Model save
Browse files- README.md +2 -4
- all_results.json +5 -10
- train_results.json +5 -5
- trainer_state.json +222 -2036
README.md
CHANGED
|
@@ -1,11 +1,9 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
-
datasets: open-r1/OpenR1-Math-220k
|
| 4 |
library_name: transformers
|
| 5 |
model_name: Qwen2.5-1.5B-Open-R1-Distill
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
-
- open-r1
|
| 9 |
- trl
|
| 10 |
- sft
|
| 11 |
licence: license
|
|
@@ -13,7 +11,7 @@ licence: license
|
|
| 13 |
|
| 14 |
# Model Card for Qwen2.5-1.5B-Open-R1-Distill
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
|
| 17 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 18 |
|
| 19 |
## Quick start
|
|
@@ -29,7 +27,7 @@ print(output["generated_text"])
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/
|
| 33 |
|
| 34 |
|
| 35 |
This model was trained with SFT.
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: Qwen2.5-1.5B-Open-R1-Distill
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
licence: license
|
|
|
|
| 11 |
|
| 12 |
# Model Card for Qwen2.5-1.5B-Open-R1-Distill
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/2sdy2t94)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
all_results.json
CHANGED
|
@@ -1,13 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"eval_samples_per_second": 4.944,
|
| 6 |
-
"eval_steps_per_second": 1.265,
|
| 7 |
-
"total_flos": 65635690217472.0,
|
| 8 |
-
"train_loss": 0.0,
|
| 9 |
-
"train_runtime": 0.9025,
|
| 10 |
"train_samples": 93733,
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"total_flos": 487709642588160.0,
|
| 3 |
+
"train_loss": 0.5792717831348305,
|
| 4 |
+
"train_runtime": 20654.3187,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 1.661,
|
| 7 |
+
"train_steps_per_second": 0.013
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"total_flos":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 93733,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"total_flos": 487709642588160.0,
|
| 3 |
+
"train_loss": 0.5792717831348305,
|
| 4 |
+
"train_runtime": 20654.3187,
|
| 5 |
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 1.661,
|
| 7 |
+
"train_steps_per_second": 0.013
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,2205 +2,391 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 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 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"eval_reasoning_steps_per_second": 1.202,
|
| 24 |
-
"step": 5
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.0073964497041420114,
|
| 28 |
-
"eval_utility_loss": 1.4049550294876099,
|
| 29 |
-
"eval_utility_runtime": 1.7594,
|
| 30 |
-
"eval_utility_samples_per_second": 120.498,
|
| 31 |
-
"eval_utility_steps_per_second": 1.137,
|
| 32 |
-
"step": 5
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.014792899408284023,
|
| 36 |
-
"grad_norm": 2.225119430385955,
|
| 37 |
-
"learning_rate": 1.4705882352941177e-05,
|
| 38 |
-
"loss": 2.5801,
|
| 39 |
-
"step": 10
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.014792899408284023,
|
| 43 |
-
"eval_reasoning_loss": 1.1661676168441772,
|
| 44 |
-
"eval_reasoning_runtime": 4.4119,
|
| 45 |
-
"eval_reasoning_samples_per_second": 121.264,
|
| 46 |
-
"eval_reasoning_steps_per_second": 1.133,
|
| 47 |
-
"step": 10
|
| 48 |
-
},
|
| 49 |
-
{
|
| 50 |
-
"epoch": 0.014792899408284023,
|
| 51 |
-
"eval_utility_loss": 1.3157464265823364,
|
| 52 |
-
"eval_utility_runtime": 1.7506,
|
| 53 |
-
"eval_utility_samples_per_second": 121.103,
|
| 54 |
-
"eval_utility_steps_per_second": 1.142,
|
| 55 |
"step": 10
|
| 56 |
},
|
| 57 |
{
|
| 58 |
-
"epoch": 0.
|
| 59 |
-
"grad_norm":
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss":
|
| 62 |
-
"step": 15
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.022189349112426034,
|
| 66 |
-
"eval_reasoning_loss": 1.0858653783798218,
|
| 67 |
-
"eval_reasoning_runtime": 4.5635,
|
| 68 |
-
"eval_reasoning_samples_per_second": 117.233,
|
| 69 |
-
"eval_reasoning_steps_per_second": 1.096,
|
| 70 |
-
"step": 15
|
| 71 |
-
},
|
| 72 |
-
{
|
| 73 |
-
"epoch": 0.022189349112426034,
|
| 74 |
-
"eval_utility_loss": 1.2957844734191895,
|
| 75 |
-
"eval_utility_runtime": 1.8291,
|
| 76 |
-
"eval_utility_samples_per_second": 115.901,
|
| 77 |
-
"eval_utility_steps_per_second": 1.093,
|
| 78 |
"step": 15
|
| 79 |
},
|
| 80 |
{
|
| 81 |
-
"epoch": 0.
|
| 82 |
-
"grad_norm":
|
| 83 |
-
"learning_rate":
|
| 84 |
-
"loss":
|
| 85 |
-
"step": 20
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 0.029585798816568046,
|
| 89 |
-
"eval_reasoning_loss": 1.0403348207473755,
|
| 90 |
-
"eval_reasoning_runtime": 4.8727,
|
| 91 |
-
"eval_reasoning_samples_per_second": 109.796,
|
| 92 |
-
"eval_reasoning_steps_per_second": 1.026,
|
| 93 |
-
"step": 20
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.029585798816568046,
|
| 97 |
-
"eval_utility_loss": 1.2852095365524292,
|
| 98 |
-
"eval_utility_runtime": 1.8864,
|
| 99 |
-
"eval_utility_samples_per_second": 112.384,
|
| 100 |
-
"eval_utility_steps_per_second": 1.06,
|
| 101 |
"step": 20
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 0.
|
| 105 |
-
"grad_norm":
|
| 106 |
-
"learning_rate":
|
| 107 |
-
"loss":
|
| 108 |
"step": 25
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 0.
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"eval_reasoning_steps_per_second": 1.067,
|
| 116 |
-
"step": 25
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.03698224852071006,
|
| 120 |
-
"eval_utility_loss": 1.274791955947876,
|
| 121 |
-
"eval_utility_runtime": 1.8048,
|
| 122 |
-
"eval_utility_samples_per_second": 117.463,
|
| 123 |
-
"eval_utility_steps_per_second": 1.108,
|
| 124 |
-
"step": 25
|
| 125 |
-
},
|
| 126 |
-
{
|
| 127 |
-
"epoch": 0.04437869822485207,
|
| 128 |
-
"grad_norm": 1.3591976835447737,
|
| 129 |
-
"learning_rate": 4.411764705882353e-05,
|
| 130 |
-
"loss": 2.219,
|
| 131 |
-
"step": 30
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 0.04437869822485207,
|
| 135 |
-
"eval_reasoning_loss": 0.9981840252876282,
|
| 136 |
-
"eval_reasoning_runtime": 4.7288,
|
| 137 |
-
"eval_reasoning_samples_per_second": 113.138,
|
| 138 |
-
"eval_reasoning_steps_per_second": 1.057,
|
| 139 |
-
"step": 30
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 0.04437869822485207,
|
| 143 |
-
"eval_utility_loss": 1.2681363821029663,
|
| 144 |
-
"eval_utility_runtime": 2.0119,
|
| 145 |
-
"eval_utility_samples_per_second": 105.371,
|
| 146 |
-
"eval_utility_steps_per_second": 0.994,
|
| 147 |
"step": 30
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"grad_norm":
|
| 152 |
-
"learning_rate": 4.
