End of training
Browse files- README.md +4 -2
- all_results.json +11 -11
- eval_results.json +6 -6
- p_object.json +0 -0
- prediction_reference.json +0 -0
- train_results.json +6 -6
- trainer_state.json +102 -2413
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/dit-base-finetuned-rvlcdip
|
| 3 |
tags:
|
|
|
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- f1
|
|
@@ -16,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- F1: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/dit-base-finetuned-rvlcdip
|
| 3 |
tags:
|
| 4 |
+
- image-classification
|
| 5 |
+
- vision
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- f1
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1870
|
| 22 |
+
- F1: 0.3826
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.271580010095911,
|
| 3 |
+
"eval_f1": 0.38255795104555035,
|
| 4 |
+
"eval_loss": 0.18703292310237885,
|
| 5 |
+
"eval_runtime": 571.9074,
|
| 6 |
+
"eval_samples_per_second": 360.656,
|
| 7 |
+
"eval_steps_per_second": 2.819,
|
| 8 |
+
"total_flos": 4.4623040438986555e+19,
|
| 9 |
+
"train_loss": 0.13670311906602647,
|
| 10 |
+
"train_runtime": 12745.6466,
|
| 11 |
+
"train_samples_per_second": 301.279,
|
| 12 |
+
"train_steps_per_second": 2.354
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.271580010095911,
|
| 3 |
+
"eval_f1": 0.38255795104555035,
|
| 4 |
+
"eval_loss": 0.18703292310237885,
|
| 5 |
+
"eval_runtime": 571.9074,
|
| 6 |
+
"eval_samples_per_second": 360.656,
|
| 7 |
+
"eval_steps_per_second": 2.819
|
| 8 |
}
|
p_object.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
prediction_reference.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.271580010095911,
|
| 3 |
+
"total_flos": 4.4623040438986555e+19,
|
| 4 |
+
"train_loss": 0.13670311906602647,
|
| 5 |
+
"train_runtime": 12745.6466,
|
| 6 |
+
"train_samples_per_second": 301.279,
|
| 7 |
+
"train_steps_per_second": 2.354
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,2452 +1,141 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./step_test_microsoft_dit/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
"epoch": 0.005049229992426155,
|
| 20 |
-
"grad_norm": 1.5600422620773315,
|
| 21 |
-
"learning_rate": 2.994e-05,
|
| 22 |
-
"loss": 0.2047,
|
| 23 |
-
"step": 20
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.007573844988639233,
|
| 27 |
-
"grad_norm": 2.1541621685028076,
|
| 28 |
-
"learning_rate": 2.991e-05,
|
| 29 |
-
"loss": 0.1528,
|
| 30 |
-
"step": 30
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.01009845998485231,
|
| 34 |
-
"grad_norm": 1.805535078048706,
|
| 35 |
-
"learning_rate": 2.9880000000000002e-05,
|
| 36 |
-
"loss": 0.1252,
|
| 37 |
-
"step": 40
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.012623074981065387,
|
| 41 |
-
"grad_norm": 1.1236392259597778,
|
| 42 |
-
"learning_rate": 2.985e-05,
|
| 43 |
-
"loss": 0.1165,
|
| 44 |
-
"step": 50
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.012623074981065387,
|
| 48 |
-
"eval_f1": 0.4177168854259269,
|
| 49 |
-
"eval_loss": 0.06423712521791458,
|
| 50 |
-
"eval_runtime": 1142.2038,
|
| 51 |
-
"eval_samples_per_second": 180.582,
|
| 52 |
-
"eval_steps_per_second": 2.822,
|
| 53 |
-
"step": 50
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"epoch": 0.015147689977278465,
|
| 57 |
-
"grad_norm": 1.1924934387207031,
|
| 58 |
-
"learning_rate": 2.982e-05,
|
| 59 |
-
"loss": 0.1029,
|
| 60 |
-
"step": 60
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 0.017672304973491544,
|
| 64 |
-
"grad_norm": 1.225701928138733,
|
| 65 |
-
"learning_rate": 2.979e-05,
|
| 66 |
-
"loss": 0.117,
|
| 67 |
-
"step": 70
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 0.02019691996970462,
|
| 71 |
-
"grad_norm": 2.702486515045166,
|
| 72 |
-
"learning_rate": 2.976e-05,
|
| 73 |
-
"loss": 0.1103,
|
| 74 |
-
"step": 80
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.022721534965917698,
|
| 78 |
-
"grad_norm": 2.0278918743133545,
|
| 79 |
-
"learning_rate": 2.973e-05,
|
| 80 |
-
"loss": 0.1054,
|
| 81 |
-
"step": 90
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.025246149962130773,
|
| 85 |
-
"grad_norm": 1.9288796186447144,
|
| 86 |
-
"learning_rate": 2.97e-05,
|
| 87 |
-
"loss": 0.0942,
|
| 88 |
-
"step": 100
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 0.025246149962130773,
|
| 92 |
-
"eval_f1": 0.4771817453963171,
|
| 93 |
-
"eval_loss": 0.048530641943216324,
|
| 94 |
-
"eval_runtime": 1007.4651,
|
| 95 |
-
"eval_samples_per_second": 204.734,
|
| 96 |
-
"eval_steps_per_second": 3.199,
|
| 97 |
-
"step": 100
|
| 98 |
-
},
|
| 99 |
-
{
|
| 100 |
-
"epoch": 0.027770764958343852,
|
| 101 |
-
"grad_norm": 1.4688999652862549,
|
| 102 |
-
"learning_rate": 2.967e-05,
|
| 103 |
-
"loss": 0.0992,
|
| 104 |
-
"step": 110
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 0.03029537995455693,
|
| 108 |
-
"grad_norm": 1.1097605228424072,
|
| 109 |
-
"learning_rate": 2.964e-05,
|
| 110 |
-
"loss": 0.1126,
|
| 111 |
-
"step": 120
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.03281999495077001,
|
| 115 |
-
"grad_norm": 1.0353784561157227,
|
| 116 |
-
"learning_rate": 2.961e-05,
|
| 117 |
-
"loss": 0.0949,
|
| 118 |
-
"step": 130
|
| 119 |
-
},
|
| 120 |
-
{
|
| 121 |
-
"epoch": 0.03534460994698309,
|
| 122 |
-
"grad_norm": 1.7303999662399292,
|
| 123 |
-
"learning_rate": 2.958e-05,
|
| 124 |
-
"loss": 0.1025,
|
| 125 |
-
"step": 140
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 0.03786922494319616,
|
| 129 |
-
"grad_norm": 1.1177138090133667,
|
| 130 |
-
"learning_rate": 2.955e-05,
|
| 131 |
-
"loss": 0.1076,
|
| 132 |
-
"step": 150
|
| 133 |
-
},
|
| 134 |
-
{
|
| 135 |
-
"epoch": 0.03786922494319616,
|
| 136 |
-
"eval_f1": 0.46432628333423487,
|
| 137 |
-
"eval_loss": 0.05836363136768341,
|
| 138 |
-
"eval_runtime": 980.1012,
|
| 139 |
-
"eval_samples_per_second": 210.45,
|
| 140 |
-
"eval_steps_per_second": 3.288,
|
| 141 |
-
"step": 150
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 0.04039383993940924,
|
| 145 |
-
"grad_norm": 1.1965147256851196,
|
| 146 |
-
"learning_rate": 2.9520000000000002e-05,
|
| 147 |
-
"loss": 0.0961,
|
| 148 |
-
"step": 160
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"epoch": 0.04291845493562232,
|
| 152 |
-
"grad_norm": 1.0545780658721924,
|
| 153 |
-
"learning_rate": 2.949e-05,
|
| 154 |
-
"loss": 0.104,
|
| 155 |
-
"step": 170
|
| 156 |
-
},
|
| 157 |
-
{
|
| 158 |
-
"epoch": 0.045443069931835396,
|
| 159 |
-
"grad_norm": 1.8348199129104614,
|
| 160 |
-
"learning_rate": 2.946e-05,
|
| 161 |
-
"loss": 0.0932,
|
| 162 |
-
"step": 180
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 0.047967684928048475,
|
| 166 |
-
"grad_norm": 1.8478541374206543,
|
| 167 |
-
"learning_rate": 2.943e-05,
|
| 168 |
-
"loss": 0.1069,
|
| 169 |
-
"step": 190
|
| 170 |
-
},
|
| 171 |
-
{
|
| 172 |
-
"epoch": 0.05049229992426155,
|
| 173 |
-
"grad_norm": 0.9377999305725098,
|
| 174 |
-
"learning_rate": 2.94e-05,
|
| 175 |
-
"loss": 0.1103,
|
| 176 |
-
"step": 200
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.05049229992426155,
|
| 180 |
-
"eval_f1": NaN,
|
| 181 |
-
"eval_loss": 0.044557176530361176,
|
| 182 |
-
"eval_runtime": 978.7525,
|
| 183 |
-
"eval_samples_per_second": 210.74,
|
| 184 |
-
"eval_steps_per_second": 3.293,
|
| 185 |
-
"step": 200
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.053016914920474625,
|
| 189 |
-
"grad_norm": 1.6204830408096313,
|
| 190 |
-
"learning_rate": 2.9370000000000002e-05,
|
| 191 |
-
"loss": 0.1019,
|
| 192 |
-
"step": 210
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.055541529916687704,
|
| 196 |
-
"grad_norm": 1.1411000490188599,
|
| 197 |
-
"learning_rate": 2.934e-05,
|
| 198 |
-
"loss": 0.0969,
|
| 199 |
-
"step": 220
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.05806614491290078,
|
| 203 |
-
"grad_norm": 1.1179866790771484,
|
| 204 |
-
"learning_rate": 2.931e-05,
|
| 205 |
-
"loss": 0.1031,
|
| 206 |
-
"step": 230
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.06059075990911386,
|
| 210 |
-
"grad_norm": 1.2155176401138306,
|
| 211 |
-
"learning_rate": 2.928e-05,
|
| 212 |
-
"loss": 0.0851,
|
| 213 |
-
"step": 240
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.06311537490532694,
|
| 217 |
-
"grad_norm": 1.4578701257705688,
|
| 218 |
-
"learning_rate": 2.925e-05,
|
| 219 |
-
"loss": 0.0873,
|
| 220 |
-
"step": 250
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.06311537490532694,
|
| 224 |
-
"eval_f1": 0.5313367950730588,
|
| 225 |
-
"eval_loss": 0.05184657499194145,
|
| 226 |
-
"eval_runtime": 982.8389,
|
| 227 |
-
"eval_samples_per_second": 209.863,
|
| 228 |
-
"eval_steps_per_second": 3.279,
|
| 229 |
-
"step": 250
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 0.06563998990154002,
|
| 233 |
-
"grad_norm": 1.2894303798675537,
|
| 234 |
-
"learning_rate": 2.922e-05,
|
| 235 |
-
"loss": 0.0876,
|
| 236 |
-
"step": 260
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 0.0681646048977531,
|
| 240 |
-
"grad_norm": 0.8404099941253662,
|
| 241 |
-
"learning_rate": 2.919e-05,
|
| 242 |
-
"loss": 0.0904,
|
| 243 |
-
"step": 270
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 0.07068921989396618,
|
| 247 |
-
"grad_norm": 2.0062506198883057,
|
| 248 |
-
"learning_rate": 2.916e-05,
|
| 249 |
-
"loss": 0.1009,
|
| 250 |
-
"step": 280
|
| 251 |
-
},
|
| 252 |
-
{
|
| 253 |
-
"epoch": 0.07321383489017924,
|
| 254 |
-
"grad_norm": 0.8900242447853088,
|
| 255 |
-
"learning_rate": 2.913e-05,
|
| 256 |
-
"loss": 0.0925,
|
| 257 |
-
"step": 290
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 0.07573844988639232,
|
| 261 |
-
"grad_norm": 1.051013708114624,
|
| 262 |
-
"learning_rate": 2.91e-05,
|
| 263 |
-
"loss": 0.1053,
|
| 264 |
-
"step": 300
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 0.07573844988639232,
|
| 268 |
-
"eval_f1": 0.532925682031985,
|
| 269 |
-
"eval_loss": 0.07359323650598526,
|
| 270 |
-
"eval_runtime": 980.9407,
|
| 271 |
-
"eval_samples_per_second": 210.27,
|
| 272 |
-
"eval_steps_per_second": 3.286,
|
| 273 |
-
"step": 300
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.0782630648826054,
|
| 277 |
-
"grad_norm": 0.7765111327171326,
|
| 278 |
-
"learning_rate": 2.907e-05,
|
| 279 |
-
"loss": 0.0848,
|
| 280 |
-
"step": 310
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"epoch": 0.08078767987881848,
|
| 284 |
-
"grad_norm": 0.9605777859687805,
|
| 285 |
-
"learning_rate": 2.904e-05,
|
| 286 |
-
"loss": 0.0746,
|
| 287 |
-
"step": 320
|
| 288 |
-
},
|
| 289 |
-
{
|
| 290 |
-
"epoch": 0.08331229487503156,
|
| 291 |
-
"grad_norm": 1.9086962938308716,
|
| 292 |
-
"learning_rate": 2.901e-05,
|
| 293 |
-
"loss": 0.1023,
|
| 294 |
-
"step": 330
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 0.08583690987124463,
|
| 298 |
-
"grad_norm": 1.5782345533370972,
|
| 299 |
-
"learning_rate": 2.898e-05,
|
| 300 |
-
"loss": 0.0751,
|
| 301 |
-
"step": 340
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 0.08836152486745771,
|
| 305 |
-
"grad_norm": 1.2298818826675415,
|
| 306 |
-
"learning_rate": 2.895e-05,
|
| 307 |
-
"loss": 0.0797,
|
| 308 |
-
"step": 350
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.08836152486745771,
|
| 312 |
-
"eval_f1": 0.5325518588749066,
|
| 313 |
-
"eval_loss": 0.07257544994354248,
|
| 314 |
-
"eval_runtime": 979.2135,
|
| 315 |
-
"eval_samples_per_second": 210.64,
|
| 316 |
-
"eval_steps_per_second": 3.291,
|
| 317 |
-
"step": 350
