1836 |
-
"grad_norm": 0.018968598917126656,
|
| 1837 |
-
"learning_rate": 6.415321195465476e-06,
|
| 1838 |
-
"loss": 1.7024,
|
| 1839 |
-
"step": 101500
|
| 1840 |
-
},
|
| 1841 |
-
{
|
| 1842 |
-
"epoch": 35.0,
|
| 1843 |
-
"eval_accuracy": 0.8873152789957984,
|
| 1844 |
-
"eval_f1": 0.6722725312634755,
|
| 1845 |
-
"eval_loss": 2.0370359420776367,
|
| 1846 |
-
"eval_precision": 0.6647620672010915,
|
| 1847 |
-
"eval_recall": 0.6799546406140963,
|
| 1848 |
-
"eval_runtime": 4.5075,
|
| 1849 |
-
"eval_samples_per_second": 645.593,
|
| 1850 |
-
"eval_steps_per_second": 80.755,
|
| 1851 |
-
"step": 101885
|
| 1852 |
-
},
|
| 1853 |
-
{
|
| 1854 |
-
"epoch": 35.03950532463071,
|
| 1855 |
-
"grad_norm": 0.031130915507674217,
|
| 1856 |
-
"learning_rate": 6.200618344211612e-06,
|
| 1857 |
-
"loss": 1.7028,
|
| 1858 |
-
"step": 102000
|
| 1859 |
-
},
|
| 1860 |
-
{
|
| 1861 |
-
"epoch": 35.2112676056338,
|
| 1862 |
-
"grad_norm": 0.015709536150097847,
|
| 1863 |
-
"learning_rate": 5.9859154929577465e-06,
|
| 1864 |
-
"loss": 1.7026,
|
| 1865 |
-
"step": 102500
|
| 1866 |
-
},
|
| 1867 |
-
{
|
| 1868 |
-
"epoch": 35.3830298866369,
|
| 1869 |
-
"grad_norm": 0.013832608237862587,
|
| 1870 |
-
"learning_rate": 5.771212641703882e-06,
|
| 1871 |
-
"loss": 1.7023,
|
| 1872 |
-
"step": 103000
|
| 1873 |
-
},
|
| 1874 |
-
{
|
| 1875 |
-
"epoch": 35.55479216763999,
|
| 1876 |
-
"grad_norm": 0.033963147550821304,
|
| 1877 |
-
"learning_rate": 5.556509790450017e-06,
|
| 1878 |
-
"loss": 1.7025,
|
| 1879 |
-
"step": 103500
|
| 1880 |
-
},
|
| 1881 |
-
{
|
| 1882 |
-
"epoch": 35.72655444864308,
|
| 1883 |
-
"grad_norm": 0.010256431065499783,
|
| 1884 |
-
"learning_rate": 5.341806939196153e-06,
|
| 1885 |
-
"loss": 1.7025,
|
| 1886 |
-
"step": 104000
|
| 1887 |
-
},
|
| 1888 |
-
{
|
| 1889 |
-
"epoch": 35.89831672964617,
|
| 1890 |
-
"grad_norm": 0.01719123311340809,
|
| 1891 |
-
"learning_rate": 5.127104087942288e-06,
|
| 1892 |
-
"loss": 1.703,
|
| 1893 |
-
"step": 104500
|
| 1894 |
-
},
|
| 1895 |
-
{
|
| 1896 |
-
"epoch": 36.0,
|
| 1897 |
-
"eval_accuracy": 0.8867524444037226,
|
| 1898 |
-
"eval_f1": 0.6718547341115435,
|
| 1899 |
-
"eval_loss": 2.0409553050994873,
|
| 1900 |
-
"eval_precision": 0.6660380593176753,
|
| 1901 |
-
"eval_recall": 0.6777739009071877,
|
| 1902 |
-
"eval_runtime": 4.3391,
|
| 1903 |
-
"eval_samples_per_second": 670.65,
|
| 1904 |
-
"eval_steps_per_second": 83.889,
|
| 1905 |
-
"step": 104796
|
| 1906 |
-
},
|
| 1907 |
-
{
|
| 1908 |
-
"epoch": 36.07007901064926,
|
| 1909 |
-
"grad_norm": 0.010260261595249176,
|
| 1910 |
-
"learning_rate": 4.912401236688424e-06,
|
| 1911 |
-
"loss": 1.7023,
|
| 1912 |
-
"step": 105000
|
| 1913 |
-
},
|
| 1914 |
-
{
|
| 1915 |
-
"epoch": 36.24184129165236,
|
| 1916 |
-
"grad_norm": 0.016782447695732117,
|
| 1917 |
-
"learning_rate": 4.697698385434559e-06,
|
| 1918 |
-
"loss": 1.7022,
|
| 1919 |
-
"step": 105500
|
| 1920 |
-
},
|
| 1921 |
-
{
|
| 1922 |
-
"epoch": 36.41360357265545,
|
| 1923 |
-
"grad_norm": 0.017756333574652672,
|
| 1924 |
-
"learning_rate": 4.482995534180694e-06,
|
| 1925 |
-
"loss": 1.7027,
|
| 1926 |
-
"step": 106000
|
| 1927 |
-
},
|
| 1928 |
-
{
|
| 1929 |
-
"epoch": 36.58536585365854,
|
| 1930 |
-
"grad_norm": 0.02108193188905716,
|
| 1931 |
-
"learning_rate": 4.26829268292683e-06,
|
| 1932 |
-
"loss": 1.7027,
|
| 1933 |
-
"step": 106500
|
| 1934 |
-
},
|
| 1935 |
-
{
|
| 1936 |
-
"epoch": 36.75712813466163,
|
| 1937 |
-
"grad_norm": 0.023750385269522667,
|
| 1938 |
-
"learning_rate": 4.053589831672965e-06,
|
| 1939 |
-
"loss": 1.7027,
|
| 1940 |
-
"step": 107000
|
| 1941 |
-
},
|
| 1942 |
-
{
|
| 1943 |
-
"epoch": 36.92889041566472,
|
| 1944 |
-
"grad_norm": 0.01755833625793457,
|
| 1945 |
-
"learning_rate": 3.8388869804191e-06,
|
| 1946 |
-
"loss": 1.7023,
|
| 1947 |
-
"step": 107500
|
| 1948 |
-
},
|
| 1949 |
-
{
|
| 1950 |
-
"epoch": 37.0,
|
| 1951 |
-
"eval_accuracy": 0.8871058521708399,
|
| 1952 |
-
"eval_f1": 0.6730462519936204,
|
| 1953 |
-
"eval_loss": 2.039201498031616,
|
| 1954 |
-
"eval_precision": 0.6652748189177674,
|
| 1955 |
-
"eval_recall": 0.6810013956734124,
|
| 1956 |
-
"eval_runtime": 4.3606,
|
| 1957 |
-
"eval_samples_per_second": 667.332,
|
| 1958 |
-
"eval_steps_per_second": 83.474,
|
| 1959 |
-
"step": 107707
|
| 1960 |
-
},
|
| 1961 |
-
{
|
| 1962 |
-
"epoch": 37.100652696667815,
|
| 1963 |
-
"grad_norm": 0.00990867055952549,
|
| 1964 |
-
"learning_rate": 3.6241841291652353e-06,
|
| 1965 |
-
"loss": 1.7024,
|
| 1966 |
-
"step": 108000
|
| 1967 |
-
},
|
| 1968 |
-
{
|
| 1969 |
-
"epoch": 37.272414977670906,
|
| 1970 |
-
"grad_norm": 0.011056340299546719,
|
| 1971 |
-
"learning_rate": 3.409481277911371e-06,