|
| 153 |
-
"loss":
|
| 154 |
-
"step": 35
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 0.051775147928994084,
|
| 158 |
-
"eval_reasoning_loss": 0.9858483076095581,
|
| 159 |
-
"eval_reasoning_runtime": 4.6465,
|
| 160 |
-
"eval_reasoning_samples_per_second": 115.139,
|
| 161 |
-
"eval_reasoning_steps_per_second": 1.076,
|
| 162 |
-
"step": 35
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 0.051775147928994084,
|
| 166 |
-
"eval_utility_loss": 1.2649621963500977,
|
| 167 |
-
"eval_utility_runtime": 1.8766,
|
| 168 |
-
"eval_utility_samples_per_second": 112.968,
|
| 169 |
-
"eval_utility_steps_per_second": 1.066,
|
| 170 |
"step": 35
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate": 4.
|
| 176 |
-
"loss":
|
| 177 |
-
"step": 40
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.05917159763313609,
|
| 181 |
-
"eval_reasoning_loss": 0.9769134521484375,
|
| 182 |
-
"eval_reasoning_runtime": 4.7512,
|
| 183 |
-
"eval_reasoning_samples_per_second": 112.604,
|
| 184 |
-
"eval_reasoning_steps_per_second": 1.052,
|
| 185 |
-
"step": 40
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.05917159763313609,
|
| 189 |
-
"eval_utility_loss": 1.2631217241287231,
|
| 190 |
-
"eval_utility_runtime": 1.8913,
|
| 191 |
-
"eval_utility_samples_per_second": 112.092,
|
| 192 |
-
"eval_utility_steps_per_second": 1.057,
|
| 193 |
"step": 40
|
| 194 |
},
|
| 195 |
{
|
| 196 |
-
"epoch": 0.
|
| 197 |
-
"grad_norm":
|
| 198 |
-
"learning_rate": 4.
|
| 199 |
-
"loss":
|
| 200 |
"step": 45
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 0.
|
| 204 |
-
"
|
| 205 |
-
"
|
| 206 |
-
"
|
| 207 |
-
"eval_reasoning_steps_per_second": 1.058,
|
| 208 |
-
"step": 45
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"epoch": 0.06656804733727811,
|
| 212 |
-
"eval_utility_loss": 1.262032389640808,
|
| 213 |
-
"eval_utility_runtime": 1.8046,
|
| 214 |
-
"eval_utility_samples_per_second": 117.475,
|
| 215 |
-
"eval_utility_steps_per_second": 1.108,
|
| 216 |
-
"step": 45
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"epoch": 0.07396449704142012,
|
| 220 |
-
"grad_norm": 1.1574292202420797,
|
| 221 |
-
"learning_rate": 4.993107126490191e-05,
|
| 222 |
-
"loss": 2.1602,
|
| 223 |
-
"step": 50
|
| 224 |
-
},
|
| 225 |
-
{
|
| 226 |
-
"epoch": 0.07396449704142012,
|
| 227 |
-
"eval_reasoning_loss": 0.965384840965271,
|
| 228 |
-
"eval_reasoning_runtime": 4.7496,
|
| 229 |
-
"eval_reasoning_samples_per_second": 112.641,
|
| 230 |
-
"eval_reasoning_steps_per_second": 1.053,
|
| 231 |
-
"step": 50
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 0.07396449704142012,
|
| 235 |
-
"eval_utility_loss": 1.2599124908447266,
|
| 236 |
-
"eval_utility_runtime": 1.8864,
|
| 237 |
-
"eval_utility_samples_per_second": 112.382,
|
| 238 |
-
"eval_utility_steps_per_second": 1.06,
|
| 239 |
"step": 50
|
| 240 |
},
|
| 241 |
{
|
| 242 |
-
"epoch": 0.
|
| 243 |
-
"grad_norm":
|
| 244 |
-
"learning_rate": 4.
|
| 245 |
-
"loss":
|
| 246 |
-
"step": 55
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 0.08136094674556213,
|
| 250 |
-
"eval_reasoning_loss": 0.9624860882759094,
|
| 251 |
-
"eval_reasoning_runtime": 4.6346,
|
| 252 |
-
"eval_reasoning_samples_per_second": 115.436,
|
| 253 |
-
"eval_reasoning_steps_per_second": 1.079,
|
| 254 |
-
"step": 55
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 0.08136094674556213,
|
| 258 |
-
"eval_utility_loss": 1.2610447406768799,
|
| 259 |
-
"eval_utility_runtime": 1.81,
|
| 260 |
-
"eval_utility_samples_per_second": 117.129,
|
| 261 |
-
"eval_utility_steps_per_second": 1.105,
|
| 262 |
"step": 55
|
| 263 |
},
|
| 264 |
{
|
| 265 |
-
"epoch": 0.
|
| 266 |
-
"grad_norm":
|
| 267 |
-
"learning_rate": 4.
|
| 268 |
-
"loss":
|
| 269 |
-
"step": 60
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.08875739644970414,
|
| 273 |
-
"eval_reasoning_loss": 0.9584144949913025,
|
| 274 |
-
"eval_reasoning_runtime": 4.7014,
|
| 275 |
-
"eval_reasoning_samples_per_second": 113.796,
|
| 276 |
-
"eval_reasoning_steps_per_second": 1.064,
|
| 277 |
-
"step": 60
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.08875739644970414,
|
| 281 |
-
"eval_utility_loss": 1.2589086294174194,
|
| 282 |
-
"eval_utility_runtime": 1.8524,
|
| 283 |
-
"eval_utility_samples_per_second": 114.446,
|
| 284 |
-
"eval_utility_steps_per_second": 1.08,
|
| 285 |
"step": 60
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 0.
|
| 289 |
-
"grad_norm":
|
| 290 |
-
"learning_rate": 4.
|
| 291 |
-
"loss":
|
| 292 |
"step": 65
|
| 293 |
},
|
| 294 |
{
|
| 295 |
-
"epoch": 0.
|
| 296 |
-
"
|
| 297 |
-
"
|
| 298 |
-
"
|
| 299 |
-
"eval_reasoning_steps_per_second": 0.997,
|
| 300 |
-
"step": 65
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 0.09615384615384616,
|
| 304 |
-
"eval_utility_loss": 1.2607706785202026,
|
| 305 |
-
"eval_utility_runtime": 1.7411,
|
| 306 |
-
"eval_utility_samples_per_second": 121.759,
|
| 307 |
-
"eval_utility_steps_per_second": 1.149,
|
| 308 |
-
"step": 65
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.10355029585798817,
|
| 312 |
-
"grad_norm": 1.1278141586447843,
|
| 313 |
-
"learning_rate": 4.965177193256699e-05,
|
| 314 |
-
"loss": 2.1095,
|
| 315 |
-
"step": 70
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.10355029585798817,
|
| 319 |
-
"eval_reasoning_loss": 0.9497982859611511,
|
| 320 |
-
"eval_reasoning_runtime": 4.9054,
|
| 321 |
-
"eval_reasoning_samples_per_second": 109.063,
|
| 322 |
-
"eval_reasoning_steps_per_second": 1.019,
|
| 323 |
-
"step": 70
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 0.10355029585798817,
|
| 327 |
-
"eval_utility_loss": 1.25819993019104,
|
| 328 |
-
"eval_utility_runtime": 1.7991,
|
| 329 |
-
"eval_utility_samples_per_second": 117.834,
|
| 330 |
-
"eval_utility_steps_per_second": 1.112,
|
| 331 |
"step": 70
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm":
|
| 336 |
-
"learning_rate": 4.
|
| 337 |
-
"loss":
|
| 338 |
-
"step": 75
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.11094674556213018,
|
| 342 |
-
"eval_reasoning_loss": 0.9482110142707825,
|
| 343 |
-
"eval_reasoning_runtime": 4.6282,
|
| 344 |
-
"eval_reasoning_samples_per_second": 115.596,
|
| 345 |
-
"eval_reasoning_steps_per_second": 1.08,
|
| 346 |
-
"step": 75
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.11094674556213018,
|
| 350 |
-
"eval_utility_loss": 1.2583030462265015,
|
| 351 |
-
"eval_utility_runtime": 1.8216,
|
| 352 |
-
"eval_utility_samples_per_second": 116.379,
|
| 353 |
-
"eval_utility_steps_per_second": 1.098,
|
| 354 |
"step": 75
|
| 355 |
},
|
| 356 |
{
|
| 357 |
-
"epoch": 0.