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 0.09088613986367079,
|
| 321 |
-
"grad_norm": 1.1932893991470337,
|
| 322 |
-
"learning_rate": 2.892e-05,
|
| 323 |
-
"loss": 0.0803,
|
| 324 |
-
"step": 360
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.09341075485988387,
|
| 328 |
-
"grad_norm": 0.896007776260376,
|
| 329 |
-
"learning_rate": 2.889e-05,
|
| 330 |
-
"loss": 0.088,
|
| 331 |
-
"step": 370
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 0.09593536985609695,
|
| 335 |
-
"grad_norm": 2.385890483856201,
|
| 336 |
-
"learning_rate": 2.8859999999999998e-05,
|
| 337 |
-
"loss": 0.0886,
|
| 338 |
-
"step": 380
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.09845998485231003,
|
| 342 |
-
"grad_norm": 0.966077446937561,
|
| 343 |
-
"learning_rate": 2.883e-05,
|
| 344 |
-
"loss": 0.1038,
|
| 345 |
-
"step": 390
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.1009845998485231,
|
| 349 |
-
"grad_norm": 0.969159722328186,
|
| 350 |
-
"learning_rate": 2.88e-05,
|
| 351 |
-
"loss": 0.0857,
|
| 352 |
-
"step": 400
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 0.1009845998485231,
|
| 356 |
-
"eval_f1": 0.5497736226259776,
|
| 357 |
-
"eval_loss": 0.06929118931293488,
|
| 358 |
-
"eval_runtime": 978.0405,
|
| 359 |
-
"eval_samples_per_second": 210.893,
|
| 360 |
-
"eval_steps_per_second": 3.295,
|
| 361 |
-
"step": 400
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.10350921484473617,
|
| 365 |
-
"grad_norm": 0.8633397817611694,
|
| 366 |
-
"learning_rate": 2.877e-05,
|
| 367 |
-
"loss": 0.0895,
|
| 368 |
-
"step": 410
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 0.10603382984094925,
|
| 372 |
-
"grad_norm": 1.163271188735962,
|
| 373 |
-
"learning_rate": 2.874e-05,
|
| 374 |
-
"loss": 0.0861,
|
| 375 |
-
"step": 420
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.10855844483716233,
|
| 379 |
-
"grad_norm": 1.102964997291565,
|
| 380 |
-
"learning_rate": 2.871e-05,
|
| 381 |
-
"loss": 0.0962,
|
| 382 |
-
"step": 430
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 0.11108305983337541,
|
| 386 |
-
"grad_norm": 1.520044207572937,
|
| 387 |
-
"learning_rate": 2.868e-05,
|
| 388 |
-
"loss": 0.0981,
|
| 389 |
-
"step": 440
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.11360767482958849,
|
| 393 |
-
"grad_norm": 1.8637338876724243,
|
| 394 |
-
"learning_rate": 2.865e-05,
|
| 395 |
-
"loss": 0.0885,
|
| 396 |
-
"step": 450
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 0.11360767482958849,
|
| 400 |
-
"eval_f1": NaN,
|
| 401 |
-
"eval_loss": 0.09174469113349915,
|
| 402 |
-
"eval_runtime": 1032.8967,
|
| 403 |
-
"eval_samples_per_second": 199.693,
|
| 404 |
-
"eval_steps_per_second": 3.12,
|
| 405 |
-
"step": 450
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.11613228982580157,
|
| 409 |
-
"grad_norm": 1.1974824666976929,
|
| 410 |
-
"learning_rate": 2.862e-05,
|
| 411 |
-
"loss": 0.0784,
|
| 412 |
-
"step": 460
|
| 413 |
-
},
|
| 414 |
-
{
|
| 415 |
-
"epoch": 0.11865690482201464,
|
| 416 |
-
"grad_norm": 1.6933320760726929,
|
| 417 |
-
"learning_rate": 2.859e-05,
|
| 418 |
-
"loss": 0.078,
|
| 419 |
-
"step": 470
|
| 420 |
-
},
|
| 421 |
-
{
|
| 422 |
-
"epoch": 0.12118151981822772,
|
| 423 |
-
"grad_norm": 1.7774609327316284,
|
| 424 |
-
"learning_rate": 2.856e-05,
|
| 425 |
-
"loss": 0.0715,
|
| 426 |
-
"step": 480
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"epoch": 0.1237061348144408,
|
| 430 |
-
"grad_norm": 0.7675666213035583,
|
| 431 |
-
"learning_rate": 2.853e-05,
|
| 432 |
-
"loss": 0.0817,
|
| 433 |
-
"step": 490
|
| 434 |
-
},
|
| 435 |
-
{
|
| 436 |
-
"epoch": 0.12623074981065388,
|
| 437 |
-
"grad_norm": 1.169325590133667,
|
| 438 |
-
"learning_rate": 2.8499999999999998e-05,
|
| 439 |
-
"loss": 0.102,
|
| 440 |
-
"step": 500
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 0.12623074981065388,
|
| 444 |
-
"eval_f1": 0.5648781658864481,
|
| 445 |
-
"eval_loss": 0.057994671165943146,
|
| 446 |
-
"eval_runtime": 967.2924,
|
| 447 |
-
"eval_samples_per_second": 213.236,
|
| 448 |
-
"eval_steps_per_second": 3.332,
|
| 449 |
-
"step": 500
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 0.12875536480686695,
|
| 453 |
-
"grad_norm": 0.9567933678627014,
|
| 454 |
-
"learning_rate": 2.847e-05,
|
| 455 |
-
"loss": 0.0762,
|
| 456 |
-
"step": 510
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 0.13127997980308004,
|
| 460 |
-
"grad_norm": 0.7539889216423035,
|
| 461 |
-
"learning_rate": 2.844e-05,
|
| 462 |
-
"loss": 0.0655,
|
| 463 |
-
"step": 520
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"epoch": 0.1338045947992931,
|
| 467 |
-
"grad_norm": 1.873833179473877,
|
| 468 |
-
"learning_rate": 2.841e-05,
|
| 469 |
-
"loss": 0.0747,
|
| 470 |
-
"step": 530
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 0.1363292097955062,
|
| 474 |
-
"grad_norm": 0.7834559082984924,
|
| 475 |
-
"learning_rate": 2.838e-05,
|
| 476 |
-
"loss": 0.0923,
|
| 477 |
-
"step": 540
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 0.13885382479171926,
|
| 481 |
-
"grad_norm": 0.6193771362304688,
|
| 482 |
-
"learning_rate": 2.8349999999999998e-05,
|
| 483 |
-
"loss": 0.0716,
|
| 484 |
-
"step": 550
|
| 485 |
-
},
|
| 486 |
-
{
|
| 487 |
-
"epoch": 0.13885382479171926,
|
| 488 |
-
"eval_f1": 0.538135593220339,
|
| 489 |
-
"eval_loss": 0.07973095029592514,
|
| 490 |
-
"eval_runtime": 974.1593,
|
| 491 |
-
"eval_samples_per_second": 211.733,
|
| 492 |
-
"eval_steps_per_second": 3.308,
|
| 493 |
-
"step": 550
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 0.14137843978793235,
|
| 497 |
-
"grad_norm": 1.1256766319274902,
|
| 498 |
-
"learning_rate": 2.832e-05,
|
| 499 |
-
"loss": 0.0798,
|
| 500 |
-
"step": 560
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.14390305478414542,
|
| 504 |
-
"grad_norm": 1.0669515132904053,
|
| 505 |
-
"learning_rate": 2.829e-05,
|
| 506 |
-
"loss": 0.0795,
|
| 507 |
-
"step": 570
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 0.14642766978035848,
|
| 511 |
-
"grad_norm": 1.018234133720398,
|
| 512 |
-
"learning_rate": 2.826e-05,
|
| 513 |
-
"loss": 0.073,
|
| 514 |
-
"step": 580
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 0.14895228477657158,
|
| 518 |
-
"grad_norm": 1.2367616891860962,
|
| 519 |
-
"learning_rate": 2.823e-05,
|
| 520 |
-
"loss": 0.0879,
|
| 521 |
-
"step": 590
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 0.15147689977278464,
|
| 525 |
-
"grad_norm": 1.5840317010879517,
|
| 526 |
-
"learning_rate": 2.8199999999999998e-05,
|
| 527 |
-
"loss": 0.0854,
|
| 528 |
-
"step": 600
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 0.15147689977278464,
|
| 532 |
-
"eval_f1": 0.571752762018513,
|
| 533 |
-
"eval_loss": 0.07439474016427994,
|
| 534 |
-
"eval_runtime": 970.5653,
|
| 535 |
-
"eval_samples_per_second": 212.517,
|
| 536 |
-
"eval_steps_per_second": 3.321,
|
| 537 |
-
"step": 600
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.15400151476899773,
|
| 541 |
-
"grad_norm": 0.5361483097076416,
|
| 542 |
-
"learning_rate": 2.817e-05,
|
| 543 |
-
"loss": 0.0854,
|
| 544 |
-
"step": 610
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 0.1565261297652108,
|
| 548 |
-
"grad_norm": 0.9658698439598083,
|
| 549 |
-
"learning_rate": 2.8139999999999998e-05,
|
| 550 |
-
"loss": 0.095,
|
| 551 |
-
"step": 620
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 0.1590507447614239,
|
| 555 |
-
"grad_norm": 0.820649266242981,
|
| 556 |
-
"learning_rate": 2.8110000000000004e-05,
|
| 557 |
-
"loss": 0.0921,
|
| 558 |
-
"step": 630
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 0.16157535975763695,
|
| 562 |
-
"grad_norm": 1.1583890914916992,
|
| 563 |
-
"learning_rate": 2.8080000000000002e-05,
|
| 564 |
-
"loss": 0.077,
|
| 565 |
-
"step": 640
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"epoch": 0.16409997475385005,
|
| 569 |
-
"grad_norm": 0.8755506277084351,
|
| 570 |
-
"learning_rate": 2.805e-05,
|
| 571 |
-
"loss": 0.089,
|
| 572 |
-
"step": 650
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 0.16409997475385005,
|
| 576 |
-
"eval_f1": 0.5789600675594161,
|
| 577 |
-
"eval_loss": 0.0503680482506752,
|
| 578 |
-
"eval_runtime": 976.7796,
|
| 579 |
-
"eval_samples_per_second": 211.165,
|
| 580 |
-
"eval_steps_per_second": 3.3,
|
| 581 |
-
"step": 650
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 0.1666245897500631,
|
| 585 |
-
"grad_norm": 0.5073147416114807,
|
| 586 |
-
"learning_rate": 2.8020000000000003e-05,
|
| 587 |
-
"loss": 0.0784,
|
| 588 |
-
"step": 660
|
| 589 |
-
},
|
| 590 |
-
{
|
| 591 |
-
"epoch": 0.1691492047462762,
|
| 592 |
-
"grad_norm": 1.0332393646240234,
|
| 593 |
-
"learning_rate": 2.799e-05,
|
| 594 |
-
"loss": 0.0906,
|
| 595 |
-
"step": 670
|
| 596 |
-
},
|
| 597 |
-
{
|
| 598 |
-
"epoch": 0.17167381974248927,
|
| 599 |
-
"grad_norm": 1.1538151502609253,
|
| 600 |
-
"learning_rate": 2.7960000000000003e-05,
|
| 601 |
-
"loss": 0.0799,
|
| 602 |
-
"step": 680
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 0.17419843473870233,
|
| 606 |
-
"grad_norm": 1.2075843811035156,
|
| 607 |
-
"learning_rate": 2.7930000000000002e-05,
|
| 608 |
-
"loss": 0.0795,
|
| 609 |
-
"step": 690
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 0.17672304973491543,
|
| 613 |
-
"grad_norm": 2.1169683933258057,
|
| 614 |
-
"learning_rate": 2.79e-05,
|
| 615 |
-
"loss": 0.0721,
|
| 616 |
-
"step": 700
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 0.17672304973491543,
|
| 620 |
-
"eval_f1": 0.5727175590644663,
|
| 621 |
-
"eval_loss": 0.0618172287940979,
|
| 622 |
-
"eval_runtime": 975.6558,
|
| 623 |
-
"eval_samples_per_second": 211.409,
|
| 624 |
-
"eval_steps_per_second": 3.303,
|
| 625 |
-
"step": 700
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 0.1792476647311285,
|
| 629 |
-
"grad_norm": 1.3094089031219482,
|
| 630 |
-
"learning_rate": 2.7870000000000003e-05,
|
| 631 |
-
"loss": 0.0723,
|
| 632 |
-
"step": 710
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch": 0.18177227972734158,
|
| 636 |
-
"grad_norm": 0.9937088489532471,
|
| 637 |
-
"learning_rate": 2.784e-05,
|
| 638 |
-
"loss": 0.0704,
|
| 639 |
-
"step": 720
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 0.18429689472355465,
|
| 643 |
-
"grad_norm": 0.6464220881462097,
|
| 644 |
-
"learning_rate": 2.7810000000000003e-05,
|
| 645 |
-
"loss": 0.0731,
|
| 646 |
-
"step": 730
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 0.18682150971976774,
|
| 650 |
-
"grad_norm": 0.5544419288635254,
|
| 651 |
-
"learning_rate": 2.778e-05,
|
| 652 |
-
"loss": 0.0894,
|
| 653 |
-
"step": 740
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"epoch": 0.1893461247159808,
|
| 657 |
-
"grad_norm": 0.6369556188583374,
|
| 658 |
-
"learning_rate": 2.7750000000000004e-05,
|
| 659 |
-
"loss": 0.0721,
|
| 660 |
-
"step": 750
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"epoch": 0.1893461247159808,
|
| 664 |
-
"eval_f1": 0.5904197411394702,
|
| 665 |
-
"eval_loss": 0.07033708691596985,
|
| 666 |
-
"eval_runtime": 967.5811,
|
| 667 |
-
"eval_samples_per_second": 213.173,
|
| 668 |
-
"eval_steps_per_second": 3.331,
|
| 669 |
-
"step": 750
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 0.1918707397121939,
|
| 673 |
-
"grad_norm": 2.0700013637542725,
|
| 674 |
-
"learning_rate": 2.7720000000000002e-05,
|
| 675 |
-
"loss": 0.0831,
|
| 676 |
-
"step": 760
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 0.19439535470840696,