|
| 1972 |
-
"loss": 1.7023,
|
| 1973 |
-
"step": 108500
|
| 1974 |
-
},
|
| 1975 |
-
{
|
| 1976 |
-
"epoch": 37.444177258673996,
|
| 1977 |
-
"grad_norm": 0.011399239301681519,
|
| 1978 |
-
"learning_rate": 3.194778426657506e-06,
|
| 1979 |
-
"loss": 1.7025,
|
| 1980 |
-
"step": 109000
|
| 1981 |
-
},
|
| 1982 |
-
{
|
| 1983 |
-
"epoch": 37.615939539677086,
|
| 1984 |
-
"grad_norm": 0.11473862081766129,
|
| 1985 |
-
"learning_rate": 2.9800755754036418e-06,
|
| 1986 |
-
"loss": 1.7024,
|
| 1987 |
-
"step": 109500
|
| 1988 |
-
},
|
| 1989 |
-
{
|
| 1990 |
-
"epoch": 37.78770182068018,
|
| 1991 |
-
"grad_norm": 0.013430794700980186,
|
| 1992 |
-
"learning_rate": 2.7653727241497766e-06,
|
| 1993 |
-
"loss": 1.7026,
|
| 1994 |
-
"step": 110000
|
| 1995 |
-
},
|
| 1996 |
-
{
|
| 1997 |
-
"epoch": 37.95946410168327,
|
| 1998 |
-
"grad_norm": 0.6538777351379395,
|
| 1999 |
-
"learning_rate": 2.5506698728959122e-06,
|
| 2000 |
-
"loss": 1.7022,
|
| 2001 |
-
"step": 110500
|
| 2002 |
-
},
|
| 2003 |
-
{
|
| 2004 |
-
"epoch": 38.0,
|
| 2005 |
-
"eval_accuracy": 0.8873545465254781,
|
| 2006 |
-
"eval_f1": 0.6726804123711341,
|
| 2007 |
-
"eval_loss": 2.0390825271606445,
|
| 2008 |
-
"eval_precision": 0.6626607989167231,
|
| 2009 |
-
"eval_recall": 0.6830076762037683,
|
| 2010 |
-
"eval_runtime": 4.3713,
|
| 2011 |
-
"eval_samples_per_second": 665.706,
|
| 2012 |
-
"eval_steps_per_second": 83.27,
|
| 2013 |
-
"step": 110618
|
| 2014 |
-
},
|
| 2015 |
-
{
|
| 2016 |
-
"epoch": 38.131226382686364,
|
| 2017 |
-
"grad_norm": 0.022718122228980064,
|
| 2018 |
-
"learning_rate": 2.3359670216420474e-06,
|
| 2019 |
-
"loss": 1.7021,
|
| 2020 |
-
"step": 111000
|
| 2021 |
-
},
|
| 2022 |
-
{
|
| 2023 |
-
"epoch": 38.302988663689455,
|
| 2024 |
-
"grad_norm": 0.00782406609505415,
|
| 2025 |
-
"learning_rate": 2.121264170388183e-06,
|
| 2026 |
-
"loss": 1.7024,
|
| 2027 |
-
"step": 111500
|
| 2028 |
-
},
|
| 2029 |
-
{
|
| 2030 |
-
"epoch": 38.474750944692545,
|
| 2031 |
-
"grad_norm": 0.06520986557006836,
|
| 2032 |
-
"learning_rate": 1.906561319134318e-06,
|
| 2033 |
-
"loss": 1.7025,
|
| 2034 |
-
"step": 112000
|
| 2035 |
-
},
|
| 2036 |
-
{
|
| 2037 |
-
"epoch": 38.646513225695635,
|
| 2038 |
-
"grad_norm": 0.011009753681719303,
|
| 2039 |
-
"learning_rate": 1.6918584678804535e-06,
|
| 2040 |
-
"loss": 1.7024,
|
| 2041 |
-
"step": 112500
|
| 2042 |
-
},
|
| 2043 |
-
{
|
| 2044 |
-
"epoch": 38.818275506698726,
|
| 2045 |
-
"grad_norm": 0.01437163446098566,
|
| 2046 |
-
"learning_rate": 1.477155616626589e-06,
|
| 2047 |
-
"loss": 1.7024,
|
| 2048 |
-
"step": 113000
|
| 2049 |
-
},
|
| 2050 |
-
{
|
| 2051 |
-
"epoch": 38.99003778770182,
|
| 2052 |
-
"grad_norm": 0.020153211429715157,
|
| 2053 |
-
"learning_rate": 1.2624527653727242e-06,
|
| 2054 |
-
"loss": 1.7022,
|
| 2055 |
-
"step": 113500
|
| 2056 |
-
},
|
| 2057 |
-
{
|
| 2058 |
-
"epoch": 39.0,
|
| 2059 |
-
"eval_accuracy": 0.8869356928755612,
|
| 2060 |
-
"eval_f1": 0.6716757545833154,
|
| 2061 |
-
"eval_loss": 2.039407968521118,
|
| 2062 |
-
"eval_precision": 0.6613680561427243,
|
| 2063 |
-
"eval_recall": 0.6823098394975575,
|
| 2064 |
-
"eval_runtime": 4.3449,
|
| 2065 |
-
"eval_samples_per_second": 669.757,
|
| 2066 |
-
"eval_steps_per_second": 83.777,
|
| 2067 |
-
"step": 113529
|
| 2068 |
-
},
|
| 2069 |
-
{
|
| 2070 |
-
"epoch": 39.16180006870491,
|
| 2071 |
-
"grad_norm": 0.020474748685956,
|
| 2072 |
-
"learning_rate": 1.0477499141188596e-06,
|
| 2073 |
-
"loss": 1.7027,
|
| 2074 |
-
"step": 114000
|
| 2075 |
-
},
|
| 2076 |
-
{
|
| 2077 |
-
"epoch": 39.333562349708004,
|
| 2078 |
-
"grad_norm": 0.010198526084423065,
|
| 2079 |
-
"learning_rate": 8.330470628649948e-07,
|
| 2080 |
-
"loss": 1.7023,
|
| 2081 |
-
"step": 114500
|
| 2082 |
-
},
|
| 2083 |
-
{
|
| 2084 |
-
"epoch": 39.505324630711094,
|
| 2085 |
-
"grad_norm": 0.02069229632616043,
|
| 2086 |
-
"learning_rate": 6.183442116111302e-07,
|
| 2087 |
-
"loss": 1.7022,
|
| 2088 |
-
"step": 115000
|
| 2089 |
-
},
|
| 2090 |
-
{
|
| 2091 |
-
"epoch": 39.677086911714184,
|
| 2092 |
-
"grad_norm": 0.04512259364128113,
|
| 2093 |
-
"learning_rate": 4.0364136035726557e-07,
|
| 2094 |
-
"loss": 1.7024,
|
| 2095 |
-
"step": 115500
|
| 2096 |
-
},
|
| 2097 |
-
{
|
| 2098 |
-
"epoch": 39.84884919271728,
|
| 2099 |
-
"grad_norm": 0.02132527157664299,
|
| 2100 |
-
"learning_rate": 1.889385091034009e-07,
|
| 2101 |
-
"loss": 1.7023,
|
| 2102 |
-
"step": 116000
|
| 2103 |
-
},
|
| 2104 |
-
{
|
| 2105 |
-
"epoch": 40.0,
|
| 2106 |
-
"eval_accuracy": 0.8874069032317177,
|
| 2107 |
-
"eval_f1": 0.6728642134710566,
|
| 2108 |
-
"eval_loss": 2.0384275913238525,
|
| 2109 |
-