|
| 358 |
-
"grad_norm":
|
| 359 |
-
"learning_rate": 4.
|
| 360 |
-
"loss":
|
| 361 |
-
"step": 80
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.11834319526627218,
|
| 365 |
-
"eval_reasoning_loss": 0.9451742768287659,
|
| 366 |
-
"eval_reasoning_runtime": 4.6101,
|
| 367 |
-
"eval_reasoning_samples_per_second": 116.049,
|
| 368 |
-
"eval_reasoning_steps_per_second": 1.085,
|
| 369 |
-
"step": 80
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.11834319526627218,
|
| 373 |
-
"eval_utility_loss": 1.2601256370544434,
|
| 374 |
-
"eval_utility_runtime": 1.8824,
|
| 375 |
-
"eval_utility_samples_per_second": 112.621,
|
| 376 |
-
"eval_utility_steps_per_second": 1.062,
|
| 377 |
"step": 80
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 0.
|
| 381 |
-
"grad_norm":
|
| 382 |
-
"learning_rate": 4.
|
| 383 |
-
"loss":
|
| 384 |
"step": 85
|
| 385 |
},
|
| 386 |
{
|
| 387 |
-
"epoch": 0.
|
| 388 |
-
"
|
| 389 |
-
"
|
| 390 |
-
"
|
| 391 |
-
"eval_reasoning_steps_per_second": 1.088,
|
| 392 |
-
"step": 85
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 0.1257396449704142,
|
| 396 |
-
"eval_utility_loss": 1.2616825103759766,
|
| 397 |
-
"eval_utility_runtime": 1.8916,
|
| 398 |
-
"eval_utility_samples_per_second": 112.077,
|
| 399 |
-
"eval_utility_steps_per_second": 1.057,
|
| 400 |
-
"step": 85
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 0.13313609467455623,
|
| 404 |
-
"grad_norm": 1.0927334096818122,
|
| 405 |
-
"learning_rate": 4.916046497905381e-05,
|
| 406 |
-
"loss": 2.0583,
|
| 407 |
-
"step": 90
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 0.13313609467455623,
|
| 411 |
-
"eval_reasoning_loss": 0.940236508846283,
|
| 412 |
-
"eval_reasoning_runtime": 4.5778,
|
| 413 |
-
"eval_reasoning_samples_per_second": 116.869,
|
| 414 |
-
"eval_reasoning_steps_per_second": 1.092,
|
| 415 |
-
"step": 90
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 0.13313609467455623,
|
| 419 |
-
"eval_utility_loss": 1.2627779245376587,
|
| 420 |
-
"eval_utility_runtime": 1.8424,
|
| 421 |
-
"eval_utility_samples_per_second": 115.065,
|
| 422 |
-
"eval_utility_steps_per_second": 1.086,
|
| 423 |
"step": 90
|
| 424 |
},
|
| 425 |
{
|
| 426 |
-
"epoch": 0.
|
| 427 |
-
"grad_norm":
|
| 428 |
-
"learning_rate":
|
| 429 |
-
"loss":
|
| 430 |
-
"step": 95
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 0.14053254437869822,
|
| 434 |
-
"eval_reasoning_loss": 0.9385782480239868,
|
| 435 |
-
"eval_reasoning_runtime": 4.7307,
|
| 436 |
-
"eval_reasoning_samples_per_second": 113.091,
|
| 437 |
-
"eval_reasoning_steps_per_second": 1.057,
|
| 438 |
-
"step": 95
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 0.14053254437869822,
|
| 442 |
-
"eval_utility_loss": 1.2633188962936401,
|
| 443 |
-
"eval_utility_runtime": 1.8137,
|
| 444 |
-
"eval_utility_samples_per_second": 116.888,
|
| 445 |
-
"eval_utility_steps_per_second": 1.103,
|
| 446 |
"step": 95
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch": 0.
|
| 450 |
-
"grad_norm":
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss":
|
| 453 |
-
"step": 100
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.14792899408284024,
|
| 457 |
-
"eval_reasoning_loss": 0.9367873668670654,
|
| 458 |
-
"eval_reasoning_runtime": 4.6168,
|
| 459 |
-
"eval_reasoning_samples_per_second": 115.881,
|
| 460 |
-
"eval_reasoning_steps_per_second": 1.083,
|
| 461 |
-
"step": 100
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 0.14792899408284024,
|
| 465 |
-
"eval_utility_loss": 1.2648777961730957,
|
| 466 |
-
"eval_utility_runtime": 1.8308,
|
| 467 |
-
"eval_utility_samples_per_second": 115.798,
|
| 468 |
-
"eval_utility_steps_per_second": 1.092,
|
| 469 |
"step": 100
|
| 470 |
},
|
| 471 |
{
|
| 472 |
-
"epoch": 0.
|
| 473 |
-
"grad_norm": 0.
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 105
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch": 0.
|
| 480 |
-
"
|
| 481 |
-
"
|
| 482 |
-
"
|
| 483 |
-
"eval_steps_per_second": 1.285,
|
| 484 |
-
"step": 105
|
| 485 |
-
},
|
| 486 |
-
{
|
| 487 |
-
"epoch": 0.16272189349112426,
|
| 488 |
-
"grad_norm": 0.9788732678912112,
|
| 489 |
-
"learning_rate": 4.846185254822698e-05,
|
| 490 |
-
"loss": 0.9177,
|
| 491 |
-
"step": 110
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 0.16272189349112426,
|
| 495 |
-
"eval_loss": 0.935136616230011,
|
| 496 |
-
"eval_runtime": 3.9303,
|
| 497 |
-
"eval_samples_per_second": 136.121,
|
| 498 |
-
"eval_steps_per_second": 1.272,
|
| 499 |
"step": 110
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch": 0.
|
| 503 |
-
"grad_norm": 0.
|
| 504 |
-
"learning_rate":
|
| 505 |
-
"loss": 0.
|
| 506 |
-
"step": 115
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.17011834319526628,
|
| 510 |
-
"eval_loss": 0.9333159327507019,
|
| 511 |
-
"eval_runtime": 4.2183,
|
| 512 |
-
"eval_samples_per_second": 126.828,
|
| 513 |
-
"eval_steps_per_second": 1.185,
|
| 514 |
"step": 115
|
| 515 |
},
|
| 516 |
{
|
| 517 |
-
"epoch": 0.
|
| 518 |
-
"grad_norm": 0.
|
| 519 |
-
"learning_rate":
|
| 520 |
-
"loss": 0.
|
| 521 |
-
"step": 120
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 0.17751479289940827,
|
| 525 |
-
"eval_loss": 0.9326120018959045,
|
| 526 |
-
"eval_runtime": 4.33,
|
| 527 |
-
"eval_samples_per_second": 123.557,
|
| 528 |
-
"eval_steps_per_second": 1.155,
|
| 529 |
"step": 120
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch": 0.
|
| 533 |
-
"grad_norm": 0.