|
| 680 |
-
"grad_norm": 0.765533983707428,
|
| 681 |
-
"learning_rate": 2.769e-05,
|
| 682 |
-
"loss": 0.0707,
|
| 683 |
-
"step": 770
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 0.19691996970462006,
|
| 687 |
-
"grad_norm": 1.6104159355163574,
|
| 688 |
-
"learning_rate": 2.7660000000000003e-05,
|
| 689 |
-
"loss": 0.073,
|
| 690 |
-
"step": 780
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 0.19944458470083312,
|
| 694 |
-
"grad_norm": 1.1069729328155518,
|
| 695 |
-
"learning_rate": 2.763e-05,
|
| 696 |
-
"loss": 0.0702,
|
| 697 |
-
"step": 790
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 0.2019691996970462,
|
| 701 |
-
"grad_norm": 1.6577630043029785,
|
| 702 |
-
"learning_rate": 2.7600000000000003e-05,
|
| 703 |
-
"loss": 0.0865,
|
| 704 |
-
"step": 800
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 0.2019691996970462,
|
| 708 |
-
"eval_f1": 0.5952780441035476,
|
| 709 |
-
"eval_loss": 0.058820515871047974,
|
| 710 |
-
"eval_runtime": 917.4267,
|
| 711 |
-
"eval_samples_per_second": 224.827,
|
| 712 |
-
"eval_steps_per_second": 3.513,
|
| 713 |
-
"step": 800
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 0.20449381469325928,
|
| 717 |
-
"grad_norm": 1.5197840929031372,
|
| 718 |
-
"learning_rate": 2.7570000000000002e-05,
|
| 719 |
-
"loss": 0.0846,
|
| 720 |
-
"step": 810
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 0.20701842968947234,
|
| 724 |
-
"grad_norm": 1.1758556365966797,
|
| 725 |
-
"learning_rate": 2.754e-05,
|
| 726 |
-
"loss": 0.0813,
|
| 727 |
-
"step": 820
|
| 728 |
-
},
|
| 729 |
-
{
|
| 730 |
-
"epoch": 0.20954304468568544,
|
| 731 |
-
"grad_norm": 0.5016022324562073,
|
| 732 |
-
"learning_rate": 2.7510000000000003e-05,
|
| 733 |
-
"loss": 0.0718,
|
| 734 |
-
"step": 830
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 0.2120676596818985,
|
| 738 |
-
"grad_norm": 1.3600627183914185,
|
| 739 |
-
"learning_rate": 2.748e-05,
|
| 740 |
-
"loss": 0.0942,
|
| 741 |
-
"step": 840
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 0.2145922746781116,
|
| 745 |
-
"grad_norm": 0.6990534067153931,
|
| 746 |
-
"learning_rate": 2.7450000000000003e-05,
|
| 747 |
-
"loss": 0.0767,
|
| 748 |
-
"step": 850
|
| 749 |
-
},
|
| 750 |
-
{
|
| 751 |
-
"epoch": 0.2145922746781116,
|
| 752 |
-
"eval_f1": 0.5918155918155918,
|
| 753 |
-
"eval_loss": 0.04372716695070267,
|
| 754 |
-
"eval_runtime": 913.4291,
|
| 755 |
-
"eval_samples_per_second": 225.811,
|
| 756 |
-
"eval_steps_per_second": 3.528,
|
| 757 |
-
"step": 850
|
| 758 |
-
},
|
| 759 |
-
{
|
| 760 |
-
"epoch": 0.21711688967432466,
|
| 761 |
-
"grad_norm": 1.0468288660049438,
|
| 762 |
-
"learning_rate": 2.7420000000000002e-05,
|
| 763 |
-
"loss": 0.0805,
|
| 764 |
-
"step": 860
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 0.21964150467053775,
|
| 768 |
-
"grad_norm": 1.2046771049499512,
|
| 769 |
-
"learning_rate": 2.739e-05,
|
| 770 |
-
"loss": 0.0879,
|
| 771 |
-
"step": 870
|
| 772 |
-
},
|
| 773 |
-
{
|
| 774 |
-
"epoch": 0.22216611966675082,
|
| 775 |
-
"grad_norm": 0.9044977426528931,
|
| 776 |
-
"learning_rate": 2.7360000000000002e-05,
|
| 777 |
-
"loss": 0.0597,
|
| 778 |
-
"step": 880
|
| 779 |
-
},
|
| 780 |
-
{
|
| 781 |
-
"epoch": 0.2246907346629639,
|
| 782 |
-
"grad_norm": 1.145572304725647,
|
| 783 |
-
"learning_rate": 2.733e-05,
|
| 784 |
-
"loss": 0.1007,
|
| 785 |
-
"step": 890
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 0.22721534965917697,
|
| 789 |
-
"grad_norm": 1.058166742324829,
|
| 790 |
-
"learning_rate": 2.7300000000000003e-05,
|
| 791 |
-
"loss": 0.0773,
|
| 792 |
-
"step": 900
|
| 793 |
-
},
|
| 794 |
-
{
|
| 795 |
-
"epoch": 0.22721534965917697,
|
| 796 |
-
"eval_f1": 0.5956852791878172,
|
| 797 |
-
"eval_loss": 0.05675825849175453,
|
| 798 |
-
"eval_runtime": 923.1927,
|
| 799 |
-
"eval_samples_per_second": 223.422,
|
| 800 |
-
"eval_steps_per_second": 3.491,
|
| 801 |
-
"step": 900
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 0.22973996465539007,
|
| 805 |
-
"grad_norm": 0.7665570974349976,
|
| 806 |
-
"learning_rate": 2.727e-05,
|
| 807 |
-
"loss": 0.084,
|
| 808 |
-
"step": 910
|
| 809 |
-
},
|
| 810 |
-
{
|
| 811 |
-
"epoch": 0.23226457965160313,
|
| 812 |
-
"grad_norm": 0.8884145021438599,
|
| 813 |
-
"learning_rate": 2.724e-05,
|
| 814 |
-
"loss": 0.0748,
|
| 815 |
-
"step": 920
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 0.2347891946478162,
|
| 819 |
-
"grad_norm": 0.7132917046546936,
|
| 820 |
-
"learning_rate": 2.7210000000000002e-05,
|
| 821 |
-
"loss": 0.0861,
|
| 822 |
-
"step": 930
|
| 823 |
-
},
|
| 824 |
-
{
|
| 825 |
-
"epoch": 0.2373138096440293,
|
| 826 |
-
"grad_norm": 1.3353750705718994,
|
| 827 |
-
"learning_rate": 2.718e-05,
|
| 828 |
-
"loss": 0.091,
|
| 829 |
-
"step": 940
|
| 830 |
-
},
|
| 831 |
-
{
|
| 832 |
-
"epoch": 0.23983842464024235,
|
| 833 |
-
"grad_norm": 1.216691255569458,
|
| 834 |
-
"learning_rate": 2.7150000000000003e-05,
|
| 835 |
-
"loss": 0.0748,
|
| 836 |
-
"step": 950
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 0.23983842464024235,
|
| 840 |
-
"eval_f1": 0.5942299042601041,
|
| 841 |
-
"eval_loss": 0.04645048826932907,
|
| 842 |
-
"eval_runtime": 919.478,
|
| 843 |
-
"eval_samples_per_second": 224.325,
|
| 844 |
-
"eval_steps_per_second": 3.505,
|
| 845 |
-
"step": 950
|
| 846 |
-
},
|
| 847 |
-
{
|
| 848 |
-
"epoch": 0.24236303963645545,
|
| 849 |
-
"grad_norm": 1.0420501232147217,
|
| 850 |
-
"learning_rate": 2.712e-05,
|
| 851 |
-
"loss": 0.0953,
|
| 852 |
-
"step": 960
|
| 853 |
-
},
|
| 854 |
-
{
|
| 855 |
-
"epoch": 0.2448876546326685,
|
| 856 |
-
"grad_norm": 1.1488158702850342,
|
| 857 |
-
"learning_rate": 2.709e-05,
|
| 858 |
-
"loss": 0.0796,
|
| 859 |
-
"step": 970
|
| 860 |
-
},
|
| 861 |
-
{
|
| 862 |
-
"epoch": 0.2474122696288816,
|
| 863 |
-
"grad_norm": 0.7872379422187805,
|
| 864 |
-
"learning_rate": 2.7060000000000002e-05,
|
| 865 |
-
"loss": 0.0844,
|
| 866 |
-
"step": 980
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 0.24993688462509467,
|
| 870 |
-
"grad_norm": 0.9102885127067566,
|
| 871 |
-
"learning_rate": 2.703e-05,
|
| 872 |
-
"loss": 0.0792,
|
| 873 |
-
"step": 990
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 0.25246149962130776,
|
| 877 |
-
"grad_norm": 1.040650486946106,
|
| 878 |
-
"learning_rate": 2.7000000000000002e-05,
|
| 879 |
-
"loss": 0.0761,
|
| 880 |
-
"step": 1000
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 0.25246149962130776,
|
| 884 |
-
"eval_f1": NaN,
|
| 885 |
-
"eval_loss": 0.06595388799905777,
|
| 886 |
-
"eval_runtime": 948.4123,
|
| 887 |
-
"eval_samples_per_second": 217.481,
|
| 888 |
-
"eval_steps_per_second": 3.398,
|
| 889 |
-
"step": 1000
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 0.25498611461752085,
|
| 893 |
-
"grad_norm": 1.0717836618423462,
|
| 894 |
-
"learning_rate": 2.697e-05,
|
| 895 |
-
"loss": 0.0569,
|
| 896 |
-
"step": 1010
|
| 897 |
-
},
|
| 898 |
-
{
|
| 899 |
-
"epoch": 0.2575107296137339,
|
| 900 |
-
"grad_norm": 0.7504699230194092,
|
| 901 |
-
"learning_rate": 2.6940000000000003e-05,
|
| 902 |
-
"loss": 0.072,
|
| 903 |
-
"step": 1020
|
| 904 |
-
},
|
| 905 |
-
{
|
| 906 |
-
"epoch": 0.260035344609947,
|
| 907 |
-
"grad_norm": 0.9767778515815735,
|
| 908 |
-
"learning_rate": 2.691e-05,
|
| 909 |
-
"loss": 0.0658,
|
| 910 |
-
"step": 1030
|
| 911 |
-
},
|
| 912 |
-
{
|
| 913 |
-
"epoch": 0.2625599596061601,
|
| 914 |
-
"grad_norm": 0.5905674695968628,
|
| 915 |
-
"learning_rate": 2.688e-05,
|
| 916 |
-
"loss": 0.0775,
|
| 917 |
-
"step": 1040
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 0.2650845746023731,
|
| 921 |
-
"grad_norm": 1.6352293491363525,
|
| 922 |
-
"learning_rate": 2.6850000000000002e-05,
|
| 923 |
-
"loss": 0.0855,
|
| 924 |
-
"step": 1050
|
| 925 |
-
},
|
| 926 |
-
{
|
| 927 |
-
"epoch": 0.2650845746023731,
|
| 928 |
-
"eval_f1": 0.5963938973647711,
|
| 929 |
-
"eval_loss": 0.04910014942288399,
|
| 930 |
-
"eval_runtime": 986.8376,
|
| 931 |
-
"eval_samples_per_second": 209.013,
|
| 932 |
-
"eval_steps_per_second": 3.266,
|
| 933 |
-
"step": 1050
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 0.2676091895985862,
|
| 937 |
-
"grad_norm": 0.6634190082550049,
|
| 938 |
-
"learning_rate": 2.682e-05,
|
| 939 |
-
"loss": 0.0741,
|
| 940 |
-
"step": 1060
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 0.2701338045947993,
|
| 944 |
-
"grad_norm": 0.5896914601325989,
|
| 945 |
-
"learning_rate": 2.6790000000000003e-05,
|
| 946 |
-
"loss": 0.0713,
|
| 947 |
-
"step": 1070
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 0.2726584195910124,
|
| 951 |
-
"grad_norm": 1.3768564462661743,
|
| 952 |
-
"learning_rate": 2.676e-05,
|
| 953 |
-
"loss": 0.0684,
|
| 954 |
-
"step": 1080
|
| 955 |
-
},
|
| 956 |
-
{
|
| 957 |
-
"epoch": 0.27518303458722543,
|
| 958 |
-
"grad_norm": 0.7323074340820312,
|
| 959 |
-
"learning_rate": 2.673e-05,
|
| 960 |
-
"loss": 0.084,
|
| 961 |
-
"step": 1090
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 0.2777076495834385,
|
| 965 |
-
"grad_norm": 0.6660707592964172,
|
| 966 |
-
"learning_rate": 2.6700000000000002e-05,
|
| 967 |
-
"loss": 0.0832,
|
| 968 |
-
"step": 1100
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 0.2777076495834385,
|
| 972 |
-
"eval_f1": 0.6048397002825205,
|
| 973 |
-
"eval_loss": 0.049847185611724854,
|
| 974 |
-
"eval_runtime": 967.6797,
|
| 975 |
-
"eval_samples_per_second": 213.151,
|
| 976 |
-
"eval_steps_per_second": 3.331,
|
| 977 |
-
"step": 1100
|
| 978 |
-
},
|
| 979 |
-
{
|
| 980 |
-
"epoch": 0.2802322645796516,
|
| 981 |
-
"grad_norm": 1.425309419631958,
|
| 982 |
-
"learning_rate": 2.667e-05,
|
| 983 |
-
"loss": 0.0793,
|
| 984 |
-
"step": 1110
|
| 985 |
-
},
|
| 986 |
-
{
|
| 987 |
-
"epoch": 0.2827568795758647,
|
| 988 |
-
"grad_norm": 1.3583918809890747,
|
| 989 |
-
"learning_rate": 2.6640000000000002e-05,
|
| 990 |
-
"loss": 0.0808,
|
| 991 |
-
"step": 1120
|
| 992 |
-
},
|
| 993 |
-
{
|
| 994 |
-
"epoch": 0.28528149457207774,
|
| 995 |
-
"grad_norm": 1.1851533651351929,
|
| 996 |
-
"learning_rate": 2.661e-05,
|
| 997 |
-
"loss": 0.0738,
|
| 998 |
-
"step": 1130
|
| 999 |
-
},
|
| 1000 |
-
{
|
| 1001 |
-
"epoch": 0.28780610956829084,
|
| 1002 |
-
"grad_norm": 1.4497005939483643,
|
| 1003 |
-
"learning_rate": 2.658e-05,
|
| 1004 |
-
"loss": 0.078,
|
| 1005 |
-
"step": 1140
|
| 1006 |
-
},
|
| 1007 |
-
{
|
| 1008 |
-
"epoch": 0.29033072456450393,
|
| 1009 |
-
"grad_norm": 1.4407027959823608,
|
| 1010 |
-
"learning_rate": 2.655e-05,
|
| 1011 |
-
"loss": 0.0821,
|
| 1012 |
-
"step": 1150
|
| 1013 |
-
},
|
| 1014 |
-
{
|
| 1015 |
-
"epoch": 0.29033072456450393,
|
| 1016 |
-
"eval_f1": 0.6031633616619453,
|
| 1017 |
-
"eval_loss": 0.059650588780641556,
|
| 1018 |
-
"eval_runtime": 962.0892,
|
| 1019 |
-
"eval_samples_per_second": 214.39,
|
| 1020 |
-
"eval_steps_per_second": 3.35,
|
| 1021 |
-
"step": 1150
|
| 1022 |
-
},
|
| 1023 |
-
{
|
| 1024 |
-
"epoch": 0.29285533956071697,
|
| 1025 |
-
"grad_norm": 1.0721668004989624,
|
| 1026 |
-
"learning_rate": 2.652e-05,
|
| 1027 |
-
"loss": 0.0706,
|
| 1028 |
-
"step": 1160
|
| 1029 |
-
},
|
| 1030 |
-
{
|
| 1031 |
-
"epoch": 0.29537995455693006,
|
| 1032 |
-
"grad_norm": 1.1033729314804077,
|
| 1033 |
-
"learning_rate": 2.6490000000000002e-05,
|
| 1034 |
-
"loss": 0.0737,
|
| 1035 |
-
"step": 1170
|
| 1036 |
-
},
|
| 1037 |
-
{
|
| 1038 |
-
"epoch": 0.29790456955314315,
|
| 1039 |
-