"eval_precision": 0.6640897120040778,
|
| 2110 |
-
"eval_recall": 0.6818736915561758,
|
| 2111 |
-
"eval_runtime": 4.3494,
|
| 2112 |
-
"eval_samples_per_second": 669.052,
|
| 2113 |
-
"eval_steps_per_second": 83.689,
|
| 2114 |
-
"step": 116440
|
| 2115 |
-
},
|
| 2116 |
-
{
|
| 2117 |
-
"epoch": 40.0,
|
| 2118 |
-
"step": 116440,
|
| 2119 |
-
"total_flos": 3.172672952125471e+16,
|
| 2120 |
-
"train_loss": 1.7340915796560996,
|
| 2121 |
-
"train_runtime": 6267.5858,
|
| 2122 |
-
"train_samples_per_second": 148.606,
|
| 2123 |
-
"train_steps_per_second": 18.578
|
| 2124 |
}
|
| 2125 |
],
|
| 2126 |
"logging_steps": 500,
|
| 2127 |
-
"max_steps":
|
| 2128 |
"num_input_tokens_seen": 0,
|
| 2129 |
-
"num_train_epochs":
|
| 2130 |
"save_steps": 500,
|
| 2131 |
"stateful_callbacks": {
|
| 2132 |
"TrainerControl": {
|
|
@@ -2140,7 +825,7 @@
|
|
| 2140 |
"attributes": {}
|
| 2141 |
}
|
| 2142 |
},
|
| 2143 |
-
"total_flos":
|
| 2144 |
"train_batch_size": 8,
|
| 2145 |
"trial_name": null,
|
| 2146 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_global_step": 5822,
|
| 3 |
+
"best_metric": 1.5156257152557373,
|
| 4 |
"best_model_checkpoint": "./output/bert-base-medmentions/checkpoint-5822",
|
| 5 |
+
"epoch": 15.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 43665,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.1717622810030917,
|
| 14 |
+
"grad_norm": 1.9404675960540771,
|
| 15 |
+
"learning_rate": 4.9427459063323026e-05,
|
| 16 |
+
"loss": 1.7239,
|
| 17 |
"step": 500
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.3435245620061834,
|
| 21 |
+
"grad_norm": 1.6719824075698853,
|
| 22 |
+
"learning_rate": 4.885491812664606e-05,
|
| 23 |
+
"loss": 1.6163,
|
| 24 |
"step": 1000
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.5152868430092752,
|
| 28 |
+
"grad_norm": 1.837388515472412,
|
| 29 |
+
"learning_rate": 4.828237718996909e-05,
|
| 30 |
+
"loss": 1.5924,
|
| 31 |
"step": 1500
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.6870491240123668,
|
| 35 |
+
"grad_norm": 2.1180434226989746,
|
| 36 |
+
"learning_rate": 4.770983625329211e-05,
|
| 37 |
+
"loss": 1.5717,
|
| 38 |
"step": 2000
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.8588114050154586,
|
| 42 |
+
"grad_norm": 1.800995945930481,
|
| 43 |
+
"learning_rate": 4.7137295316615135e-05,
|
| 44 |
+
"loss": 1.5686,
|
| 45 |
"step": 2500
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 1.0,
|
| 49 |
+
"eval_accuracy": 0.8549719237162791,
|
| 50 |
+
"eval_f1": 0.5650458863307036,
|
| 51 |
+
"eval_loss": 1.5439889430999756,
|
| 52 |
+
"eval_precision": 0.5245889387144993,
|
| 53 |
+
"eval_recall": 0.6122644801116539,
|
| 54 |
+
"eval_runtime": 4.1137,
|
| 55 |
+
"eval_samples_per_second": 707.39,
|
| 56 |
+
"eval_steps_per_second": 88.485,
|
| 57 |
"step": 2911
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 1.0305736860185504,
|
| 61 |
+
"grad_norm": 1.0917384624481201,
|
| 62 |
+
"learning_rate": 4.6564754379938166e-05,
|
| 63 |
+
"loss": 1.5484,
|
| 64 |
"step": 3000
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"epoch": 1.202335967021642,
|
| 68 |
+
"grad_norm": 1.0721220970153809,
|
| 69 |
+
"learning_rate": 4.59922134432612e-05,
|
| 70 |
+
"loss": 1.4824,
|
| 71 |
"step": 3500
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 1.3740982480247337,
|
| 75 |
+
"grad_norm": 1.5045437812805176,
|
| 76 |
+
"learning_rate": 4.541967250658422e-05,
|
| 77 |
+
"loss": 1.4894,
|
| 78 |
"step": 4000
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 1.5458605290278253,
|
| 82 |
+
"grad_norm": 3.3368799686431885,
|
| 83 |
+
"learning_rate": 4.484713156990725e-05,
|
| 84 |
+
"loss": 1.4863,
|
| 85 |
"step": 4500
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 1.7176228100309172,
|
| 89 |
+
"grad_norm": 2.191357374191284,
|
| 90 |
+
"learning_rate": 4.427459063323028e-05,
|
| 91 |
+
"loss": 1.4806,
|
| 92 |
"step": 5000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 1.889385091034009,
|
| 96 |
+
"grad_norm": 2.575375556945801,
|
| 97 |
+
"learning_rate": 4.3702049696553306e-05,
|
| 98 |
+
"loss": 1.4792,
|
| 99 |
"step": 5500
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 2.0,
|
| 103 |
+
"eval_accuracy": 0.8688595400463357,
|
| 104 |
+
"eval_f1": 0.6071204975165909,
|
| 105 |
+
"eval_loss": 1.5156257152557373,
|
| 106 |
+
"eval_precision": 0.5820728291316527,
|
| 107 |
+
"eval_recall": 0.6344207955338451,
|
| 108 |
+
"eval_runtime": 4.3513,
|
| 109 |
+
"eval_samples_per_second": 668.77,
|
| 110 |
+
"eval_steps_per_second": 83.654,
|
| 111 |
"step": 5822
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 2.0611473720371007,
|
| 115 |
+
"grad_norm": 4.3115081787109375,