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss": 0.
|
| 536 |
"step": 125
|
| 537 |
},
|
| 538 |
{
|
| 539 |
-
"epoch": 0.
|
| 540 |
-
"
|
| 541 |
-
"
|
| 542 |
-
"
|
| 543 |
-
"eval_steps_per_second": 1.147,
|
| 544 |
-
"step": 125
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 0.19230769230769232,
|
| 548 |
-
"grad_norm": 0.9745000016888925,
|
| 549 |
-
"learning_rate": 4.756262083927795e-05,
|
| 550 |
-
"loss": 0.917,
|
| 551 |
-
"step": 130
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 0.19230769230769232,
|
| 555 |
-
"eval_loss": 0.9290282130241394,
|
| 556 |
-
"eval_runtime": 4.3713,
|
| 557 |
-
"eval_samples_per_second": 122.388,
|
| 558 |
-
"eval_steps_per_second": 1.144,
|
| 559 |
"step": 130
|
| 560 |
},
|
| 561 |
{
|
| 562 |
-
"epoch": 0.
|
| 563 |
-
"grad_norm": 0.
|
| 564 |
-
"learning_rate":
|
| 565 |
-
"loss": 0.
|
| 566 |
-
"step": 135
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.1997041420118343,
|
| 570 |
-
"eval_loss": 0.9284210205078125,
|
| 571 |
-
"eval_runtime": 4.4499,
|
| 572 |
-
"eval_samples_per_second": 120.228,
|
| 573 |
-
"eval_steps_per_second": 1.124,
|
| 574 |
"step": 135
|
| 575 |
},
|
| 576 |
{
|
| 577 |
-
"epoch": 0.
|
| 578 |
-
"grad_norm": 0.
|
| 579 |
-
"learning_rate":
|
| 580 |
-
"loss": 0.
|
| 581 |
-
"step": 140
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 0.20710059171597633,
|
| 585 |
-
"eval_loss": 0.9253069758415222,
|
| 586 |
-
"eval_runtime": 4.4492,
|
| 587 |
-
"eval_samples_per_second": 120.247,
|
| 588 |
-
"eval_steps_per_second": 1.124,
|
| 589 |
"step": 140
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch": 0.
|
| 593 |
-
"grad_norm": 0.
|
| 594 |
-
"learning_rate":
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 145
|
| 597 |
},
|
| 598 |
{
|
| 599 |
-
"epoch": 0.
|
| 600 |
-
"
|
| 601 |
-
"
|
| 602 |
-
"
|
| 603 |
-
"eval_steps_per_second": 1.101,
|
| 604 |
-
"step": 145
|
| 605 |
-
},
|
| 606 |
-
{
|
| 607 |
-
"epoch": 0.22189349112426035,
|
| 608 |
-
"grad_norm": 0.9600510868099964,
|
| 609 |
-
"learning_rate": 4.647137611522186e-05,
|
| 610 |
-
"loss": 0.8967,
|
| 611 |
-
"step": 150
|
| 612 |
-
},
|
| 613 |
-
{
|
| 614 |
-
"epoch": 0.22189349112426035,
|
| 615 |
-
"eval_loss": 0.921413242816925,
|
| 616 |
-
"eval_runtime": 4.5563,
|
| 617 |
-
"eval_samples_per_second": 117.419,
|
| 618 |
-
"eval_steps_per_second": 1.097,
|
| 619 |
"step": 150
|
| 620 |
},
|
| 621 |
{
|
| 622 |
-
"epoch": 0.
|
| 623 |
-
"grad_norm": 0.
|
| 624 |
-
"learning_rate":
|
| 625 |
-
"loss": 0.
|
| 626 |
-
"step": 155
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 0.22928994082840237,
|
| 630 |
-
"eval_loss": 0.9195402264595032,
|
| 631 |
-
"eval_runtime": 4.4933,
|
| 632 |
-
"eval_samples_per_second": 119.067,
|
| 633 |
-
"eval_steps_per_second": 1.113,
|
| 634 |
"step": 155
|
| 635 |
},
|
| 636 |
{
|
| 637 |
-
"epoch": 0.
|
| 638 |
-
"grad_norm": 0.
|
| 639 |
-
"learning_rate":
|
| 640 |
-
"loss": 0.
|
| 641 |
-
"step": 160
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 0.23668639053254437,
|
| 645 |
-
"eval_loss": 0.9192004203796387,
|
| 646 |
-
"eval_runtime": 4.5417,
|
| 647 |
-
"eval_samples_per_second": 117.797,
|
| 648 |
-
"eval_steps_per_second": 1.101,
|
| 649 |
"step": 160
|
| 650 |
},
|
| 651 |
{
|
| 652 |
-
"epoch": 0.
|
| 653 |
-
"grad_norm": 0.
|
| 654 |
-
"learning_rate":
|
| 655 |
-
"loss": 0.
|
| 656 |
"step": 165
|
| 657 |
},
|
| 658 |
{
|
| 659 |
-
"epoch": 0.
|
| 660 |
-
"
|
| 661 |
-
"
|
| 662 |
-
"
|
| 663 |
-
"eval_steps_per_second": 1.102,
|
| 664 |
-
"step": 165
|
| 665 |
-
},
|
| 666 |
-
{
|
| 667 |
-
"epoch": 0.2514792899408284,
|
| 668 |
-
"grad_norm": 0.9532036102972735,
|
| 669 |
-
"learning_rate": 4.5198562335069036e-05,
|
| 670 |
-
"loss": 0.9106,
|
| 671 |
-
"step": 170
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 0.2514792899408284,
|
| 675 |
-
"eval_loss": 0.9174200892448425,
|
| 676 |
-
"eval_runtime": 4.5738,
|
| 677 |
-
"eval_samples_per_second": 116.971,
|
| 678 |
-
"eval_steps_per_second": 1.093,
|
| 679 |
"step": 170
|
| 680 |
},
|
| 681 |
{
|
| 682 |
-
"epoch": 0.
|
| 683 |
-
"grad_norm": 0.
|
| 684 |
-
"learning_rate":
|
| 685 |
-
"loss": 0.
|
| 686 |
-
"step": 175
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"epoch": 0.2588757396449704,
|
| 690 |
-
"eval_loss": 0.9161617755889893,
|
| 691 |
-
"eval_runtime": 4.5176,
|
| 692 |
-
"eval_samples_per_second": 118.425,
|
| 693 |
-
"eval_steps_per_second": 1.107,
|
| 694 |
"step": 175
|
| 695 |
},
|
| 696 |
{
|
| 697 |
-
"epoch": 0.
|
| 698 |
-
"grad_norm":
|
| 699 |
-
"learning_rate":
|
| 700 |
-
"loss": 0.
|
| 701 |
-
"step": 180
|
| 702 |
-
},
|
| 703 |
-
{
|
| 704 |
-
"epoch": 0.26627218934911245,
|
| 705 |
-
"eval_loss": 0.9148706793785095,
|
| 706 |
-
"eval_runtime": 4.4688,
|
| 707 |
-
"eval_samples_per_second": 119.718,
|
| 708 |
-
"eval_steps_per_second": 1.119,
|
| 709 |
"step": 180
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 0.
|
| 713 |
-
"grad_norm": 0.
|
| 714 |
-
"learning_rate":
|
| 715 |
-
"loss": 0.
|
| 716 |
"step": 185
|
| 717 |
},
|
| 718 |
{
|
| 719 |
-
"epoch": 0.
|
| 720 |
-
"
|
| 721 |
-
"
|
| 722 |
-
"
|
| 723 |
-
"eval_steps_per_second": 1.118,
|
| 724 |
-
"step": 185
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 0.28106508875739644,
|
| 728 |
-
"grad_norm": 0.8083730916154258,
|
| 729 |
-
"learning_rate": 4.3756361197988056e-05,
|
| 730 |
-
"loss": 0.8857,
|
| 731 |
-
"step": 190
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 0.28106508875739644,
|
| 735 |
-
"eval_loss": 0.9111117124557495,
|
| 736 |
-
"eval_runtime": 4.5302,
|
| 737 |
-
"eval_samples_per_second": 118.096,
|
| 738 |
-
"eval_steps_per_second": 1.104,
|
| 739 |
"step": 190
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch": 0.
|
| 743 |
-
"grad_norm": 0.