"grad_norm": 0.9764577746391296,
|
| 1040 |
-
"learning_rate": 2.646e-05,
|
| 1041 |
-
"loss": 0.0743,
|
| 1042 |
-
"step": 1180
|
| 1043 |
-
},
|
| 1044 |
-
{
|
| 1045 |
-
"epoch": 0.30042918454935624,
|
| 1046 |
-
"grad_norm": 1.2160297632217407,
|
| 1047 |
-
"learning_rate": 2.643e-05,
|
| 1048 |
-
"loss": 0.0768,
|
| 1049 |
-
"step": 1190
|
| 1050 |
-
},
|
| 1051 |
-
{
|
| 1052 |
-
"epoch": 0.3029537995455693,
|
| 1053 |
-
"grad_norm": 0.8387085795402527,
|
| 1054 |
-
"learning_rate": 2.64e-05,
|
| 1055 |
-
"loss": 0.0715,
|
| 1056 |
-
"step": 1200
|
| 1057 |
-
},
|
| 1058 |
-
{
|
| 1059 |
-
"epoch": 0.3029537995455693,
|
| 1060 |
-
"eval_f1": NaN,
|
| 1061 |
-
"eval_loss": 0.06428094953298569,
|
| 1062 |
-
"eval_runtime": 961.1037,
|
| 1063 |
-
"eval_samples_per_second": 214.61,
|
| 1064 |
-
"eval_steps_per_second": 3.353,
|
| 1065 |
-
"step": 1200
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 0.3054784145417824,
|
| 1069 |
-
"grad_norm": 1.061087727546692,
|
| 1070 |
-
"learning_rate": 2.637e-05,
|
| 1071 |
-
"loss": 0.0672,
|
| 1072 |
-
"step": 1210
|
| 1073 |
-
},
|
| 1074 |
-
{
|
| 1075 |
-
"epoch": 0.30800302953799547,
|
| 1076 |
-
"grad_norm": 0.6768150925636292,
|
| 1077 |
-
"learning_rate": 2.6340000000000002e-05,
|
| 1078 |
-
"loss": 0.0762,
|
| 1079 |
-
"step": 1220
|
| 1080 |
-
},
|
| 1081 |
-
{
|
| 1082 |
-
"epoch": 0.31052764453420856,
|
| 1083 |
-
"grad_norm": 0.7020296454429626,
|
| 1084 |
-
"learning_rate": 2.631e-05,
|
| 1085 |
-
"loss": 0.0838,
|
| 1086 |
-
"step": 1230
|
| 1087 |
-
},
|
| 1088 |
-
{
|
| 1089 |
-
"epoch": 0.3130522595304216,
|
| 1090 |
-
"grad_norm": 0.9264736175537109,
|
| 1091 |
-
"learning_rate": 2.628e-05,
|
| 1092 |
-
"loss": 0.0769,
|
| 1093 |
-
"step": 1240
|
| 1094 |
-
},
|
| 1095 |
-
{
|
| 1096 |
-
"epoch": 0.3155768745266347,
|
| 1097 |
-
"grad_norm": 0.657778799533844,
|
| 1098 |
-
"learning_rate": 2.625e-05,
|
| 1099 |
-
"loss": 0.085,
|
| 1100 |
-
"step": 1250
|
| 1101 |
-
},
|
| 1102 |
-
{
|
| 1103 |
-
"epoch": 0.3155768745266347,
|
| 1104 |
-
"eval_f1": 0.6054250016184373,
|
| 1105 |
-
"eval_loss": 0.06593530625104904,
|
| 1106 |
-
"eval_runtime": 970.0262,
|
| 1107 |
-
"eval_samples_per_second": 212.635,
|
| 1108 |
-
"eval_steps_per_second": 3.323,
|
| 1109 |
-
"step": 1250
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"epoch": 0.3181014895228478,
|
| 1113 |
-
"grad_norm": 0.6904731392860413,
|
| 1114 |
-
"learning_rate": 2.622e-05,
|
| 1115 |
-
"loss": 0.0736,
|
| 1116 |
-
"step": 1260
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 0.3206261045190608,
|
| 1120 |
-
"grad_norm": 1.4745820760726929,
|
| 1121 |
-
"learning_rate": 2.619e-05,
|
| 1122 |
-
"loss": 0.0832,
|
| 1123 |
-
"step": 1270
|
| 1124 |
-
},
|
| 1125 |
-
{
|
| 1126 |
-
"epoch": 0.3231507195152739,
|
| 1127 |
-
"grad_norm": 1.0614553689956665,
|
| 1128 |
-
"learning_rate": 2.616e-05,
|
| 1129 |
-
"loss": 0.0781,
|
| 1130 |
-
"step": 1280
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 0.325675334511487,
|
| 1134 |
-
"grad_norm": 1.2228913307189941,
|
| 1135 |
-
"learning_rate": 2.6130000000000002e-05,
|
| 1136 |
-
"loss": 0.0872,
|
| 1137 |
-
"step": 1290
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 0.3281999495077001,
|
| 1141 |
-
"grad_norm": 0.9905760288238525,
|
| 1142 |
-
"learning_rate": 2.61e-05,
|
| 1143 |
-
"loss": 0.0826,
|
| 1144 |
-
"step": 1300
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 0.3281999495077001,
|
| 1148 |
-
"eval_f1": 0.6011740745177908,
|
| 1149 |
-
"eval_loss": 0.05560224503278732,
|
| 1150 |
-
"eval_runtime": 964.1962,
|
| 1151 |
-
"eval_samples_per_second": 213.921,
|
| 1152 |
-
"eval_steps_per_second": 3.343,
|
| 1153 |
-
"step": 1300
|
| 1154 |
-
},
|
| 1155 |
-
{
|
| 1156 |
-
"epoch": 0.33072456450391313,
|
| 1157 |
-
"grad_norm": 1.1195616722106934,
|
| 1158 |
-
"learning_rate": 2.607e-05,
|
| 1159 |
-
"loss": 0.0751,
|
| 1160 |
-
"step": 1310
|
| 1161 |
-
},
|
| 1162 |
-
{
|
| 1163 |
-
"epoch": 0.3332491795001262,
|
| 1164 |
-
"grad_norm": 0.9830445647239685,
|
| 1165 |
-
"learning_rate": 2.604e-05,
|
| 1166 |
-
"loss": 0.0694,
|
| 1167 |
-
"step": 1320
|
| 1168 |
-
},
|
| 1169 |
-
{
|
| 1170 |
-
"epoch": 0.3357737944963393,
|
| 1171 |
-
"grad_norm": 1.7140698432922363,
|
| 1172 |
-
"learning_rate": 2.601e-05,
|
| 1173 |
-
"loss": 0.0694,
|
| 1174 |
-
"step": 1330
|
| 1175 |
-
},
|
| 1176 |
-
{
|
| 1177 |
-
"epoch": 0.3382984094925524,
|
| 1178 |
-
"grad_norm": 0.9545607566833496,
|
| 1179 |
-
"learning_rate": 2.5980000000000002e-05,
|
| 1180 |
-
"loss": 0.0626,
|
| 1181 |
-
"step": 1340
|
| 1182 |
-
},
|
| 1183 |
-
{
|
| 1184 |
-
"epoch": 0.34082302448876545,
|
| 1185 |
-
"grad_norm": 0.8236456513404846,
|
| 1186 |
-
"learning_rate": 2.595e-05,
|
| 1187 |
-
"loss": 0.064,
|
| 1188 |
-
"step": 1350
|
| 1189 |
-
},
|
| 1190 |
-
{
|
| 1191 |
-
"epoch": 0.34082302448876545,
|
| 1192 |
-
"eval_f1": NaN,
|
| 1193 |
-
"eval_loss": 0.0564185306429863,
|
| 1194 |
-
"eval_runtime": 1030.8018,
|
| 1195 |
-
"eval_samples_per_second": 200.099,
|
| 1196 |
-
"eval_steps_per_second": 3.127,
|
| 1197 |
-
"step": 1350
|
| 1198 |
-
},
|
| 1199 |
-
{
|
| 1200 |
-
"epoch": 0.34334763948497854,
|
| 1201 |
-
"grad_norm": 1.0344712734222412,
|
| 1202 |
-
"learning_rate": 2.592e-05,
|
| 1203 |
-
"loss": 0.074,
|
| 1204 |
-
"step": 1360
|
| 1205 |
-
},
|
| 1206 |
-
{
|
| 1207 |
-
"epoch": 0.34587225448119163,
|
| 1208 |
-
"grad_norm": 1.647894024848938,
|
| 1209 |
-
"learning_rate": 2.589e-05,
|
| 1210 |
-
"loss": 0.0756,
|
| 1211 |
-
"step": 1370
|
| 1212 |
-
},
|
| 1213 |
-
{
|
| 1214 |
-
"epoch": 0.34839686947740467,
|
| 1215 |
-
"grad_norm": 1.0268642902374268,
|
| 1216 |
-
"learning_rate": 2.586e-05,
|
| 1217 |
-
"loss": 0.064,
|
| 1218 |
-
"step": 1380
|
| 1219 |
-
},
|
| 1220 |
-
{
|
| 1221 |
-
"epoch": 0.35092148447361776,
|
| 1222 |
-
"grad_norm": 0.6588199734687805,
|
| 1223 |
-
"learning_rate": 2.5830000000000002e-05,
|
| 1224 |
-
"loss": 0.0685,
|
| 1225 |
-
"step": 1390
|
| 1226 |
-
},
|
| 1227 |
-
{
|
| 1228 |
-
"epoch": 0.35344609946983085,
|
| 1229 |
-
"grad_norm": 0.8278918862342834,
|
| 1230 |
-
"learning_rate": 2.58e-05,
|
| 1231 |
-
"loss": 0.0854,
|
| 1232 |
-
"step": 1400
|
| 1233 |
-
},
|
| 1234 |
-
{
|
| 1235 |
-
"epoch": 0.35344609946983085,
|
| 1236 |
-
"eval_f1": NaN,
|
| 1237 |
-
"eval_loss": 0.05516933649778366,
|
| 1238 |
-
"eval_runtime": 1032.3177,
|
| 1239 |
-
"eval_samples_per_second": 199.805,
|
| 1240 |
-
"eval_steps_per_second": 3.122,
|
| 1241 |
-
"step": 1400
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 0.35597071446604395,
|
| 1245 |
-
"grad_norm": 0.4216013550758362,
|
| 1246 |
-
"learning_rate": 2.577e-05,
|
| 1247 |
-
"loss": 0.0785,
|
| 1248 |
-
"step": 1410
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 0.358495329462257,
|
| 1252 |
-
"grad_norm": 0.9567118287086487,
|
| 1253 |
-
"learning_rate": 2.574e-05,
|
| 1254 |
-
"loss": 0.089,
|
| 1255 |
-
"step": 1420
|
| 1256 |
-
},
|
| 1257 |
-
{
|
| 1258 |
-
"epoch": 0.3610199444584701,
|
| 1259 |
-
"grad_norm": 1.3202637434005737,
|
| 1260 |
-
"learning_rate": 2.571e-05,
|
| 1261 |
-
"loss": 0.0884,
|
| 1262 |
-
"step": 1430
|
| 1263 |
-
},
|
| 1264 |
-
{
|
| 1265 |
-
"epoch": 0.36354455945468317,
|
| 1266 |
-
"grad_norm": 1.3245704174041748,
|
| 1267 |
-
"learning_rate": 2.568e-05,
|
| 1268 |
-
"loss": 0.0739,
|
| 1269 |
-
"step": 1440
|
| 1270 |
-
},
|
| 1271 |
-
{
|
| 1272 |
-
"epoch": 0.36606917445089626,
|
| 1273 |
-
"grad_norm": 0.6416196823120117,
|
| 1274 |
-
"learning_rate": 2.565e-05,
|
| 1275 |
-
"loss": 0.0702,
|
| 1276 |
-
"step": 1450
|
| 1277 |
-
},
|
| 1278 |
-
{
|
| 1279 |
-
"epoch": 0.36606917445089626,
|
| 1280 |
-
"eval_f1": 0.6061020319393525,
|
| 1281 |
-
"eval_loss": 0.06748606264591217,
|
| 1282 |
-
"eval_runtime": 999.3826,
|
| 1283 |
-
"eval_samples_per_second": 206.389,
|
| 1284 |
-
"eval_steps_per_second": 3.225,
|
| 1285 |
-
"step": 1450
|
| 1286 |
-
},
|
| 1287 |
-
{
|
| 1288 |
-
"epoch": 0.3685937894471093,
|
| 1289 |
-
"grad_norm": 0.9312785267829895,
|
| 1290 |
-
"learning_rate": 2.562e-05,
|
| 1291 |
-
"loss": 0.0674,
|
| 1292 |
-
"step": 1460
|
| 1293 |
-
},
|
| 1294 |
-
{
|
| 1295 |
-
"epoch": 0.3711184044433224,
|
| 1296 |
-
"grad_norm": 0.9092572927474976,
|
| 1297 |
-
"learning_rate": 2.559e-05,
|
| 1298 |
-
"loss": 0.0676,
|
| 1299 |
-
"step": 1470
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 0.3736430194395355,
|
| 1303 |
-
"grad_norm": 1.4935100078582764,
|
| 1304 |
-
"learning_rate": 2.556e-05,
|
| 1305 |
-
"loss": 0.0712,
|
| 1306 |
-
"step": 1480
|
| 1307 |
-
},
|
| 1308 |
-
{
|
| 1309 |
-
"epoch": 0.3761676344357485,
|
| 1310 |
-
"grad_norm": 0.9569060802459717,
|
| 1311 |
-
"learning_rate": 2.553e-05,
|
| 1312 |
-
"loss": 0.0747,
|
| 1313 |
-
"step": 1490
|
| 1314 |
-
},
|
| 1315 |
-
{
|
| 1316 |
-
"epoch": 0.3786922494319616,
|
| 1317 |
-
"grad_norm": 0.947384774684906,
|
| 1318 |
-
"learning_rate": 2.55e-05,
|
| 1319 |
-
"loss": 0.0771,
|
| 1320 |
-
"step": 1500
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"epoch": 0.3786922494319616,
|
| 1324 |
-
"eval_f1": NaN,
|
| 1325 |
-
"eval_loss": 0.057753585278987885,
|
| 1326 |
-
"eval_runtime": 1000.0105,
|
| 1327 |
-
"eval_samples_per_second": 206.26,
|
| 1328 |
-
"eval_steps_per_second": 3.223,
|
| 1329 |
-
"step": 1500
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 0.3812168644281747,
|
| 1333 |
-
"grad_norm": 0.6996080875396729,
|
| 1334 |
-
"learning_rate": 2.547e-05,
|
| 1335 |
-
"loss": 0.0696,
|
| 1336 |
-
"step": 1510
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 0.3837414794243878,
|
| 1340 |
-
"grad_norm": 0.5415595173835754,
|
| 1341 |
-
"learning_rate": 2.544e-05,
|
| 1342 |
-
"loss": 0.0757,
|
| 1343 |
-
"step": 1520
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 0.38626609442060084,
|
| 1347 |
-
"grad_norm": 0.5137012600898743,
|
| 1348 |
-
"learning_rate": 2.541e-05,
|
| 1349 |
-
"loss": 0.0621,
|
| 1350 |
-
"step": 1530
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 0.38879070941681393,
|
| 1354 |
-
"grad_norm": 0.9606865048408508,
|
| 1355 |
-
"learning_rate": 2.538e-05,
|
| 1356 |
-
"loss": 0.073,
|
| 1357 |
-
"step": 1540
|
| 1358 |
-
},
|
| 1359 |
-
{
|
| 1360 |
-
"epoch": 0.391315324413027,
|
| 1361 |
-
"grad_norm": 1.1751604080200195,
|
| 1362 |
-
"learning_rate": 2.535e-05,
|
| 1363 |
-
"loss": 0.08,
|
| 1364 |
-
"step": 1550
|
| 1365 |
-
},
|
| 1366 |
-
{
|
| 1367 |
-
"epoch": 0.391315324413027,
|
| 1368 |
-
"eval_f1": NaN,
|
| 1369 |
-
"eval_loss": 0.0491572804749012,
|
| 1370 |
-
"eval_runtime": 963.3777,
|
| 1371 |
-
"eval_samples_per_second": 214.103,
|
| 1372 |
-
"eval_steps_per_second": 3.346,
|
| 1373 |
-
"step": 1550
|
| 1374 |
-
},
|
| 1375 |
-
{
|
| 1376 |
-
"epoch": 0.3938399394092401,
|
| 1377 |
-
"grad_norm": 0.935338020324707,
|
| 1378 |
-
"learning_rate": 2.5319999999999998e-05,
|
| 1379 |
-
"loss": 0.0729,
|
| 1380 |
-
"step": 1560
|
| 1381 |
-
},
|
| 1382 |
-
{
|
| 1383 |
-
"epoch": 0.39636455440545315,
|
| 1384 |
-
"grad_norm": 0.7157814502716064,
|
| 1385 |
-
"learning_rate": 2.529e-05,
|
| 1386 |
-
"loss": 0.0719,
|
| 1387 |
-
"step": 1570
|
| 1388 |
-
},
|
| 1389 |
-
{
|
| 1390 |
-
"epoch": 0.39888916940166624,
|
| 1391 |
-
"grad_norm": 0.6739543676376343,
|
| 1392 |
-
"learning_rate": 2.526e-05,
|
| 1393 |
-
"loss": 0.0631,
|
| 1394 |
-
"step": 1580
|
| 1395 |
-
},
|
| 1396 |
-
{
|
| 1397 |
-
"epoch": 0.40141378439787934,
|
| 1398 |
-