|
| 116 |
+
"learning_rate": 4.3129508759876336e-05,
|
| 117 |
+
"loss": 1.4566,
|
| 118 |
"step": 6000
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 2.2329096530401924,
|
| 122 |
+
"grad_norm": 1.5031124353408813,
|
| 123 |
+
"learning_rate": 4.255696782319936e-05,
|
| 124 |
+
"loss": 1.4053,
|
| 125 |
"step": 6500
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 2.404671934043284,
|
| 129 |
+
"grad_norm": 2.4502875804901123,
|
| 130 |
+
"learning_rate": 4.198442688652239e-05,
|
| 131 |
+
"loss": 1.4111,
|
| 132 |
"step": 7000
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.5764342150463757,
|
| 136 |
+
"grad_norm": 1.5572278499603271,
|
| 137 |
+
"learning_rate": 4.1411885949845415e-05,
|
| 138 |
+
"loss": 1.4096,
|
| 139 |
"step": 7500
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.7481964960494674,
|
| 143 |
+
"grad_norm": 1.3663930892944336,
|
| 144 |
+
"learning_rate": 4.0839345013168445e-05,
|
| 145 |
+
"loss": 1.4097,
|
| 146 |
"step": 8000
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 2.9199587770525595,
|
| 150 |
+
"grad_norm": 3.3840882778167725,
|
| 151 |
+
"learning_rate": 4.026680407649147e-05,
|
| 152 |
+
"loss": 1.4111,
|
| 153 |
"step": 8500
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 3.0,
|
| 157 |
+
"eval_accuracy": 0.8713595727692771,
|
| 158 |
+
"eval_f1": 0.6163334575106585,
|
| 159 |
+
"eval_loss": 1.519059419631958,
|
| 160 |
+
"eval_precision": 0.5864513588026782,
|
| 161 |
+
"eval_recall": 0.6494242847173761,
|
| 162 |
+
"eval_runtime": 4.33,
|
| 163 |
+
"eval_samples_per_second": 672.06,
|
| 164 |
+
"eval_steps_per_second": 84.065,
|
| 165 |
"step": 8733
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 3.091721058055651,
|
| 169 |
+
"grad_norm": 1.4997501373291016,
|
| 170 |
+
"learning_rate": 3.96942631398145e-05,
|
| 171 |
+
"loss": 1.3798,
|
| 172 |
"step": 9000
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 3.2634833390587428,
|
| 176 |
+
"grad_norm": 1.4717656373977661,
|
| 177 |
+
"learning_rate": 3.912172220313753e-05,
|
| 178 |
+
"loss": 1.3517,
|
| 179 |
"step": 9500
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 3.4352456200618344,
|
| 183 |
+
"grad_norm": 2.0151214599609375,
|
| 184 |
+
"learning_rate": 3.8549181266460554e-05,
|
| 185 |
+
"loss": 1.3532,
|
| 186 |
"step": 10000
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 3.607007901064926,
|
| 190 |
+
"grad_norm": 2.7060940265655518,
|
| 191 |
+
"learning_rate": 3.797664032978358e-05,
|
| 192 |
+
"loss": 1.3546,
|
| 193 |
"step": 10500
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 3.7787701820680177,
|
| 197 |
+
"grad_norm": 3.2001101970672607,
|
| 198 |
+
"learning_rate": 3.740409939310661e-05,
|
| 199 |
+
"loss": 1.355,
|
| 200 |
"step": 11000
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 3.9505324630711094,
|
| 204 |
+
"grad_norm": 2.374141216278076,
|
| 205 |
+
"learning_rate": 3.683155845642964e-05,
|
| 206 |
+
"loss": 1.356,
|
| 207 |
"step": 11500
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 4.0,
|
| 211 |
+
"eval_accuracy": 0.8777209125773897,
|
| 212 |
+
"eval_f1": 0.6318054658919734,
|
| 213 |
+
"eval_loss": 1.5293220281600952,
|
| 214 |
+
"eval_precision": 0.6235663919802905,
|
| 215 |
+
"eval_recall": 0.6402651779483601,
|
| 216 |
+
"eval_runtime": 4.3262,
|
| 217 |
+
"eval_samples_per_second": 672.648,
|
| 218 |
+
"eval_steps_per_second": 84.139,
|
| 219 |
"step": 11644
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 4.1222947440742015,
|
| 223 |
+
"grad_norm": 2.5122597217559814,
|
| 224 |
+
"learning_rate": 3.6259017519752663e-05,
|
| 225 |
+
"loss": 1.3298,
|
| 226 |
"step": 12000
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 4.294057025077293,
|
| 230 |
+
"grad_norm": 1.870731234550476,
|
| 231 |
+
"learning_rate": 3.568647658307569e-05,
|
| 232 |
+
"loss": 1.3148,
|
| 233 |
"step": 12500
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 4.465819306080385,
|
| 237 |
+
"grad_norm": 2.1130025386810303,
|
| 238 |
+
"learning_rate": 3.511393564639872e-05,
|
| 239 |
+
"loss": 1.3147,
|
| 240 |
"step": 13000
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 4.637581587083476,
|
| 244 |
+
"grad_norm": 1.9891668558120728,
|
| 245 |
+
"learning_rate": 3.454139470972175e-05,
|
| 246 |
+
"loss": 1.3176,
|
| 247 |
"step": 13500
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 4.809343868086568,
|
| 251 |
+
"grad_norm": 2.144550085067749,
|
| 252 |
+
"learning_rate": 3.396885377304477e-05,
|
| 253 |
+
"loss": 1.3207,
|
| 254 |
"step": 14000
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 4.98110614908966,
|
| 258 |
+
"grad_norm": 1.166013240814209,
|
| 259 |