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss": 0.
|
| 746 |
-
"step": 195
|
| 747 |
-
},
|
| 748 |
-
{
|
| 749 |
-
"epoch": 0.28846153846153844,
|
| 750 |
-
"eval_loss": 0.9104787707328796,
|
| 751 |
-
"eval_runtime": 4.5367,
|
| 752 |
-
"eval_samples_per_second": 117.928,
|
| 753 |
-
"eval_steps_per_second": 1.102,
|
| 754 |
"step": 195
|
| 755 |
},
|
| 756 |
{
|
| 757 |
-
"epoch": 0.
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
-
"learning_rate":
|
| 760 |
-
"loss": 0.
|
| 761 |
-
"step": 200
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 0.2958579881656805,
|
| 765 |
-
"eval_loss": 0.9094380736351013,
|
| 766 |
-
"eval_runtime": 4.5088,
|
| 767 |
-
"eval_samples_per_second": 118.657,
|
| 768 |
-
"eval_steps_per_second": 1.109,
|
| 769 |
"step": 200
|
| 770 |
},
|
| 771 |
{
|
| 772 |
-
"epoch": 0.
|
| 773 |
-
"grad_norm": 0.
|
| 774 |
-
"learning_rate":
|
| 775 |
-
"loss": 0.
|
| 776 |
"step": 205
|
| 777 |
},
|
| 778 |
{
|
| 779 |
-
"epoch": 0.
|
| 780 |
-
"
|
| 781 |
-
"
|
| 782 |
-
"
|
| 783 |
-
"eval_steps_per_second": 1.1,
|
| 784 |
-
"step": 205
|
| 785 |
-
},
|
| 786 |
-
{
|
| 787 |
-
"epoch": 0.3106508875739645,
|
| 788 |
-
"grad_norm": 0.840098337392708,
|
| 789 |
-
"learning_rate": 4.2158575556105764e-05,
|
| 790 |
-
"loss": 0.8914,
|
| 791 |
-
"step": 210
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 0.3106508875739645,
|
| 795 |
-
"eval_loss": 0.9070125818252563,
|
| 796 |
-
"eval_runtime": 4.6468,
|
| 797 |
-
"eval_samples_per_second": 115.134,
|
| 798 |
-
"eval_steps_per_second": 1.076,
|
| 799 |
"step": 210
|
| 800 |
},
|
| 801 |
{
|
| 802 |
-
"epoch": 0.
|
| 803 |
-
"grad_norm": 0.
|
| 804 |
-
"learning_rate":
|
| 805 |
-
"loss": 0.
|
| 806 |
-
"step": 215
|
| 807 |
-
},
|
| 808 |
-
{
|
| 809 |
-
"epoch": 0.3180473372781065,
|
| 810 |
-
"eval_loss": 0.9057661890983582,
|
| 811 |
-
"eval_runtime": 4.582,
|
| 812 |
-
"eval_samples_per_second": 116.76,
|
| 813 |
-
"eval_steps_per_second": 1.091,
|
| 814 |
"step": 215
|
| 815 |
},
|
| 816 |
{
|
| 817 |
-
"epoch": 0.
|
| 818 |
-
"grad_norm": 0.
|
| 819 |
-
"learning_rate":
|
| 820 |
-
"loss": 0.
|
| 821 |
-
"step": 220
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 0.3254437869822485,
|
| 825 |
-
"eval_loss": 0.9040650725364685,
|
| 826 |
-
"eval_runtime": 4.6541,
|
| 827 |
-
"eval_samples_per_second": 114.953,
|
| 828 |
-
"eval_steps_per_second": 1.074,
|
| 829 |
"step": 220
|
| 830 |
},
|
| 831 |
{
|
| 832 |
-
"epoch": 0.
|
| 833 |
-
"grad_norm": 0.
|
| 834 |
-
"learning_rate":
|
| 835 |
-
"loss": 0.
|
| 836 |
"step": 225
|
| 837 |
},
|
| 838 |
{
|
| 839 |
-
"epoch": 0.
|
| 840 |
-
"
|
| 841 |
-
"
|
| 842 |
-
"
|
| 843 |
-
"eval_steps_per_second": 1.087,
|
| 844 |
-
"step": 225
|
| 845 |
-
},
|
| 846 |
-
{
|
| 847 |
-
"epoch": 0.34023668639053256,
|
| 848 |
-
"grad_norm": 0.7511534980546334,
|
| 849 |
-
"learning_rate": 4.042049731176386e-05,
|
| 850 |
-
"loss": 0.8845,
|
| 851 |
-
"step": 230
|
| 852 |
-
},
|
| 853 |
-
{
|
| 854 |
-
"epoch": 0.34023668639053256,
|
| 855 |
-
"eval_loss": 0.9032608270645142,
|
| 856 |
-
"eval_runtime": 4.5071,
|
| 857 |
-
"eval_samples_per_second": 118.703,
|
| 858 |
-
"eval_steps_per_second": 1.109,
|
| 859 |
"step": 230
|
| 860 |
},
|
| 861 |
{
|
| 862 |
-
"epoch": 0.
|
| 863 |
-
"grad_norm": 0.
|
| 864 |
-
"learning_rate":
|
| 865 |
-
"loss": 0.
|
| 866 |
-
"step": 235
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 0.34763313609467456,
|
| 870 |
-
"eval_loss": 0.9020082950592041,
|
| 871 |
-
"eval_runtime": 4.7865,
|
| 872 |
-
"eval_samples_per_second": 111.774,
|
| 873 |
-
"eval_steps_per_second": 1.045,
|
| 874 |
"step": 235
|
| 875 |
},
|
| 876 |
{
|
| 877 |
-
"epoch": 0.
|
| 878 |
-
"grad_norm": 0.
|
| 879 |
-
"learning_rate":
|
| 880 |
-
"loss": 0.
|
| 881 |
-
"step": 240
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 0.35502958579881655,
|
| 885 |
-
"eval_loss": 0.9021012187004089,
|
| 886 |
-
"eval_runtime": 4.4736,
|
| 887 |
-
"eval_samples_per_second": 119.59,
|
| 888 |
-
"eval_steps_per_second": 1.118,
|
| 889 |
"step": 240
|
| 890 |
},
|
| 891 |
{
|
| 892 |
-
"epoch": 0.
|
| 893 |
-
"grad_norm": 0.
|
| 894 |
-
"learning_rate":
|
| 895 |
-
"loss": 0.
|
| 896 |
"step": 245
|
| 897 |
},
|
| 898 |
{
|
| 899 |
-
"epoch": 0.
|
| 900 |
-
"
|
| 901 |
-
"
|
| 902 |
-
"
|
| 903 |
-
"eval_steps_per_second": 1.112,
|
| 904 |
-
"step": 245
|
| 905 |
-
},
|
| 906 |
-
{
|
| 907 |
-
"epoch": 0.3698224852071006,
|
| 908 |
-
"grad_norm": 0.6874768710018212,
|
| 909 |
-
"learning_rate": 3.855876106354553e-05,
|
| 910 |
-
"loss": 0.8662,
|
| 911 |
-
"step": 250
|
| 912 |
-
},
|
| 913 |
-
{
|
| 914 |
-
"epoch": 0.3698224852071006,
|
| 915 |
-
"eval_loss": 0.8995451331138611,
|
| 916 |
-
"eval_runtime": 4.5879,
|
| 917 |
-
"eval_samples_per_second": 116.611,
|
| 918 |
-
"eval_steps_per_second": 1.09,
|
| 919 |
"step": 250
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch": 0.
|
| 923 |
-
"grad_norm": 0.
|
| 924 |
-
"learning_rate":
|
| 925 |
-
"loss": 0.