"grad_norm": 0.4896785318851471,
|
| 1399 |
-
"learning_rate": 2.523e-05,
|
| 1400 |
-
"loss": 0.0746,
|
| 1401 |
-
"step": 1590
|
| 1402 |
-
},
|
| 1403 |
-
{
|
| 1404 |
-
"epoch": 0.4039383993940924,
|
| 1405 |
-
"grad_norm": 0.7619987726211548,
|
| 1406 |
-
"learning_rate": 2.52e-05,
|
| 1407 |
-
"loss": 0.0804,
|
| 1408 |
-
"step": 1600
|
| 1409 |
-
},
|
| 1410 |
-
{
|
| 1411 |
-
"epoch": 0.4039383993940924,
|
| 1412 |
-
"eval_f1": 0.6111605289687482,
|
| 1413 |
-
"eval_loss": 0.05378127843141556,
|
| 1414 |
-
"eval_runtime": 958.466,
|
| 1415 |
-
"eval_samples_per_second": 215.2,
|
| 1416 |
-
"eval_steps_per_second": 3.363,
|
| 1417 |
-
"step": 1600
|
| 1418 |
-
},
|
| 1419 |
-
{
|
| 1420 |
-
"epoch": 0.40646301439030547,
|
| 1421 |
-
"grad_norm": 0.7464210987091064,
|
| 1422 |
-
"learning_rate": 2.517e-05,
|
| 1423 |
-
"loss": 0.0707,
|
| 1424 |
-
"step": 1610
|
| 1425 |
-
},
|
| 1426 |
-
{
|
| 1427 |
-
"epoch": 0.40898762938651856,
|
| 1428 |
-
"grad_norm": 0.6707102656364441,
|
| 1429 |
-
"learning_rate": 2.514e-05,
|
| 1430 |
-
"loss": 0.0671,
|
| 1431 |
-
"step": 1620
|
| 1432 |
-
},
|
| 1433 |
-
{
|
| 1434 |
-
"epoch": 0.41151224438273165,
|
| 1435 |
-
"grad_norm": 1.246846079826355,
|
| 1436 |
-
"learning_rate": 2.511e-05,
|
| 1437 |
-
"loss": 0.0627,
|
| 1438 |
-
"step": 1630
|
| 1439 |
-
},
|
| 1440 |
-
{
|
| 1441 |
-
"epoch": 0.4140368593789447,
|
| 1442 |
-
"grad_norm": 0.9796457886695862,
|
| 1443 |
-
"learning_rate": 2.508e-05,
|
| 1444 |
-
"loss": 0.0677,
|
| 1445 |
-
"step": 1640
|
| 1446 |
-
},
|
| 1447 |
-
{
|
| 1448 |
-
"epoch": 0.4165614743751578,
|
| 1449 |
-
"grad_norm": 0.9717236161231995,
|
| 1450 |
-
"learning_rate": 2.505e-05,
|
| 1451 |
-
"loss": 0.083,
|
| 1452 |
-
"step": 1650
|
| 1453 |
-
},
|
| 1454 |
-
{
|
| 1455 |
-
"epoch": 0.4165614743751578,
|
| 1456 |
-
"eval_f1": 0.6047686163965234,
|
| 1457 |
-
"eval_loss": 0.057900335639715195,
|
| 1458 |
-
"eval_runtime": 962.7843,
|
| 1459 |
-
"eval_samples_per_second": 214.235,
|
| 1460 |
-
"eval_steps_per_second": 3.348,
|
| 1461 |
-
"step": 1650
|
| 1462 |
-
},
|
| 1463 |
-
{
|
| 1464 |
-
"epoch": 0.4190860893713709,
|
| 1465 |
-
"grad_norm": 1.1706446409225464,
|
| 1466 |
-
"learning_rate": 2.502e-05,
|
| 1467 |
-
"loss": 0.0764,
|
| 1468 |
-
"step": 1660
|
| 1469 |
-
},
|
| 1470 |
-
{
|
| 1471 |
-
"epoch": 0.42161070436758397,
|
| 1472 |
-
"grad_norm": 0.45280393958091736,
|
| 1473 |
-
"learning_rate": 2.499e-05,
|
| 1474 |
-
"loss": 0.0682,
|
| 1475 |
-
"step": 1670
|
| 1476 |
-
},
|
| 1477 |
-
{
|
| 1478 |
-
"epoch": 0.424135319363797,
|
| 1479 |
-
"grad_norm": 1.0100760459899902,
|
| 1480 |
-
"learning_rate": 2.4959999999999998e-05,
|
| 1481 |
-
"loss": 0.0892,
|
| 1482 |
-
"step": 1680
|
| 1483 |
-
},
|
| 1484 |
-
{
|
| 1485 |
-
"epoch": 0.4266599343600101,
|
| 1486 |
-
"grad_norm": 1.0506736040115356,
|
| 1487 |
-
"learning_rate": 2.493e-05,
|
| 1488 |
-
"loss": 0.0666,
|
| 1489 |
-
"step": 1690
|
| 1490 |
-
},
|
| 1491 |
-
{
|
| 1492 |
-
"epoch": 0.4291845493562232,
|
| 1493 |
-
"grad_norm": 0.7978639006614685,
|
| 1494 |
-
"learning_rate": 2.49e-05,
|
| 1495 |
-
"loss": 0.0701,
|
| 1496 |
-
"step": 1700
|
| 1497 |
-
},
|
| 1498 |
-
{
|
| 1499 |
-
"epoch": 0.4291845493562232,
|
| 1500 |
-
"eval_f1": 0.6044656147662996,
|
| 1501 |
-
"eval_loss": 0.06738731265068054,
|
| 1502 |
-
"eval_runtime": 1102.7864,
|
| 1503 |
-
"eval_samples_per_second": 187.037,
|
| 1504 |
-
"eval_steps_per_second": 2.923,
|
| 1505 |
-
"step": 1700
|
| 1506 |
-
},
|
| 1507 |
-
{
|
| 1508 |
-
"epoch": 0.4317091643524363,
|
| 1509 |
-
"grad_norm": 1.121317982673645,
|
| 1510 |
-
"learning_rate": 2.487e-05,
|
| 1511 |
-
"loss": 0.0771,
|
| 1512 |
-
"step": 1710
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 0.4342337793486493,
|
| 1516 |
-
"grad_norm": 1.0836131572723389,
|
| 1517 |
-
"learning_rate": 2.484e-05,
|
| 1518 |
-
"loss": 0.0719,
|
| 1519 |
-
"step": 1720
|
| 1520 |
-
},
|
| 1521 |
-
{
|
| 1522 |
-
"epoch": 0.4367583943448624,
|
| 1523 |
-
"grad_norm": 0.61658775806427,
|
| 1524 |
-
"learning_rate": 2.4809999999999998e-05,
|
| 1525 |
-
"loss": 0.0681,
|
| 1526 |
-
"step": 1730
|
| 1527 |
-
},
|
| 1528 |
-
{
|
| 1529 |
-
"epoch": 0.4392830093410755,
|
| 1530 |
-
"grad_norm": 0.647393524646759,
|
| 1531 |
-
"learning_rate": 2.478e-05,
|
| 1532 |
-
"loss": 0.0668,
|
| 1533 |
-
"step": 1740
|
| 1534 |
-
},
|
| 1535 |
-
{
|
| 1536 |
-
"epoch": 0.44180762433728854,
|
| 1537 |
-
"grad_norm": 0.782483696937561,
|
| 1538 |
-
"learning_rate": 2.475e-05,
|
| 1539 |
-
"loss": 0.0721,
|
| 1540 |
-
"step": 1750
|
| 1541 |
-
},
|
| 1542 |
-
{
|
| 1543 |
-
"epoch": 0.44180762433728854,
|
| 1544 |
-
"eval_f1": 0.5979155238617663,
|
| 1545 |
-
"eval_loss": 0.04912808537483215,
|
| 1546 |
-
"eval_runtime": 1171.9033,
|
| 1547 |
-
"eval_samples_per_second": 176.006,
|
| 1548 |
-
"eval_steps_per_second": 2.75,
|
| 1549 |
-
"step": 1750
|
| 1550 |
-
},
|
| 1551 |
-
{
|
| 1552 |
-
"epoch": 0.44433223933350163,
|
| 1553 |
-
"grad_norm": 0.4538789987564087,
|
| 1554 |
-
"learning_rate": 2.472e-05,
|
| 1555 |
-
"loss": 0.0641,
|
| 1556 |
-
"step": 1760
|
| 1557 |
-
},
|
| 1558 |
-
{
|
| 1559 |
-
"epoch": 0.4468568543297147,
|
| 1560 |
-
"grad_norm": 0.7954159379005432,
|
| 1561 |
-
"learning_rate": 2.469e-05,
|
| 1562 |
-
"loss": 0.079,
|
| 1563 |
-
"step": 1770
|
| 1564 |
-
},
|
| 1565 |
-
{
|
| 1566 |
-
"epoch": 0.4493814693259278,
|
| 1567 |
-
"grad_norm": 0.4370203912258148,
|
| 1568 |
-
"learning_rate": 2.4659999999999998e-05,
|
| 1569 |
-
"loss": 0.0769,
|
| 1570 |
-
"step": 1780
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"epoch": 0.45190608432214086,
|
| 1574 |
-
"grad_norm": 1.2641068696975708,
|
| 1575 |
-
"learning_rate": 2.463e-05,
|
| 1576 |
-
"loss": 0.0649,
|
| 1577 |
-
"step": 1790
|
| 1578 |
},
|
| 1579 |
{
|
| 1580 |
-
"epoch": 0.
|
| 1581 |
-
"grad_norm":
|
| 1582 |
-
"learning_rate":
|
| 1583 |
-
"loss": 0.
|
| 1584 |
-
"step":
|
| 1585 |
},
|
| 1586 |
{
|
| 1587 |
-
"epoch": 0.
|
| 1588 |
"eval_f1": NaN,
|
| 1589 |
-
"eval_loss": 0.
|
| 1590 |
-
"eval_runtime":
|
| 1591 |
-
"eval_samples_per_second":
|
| 1592 |
-
"eval_steps_per_second": 2.
|
| 1593 |
-
"step":
|
| 1594 |
-
},
|
| 1595 |
-
{
|
| 1596 |
-
"epoch": 0.45695531431456704,
|
| 1597 |
-
"grad_norm": 1.0922938585281372,
|
| 1598 |
-
"learning_rate": 2.457e-05,
|
| 1599 |
-
"loss": 0.074,
|
| 1600 |
-
"step": 1810
|
| 1601 |
-
},
|
| 1602 |
-
{
|
| 1603 |
-
"epoch": 0.45947992931078013,
|
| 1604 |
-
"grad_norm": 0.8298421502113342,
|
| 1605 |
-
"learning_rate": 2.454e-05,
|
| 1606 |
-
"loss": 0.0778,
|
| 1607 |
-
"step": 1820
|
| 1608 |
-
},
|
| 1609 |
-
{
|
| 1610 |
-
"epoch": 0.46200454430699317,
|
| 1611 |
-
"grad_norm": 1.182712435722351,
|
| 1612 |
-
"learning_rate": 2.4509999999999997e-05,
|
| 1613 |
-
"loss": 0.0793,
|
| 1614 |
-
"step": 1830
|
| 1615 |
-
},
|
| 1616 |
-
{
|
| 1617 |
-
"epoch": 0.46452915930320626,
|
| 1618 |
-
"grad_norm": 0.7366443276405334,
|
| 1619 |
-
"learning_rate": 2.448e-05,
|
| 1620 |
-
"loss": 0.0655,
|
| 1621 |
-
"step": 1840
|
| 1622 |
-
},
|
| 1623 |
-
{
|
| 1624 |
-
"epoch": 0.46705377429941936,
|
| 1625 |
-
"grad_norm": 0.9185643792152405,
|
| 1626 |
-
"learning_rate": 2.4449999999999998e-05,
|
| 1627 |
-
"loss": 0.0692,
|
| 1628 |
-
"step": 1850
|
| 1629 |
-
},
|
| 1630 |
-
{
|
| 1631 |
-
"epoch": 0.46705377429941936,
|
| 1632 |
-
"eval_f1": 0.6057632592224568,
|
| 1633 |
-
"eval_loss": 0.04681675508618355,
|
| 1634 |
-
"eval_runtime": 1170.8075,
|
| 1635 |
-
"eval_samples_per_second": 176.171,
|
| 1636 |
-
"eval_steps_per_second": 2.753,
|
| 1637 |
-
"step": 1850
|
| 1638 |
-
},
|
| 1639 |
-
{
|
| 1640 |
-
"epoch": 0.4695783892956324,
|
| 1641 |
-
"grad_norm": 0.99897301197052,
|
| 1642 |
-
"learning_rate": 2.442e-05,
|
| 1643 |
-
"loss": 0.0685,
|
| 1644 |
-
"step": 1860
|
| 1645 |
-
},
|
| 1646 |
-
{
|
| 1647 |
-
"epoch": 0.4721030042918455,
|
| 1648 |
-
"grad_norm": 1.0028034448623657,
|
| 1649 |
-
"learning_rate": 2.439e-05,
|
| 1650 |
-
"loss": 0.0748,
|
| 1651 |
-
"step": 1870
|
| 1652 |
-
},
|
| 1653 |
-
{
|
| 1654 |
-
"epoch": 0.4746276192880586,
|
| 1655 |
-
"grad_norm": 2.5226945877075195,
|
| 1656 |
-
"learning_rate": 2.4360000000000004e-05,
|
| 1657 |
-
"loss": 0.0715,
|
| 1658 |
-
"step": 1880
|
| 1659 |
-
},
|
| 1660 |
-
{
|
| 1661 |
-
"epoch": 0.47715223428427167,
|
| 1662 |
-
"grad_norm": 0.903256893157959,
|
| 1663 |
-
"learning_rate": 2.4330000000000003e-05,
|
| 1664 |
-
"loss": 0.0709,
|
| 1665 |
-
"step": 1890
|
| 1666 |
-
},
|
| 1667 |
-
{
|
| 1668 |
-
"epoch": 0.4796768492804847,
|
| 1669 |
-
"grad_norm": 0.9269793629646301,
|
| 1670 |
-
"learning_rate": 2.43e-05,
|
| 1671 |
-
"loss": 0.0761,
|
| 1672 |
-
"step": 1900
|
| 1673 |
-
},
|
| 1674 |
-
{
|
| 1675 |
-
"epoch": 0.4796768492804847,
|
| 1676 |
-
"eval_f1": 0.6124984470120511,
|
| 1677 |
-
"eval_loss": 0.05741230770945549,
|
| 1678 |
-
"eval_runtime": 1159.3714,
|
| 1679 |
-
"eval_samples_per_second": 177.908,
|
| 1680 |
-
"eval_steps_per_second": 2.78,
|
| 1681 |
-
"step": 1900
|
| 1682 |
-
},
|
| 1683 |
-
{
|
| 1684 |
-
"epoch": 0.4822014642766978,
|
| 1685 |
-
"grad_norm": 1.0651170015335083,
|
| 1686 |
-
"learning_rate": 2.4270000000000003e-05,
|
| 1687 |
-
"loss": 0.0751,
|
| 1688 |
-
"step": 1910
|
| 1689 |
-
},
|
| 1690 |
-
{
|
| 1691 |
-
"epoch": 0.4847260792729109,
|
| 1692 |
-
"grad_norm": 1.2628437280654907,
|
| 1693 |
-
"learning_rate": 2.4240000000000002e-05,
|
| 1694 |
-
"loss": 0.0852,
|
| 1695 |
-
"step": 1920
|
| 1696 |
-
},
|
| 1697 |
-
{
|
| 1698 |
-
"epoch": 0.487250694269124,
|
| 1699 |
-
"grad_norm": 1.3889621496200562,
|
| 1700 |
-
"learning_rate": 2.4210000000000004e-05,
|
| 1701 |
-
"loss": 0.073,
|
| 1702 |
-
"step": 1930
|
| 1703 |
-
},
|
| 1704 |
-
{
|
| 1705 |
-
"epoch": 0.489775309265337,
|
| 1706 |
-
"grad_norm": 1.028456687927246,
|
| 1707 |
-
"learning_rate": 2.4180000000000002e-05,
|
| 1708 |
-
"loss": 0.0644,
|
| 1709 |
-
"step": 1940
|
| 1710 |
-
},
|
| 1711 |
-
{
|
| 1712 |
-
"epoch": 0.4922999242615501,
|
| 1713 |
-
"grad_norm": 0.6997565627098083,
|
| 1714 |
-
"learning_rate": 2.415e-05,
|
| 1715 |
-
"loss": 0.0757,
|
| 1716 |
-
"step": 1950
|
| 1717 |
-
},
|
| 1718 |
-
{
|
| 1719 |
-
"epoch": 0.4922999242615501,
|
| 1720 |
-
"eval_f1": 0.6126181795711549,
|
| 1721 |
-
"eval_loss": 0.05692484602332115,
|
| 1722 |
-
"eval_runtime": 1161.9825,
|
| 1723 |
-
"eval_samples_per_second": 177.509,
|
| 1724 |
-
"eval_steps_per_second": 2.774,
|
| 1725 |
-
"step": 1950
|
| 1726 |
-
},
|
| 1727 |
-
{
|
| 1728 |
-
"epoch": 0.4948245392577632,
|
| 1729 |
-
"grad_norm": 1.384186863899231,
|
| 1730 |
-
"learning_rate": 2.4120000000000003e-05,
|
| 1731 |
-
"loss": 0.0697,
|
| 1732 |
-
"step": 1960
|
| 1733 |
-
},
|
| 1734 |
-
{
|
| 1735 |
-
"epoch": 0.49734915425397624,
|
| 1736 |
-
"grad_norm": 0.8674394488334656,
|
| 1737 |
-
"learning_rate": 2.409e-05,
|
| 1738 |
-
"loss": 0.0739,
|
| 1739 |
-
"step": 1970
|
| 1740 |
-
},
|
| 1741 |
-
{
|
| 1742 |
-
"epoch": 0.49987376925018934,
|
| 1743 |
-
"grad_norm": 1.826121211051941,
|
| 1744 |
-
"learning_rate": 2.4060000000000003e-05,
|
| 1745 |
-
"loss": 0.0739,
|
| 1746 |
-
"step": 1980
|
| 1747 |
-
},
|
| 1748 |
-
{
|
| 1749 |
-
"epoch": 0.5023983842464024,
|
| 1750 |
-
"grad_norm": 0.6903666257858276,
|
| 1751 |
-
"learning_rate": 2.4030000000000002e-05,
|
| 1752 |
-
"loss": 0.0661,
|
| 1753 |
-
"step": 1990
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
-
"epoch": 0.