+
"learning_rate": 3.33963128363678e-05,
|
| 260 |
+
"loss": 1.3182,
|
| 261 |
"step": 14500
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 5.0,
|
| 265 |
+
"eval_accuracy": 0.8789120276443408,
|
| 266 |
+
"eval_f1": 0.6353600689952565,
|
| 267 |
+
"eval_loss": 1.543265461921692,
|
| 268 |
+
"eval_precision": 0.6282619819205185,
|
| 269 |
+
"eval_recall": 0.6426203768318214,
|
| 270 |
+
"eval_runtime": 4.3312,
|
| 271 |
+
"eval_samples_per_second": 671.862,
|
| 272 |
+
"eval_steps_per_second": 84.041,
|
| 273 |
"step": 14555
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 5.152868430092751,
|
| 277 |
+
"grad_norm": 1.4789066314697266,
|
| 278 |
+
"learning_rate": 3.2823771899690834e-05,
|
| 279 |
+
"loss": 1.2897,
|
| 280 |
"step": 15000
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 5.3246307110958435,
|
| 284 |
+
"grad_norm": 2.067422866821289,
|
| 285 |
+
"learning_rate": 3.225123096301386e-05,
|
| 286 |
+
"loss": 1.2908,
|
| 287 |
"step": 15500
|
| 288 |
},
|
| 289 |
{
|
| 290 |
"epoch": 5.496392992098935,
|
| 291 |
+
"grad_norm": 1.4258556365966797,
|
| 292 |
+
"learning_rate": 3.167869002633688e-05,
|
| 293 |
+
"loss": 1.2946,
|
| 294 |
"step": 16000
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 5.668155273102027,
|
| 298 |
+
"grad_norm": 1.9385099411010742,
|
| 299 |
+
"learning_rate": 3.110614908965991e-05,
|
| 300 |
+
"loss": 1.2914,
|
| 301 |
"step": 16500
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 5.839917554105119,
|
| 305 |
+
"grad_norm": 2.5622832775115967,
|
| 306 |
+
"learning_rate": 3.053360815298294e-05,
|
| 307 |
+
"loss": 1.2919,
|
| 308 |
"step": 17000
|
| 309 |
},
|
| 310 |
{
|
| 311 |
"epoch": 6.0,
|
| 312 |
+
"eval_accuracy": 0.8793701488239375,
|
| 313 |
+
"eval_f1": 0.6428903837204383,
|
| 314 |
+
"eval_loss": 1.5671014785766602,
|
| 315 |
+
"eval_precision": 0.6241682411895177,
|
| 316 |
+
"eval_recall": 0.6627704117236567,
|
| 317 |
+
"eval_runtime": 4.523,
|
| 318 |
+
"eval_samples_per_second": 643.376,
|
| 319 |
+
"eval_steps_per_second": 80.477,
|
| 320 |
"step": 17466
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 6.01167983510821,
|
| 324 |
+
"grad_norm": 1.9045183658599854,
|
| 325 |
+
"learning_rate": 2.9961067216305967e-05,
|
| 326 |
+
"loss": 1.2899,
|
| 327 |
"step": 17500
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 6.183442116111302,
|
| 331 |
+
"grad_norm": 5.356103420257568,
|
| 332 |
+
"learning_rate": 2.9388526279628997e-05,
|
| 333 |
+
"loss": 1.2716,
|
| 334 |
"step": 18000
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 6.3552043971143934,
|
| 338 |
+
"grad_norm": 1.4505314826965332,
|
| 339 |
+
"learning_rate": 2.8815985342952025e-05,
|
| 340 |
+
"loss": 1.2736,
|
| 341 |
"step": 18500
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 6.5269666781174855,
|
| 345 |
+
"grad_norm": 2.0673441886901855,
|
| 346 |
+
"learning_rate": 2.824344440627505e-05,
|
| 347 |
+
"loss": 1.2755,
|
| 348 |
"step": 19000
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 6.698728959120577,
|
| 352 |
+
"grad_norm": 7.07130765914917,
|
| 353 |
+
"learning_rate": 2.7670903469598076e-05,
|
| 354 |
+
"loss": 1.2739,
|
| 355 |
"step": 19500
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 6.870491240123669,
|
| 359 |
+
"grad_norm": 2.692305326461792,
|
| 360 |
+
"learning_rate": 2.7098362532921106e-05,
|
| 361 |
+
"loss": 1.2743,
|
| 362 |
"step": 20000
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 7.0,
|
| 366 |
+
"eval_accuracy": 0.8809277608345659,
|
| 367 |
+
"eval_f1": 0.6462844646455984,
|
| 368 |
+
"eval_loss": 1.5696512460708618,
|
| 369 |
+
"eval_precision": 0.6355739225773804,
|
| 370 |
+
"eval_recall": 0.6573621772505234,
|
| 371 |
+
"eval_runtime": 4.3283,
|
| 372 |
+
"eval_samples_per_second": 672.312,
|
| 373 |
+
"eval_steps_per_second": 84.097,
|
| 374 |
"step": 20377
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 7.042253521126761,
|
| 378 |
+
"grad_norm": 0.9224966764450073,
|
| 379 |
+
"learning_rate": 2.6525821596244134e-05,
|
| 380 |
+
"loss": 1.2716,
|
| 381 |
"step": 20500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 7.214015802129852,
|
| 385 |
+
"grad_norm": 2.72609543800354,
|
| 386 |
+
"learning_rate": 2.5953280659567158e-05,
|
| 387 |
+
"loss": 1.2578,
|
| 388 |
"step": 21000
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 7.385778083132944,
|
| 392 |
+
"grad_norm": 1.7019892930984497,
|
| 393 |
+
"learning_rate": 2.538073972289019e-05,
|
| 394 |
+
"loss": 1.2612,
|
| 395 |
"step": 21500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 7.5575403641360355,
|
| 399 |
+
"grad_norm": 4.017130374908447,
|
| 400 |
+