|
| 926 |
-
"step": 255
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 0.3772189349112426,
|
| 930 |
-
"eval_loss": 0.8975517749786377,
|
| 931 |
-
"eval_runtime": 4.5179,
|
| 932 |
-
"eval_samples_per_second": 118.417,
|
| 933 |
-
"eval_steps_per_second": 1.107,
|
| 934 |
"step": 255
|
| 935 |
},
|
| 936 |
{
|
| 937 |
-
"epoch": 0.
|
| 938 |
-
"grad_norm": 0.
|
| 939 |
-
"learning_rate":
|
| 940 |
-
"loss": 0.
|
| 941 |
-
"step": 260
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"epoch": 0.38461538461538464,
|
| 945 |
-
"eval_loss": 0.8961707353591919,
|
| 946 |
-
"eval_runtime": 4.6188,
|
| 947 |
-
"eval_samples_per_second": 115.83,
|
| 948 |
-
"eval_steps_per_second": 1.083,
|
| 949 |
"step": 260
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch": 0.
|
| 953 |
-
"grad_norm": 0.
|
| 954 |
-
"learning_rate":
|
| 955 |
-
"loss": 0.
|
| 956 |
"step": 265
|
| 957 |
},
|
| 958 |
-
{
|
| 959 |
-
"epoch": 0.39201183431952663,
|
| 960 |
-
"eval_loss": 0.8945226073265076,
|
| 961 |
-
"eval_runtime": 4.6059,
|
| 962 |
-
"eval_samples_per_second": 116.155,
|
| 963 |
-
"eval_steps_per_second": 1.086,
|
| 964 |
-
"step": 265
|
| 965 |
-
},
|
| 966 |
-
{
|
| 967 |
-
"epoch": 0.3994082840236686,
|
| 968 |
-
"grad_norm": 0.7672004326970635,
|
| 969 |
-
"learning_rate": 3.6591184901779965e-05,
|
| 970 |
-
"loss": 0.884,
|
| 971 |
-
"step": 270
|
| 972 |
-
},
|
| 973 |
-
{
|
| 974 |
-
"epoch": 0.3994082840236686,
|
| 975 |
-
"eval_loss": 0.8951981663703918,
|
| 976 |
-
"eval_runtime": 4.5266,
|
| 977 |
-
"eval_samples_per_second": 118.191,
|
| 978 |
-
"eval_steps_per_second": 1.105,
|
| 979 |
-
"step": 270
|
| 980 |
-
},
|
| 981 |
-
{
|
| 982 |
-
"epoch": 0.4068047337278107,
|
| 983 |
-
"grad_norm": 0.8279425083821433,
|
| 984 |
-
"learning_rate": 3.6084940419110235e-05,
|
| 985 |
-
"loss": 0.865,
|
| 986 |
-
"step": 275
|
| 987 |
-
},
|
| 988 |
-
{
|
| 989 |
-
"epoch": 0.4068047337278107,
|
| 990 |
-
"eval_loss": 0.8942187428474426,
|
| 991 |
-
"eval_runtime": 4.4718,
|
| 992 |
-
"eval_samples_per_second": 119.638,
|
| 993 |
-
"eval_steps_per_second": 1.118,
|
| 994 |
-
"step": 275
|
| 995 |
-
},
|
| 996 |
-
{
|
| 997 |
-
"epoch": 0.41420118343195267,
|
| 998 |
-
"grad_norm": 0.6924917194060726,
|
| 999 |
-
"learning_rate": 3.557355685716056e-05,
|
| 1000 |
-
"loss": 0.8963,
|
| 1001 |
-
"step": 280
|
| 1002 |
-
},
|
| 1003 |
-
{
|
| 1004 |
-
"epoch": 0.41420118343195267,
|
| 1005 |
-
"eval_loss": 0.8927004337310791,
|
| 1006 |
-
"eval_runtime": 4.5867,
|
| 1007 |
-
"eval_samples_per_second": 116.642,
|
| 1008 |
-
"eval_steps_per_second": 1.09,
|
| 1009 |
-
"step": 280
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"epoch": 0.42159763313609466,
|
| 1013 |
-
"grad_norm": 0.7300617000412236,
|
| 1014 |
-
"learning_rate": 3.505734033810989e-05,
|
| 1015 |
-
"loss": 0.878,
|
| 1016 |
-
"step": 285
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 0.42159763313609466,
|
| 1020 |
-
"eval_loss": 0.8926271796226501,
|
| 1021 |
-
"eval_runtime": 4.5293,
|
| 1022 |
-
"eval_samples_per_second": 118.121,
|
| 1023 |
-
"eval_steps_per_second": 1.104,
|
| 1024 |
-
"step": 285
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 0.4289940828402367,
|
| 1028 |
-
"grad_norm": 0.8294306981958416,
|
| 1029 |
-
"learning_rate": 3.45365998772207e-05,
|
| 1030 |
-
"loss": 0.876,
|
| 1031 |
-
"step": 290
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 0.4289940828402367,
|
| 1035 |
-
"eval_loss": 0.8919618725776672,
|
| 1036 |
-
"eval_runtime": 4.533,
|
| 1037 |
-
"eval_samples_per_second": 118.024,
|
| 1038 |
-
"eval_steps_per_second": 1.103,
|
| 1039 |
-
"step": 290
|
| 1040 |
-
},
|
| 1041 |
-
{
|
| 1042 |
-
"epoch": 0.4363905325443787,
|
| 1043 |
-
"grad_norm": 0.6786743799594892,
|
| 1044 |
-
"learning_rate": 3.4011647197857654e-05,
|
| 1045 |
-
"loss": 0.8816,
|
| 1046 |
-
"step": 295
|
| 1047 |
-
},
|
| 1048 |
-
{
|
| 1049 |
-
"epoch": 0.4363905325443787,
|
| 1050 |
-
"eval_loss": 0.8911965489387512,
|
| 1051 |
-
"eval_runtime": 4.6093,
|
| 1052 |
-
"eval_samples_per_second": 116.069,
|
| 1053 |
-
"eval_steps_per_second": 1.085,
|
| 1054 |
-
"step": 295
|
| 1055 |
-
},
|
| 1056 |
-
{
|
| 1057 |
-
"epoch": 0.4437869822485207,
|
| 1058 |
-
"grad_norm": 0.833036937401054,
|
| 1059 |
-
"learning_rate": 3.34827965448851e-05,
|
| 1060 |
-
"loss": 0.8727,
|
| 1061 |
-
"step": 300
|
| 1062 |
-
},
|
| 1063 |
-
{
|
| 1064 |
-
"epoch": 0.4437869822485207,
|
| 1065 |
-
"eval_loss": 0.8890377879142761,
|
| 1066 |
-
"eval_runtime": 4.5425,
|
| 1067 |
-
"eval_samples_per_second": 117.776,
|
| 1068 |
-
"eval_steps_per_second": 1.101,
|
| 1069 |
-
"step": 300
|
| 1070 |
-
},
|
| 1071 |
-
{
|
| 1072 |
-
"epoch": 0.4511834319526627,
|
| 1073 |
-
"grad_norm": 0.7813589947732351,
|
| 1074 |
-
"learning_rate": 3.2950364496555214e-05,
|
| 1075 |
-
"loss": 0.8738,
|
| 1076 |
-
"step": 305
|
| 1077 |
-
},
|
| 1078 |
-
{
|
| 1079 |
-
"epoch": 0.4511834319526627,
|
| 1080 |
-
"eval_loss": 0.8887431621551514,
|
| 1081 |
-
"eval_runtime": 4.6379,
|
| 1082 |
-