|
| 1757 |
-
"
|
| 1758 |
-
"
|
| 1759 |
-
"
|
| 1760 |
-
"
|
|
|
|
|
|
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
-
"epoch":
|
| 1764 |
-
"
|
| 1765 |
-
"
|
| 1766 |
-
"
|
| 1767 |
-
"eval_samples_per_second": 176.587,
|
| 1768 |
-
"eval_steps_per_second": 2.759,
|
| 1769 |
"step": 2000
|
| 1770 |
},
|
| 1771 |
{
|
| 1772 |
-
"epoch":
|
| 1773 |
-
"
|
| 1774 |
-
"
|
| 1775 |
-
"
|
| 1776 |
-
"
|
| 1777 |
-
},
|
| 1778 |
-
{
|
| 1779 |
-
"epoch": 0.5099722292350417,
|
| 1780 |
-
"grad_norm": 1.0800750255584717,
|
| 1781 |
-
"learning_rate": 2.394e-05,
|
| 1782 |
-
"loss": 0.0781,
|
| 1783 |
-
"step": 2020
|
| 1784 |
-
},
|
| 1785 |
-
{
|
| 1786 |
-
"epoch": 0.5124968442312547,
|
| 1787 |
-
"grad_norm": 1.0992929935455322,
|
| 1788 |
-
"learning_rate": 2.3910000000000003e-05,
|
| 1789 |
-
"loss": 0.0694,
|
| 1790 |
-
"step": 2030
|
| 1791 |
-
},
|
| 1792 |
-
{
|
| 1793 |
-
"epoch": 0.5150214592274678,
|
| 1794 |
-
"grad_norm": 0.703554093837738,
|
| 1795 |
-
"learning_rate": 2.3880000000000002e-05,
|
| 1796 |
-
"loss": 0.0881,
|
| 1797 |
-
"step": 2040
|
| 1798 |
-
},
|
| 1799 |
-
{
|
| 1800 |
-
"epoch": 0.5175460742236809,
|
| 1801 |
-
"grad_norm": 1.214089274406433,
|
| 1802 |
-
"learning_rate": 2.385e-05,
|
| 1803 |
-
"loss": 0.0736,
|
| 1804 |
-
"step": 2050
|
| 1805 |
-
},
|
| 1806 |
-
{
|
| 1807 |
-
"epoch": 0.5175460742236809,
|
| 1808 |
-
"eval_f1": 0.612187690432663,
|
| 1809 |
-
"eval_loss": 0.05384594947099686,
|
| 1810 |
-
"eval_runtime": 1155.7771,
|
| 1811 |
-
"eval_samples_per_second": 178.462,
|
| 1812 |
-
"eval_steps_per_second": 2.789,
|
| 1813 |
-
"step": 2050
|
| 1814 |
-
},
|
| 1815 |
-
{
|
| 1816 |
-
"epoch": 0.520070689219894,
|
| 1817 |
-
"grad_norm": 0.8359307050704956,
|
| 1818 |
-
"learning_rate": 2.3820000000000002e-05,
|
| 1819 |
-
"loss": 0.0759,
|
| 1820 |
-
"step": 2060
|
| 1821 |
-
},
|
| 1822 |
-
{
|
| 1823 |
-
"epoch": 0.522595304216107,
|
| 1824 |
-
"grad_norm": 1.6299511194229126,
|
| 1825 |
-
"learning_rate": 2.379e-05,
|
| 1826 |
-
"loss": 0.076,
|
| 1827 |
-
"step": 2070
|
| 1828 |
-
},
|
| 1829 |
-
{
|
| 1830 |
-
"epoch": 0.5251199192123202,
|
| 1831 |
-
"grad_norm": 0.6880617737770081,
|
| 1832 |
-
"learning_rate": 2.3760000000000003e-05,
|
| 1833 |
-
"loss": 0.0745,
|
| 1834 |
-
"step": 2080
|
| 1835 |
-
},
|
| 1836 |
-
{
|
| 1837 |
-
"epoch": 0.5276445342085332,
|
| 1838 |
-
"grad_norm": 0.7822777032852173,
|
| 1839 |
-
"learning_rate": 2.373e-05,
|
| 1840 |
-
"loss": 0.0697,
|
| 1841 |
-
"step": 2090
|
| 1842 |
-
},
|
| 1843 |
-
{
|
| 1844 |
-
"epoch": 0.5301691492047462,
|
| 1845 |
-
"grad_norm": 0.7941886782646179,
|
| 1846 |
-
"learning_rate": 2.37e-05,
|
| 1847 |
-
"loss": 0.0685,
|
| 1848 |
-
"step": 2100
|
| 1849 |
-
},
|
| 1850 |
-
{
|
| 1851 |
-
"epoch": 0.5301691492047462,
|
| 1852 |
-
"eval_f1": 0.6104315862855695,
|
| 1853 |
-
"eval_loss": 0.04854836314916611,
|
| 1854 |
-
"eval_runtime": 1154.0649,
|
| 1855 |
-
"eval_samples_per_second": 178.727,
|
| 1856 |
-
"eval_steps_per_second": 2.793,
|
| 1857 |
-
"step": 2100
|
| 1858 |
-
},
|
| 1859 |
-
{
|
| 1860 |
-
"epoch": 0.5326937642009594,
|
| 1861 |
-
"grad_norm": 0.948130190372467,
|
| 1862 |
-
"learning_rate": 2.3670000000000002e-05,
|
| 1863 |
-
"loss": 0.0706,
|
| 1864 |
-
"step": 2110
|
| 1865 |
-
},
|
| 1866 |
-
{
|
| 1867 |
-
"epoch": 0.5352183791971724,
|
| 1868 |
-
"grad_norm": 0.959032416343689,
|
| 1869 |
-
"learning_rate": 2.364e-05,
|
| 1870 |
-
"loss": 0.0684,
|
| 1871 |
-
"step": 2120
|
| 1872 |
-
},
|
| 1873 |
-
{
|
| 1874 |
-
"epoch": 0.5377429941933856,
|
| 1875 |
-
"grad_norm": 1.1859666109085083,
|
| 1876 |
-
"learning_rate": 2.3610000000000003e-05,
|
| 1877 |
-
"loss": 0.0757,
|
| 1878 |
-
"step": 2130
|
| 1879 |
-
},
|
| 1880 |
-
{
|
| 1881 |
-
"epoch": 0.5402676091895986,
|
| 1882 |
-
"grad_norm": 0.9001142978668213,
|
| 1883 |
-
"learning_rate": 2.358e-05,
|
| 1884 |
-
"loss": 0.079,
|
| 1885 |
-
"step": 2140
|
| 1886 |
-
},
|
| 1887 |
-
{
|
| 1888 |
-
"epoch": 0.5427922241858116,
|
| 1889 |
-
"grad_norm": 0.47399717569351196,
|
| 1890 |
-
"learning_rate": 2.3550000000000003e-05,
|
| 1891 |
-
"loss": 0.0726,
|
| 1892 |
-
"step": 2150
|
| 1893 |
-
},
|
| 1894 |
-
{
|
| 1895 |
-
"epoch": 0.5427922241858116,
|
| 1896 |
-
"eval_f1": 0.611992731677771,
|
| 1897 |
-
"eval_loss": 0.05662121623754501,
|
| 1898 |
-
"eval_runtime": 1151.3771,
|
| 1899 |
-
"eval_samples_per_second": 179.144,
|
| 1900 |
"eval_steps_per_second": 2.799,
|
| 1901 |
-
"step":
|
| 1902 |
-
},
|
| 1903 |
-
{
|
| 1904 |
-
"epoch": 0.5453168391820248,
|
| 1905 |
-
"grad_norm": 0.6292353272438049,
|
| 1906 |
-
"learning_rate": 2.3520000000000002e-05,
|
| 1907 |
-
"loss": 0.0677,
|
| 1908 |
-
"step": 2160
|
| 1909 |
-
},
|
| 1910 |
-
{
|
| 1911 |
-
"epoch": 0.5478414541782378,
|
| 1912 |
-
"grad_norm": 0.7090362906455994,
|
| 1913 |
-
"learning_rate": 2.349e-05,
|
| 1914 |
-
"loss": 0.0703,
|
| 1915 |
-
"step": 2170
|
| 1916 |
-
},
|
| 1917 |
-
{
|
| 1918 |
-
"epoch": 0.5503660691744509,
|
| 1919 |
-
"grad_norm": 0.6082953810691833,
|
| 1920 |
-
"learning_rate": 2.3460000000000002e-05,
|
| 1921 |
-
"loss": 0.0672,
|
| 1922 |
-
"step": 2180
|
| 1923 |
-
},
|
| 1924 |
-
{
|
| 1925 |
-
"epoch": 0.552890684170664,
|
| 1926 |
-
"grad_norm": 0.5937643051147461,
|
| 1927 |
-
"learning_rate": 2.343e-05,
|
| 1928 |
-
"loss": 0.0686,
|
| 1929 |
-
"step": 2190
|
| 1930 |
-
},
|
| 1931 |
-
{
|
| 1932 |
-
"epoch": 0.555415299166877,
|
| 1933 |
-
"grad_norm": 0.7394770979881287,
|
| 1934 |
-
"learning_rate": 2.3400000000000003e-05,
|
| 1935 |
-
"loss": 0.0731,
|
| 1936 |
-
"step": 2200
|
| 1937 |
-
},
|
| 1938 |
-
{
|
| 1939 |
-
"epoch": 0.555415299166877,
|
| 1940 |
-
"eval_f1": 0.6111780293905084,
|
| 1941 |
-
"eval_loss": 0.05852247402071953,
|
| 1942 |
-
"eval_runtime": 1153.1003,
|
| 1943 |
-
"eval_samples_per_second": 178.876,
|
| 1944 |
-
"eval_steps_per_second": 2.795,
|
| 1945 |
-
"step": 2200
|
| 1946 |
-
},
|
| 1947 |
-
{
|
| 1948 |
-
"epoch": 0.5579399141630901,
|
| 1949 |
-
"grad_norm": 0.7641323804855347,
|
| 1950 |
-
"learning_rate": 2.337e-05,
|
| 1951 |
-
"loss": 0.0732,
|
| 1952 |
-
"step": 2210
|
| 1953 |
-
},
|
| 1954 |
-
{
|
| 1955 |
-
"epoch": 0.5604645291593032,
|
| 1956 |
-
"grad_norm": 0.8567935824394226,
|
| 1957 |
-
"learning_rate": 2.334e-05,
|
| 1958 |
-
"loss": 0.0599,
|
| 1959 |
-
"step": 2220
|
| 1960 |
-
},
|
| 1961 |
-
{
|
| 1962 |
-
"epoch": 0.5629891441555163,
|
| 1963 |
-
"grad_norm": 0.9106941819190979,
|
| 1964 |
-
"learning_rate": 2.3310000000000002e-05,
|
| 1965 |
-
"loss": 0.0593,
|
| 1966 |
-
"step": 2230
|
| 1967 |
-
},
|
| 1968 |
-
{
|
| 1969 |
-
"epoch": 0.5655137591517294,
|
| 1970 |
-
"grad_norm": 1.5944632291793823,
|
| 1971 |
-
"learning_rate": 2.328e-05,
|
| 1972 |
-
"loss": 0.0669,
|
| 1973 |
-
"step": 2240
|
| 1974 |
-
},
|
| 1975 |
-
{
|
| 1976 |
-
"epoch": 0.5680383741479424,
|
| 1977 |
-
"grad_norm": 0.9120457768440247,
|
| 1978 |
-
"learning_rate": 2.3250000000000003e-05,
|
| 1979 |
-
"loss": 0.0722,
|
| 1980 |
-
"step": 2250
|
| 1981 |
-
},
|
| 1982 |
-
{
|
| 1983 |
-
"epoch": 0.5680383741479424,
|
| 1984 |
-
"eval_f1": 0.6139676730710583,
|
| 1985 |
-
"eval_loss": 0.05887339636683464,
|
| 1986 |
-
"eval_runtime": 1155.9087,
|
| 1987 |