"learning_rate": 2.4808198786213216e-05,
|
| 401 |
+
"loss": 1.2622,
|
| 402 |
"step": 22000
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 7.729302645139128,
|
| 406 |
+
"grad_norm": 6.522401332855225,
|
| 407 |
+
"learning_rate": 2.4235657849536243e-05,
|
| 408 |
+
"loss": 1.2611,
|
| 409 |
"step": 22500
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 7.901064926142219,
|
| 413 |
+
"grad_norm": 3.355700731277466,
|
| 414 |
+
"learning_rate": 2.366311691285927e-05,
|
| 415 |
+
"loss": 1.2633,
|
| 416 |
"step": 23000
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 8.0,
|
| 420 |
+
"eval_accuracy": 0.8812811686016833,
|
| 421 |
+
"eval_f1": 0.6527559389741191,
|
| 422 |
+
"eval_loss": 1.5806214809417725,
|
| 423 |
+
"eval_precision": 0.636446507002569,
|
| 424 |
+
"eval_recall": 0.6699232379623168,
|
| 425 |
+
"eval_runtime": 4.329,
|
| 426 |
+
"eval_samples_per_second": 672.206,
|
| 427 |
+
"eval_steps_per_second": 84.084,
|
| 428 |
"step": 23288
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 8.07282720714531,
|
| 432 |
+
"grad_norm": 0.5228517651557922,
|
| 433 |
+
"learning_rate": 2.30905759761823e-05,
|
| 434 |
+
"loss": 1.2579,
|
| 435 |
"step": 23500
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 8.244589488148403,
|
| 439 |
+
"grad_norm": 0.2985314726829529,
|
| 440 |
+
"learning_rate": 2.2518035039505325e-05,
|
| 441 |
+
"loss": 1.2527,
|
| 442 |
"step": 24000
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 8.416351769151495,
|
| 446 |
+
"grad_norm": 1.963086724281311,
|
| 447 |
+
"learning_rate": 2.1945494102828355e-05,
|
| 448 |
+
"loss": 1.2542,
|
| 449 |
"step": 24500
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 8.588114050154585,
|
| 453 |
+
"grad_norm": 0.8812742233276367,
|
| 454 |
+
"learning_rate": 2.137295316615138e-05,
|
| 455 |
+
"loss": 1.251,
|
| 456 |
"step": 25000
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 8.759876331157677,
|
| 460 |
+
"grad_norm": 0.7020455002784729,
|
| 461 |
+
"learning_rate": 2.080041222947441e-05,
|
| 462 |
+
"loss": 1.2516,
|
| 463 |
"step": 25500
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 8.93163861216077,
|
| 467 |
+
"grad_norm": 2.0791664123535156,
|
| 468 |
+
"learning_rate": 2.0227871292797437e-05,
|
| 469 |
+
"loss": 1.2542,
|
| 470 |
"step": 26000
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 9.0,
|
| 474 |
+
"eval_accuracy": 0.880783779892407,
|
| 475 |
+
"eval_f1": 0.6498043011657758,
|
| 476 |
+
"eval_loss": 1.594204068183899,
|
| 477 |
+
"eval_precision": 0.6277953972513621,
|
| 478 |
+
"eval_recall": 0.6734124214933705,
|
| 479 |
+
"eval_runtime": 4.3509,
|
| 480 |
+
"eval_samples_per_second": 668.824,
|
| 481 |
+
"eval_steps_per_second": 83.66,
|
| 482 |
"step": 26199
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 9.103400893163862,
|
| 486 |
+
"grad_norm": 2.5551717281341553,
|
| 487 |
+
"learning_rate": 1.9655330356120464e-05,
|
| 488 |
+
"loss": 1.2496,
|
| 489 |
"step": 26500
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 9.275163174166954,
|
| 493 |
+
"grad_norm": 3.963749647140503,
|
| 494 |
+
"learning_rate": 1.908278941944349e-05,
|
| 495 |
+
"loss": 1.2453,
|
| 496 |
"step": 27000
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 9.446925455170044,
|
| 500 |
+
"grad_norm": 0.5859785676002502,
|
| 501 |
+
"learning_rate": 1.851024848276652e-05,
|
| 502 |
+
"loss": 1.2463,
|
| 503 |
"step": 27500
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 9.618687736173136,
|
| 507 |
+
"grad_norm": 0.3447531759738922,
|
| 508 |
+
"learning_rate": 1.7937707546089546e-05,
|
| 509 |
+
"loss": 1.2477,
|
| 510 |
"step": 28000
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 9.790450017176228,
|
| 514 |
+
"grad_norm": 0.3794388175010681,
|
| 515 |
+
"learning_rate": 1.7365166609412573e-05,
|
| 516 |
+
"loss": 1.2468,
|
| 517 |
"step": 28500
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 9.96221229817932,
|
| 521 |
+
"grad_norm": 1.6076109409332275,
|
| 522 |
+
"learning_rate": 1.67926256727356e-05,
|
| 523 |
+
"loss": 1.2457,
|
| 524 |
"step": 29000
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 10.0,
|
| 528 |
+
"eval_accuracy": 0.8814251495438422,
|
| 529 |
+
"eval_f1": 0.6500277789649131,
|
| 530 |
+
"eval_loss": 1.607577919960022,
|
| 531 |
+
"eval_precision": 0.6372015081692501,
|
| 532 |
+
"eval_recall": 0.6633810188415911,
|
| 533 |
+
"eval_runtime": 4.3517,
|
| 534 |
+
"eval_samples_per_second": 668.699,
|
| 535 |
+
"eval_steps_per_second": 83.645,
|
| 536 |
"step": 29110
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 10.13397457918241,
|
| 540 |
+
"grad_norm": 1.843865990638733,
|
| 541 |
+
"learning_rate": 1.622008473605863e-05,