"eval_samples_per_second": 115.353,
|
| 1083 |
-
"eval_steps_per_second": 1.078,
|
| 1084 |
-
"step": 305
|
| 1085 |
-
},
|
| 1086 |
-
{
|
| 1087 |
-
"epoch": 0.45857988165680474,
|
| 1088 |
-
"grad_norm": 0.7325656989385956,
|
| 1089 |
-
"learning_rate": 3.241466977499929e-05,
|
| 1090 |
-
"loss": 0.8658,
|
| 1091 |
-
"step": 310
|
| 1092 |
-
},
|
| 1093 |
-
{
|
| 1094 |
-
"epoch": 0.45857988165680474,
|
| 1095 |
-
"eval_loss": 0.887874186038971,
|
| 1096 |
-
"eval_runtime": 4.6002,
|
| 1097 |
-
"eval_samples_per_second": 116.301,
|
| 1098 |
-
"eval_steps_per_second": 1.087,
|
| 1099 |
-
"step": 310
|
| 1100 |
-
},
|
| 1101 |
-
{
|
| 1102 |
-
"epoch": 0.46597633136094674,
|
| 1103 |
-
"grad_norm": 0.9022362063604372,
|
| 1104 |
-
"learning_rate": 3.187603305543577e-05,
|
| 1105 |
-
"loss": 0.8705,
|
| 1106 |
-
"step": 315
|
| 1107 |
-
},
|
| 1108 |
-
{
|
| 1109 |
-
"epoch": 0.46597633136094674,
|
| 1110 |
-
"eval_loss": 0.8875709772109985,
|
| 1111 |
-
"eval_runtime": 4.59,
|
| 1112 |
-
"eval_samples_per_second": 116.559,
|
| 1113 |
-
"eval_steps_per_second": 1.089,
|
| 1114 |
-
"step": 315
|
| 1115 |
-
},
|
| 1116 |
-
{
|
| 1117 |
-
"epoch": 0.47337278106508873,
|
| 1118 |
-
"grad_norm": 0.7741483099078358,
|
| 1119 |
-
"learning_rate": 3.133477677420894e-05,
|
| 1120 |
-
"loss": 0.8922,
|
| 1121 |
-
"step": 320
|
| 1122 |
-
},
|
| 1123 |
-
{
|
| 1124 |
-
"epoch": 0.47337278106508873,
|
| 1125 |
-
"eval_loss": 0.8861641883850098,
|
| 1126 |
-
"eval_runtime": 4.5295,
|
| 1127 |
-
"eval_samples_per_second": 118.115,
|
| 1128 |
-
"eval_steps_per_second": 1.104,
|
| 1129 |
-
"step": 320
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 0.4807692307692308,
|
| 1133 |
-
"grad_norm": 0.6898160412918697,
|
| 1134 |
-
"learning_rate": 3.0791224935773624e-05,
|
| 1135 |
-
"loss": 0.8716,
|
| 1136 |
-
"step": 325
|
| 1137 |
-
},
|
| 1138 |
-
{
|
| 1139 |
-
"epoch": 0.4807692307692308,
|
| 1140 |
-
"eval_loss": 0.8853756189346313,
|
| 1141 |
-
"eval_runtime": 4.5133,
|
| 1142 |
-
"eval_samples_per_second": 118.54,
|
| 1143 |
-
"eval_steps_per_second": 1.108,
|
| 1144 |
-
"step": 325
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 0.4881656804733728,
|
| 1148 |
-
"grad_norm": 0.6815469807890937,
|
| 1149 |
-
"learning_rate": 3.0245702918740964e-05,
|
| 1150 |
-
"loss": 0.8554,
|
| 1151 |
-
"step": 330
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 0.4881656804733728,
|
| 1155 |
-
"eval_loss": 0.8842912912368774,
|
| 1156 |
-
"eval_runtime": 4.5403,
|
| 1157 |
-
"eval_samples_per_second": 117.834,
|
| 1158 |
-
"eval_steps_per_second": 1.101,
|
| 1159 |
-
"step": 330
|
| 1160 |
-
},
|
| 1161 |
-
{
|
| 1162 |
-
"epoch": 0.49556213017751477,
|
| 1163 |
-
"grad_norm": 0.6536960015603316,
|
| 1164 |
-
"learning_rate": 2.969853728110179e-05,
|
| 1165 |
-
"loss": 0.8469,
|
| 1166 |
-
"step": 335
|
| 1167 |
-
},
|
| 1168 |
-
{
|
| 1169 |
-
"epoch": 0.49556213017751477,
|
| 1170 |
-
"eval_loss": 0.8840665817260742,
|
| 1171 |
-
"eval_runtime": 4.5356,
|
| 1172 |
-
"eval_samples_per_second": 117.957,
|
| 1173 |
-
"eval_steps_per_second": 1.102,
|
| 1174 |
-
"step": 335
|
| 1175 |
-
},
|
| 1176 |
-
{
|
| 1177 |
-
"epoch": 0.5029585798816568,
|
| 1178 |
-
"grad_norm": 0.6782286300780161,
|
| 1179 |
-
"learning_rate": 2.915005556474384e-05,
|
| 1180 |
-
"loss": 0.8699,
|
| 1181 |
-
"step": 340
|
| 1182 |
-
},
|
| 1183 |
-
{
|
| 1184 |
-
"epoch": 0.5029585798816568,
|
| 1185 |
-
"eval_loss": 0.8830198645591736,
|
| 1186 |
-
"eval_runtime": 4.4892,
|
| 1187 |
-
"eval_samples_per_second": 119.175,
|
| 1188 |
-
"eval_steps_per_second": 1.114,
|
| 1189 |
-
"step": 340
|
| 1190 |
-
},
|
| 1191 |
-
{
|
| 1192 |
-
"epoch": 0.5103550295857988,
|
| 1193 |
-
"grad_norm": 0.6416520739158129,
|
| 1194 |
-
"learning_rate": 2.8600586099380123e-05,
|
| 1195 |
-
"loss": 0.8633,
|
| 1196 |
-
"step": 345
|
| 1197 |
-
},
|
| 1198 |
-
{
|
| 1199 |
-
"epoch": 0.5103550295857988,
|
| 1200 |
-
"eval_loss": 0.8818948268890381,
|
| 1201 |
-
"eval_runtime": 4.4716,
|
| 1202 |
-
"eval_samples_per_second": 119.643,
|
| 1203 |
-
"eval_steps_per_second": 1.118,
|
| 1204 |
-
"step": 345
|
| 1205 |
-
},
|
| 1206 |
-
{
|
| 1207 |
-
"epoch": 0.5177514792899408,
|
| 1208 |
-
"grad_norm": 0.7185733539593375,
|
| 1209 |
-
"learning_rate": 2.8050457806005613e-05,
|
| 1210 |
-
"loss": 0.8604,
|
| 1211 |
-
"step": 350
|
| 1212 |
-
},
|
| 1213 |
-
{
|
| 1214 |
-
"epoch": 0.5177514792899408,
|
| 1215 |
-
"eval_loss": 0.8818439245223999,
|
| 1216 |
-
"eval_runtime": 4.5556,
|
| 1217 |
-
"eval_samples_per_second": 117.438,
|
| 1218 |
-
"eval_steps_per_second": 1.098,
|
| 1219 |
-
"step": 350
|
| 1220 |
-
},
|
| 1221 |
-
{
|
| 1222 |
-
"epoch": 0.5251479289940828,
|
| 1223 |
-
"grad_norm": 0.7685402090063009,
|
| 1224 |
-
"learning_rate": 2.7500000000000004e-05,
|
| 1225 |
-
"loss": 0.8607,
|
| 1226 |
-
"step": 355
|
| 1227 |
-
},
|
| 1228 |
-
{
|
| 1229 |
-
"epoch": 0.5251479289940828,
|
| 1230 |
-
"eval_loss": 0.8809483051300049,
|
| 1231 |
-
"eval_runtime": 4.4752,
|
| 1232 |
-
"eval_samples_per_second": 119.546,