-
"eval_samples_per_second": 178.441,
|
| 1988 |
-
"eval_steps_per_second": 2.788,
|
| 1989 |
-
"step": 2250
|
| 1990 |
-
},
|
| 1991 |
-
{
|
| 1992 |
-
"epoch": 0.5705629891441555,
|
| 1993 |
-
"grad_norm": 0.8505953550338745,
|
| 1994 |
-
"learning_rate": 2.322e-05,
|
| 1995 |
-
"loss": 0.0863,
|
| 1996 |
-
"step": 2260
|
| 1997 |
-
},
|
| 1998 |
-
{
|
| 1999 |
-
"epoch": 0.5730876041403686,
|
| 2000 |
-
"grad_norm": 0.9573137164115906,
|
| 2001 |
-
"learning_rate": 2.319e-05,
|
| 2002 |
-
"loss": 0.0712,
|
| 2003 |
-
"step": 2270
|
| 2004 |
-
},
|
| 2005 |
-
{
|
| 2006 |
-
"epoch": 0.5756122191365817,
|
| 2007 |
-
"grad_norm": 1.230735182762146,
|
| 2008 |
-
"learning_rate": 2.3160000000000002e-05,
|
| 2009 |
-
"loss": 0.0677,
|
| 2010 |
-
"step": 2280
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"epoch": 0.5781368341327947,
|
| 2014 |
-
"grad_norm": 1.203621745109558,
|
| 2015 |
-
"learning_rate": 2.313e-05,
|
| 2016 |
-
"loss": 0.0634,
|
| 2017 |
-
"step": 2290
|
| 2018 |
-
},
|
| 2019 |
-
{
|
| 2020 |
-
"epoch": 0.5806614491290079,
|
| 2021 |
-
"grad_norm": 1.3590195178985596,
|
| 2022 |
-
"learning_rate": 2.3100000000000002e-05,
|
| 2023 |
-
"loss": 0.0819,
|
| 2024 |
-
"step": 2300
|
| 2025 |
-
},
|
| 2026 |
-
{
|
| 2027 |
-
"epoch": 0.5806614491290079,
|
| 2028 |
-
"eval_f1": 0.6121980676328502,
|
| 2029 |
-
"eval_loss": 0.050494007766246796,
|
| 2030 |
-
"eval_runtime": 1153.6589,
|
| 2031 |
-
"eval_samples_per_second": 178.789,
|
| 2032 |
-
"eval_steps_per_second": 2.794,
|
| 2033 |
-
"step": 2300
|
| 2034 |
-
},
|
| 2035 |
-
{
|
| 2036 |
-
"epoch": 0.5831860641252209,
|
| 2037 |
-
"grad_norm": 0.8538402318954468,
|
| 2038 |
-
"learning_rate": 2.307e-05,
|
| 2039 |
-
"loss": 0.0674,
|
| 2040 |
-
"step": 2310
|
| 2041 |
-
},
|
| 2042 |
-
{
|
| 2043 |
-
"epoch": 0.5857106791214339,
|
| 2044 |
-
"grad_norm": 1.1863012313842773,
|
| 2045 |
-
"learning_rate": 2.304e-05,
|
| 2046 |
-
"loss": 0.0665,
|
| 2047 |
-
"step": 2320
|
| 2048 |
-
},
|
| 2049 |
-
{
|
| 2050 |
-
"epoch": 0.5882352941176471,
|
| 2051 |
-
"grad_norm": 1.0120714902877808,
|
| 2052 |
-
"learning_rate": 2.301e-05,
|
| 2053 |
-
"loss": 0.0675,
|
| 2054 |
-
"step": 2330
|
| 2055 |
-
},
|
| 2056 |
-
{
|
| 2057 |
-
"epoch": 0.5907599091138601,
|
| 2058 |
-
"grad_norm": 0.8394482135772705,
|
| 2059 |
-
"learning_rate": 2.298e-05,
|
| 2060 |
-
"loss": 0.0812,
|
| 2061 |
-
"step": 2340
|
| 2062 |
-
},
|
| 2063 |
-
{
|
| 2064 |
-
"epoch": 0.5932845241100733,
|
| 2065 |
-
"grad_norm": 0.8855767250061035,
|
| 2066 |
-
"learning_rate": 2.2950000000000002e-05,
|
| 2067 |
-
"loss": 0.0694,
|
| 2068 |
-
"step": 2350
|
| 2069 |
-
},
|
| 2070 |
-
{
|
| 2071 |
-
"epoch": 0.5932845241100733,
|
| 2072 |
-
"eval_f1": 0.6101251634597422,
|
| 2073 |
-
"eval_loss": 0.053731031715869904,
|
| 2074 |
-
"eval_runtime": 1147.8424,
|
| 2075 |
-
"eval_samples_per_second": 179.695,
|
| 2076 |
-
"eval_steps_per_second": 2.808,
|
| 2077 |
-
"step": 2350
|
| 2078 |
-
},
|
| 2079 |
-
{
|
| 2080 |
-
"epoch": 0.5958091391062863,
|
| 2081 |
-
"grad_norm": 1.241045594215393,
|
| 2082 |
-
"learning_rate": 2.292e-05,
|
| 2083 |
-
"loss": 0.0646,
|
| 2084 |
-
"step": 2360
|
| 2085 |
-
},
|
| 2086 |
-
{
|
| 2087 |
-
"epoch": 0.5983337541024993,
|
| 2088 |
-
"grad_norm": 2.065401315689087,
|
| 2089 |
-
"learning_rate": 2.289e-05,
|
| 2090 |
-
"loss": 0.0792,
|
| 2091 |
-
"step": 2370
|
| 2092 |
-
},
|
| 2093 |
-
{
|
| 2094 |
-
"epoch": 0.6008583690987125,
|
| 2095 |
-
"grad_norm": 1.0024877786636353,
|
| 2096 |
-
"learning_rate": 2.286e-05,
|
| 2097 |
-
"loss": 0.0751,
|
| 2098 |
-
"step": 2380
|
| 2099 |
-
},
|
| 2100 |
-
{
|
| 2101 |
-
"epoch": 0.6033829840949255,
|
| 2102 |
-
"grad_norm": 0.4943256080150604,
|
| 2103 |
-
"learning_rate": 2.283e-05,
|
| 2104 |
-
"loss": 0.076,
|
| 2105 |
-
"step": 2390
|
| 2106 |
-
},
|
| 2107 |
-
{
|
| 2108 |
-
"epoch": 0.6059075990911386,
|
| 2109 |
-
"grad_norm": 1.0907814502716064,
|
| 2110 |
-
"learning_rate": 2.2800000000000002e-05,
|
| 2111 |
-
"loss": 0.0705,
|
| 2112 |
-
"step": 2400
|
| 2113 |
-
},
|
| 2114 |
-
{
|
| 2115 |
-
"epoch": 0.6059075990911386,
|
| 2116 |
-
"eval_f1": 0.6130196664177247,
|
| 2117 |
-
"eval_loss": 0.06461644172668457,
|
| 2118 |
-
"eval_runtime": 1149.8253,
|
| 2119 |
-
"eval_samples_per_second": 179.386,
|
| 2120 |
-
"eval_steps_per_second": 2.803,
|
| 2121 |
-
"step": 2400
|
| 2122 |
-
},
|
| 2123 |
-
{
|
| 2124 |
-
"epoch": 0.6084322140873517,
|
| 2125 |
-
"grad_norm": 1.1304162740707397,
|
| 2126 |
-
"learning_rate": 2.277e-05,
|
| 2127 |
-
"loss": 0.0548,
|
| 2128 |
-
"step": 2410
|
| 2129 |
-
},
|
| 2130 |
-
{
|
| 2131 |
-
"epoch": 0.6109568290835647,
|
| 2132 |
-
"grad_norm": 1.3394097089767456,
|
| 2133 |
-
"learning_rate": 2.274e-05,
|
| 2134 |
-
"loss": 0.0607,
|
| 2135 |
-
"step": 2420
|
| 2136 |
-
},
|
| 2137 |
-
{
|
| 2138 |
-
"epoch": 0.6134814440797778,
|
| 2139 |
-
"grad_norm": 0.5467960834503174,
|
| 2140 |
-
"learning_rate": 2.271e-05,
|
| 2141 |
-
"loss": 0.0701,
|
| 2142 |
-
"step": 2430
|
| 2143 |
-
},
|
| 2144 |
-
{
|
| 2145 |
-
"epoch": 0.6160060590759909,
|
| 2146 |
-
"grad_norm": 0.5510517954826355,
|
| 2147 |
-
"learning_rate": 2.268e-05,
|
| 2148 |
-
"loss": 0.0725,
|
| 2149 |
-
"step": 2440
|
| 2150 |
-
},
|
| 2151 |
-
{
|
| 2152 |
-
"epoch": 0.618530674072204,
|
| 2153 |
-
"grad_norm": 0.7682734131813049,
|
| 2154 |
-
"learning_rate": 2.265e-05,
|
| 2155 |
-
"loss": 0.0702,
|
| 2156 |
-
"step": 2450
|
| 2157 |
-
},
|
| 2158 |
-
{
|
| 2159 |
-
"epoch": 0.618530674072204,
|
| 2160 |
-
"eval_f1": 0.6124447065762312,
|
| 2161 |
-
"eval_loss": 0.046234920620918274,
|
| 2162 |
-
"eval_runtime": 1146.4615,
|
| 2163 |
-
"eval_samples_per_second": 179.912,
|
| 2164 |
-
"eval_steps_per_second": 2.811,
|
| 2165 |
-
"step": 2450
|
| 2166 |
-
},
|
| 2167 |
-
{
|
| 2168 |
-
"epoch": 0.6210552890684171,
|
| 2169 |
-
"grad_norm": 0.7578818798065186,
|
| 2170 |
-
"learning_rate": 2.262e-05,
|
| 2171 |
-
"loss": 0.0703,
|
| 2172 |
-
"step": 2460
|
| 2173 |
-
},
|
| 2174 |
-
{
|
| 2175 |
-
"epoch": 0.6235799040646302,
|
| 2176 |
-
"grad_norm": 0.7244108319282532,
|
| 2177 |
-
"learning_rate": 2.2590000000000002e-05,
|
| 2178 |
-
"loss": 0.0635,
|
| 2179 |
-
"step": 2470
|
| 2180 |
-
},
|
| 2181 |
-
{
|
| 2182 |
-
"epoch": 0.6261045190608432,
|
| 2183 |
-
"grad_norm": 1.1047908067703247,
|
| 2184 |
-
"learning_rate": 2.256e-05,
|
| 2185 |
-
"loss": 0.0614,
|
| 2186 |
-
"step": 2480
|
| 2187 |
-
},
|
| 2188 |
-
{
|
| 2189 |
-
"epoch": 0.6286291340570563,
|
| 2190 |
-
"grad_norm": 1.0824987888336182,
|
| 2191 |
-
"learning_rate": 2.253e-05,
|
| 2192 |
-
"loss": 0.081,
|
| 2193 |
-
"step": 2490
|
| 2194 |
-
},
|
| 2195 |
-
{
|
| 2196 |
-
"epoch": 0.6311537490532694,
|
| 2197 |
-
"grad_norm": 1.9344598054885864,
|
| 2198 |
-
"learning_rate": 2.25e-05,
|
| 2199 |
-
"loss": 0.0709,
|
| 2200 |
-
"step": 2500
|
| 2201 |
},
|
| 2202 |
{
|
| 2203 |
-
"epoch":
|
| 2204 |
-
"eval_f1":
|
| 2205 |
-
"eval_loss": 0.
|
| 2206 |
-
"eval_runtime":
|
| 2207 |
-
"eval_samples_per_second":
|
| 2208 |
-
"eval_steps_per_second": 2.
|
| 2209 |
"step": 2500
|
| 2210 |
},
|
| 2211 |
{
|
| 2212 |
-
"epoch":
|
| 2213 |
-
"grad_norm":
|
| 2214 |
-
"learning_rate":
|
| 2215 |
-
"loss": 0.