|
| 542 |
+
"loss": 1.2411,
|
| 543 |
"step": 29500
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 10.305736860185503,
|
| 547 |
+
"grad_norm": 2.924731731414795,
|
| 548 |
+
"learning_rate": 1.5647543799381655e-05,
|
| 549 |
+
"loss": 1.2402,
|
| 550 |
"step": 30000
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 10.477499141188595,
|
| 554 |
+
"grad_norm": 0.40096113085746765,
|
| 555 |
+
"learning_rate": 1.5075002862704684e-05,
|
| 556 |
+
"loss": 1.2416,
|
| 557 |
"step": 30500
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 10.649261422191687,
|
| 561 |
+
"grad_norm": 1.3067082166671753,
|
| 562 |
+
"learning_rate": 1.4502461926027711e-05,
|
| 563 |
+
"loss": 1.2422,
|
| 564 |
"step": 31000
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 10.82102370319478,
|
| 568 |
+
"grad_norm": 1.1540168523788452,
|
| 569 |
+
"learning_rate": 1.3929920989350739e-05,
|
| 570 |
+
"loss": 1.2406,
|
| 571 |
"step": 31500
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 10.99278598419787,
|
| 575 |
+
"grad_norm": 2.354355812072754,
|
| 576 |
+
"learning_rate": 1.3357380052673768e-05,
|
| 577 |
+
"loss": 1.2398,
|
| 578 |
"step": 32000
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 11.0,
|
| 582 |
+
"eval_accuracy": 0.8834932394403068,
|
| 583 |
+
"eval_f1": 0.6551724137931034,
|
| 584 |
+
"eval_loss": 1.6077239513397217,
|
| 585 |
+
"eval_precision": 0.6413770053475936,
|
| 586 |
+
"eval_recall": 0.6695743196092114,
|
| 587 |
+
"eval_runtime": 4.5309,
|
| 588 |
+
"eval_samples_per_second": 642.254,
|
| 589 |
+
"eval_steps_per_second": 80.337,
|
| 590 |
"step": 32021
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 11.164548265200962,
|
| 594 |
+
"grad_norm": 2.941948413848877,
|
| 595 |
+
"learning_rate": 1.2784839115996793e-05,
|
| 596 |
+
"loss": 1.2384,
|
| 597 |
"step": 32500
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 11.336310546204054,
|
| 601 |
+
"grad_norm": 0.06978488713502884,
|
| 602 |
+
"learning_rate": 1.2212298179319822e-05,
|
| 603 |
+
"loss": 1.238,
|
| 604 |
"step": 33000
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 11.508072827207146,
|
| 608 |
+
"grad_norm": 1.1202852725982666,
|
| 609 |
+
"learning_rate": 1.163975724264285e-05,
|
| 610 |
+
"loss": 1.2375,
|
| 611 |
"step": 33500
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 11.679835108210238,
|
| 615 |
+
"grad_norm": 3.7290749549865723,
|
| 616 |
+
"learning_rate": 1.1067216305965877e-05,
|
| 617 |
+
"loss": 1.2373,
|
| 618 |
"step": 34000
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 11.851597389213328,
|
| 622 |
+
"grad_norm": 0.5790780782699585,
|
| 623 |
+
"learning_rate": 1.0494675369288904e-05,
|
| 624 |
+
"loss": 1.2377,
|
| 625 |
"step": 34500
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 12.0,
|
| 629 |
+
"eval_accuracy": 0.8846974436838179,
|
| 630 |
+
"eval_f1": 0.6615437158469945,
|
| 631 |
+
"eval_loss": 1.6134886741638184,
|
| 632 |
+
"eval_precision": 0.6478260869565218,
|
| 633 |
+
"eval_recall": 0.6758548499651081,
|
| 634 |
+
"eval_runtime": 4.3276,
|
| 635 |
+
"eval_samples_per_second": 672.43,
|
| 636 |
+
"eval_steps_per_second": 84.112,
|
| 637 |
"step": 34932
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 12.02335967021642,
|
| 641 |
+
"grad_norm": 0.04744827747344971,
|
| 642 |
+
"learning_rate": 9.922134432611933e-06,
|
| 643 |
+
"loss": 1.2362,
|
| 644 |
"step": 35000
|
| 645 |
},
|
| 646 |
{
|
| 647 |
"epoch": 12.195121951219512,
|
| 648 |
+
"grad_norm": 0.07846707850694656,
|
| 649 |
+
"learning_rate": 9.34959349593496e-06,
|
| 650 |
+
"loss": 1.235,
|
| 651 |
"step": 35500
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 12.366884232222604,
|
| 655 |
+
"grad_norm": 3.9505062103271484,
|
| 656 |
+
"learning_rate": 8.777052559257987e-06,
|
| 657 |
+
"loss": 1.2345,
|
| 658 |
"step": 36000
|
| 659 |
},
|
| 660 |
{
|
| 661 |
"epoch": 12.538646513225697,
|
| 662 |
+
"grad_norm": 0.13419800996780396,
|
| 663 |
+
"learning_rate": 8.204511622581015e-06,
|
| 664 |
+
"loss": 1.2362,
|
| 665 |
"step": 36500
|
| 666 |
},
|
| 667 |
{
|
| 668 |
"epoch": 12.710408794228787,
|
| 669 |
+
"grad_norm": 0.205936998128891,
|
| 670 |
+
"learning_rate": 7.631970685904042e-06,
|
| 671 |
+
"loss": 1.2341,
|
| 672 |
"step": 37000
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 12.882171075231879,
|
| 676 |
+
"grad_norm": 1.917006254196167,
|
| 677 |
+
"learning_rate": 7.05942974922707e-06,
|
| 678 |
+
"loss": 1.2349,
|
| 679 |
"step": 37500
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 13.0,
|
| 683 |
+
"eval_accuracy": 0.883872825560544,
|
| 684 |
+
"eval_f1": 0.6590367597004765,
|
| 685 |
+
"eval_loss": 1.619519829750061,
|
| 686 |
+
"eval_precision": 0.6432724252491694,
|
| 687 |
+
"eval_recall": 0.6755931612002791,
|
| 688 |
+
"eval_runtime": 4.3511,
|
| 689 |
+
"eval_samples_per_second": 668.801,
|
| 690 |
+
"eval_steps_per_second": 83.658,
|
| 691 |
"step": 37843
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 13.053933356234971,
|
| 695 |
+
"grad_norm": 0.5815674662590027,
|
| 696 |
+
"learning_rate": 6.486888812550097e-06,
|
| 697 |
+
"loss": 1.2342,
|
| 698 |
"step": 38000
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 13.225695637238063,
|
| 702 |
+
"grad_norm": 0.48151713609695435,
|
| 703 |
+
"learning_rate": 5.914347875873125e-06,
|
| 704 |
+
"loss": 1.2335,
|
| 705 |
"step": 38500
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 13.397457918241154,
|
| 709 |
+
"grad_norm": 4.141974925994873,
|
| 710 |
+
"learning_rate": 5.341806939196153e-06,
|
| 711 |
+
"loss": 1.2335,
|
| 712 |
"step": 39000
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 13.569220199244246,
|
| 716 |
+
"grad_norm": 0.24046790599822998,
|
| 717 |
+
"learning_rate": 4.76926600251918e-06,
|
| 718 |
+
"loss": 1.2331,
|
| 719 |
"step": 39500
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 13.740982480247338,
|
| 723 |
+
"grad_norm": 0.08363146334886551,
|
| 724 |
+
"learning_rate": 4.196725065842208e-06,
|
| 725 |
+
"loss": 1.233,
|
| 726 |
"step": 40000
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 13.91274476125043,
|
| 730 |
+
"grad_norm": 0.5658828616142273,
|
| 731 |
+
"learning_rate": 3.6241841291652353e-06,
|
| 732 |
+
"loss": 1.2328,
|
| 733 |
"step": 40500
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 14.0,
|
| 737 |
+
"eval_accuracy": 0.8845272843885391,
|
| 738 |
+
"eval_f1": 0.6591725081210464,
|
| 739 |
+
"eval_loss": 1.6228290796279907,
|
| 740 |
+
"eval_precision": 0.6462453905464298,
|
| 741 |
+
"eval_recall": 0.6726273551988835,
|
| 742 |
+
"eval_runtime": 4.3411,
|
| 743 |
+
"eval_samples_per_second": 670.343,
|
| 744 |
+
"eval_steps_per_second": 83.85,
|
| 745 |
"step": 40754
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 14.084507042253522,
|
| 749 |
+
"grad_norm": 1.4916341304779053,
|
| 750 |
+
"learning_rate": 3.051643192488263e-06,
|
| 751 |
+
"loss": 1.2318,
|
| 752 |
"step": 41000
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 14.256269323256612,
|
| 756 |
+
"grad_norm": 0.1434667557477951,
|
| 757 |
+
"learning_rate": 2.4791022558112906e-06,
|
| 758 |
+
"loss": 1.2305,
|
| 759 |
"step": 41500
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 14.428031604259704,
|
| 763 |
+
"grad_norm": 0.10652283579111099,
|
| 764 |
+
"learning_rate": 1.906561319134318e-06,
|
| 765 |
+
"loss": 1.232,
|
| 766 |
"step": 42000
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 14.599793885262796,
|
| 770 |
+
"grad_norm": 0.8040905594825745,
|
| 771 |
+
"learning_rate": 1.3340203824573458e-06,
|
| 772 |
+
"loss": 1.2321,
|
| 773 |
"step": 42500
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 14.771556166265889,
|
| 777 |
+
"grad_norm": 0.040788378566503525,
|
| 778 |
+
"learning_rate": 7.614794457803733e-07,
|
| 779 |
+
"loss": 1.2319,
|
| 780 |
"step": 43000
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 14.943318447268979,
|
| 784 |
+
"grad_norm": 0.5179036259651184,
|
| 785 |
+
"learning_rate": 1.889385091034009e-07,
|
| 786 |
+
"loss": 1.231,
|
| 787 |
"step": 43500
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 15.0,
|
| 791 |
+
"eval_accuracy": 0.8847236220369377,
|
| 792 |
+
"eval_f1": 0.660140218878249,
|
| 793 |
+
"eval_loss": 1.6247130632400513,
|
| 794 |
+
"eval_precision": 0.6473004694835681,
|
| 795 |
+
"eval_recall": 0.6734996510816469,
|
| 796 |
+
"eval_runtime": 4.3445,
|
| 797 |
+
"eval_samples_per_second": 669.806,
|
| 798 |
+
"eval_steps_per_second": 83.783,
|
| 799 |
"step": 43665
|
| 800 |
},
|
| 801 |
{
|
| 802 |
+
"epoch": 15.0,
|
| 803 |
+
"step": 43665,
|
| 804 |
+
"total_flos": 1.1901430945516224e+16,
|
| 805 |
+
"train_loss": 1.311661433704009,
|
| 806 |
+
"train_runtime": 2299.911,
|
| 807 |
+
"train_samples_per_second": 151.865,
|
| 808 |
+
"train_steps_per_second": 18.986
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 809 |
}
|
| 810 |
],
|
| 811 |
"logging_steps": 500,
|
| 812 |
+
"max_steps": 43665,
|
| 813 |
"num_input_tokens_seen": 0,
|
| 814 |
+
"num_train_epochs": 15,
|
| 815 |
"save_steps": 500,
|
| 816 |
"stateful_callbacks": {
|
| 817 |
"TrainerControl": {
|
|
|
|
| 825 |
"attributes": {}
|
| 826 |
}
|
| 827 |
},
|
| 828 |
+
"total_flos": 1.1901430945516224e+16,
|
| 829 |
"train_batch_size": 8,
|
| 830 |
"trial_name": null,
|
| 831 |
"trial_params": null
|