|
| 2216 |
-
"step":
|
| 2217 |
-
},
|
| 2218 |
-
{
|
| 2219 |
-
"epoch": 0.6362029790456956,
|
| 2220 |
-
"grad_norm": 0.7228933572769165,
|
| 2221 |
-
"learning_rate": 2.2440000000000002e-05,
|
| 2222 |
-
"loss": 0.071,
|
| 2223 |
-
"step": 2520
|
| 2224 |
-
},
|
| 2225 |
-
{
|
| 2226 |
-
"epoch": 0.6387275940419086,
|
| 2227 |
-
"grad_norm": 0.9655591249465942,
|
| 2228 |
-
"learning_rate": 2.241e-05,
|
| 2229 |
-
"loss": 0.0611,
|
| 2230 |
-
"step": 2530
|
| 2231 |
-
},
|
| 2232 |
-
{
|
| 2233 |
-
"epoch": 0.6412522090381216,
|
| 2234 |
-
"grad_norm": 0.9924450516700745,
|
| 2235 |
-
"learning_rate": 2.238e-05,
|
| 2236 |
-
"loss": 0.0676,
|
| 2237 |
-
"step": 2540
|
| 2238 |
-
},
|
| 2239 |
-
{
|
| 2240 |
-
"epoch": 0.6437768240343348,
|
| 2241 |
-
"grad_norm": 1.12591552734375,
|
| 2242 |
-
"learning_rate": 2.235e-05,
|
| 2243 |
-
"loss": 0.0804,
|
| 2244 |
-
"step": 2550
|
| 2245 |
-
},
|
| 2246 |
-
{
|
| 2247 |
-
"epoch": 0.6437768240343348,
|
| 2248 |
-
"eval_f1": 0.612305676335696,
|
| 2249 |
-
"eval_loss": 0.04778852313756943,
|
| 2250 |
-
"eval_runtime": 1160.4576,
|
| 2251 |
-
"eval_samples_per_second": 177.742,
|
| 2252 |
-
"eval_steps_per_second": 2.777,
|
| 2253 |
-
"step": 2550
|
| 2254 |
-
},
|
| 2255 |
-
{
|
| 2256 |
-
"epoch": 0.6463014390305478,
|
| 2257 |
-
"grad_norm": 0.7478006482124329,
|
| 2258 |
-
"learning_rate": 2.232e-05,
|
| 2259 |
-
"loss": 0.0638,
|
| 2260 |
-
"step": 2560
|
| 2261 |
-
},
|
| 2262 |
-
{
|
| 2263 |
-
"epoch": 0.648826054026761,
|
| 2264 |
-
"grad_norm": 0.7661213874816895,
|
| 2265 |
-
"learning_rate": 2.2290000000000002e-05,
|
| 2266 |
-
"loss": 0.0632,
|
| 2267 |
-
"step": 2570
|
| 2268 |
-
},
|
| 2269 |
-
{
|
| 2270 |
-
"epoch": 0.651350669022974,
|
| 2271 |
-
"grad_norm": 0.9824168086051941,
|
| 2272 |
-
"learning_rate": 2.226e-05,
|
| 2273 |
-
"loss": 0.0602,
|
| 2274 |
-
"step": 2580
|
| 2275 |
-
},
|
| 2276 |
-
{
|
| 2277 |
-
"epoch": 0.653875284019187,
|
| 2278 |
-
"grad_norm": 1.1700901985168457,
|
| 2279 |
-
"learning_rate": 2.223e-05,
|
| 2280 |
-
"loss": 0.0714,
|
| 2281 |
-
"step": 2590
|
| 2282 |
-
},
|
| 2283 |
-
{
|
| 2284 |
-
"epoch": 0.6563998990154002,
|
| 2285 |
-
"grad_norm": 0.8846214413642883,
|
| 2286 |
-
"learning_rate": 2.22e-05,
|
| 2287 |
-
"loss": 0.0666,
|
| 2288 |
-
"step": 2600
|
| 2289 |
-
},
|
| 2290 |
-
{
|
| 2291 |
-
"epoch": 0.6563998990154002,
|
| 2292 |
-
"eval_f1": 0.6104417670682731,
|
| 2293 |
-
"eval_loss": 0.04546576738357544,
|
| 2294 |
-
"eval_runtime": 1160.1326,
|
| 2295 |
-
"eval_samples_per_second": 177.792,
|
| 2296 |
-
"eval_steps_per_second": 2.778,
|
| 2297 |
-
"step": 2600
|
| 2298 |
},
|
| 2299 |
{
|
| 2300 |
-
"epoch":
|
| 2301 |
-
"
|
| 2302 |
-
"
|
| 2303 |
-
"
|
| 2304 |
-
"
|
|
|
|
|
|
|
| 2305 |
},
|
| 2306 |
{
|
| 2307 |
-
"epoch":
|
| 2308 |
-
"
|
| 2309 |
-
"
|
| 2310 |
-
"
|
| 2311 |
-
"
|
| 2312 |
-
|
| 2313 |
-
|
| 2314 |
-
"epoch": 0.6639737440040394,
|
| 2315 |
-
"grad_norm": 0.6906914710998535,
|
| 2316 |
-
"learning_rate": 2.211e-05,
|
| 2317 |
-
"loss": 0.0764,
|
| 2318 |
-
"step": 2630
|
| 2319 |
-
},
|
| 2320 |
-
{
|
| 2321 |
-
"epoch": 0.6664983590002524,
|
| 2322 |
-
"grad_norm": 1.3137489557266235,
|
| 2323 |
-
"learning_rate": 2.208e-05,
|
| 2324 |
-
"loss": 0.0768,
|
| 2325 |
-
"step": 2640
|
| 2326 |
-
},
|
| 2327 |
-
{
|
| 2328 |
-
"epoch": 0.6690229739964655,
|
| 2329 |
-
"grad_norm": 0.863865077495575,
|
| 2330 |
-
"learning_rate": 2.205e-05,
|
| 2331 |
-
"loss": 0.0749,
|
| 2332 |
-
"step": 2650
|
| 2333 |
-
},
|
| 2334 |
-
{
|
| 2335 |
-
"epoch": 0.6690229739964655,
|
| 2336 |
-
"eval_f1": 0.6131900703964431,
|
| 2337 |
-
"eval_loss": 0.04790908098220825,
|
| 2338 |
-
"eval_runtime": 1162.4462,
|
| 2339 |
-
"eval_samples_per_second": 177.438,
|
| 2340 |
-
"eval_steps_per_second": 2.773,
|
| 2341 |
-
"step": 2650
|
| 2342 |
-
},
|
| 2343 |
-
{
|
| 2344 |
-
"epoch": 0.6715475889926786,
|
| 2345 |
-
"grad_norm": 0.9182652235031128,
|
| 2346 |
-
"learning_rate": 2.202e-05,
|
| 2347 |
-
"loss": 0.0625,
|
| 2348 |
-
"step": 2660
|
| 2349 |
-
},
|
| 2350 |
-
{
|
| 2351 |
-
"epoch": 0.6740722039888917,
|
| 2352 |
-
"grad_norm": 1.4961283206939697,
|
| 2353 |
-
"learning_rate": 2.199e-05,
|
| 2354 |
-
"loss": 0.0726,
|
| 2355 |
-
"step": 2670
|
| 2356 |
-
},
|
| 2357 |
-
{
|
| 2358 |
-
"epoch": 0.6765968189851048,
|
| 2359 |
-
"grad_norm": 0.7803681492805481,
|
| 2360 |
-
"learning_rate": 2.196e-05,
|
| 2361 |
-
"loss": 0.0669,
|
| 2362 |
-
"step": 2680
|
| 2363 |
-
},
|
| 2364 |
-
{
|
| 2365 |
-
"epoch": 0.6791214339813179,
|
| 2366 |
-
"grad_norm": 1.0371824502944946,
|
| 2367 |
-
"learning_rate": 2.193e-05,
|
| 2368 |
-
"loss": 0.0566,
|
| 2369 |
-
"step": 2690
|
| 2370 |
-
},
|
| 2371 |
-
{
|
| 2372 |
-
"epoch": 0.6816460489775309,
|
| 2373 |
-
"grad_norm": 1.1832714080810547,
|
| 2374 |
-
"learning_rate": 2.19e-05,
|
| 2375 |
-
"loss": 0.067,
|
| 2376 |
-
"step": 2700
|
| 2377 |
-
},
|
| 2378 |
-
{
|
| 2379 |
-
"epoch": 0.6816460489775309,
|
| 2380 |
-
"eval_f1": 0.6132461161079312,
|
| 2381 |
-
"eval_loss": 0.055793602019548416,
|
| 2382 |
-
"eval_runtime": 1161.8914,
|
| 2383 |
-
"eval_samples_per_second": 177.523,
|
| 2384 |
-
"eval_steps_per_second": 2.774,
|
| 2385 |
-
"step": 2700
|
| 2386 |
-
},
|
| 2387 |
-
{
|
| 2388 |
-
"epoch": 0.684170663973744,
|
| 2389 |
-
"grad_norm": 0.7899573445320129,
|
| 2390 |
-
"learning_rate": 2.187e-05,
|
| 2391 |
-
"loss": 0.0763,
|
| 2392 |
-
"step": 2710
|
| 2393 |
-
},
|
| 2394 |
-
{
|
| 2395 |
-
"epoch": 0.6866952789699571,
|
| 2396 |
-
"grad_norm": 1.4638808965682983,
|
| 2397 |
-
"learning_rate": 2.184e-05,
|
| 2398 |
-
"loss": 0.0768,
|
| 2399 |
-
"step": 2720
|
| 2400 |
-
},
|
| 2401 |
-
{
|
| 2402 |
-
"epoch": 0.6892198939661701,
|
| 2403 |
-
"grad_norm": 0.7547538876533508,
|
| 2404 |
-
"learning_rate": 2.181e-05,
|
| 2405 |
-
"loss": 0.0761,
|
| 2406 |
-
"step": 2730
|
| 2407 |
-
},
|
| 2408 |
-
{
|
| 2409 |
-
"epoch": 0.6917445089623833,
|
| 2410 |
-
"grad_norm": 0.5143932700157166,
|
| 2411 |
-
"learning_rate": 2.178e-05,
|
| 2412 |
-
"loss": 0.0808,
|
| 2413 |
-
"step": 2740
|
| 2414 |
-
},
|
| 2415 |
-
{
|
| 2416 |
-
"epoch": 0.6942691239585963,
|
| 2417 |
-
"grad_norm": 1.011730432510376,
|
| 2418 |
-
"learning_rate": 2.175e-05,
|
| 2419 |
-
"loss": 0.068,
|
| 2420 |
-
"step": 2750
|
| 2421 |
},
|
| 2422 |
{
|
| 2423 |
-
"epoch":
|
| 2424 |
-
"
|
| 2425 |
-
"
|
| 2426 |
-
"
|
| 2427 |
-
"
|
| 2428 |
-
"eval_steps_per_second": 2.778,
|
| 2429 |
-
"step": 2750
|
| 2430 |
},
|
| 2431 |
{
|
| 2432 |
-
"epoch":
|
| 2433 |
-
"
|
| 2434 |
-
"
|
| 2435 |
-
"
|
| 2436 |
-
"
|
| 2437 |
-
"
|
| 2438 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2439 |
}
|
| 2440 |
],
|
| 2441 |
-
"logging_steps":
|
| 2442 |
-
"max_steps":
|
| 2443 |
"num_input_tokens_seen": 0,
|
| 2444 |
-
"num_train_epochs":
|
| 2445 |
"save_steps": 500,
|
| 2446 |
"stateful_callbacks": {
|
| 2447 |
"EarlyStoppingCallback": {
|
| 2448 |
"args": {
|
| 2449 |
-
"early_stopping_patience":
|
| 2450 |
"early_stopping_threshold": 0.0
|
| 2451 |
},
|
| 2452 |
"attributes": {
|
|
@@ -2459,13 +148,13 @@
|
|
| 2459 |
"should_evaluate": false,
|
| 2460 |
"should_log": false,
|
| 2461 |
"should_save": true,
|
| 2462 |
-
"should_training_stop":
|
| 2463 |
},
|
| 2464 |
"attributes": {}
|
| 2465 |
}
|
| 2466 |
},
|
| 2467 |
-
"total_flos":
|
| 2468 |
-
"train_batch_size":
|
| 2469 |
"trial_name": null,
|
| 2470 |
"trial_params": null
|
| 2471 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.38255795104555035,
|
| 3 |
+
"best_model_checkpoint": "./step_test_microsoft_dit/checkpoint-2000",
|
| 4 |
+
"epoch": 2.271580010095911,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.2523977788995457,
|
| 13 |
+
"eval_f1": 0.3040393637715986,
|
| 14 |
+
"eval_loss": 0.16232739388942719,
|
| 15 |
+
"eval_runtime": 573.4246,
|
| 16 |
+
"eval_samples_per_second": 359.702,
|
| 17 |
+
"eval_steps_per_second": 2.811,
|
| 18 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
+
"epoch": 0.5047955577990914,
|
| 22 |
+
"grad_norm": 3.499274253845215,
|
| 23 |
+
"learning_rate": 0.0004986304738420684,
|
| 24 |
+
"loss": 0.1656,
|
| 25 |
+
"step": 1000
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 0.5047955577990914,
|
| 29 |
"eval_f1": NaN,
|
| 30 |
+
"eval_loss": 0.43072596192359924,
|
| 31 |
+
"eval_runtime": 571.3845,
|
| 32 |
+
"eval_samples_per_second": 360.986,
|
| 33 |
+
"eval_steps_per_second": 2.821,
|
| 34 |
+
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
},
|
| 36 |
{
|
| 37 |
+
"epoch": 0.7571933366986371,
|
| 38 |
+
"eval_f1": NaN,
|
| 39 |
+
"eval_loss": 0.14925973117351532,
|
| 40 |
+
"eval_runtime": 574.5622,
|
| 41 |
+
"eval_samples_per_second": 358.99,
|
| 42 |
+
"eval_steps_per_second": 2.806,
|
| 43 |
+
"step": 1500
|
| 44 |
},
|
| 45 |
{
|
| 46 |
+
"epoch": 1.0095911155981827,
|
| 47 |
+
"grad_norm": 0.47774481773376465,
|
| 48 |
+
"learning_rate": 0.0004945369001834514,
|
| 49 |
+
"loss": 0.14,
|
|
|
|
|
|
|
| 50 |
"step": 2000
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 1.0095911155981827,
|
| 54 |
+
"eval_f1": 0.38255795104555035,
|
| 55 |
+
"eval_loss": 0.18703292310237885,
|
| 56 |
+
"eval_runtime": 575.9325,
|
| 57 |
+
"eval_samples_per_second": 358.136,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
"eval_steps_per_second": 2.799,
|
| 59 |
+
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 1.2619888944977284,
|
| 63 |
+
"eval_f1": NaN,
|
| 64 |
+
"eval_loss": 0.10761596262454987,
|
| 65 |
+
"eval_runtime": 570.7076,
|
| 66 |
+
"eval_samples_per_second": 361.414,
|
| 67 |
+
"eval_steps_per_second": 2.825,
|
| 68 |
"step": 2500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.514386673397274,
|
| 72 |
+
"grad_norm": 0.8171533942222595,
|
| 73 |
+
"learning_rate": 0.0004877641290737884,
|
| 74 |
+
"loss": 0.1285,
|
| 75 |
+
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 1.514386673397274,
|
| 79 |
+
"eval_f1": 0.381203007518797,
|
| 80 |
+
"eval_loss": 0.08960258215665817,
|
| 81 |
+
"eval_runtime": 570.2026,
|
| 82 |
+
"eval_samples_per_second": 361.735,
|
| 83 |
+
"eval_steps_per_second": 2.827,
|
| 84 |
+
"step": 3000
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 1.76678445229682,
|
| 88 |
+
"eval_f1": NaN,
|
| 89 |
+
"eval_loss": 0.14047682285308838,
|
| 90 |
+
"eval_runtime": 572.8668,
|
| 91 |
+
"eval_samples_per_second": 360.052,
|
| 92 |
+
"eval_steps_per_second": 2.814,
|
| 93 |
+
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 2.0191822311963654,
|
| 97 |
+
"grad_norm": 0.7625566124916077,
|
| 98 |
+
"learning_rate": 0.0004783863644106502,
|
| 99 |
+
"loss": 0.123,
|
| 100 |
+
"step": 4000
|
|
|
|
|
|
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 2.0191822311963654,
|
| 104 |
+
"eval_f1": NaN,
|
| 105 |
+
"eval_loss": 0.20614498853683472,
|
| 106 |
+
"eval_runtime": 571.417,
|
| 107 |
+
"eval_samples_per_second": 360.966,
|
| 108 |
+
"eval_steps_per_second": 2.821,
|
| 109 |
+
"step": 4000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.271580010095911,
|
| 113 |
+
"eval_f1": 0.23949467373266953,
|
| 114 |
+
"eval_loss": 0.22833816707134247,
|
| 115 |
+
"eval_runtime": 576.5663,
|
| 116 |
+
"eval_samples_per_second": 357.742,
|
| 117 |
+
"eval_steps_per_second": 2.796,
|
| 118 |
+
"step": 4500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.271580010095911,
|
| 122 |
+
"step": 4500,
|
| 123 |
+
"total_flos": 4.4623040438986555e+19,
|
| 124 |
+
"train_loss": 0.13670311906602647,
|
| 125 |
+
"train_runtime": 12745.6466,
|
| 126 |
+
"train_samples_per_second": 301.279,
|
| 127 |
+
"train_steps_per_second": 2.354
|
| 128 |
}
|
| 129 |
],
|
| 130 |
+
"logging_steps": 1000,
|
| 131 |
+
"max_steps": 30000,
|
| 132 |
"num_input_tokens_seen": 0,
|
| 133 |
+
"num_train_epochs": 16,
|
| 134 |
"save_steps": 500,
|
| 135 |
"stateful_callbacks": {
|
| 136 |
"EarlyStoppingCallback": {
|
| 137 |
"args": {
|
| 138 |
+
"early_stopping_patience": 5,
|
| 139 |
"early_stopping_threshold": 0.0
|
| 140 |
},
|
| 141 |
"attributes": {
|
|
|
|
| 148 |
"should_evaluate": false,
|
| 149 |
"should_log": false,
|
| 150 |
"should_save": true,
|
| 151 |
+
"should_training_stop": true
|
| 152 |
},
|
| 153 |
"attributes": {}
|
| 154 |
}
|
| 155 |
},
|
| 156 |
+
"total_flos": 4.4623040438986555e+19,
|
| 157 |
+
"train_batch_size": 128,
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|
| 160 |
}
|