|
| 1233 |
-
"eval_steps_per_second": 1.117,
|
| 1234 |
-
"step": 355
|
| 1235 |
-
},
|
| 1236 |
-
{
|
| 1237 |
-
"epoch": 0.5325443786982249,
|
| 1238 |
-
"grad_norm": 0.7342686897340025,
|
| 1239 |
-
"learning_rate": 2.69495421939944e-05,
|
| 1240 |
-
"loss": 0.842,
|
| 1241 |
-
"step": 360
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 0.5325443786982249,
|
| 1245 |
-
"eval_loss": 0.8807406425476074,
|
| 1246 |
-
"eval_runtime": 4.4623,
|
| 1247 |
-
"eval_samples_per_second": 119.894,
|
| 1248 |
-
"eval_steps_per_second": 1.121,
|
| 1249 |
-
"step": 360
|
| 1250 |
-
},
|
| 1251 |
-
{
|
| 1252 |
-
"epoch": 0.5399408284023669,
|
| 1253 |
-
"grad_norm": 0.8172803037562146,
|
| 1254 |
-
"learning_rate": 2.639941390061988e-05,
|
| 1255 |
-
"loss": 0.8625,
|
| 1256 |
-
"step": 365
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 0.5399408284023669,
|
| 1260 |
-
"eval_loss": 0.8791869878768921,
|
| 1261 |
-
"eval_runtime": 4.5731,
|
| 1262 |
-
"eval_samples_per_second": 116.988,
|
| 1263 |
-
"eval_steps_per_second": 1.093,
|
| 1264 |
-
"step": 365
|
| 1265 |
-
},
|
| 1266 |
-
{
|
| 1267 |
-
"epoch": 0.5473372781065089,
|
| 1268 |
-
"grad_norm": 0.7569175685957509,
|
| 1269 |
-
"learning_rate": 2.584994443525617e-05,
|
| 1270 |
-
"loss": 0.8662,
|
| 1271 |
-
"step": 370
|
| 1272 |
-
},
|
| 1273 |
-
{
|
| 1274 |
-
"epoch": 0.5473372781065089,
|
| 1275 |
-
"eval_loss": 0.8787435293197632,
|
| 1276 |
-
"eval_runtime": 4.578,
|
| 1277 |
-
"eval_samples_per_second": 116.863,
|
| 1278 |
-
"eval_steps_per_second": 1.092,
|
| 1279 |
-
"step": 370
|
| 1280 |
-
},
|
| 1281 |
-
{
|
| 1282 |
-
"epoch": 0.5547337278106509,
|
| 1283 |
-
"grad_norm": 0.7873241841048441,
|
| 1284 |
-
"learning_rate": 2.5301462718898215e-05,
|
| 1285 |
-
"loss": 0.8552,
|
| 1286 |
-
"step": 375
|
| 1287 |
-
},
|
| 1288 |
-
{
|
| 1289 |
-
"epoch": 0.5547337278106509,
|
| 1290 |
-
"eval_loss": 0.8779678344726562,
|
| 1291 |
-
"eval_runtime": 4.532,
|
| 1292 |
-
"eval_samples_per_second": 118.05,
|
| 1293 |
-
"eval_steps_per_second": 1.103,
|
| 1294 |
-
"step": 375
|
| 1295 |
-
},
|
| 1296 |
-
{
|
| 1297 |
-
"epoch": 0.5621301775147929,
|
| 1298 |
-
"grad_norm": 0.7232681596622134,
|
| 1299 |
-
"learning_rate": 2.4754297081259048e-05,
|
| 1300 |
-
"loss": 0.8741,
|
| 1301 |
-
"step": 380
|
| 1302 |
-
},
|
| 1303 |
-
{
|
| 1304 |
-
"epoch": 0.5621301775147929,
|
| 1305 |
-
"eval_loss": 0.87770015001297,
|
| 1306 |
-
"eval_runtime": 4.585,
|
| 1307 |
-
"eval_samples_per_second": 116.685,
|
| 1308 |
-
"eval_steps_per_second": 1.091,
|
| 1309 |
-
"step": 380
|
| 1310 |
-
},
|
| 1311 |
-
{
|
| 1312 |
-
"epoch": 0.5695266272189349,
|
| 1313 |
-
"grad_norm": 0.7943811735564513,
|
| 1314 |
-
"learning_rate": 2.4208775064226384e-05,
|
| 1315 |
-
"loss": 0.8499,
|
| 1316 |
-
"step": 385
|
| 1317 |
-
},
|
| 1318 |
-
{
|
| 1319 |
-
"epoch": 0.5695266272189349,
|
| 1320 |
-
"eval_loss": 0.8768277764320374,
|
| 1321 |
-
"eval_runtime": 4.532,
|
| 1322 |
-
"eval_samples_per_second": 118.051,
|
| 1323 |
-
"eval_steps_per_second": 1.103,
|
| 1324 |
-
"step": 385
|
| 1325 |
-
},
|
| 1326 |
-
{
|
| 1327 |
-
"epoch": 0.5769230769230769,
|
| 1328 |
-
"grad_norm": 0.6788490872865308,
|
| 1329 |
-
"learning_rate": 2.3665223225791074e-05,
|
| 1330 |
-
"loss": 0.8509,
|
| 1331 |
-
"step": 390
|
| 1332 |
-
},
|
| 1333 |
-
{
|
| 1334 |
-
"epoch": 0.5769230769230769,
|
| 1335 |
-
"eval_loss": 0.876204788684845,
|
| 1336 |
-
"eval_runtime": 4.5571,
|
| 1337 |
-
"eval_samples_per_second": 117.399,
|
| 1338 |
-
"eval_steps_per_second": 1.097,
|
| 1339 |
-
"step": 390
|
| 1340 |
-
},
|
| 1341 |
-
{
|
| 1342 |
-
"epoch": 0.584319526627219,
|
| 1343 |
-
"grad_norm": 0.6283691221546651,
|
| 1344 |
-
"learning_rate": 2.3123966944564242e-05,
|
| 1345 |
-
"loss": 0.8546,
|
| 1346 |
-
"step": 395
|
| 1347 |
-
},
|
| 1348 |
-
{
|
| 1349 |
-
"epoch": 0.584319526627219,
|
| 1350 |
-
"eval_loss": 0.8753672242164612,
|
| 1351 |
-
"eval_runtime": 4.4802,
|
| 1352 |
-
"eval_samples_per_second": 119.414,
|
| 1353 |
-
"eval_steps_per_second": 1.116,
|
| 1354 |
-
"step": 395
|
| 1355 |
-
},
|
| 1356 |
-
{
|
| 1357 |
-
"epoch": 0.591715976331361,
|
| 1358 |
-
"grad_norm": 0.6786610256300601,
|
| 1359 |
-
"learning_rate": 2.258533022500071e-05,
|
| 1360 |
-
"loss": 0.836,
|
| 1361 |
-
"step": 400
|
| 1362 |
-
},
|
| 1363 |
-
{
|
| 1364 |
-
"epoch": 0.591715976331361,
|
| 1365 |
-
"eval_loss": 0.874183714389801,
|
| 1366 |
-
"eval_runtime": 4.569,
|
| 1367 |
-
"eval_samples_per_second": 117.093,
|
| 1368 |
-
"eval_steps_per_second": 1.094,
|
| 1369 |
-
"step": 400
|
| 1370 |
-
},
|
| 1371 |
-
{
|
| 1372 |
-
"epoch": 0.599112426035503,
|
| 1373 |
-
"grad_norm": 0.6813901972627211,
|
| 1374 |
-
"learning_rate": 2.2049635503444792e-05,
|
| 1375 |
-
"loss": 0.8555,
|
| 1376 |
-
"step": 405
|
| 1377 |
-
},
|
| 1378 |
-
{
|
| 1379 |
-
"epoch": 0.599112426035503,
|
| 1380 |
-
"eval_loss": 0.8732807636260986,
|
| 1381 |
-
"eval_runtime": 4.5619,
|
| 1382 |
-
"eval_samples_per_second": 117.275,
|
| 1383 |
-
"eval_steps_per_second": 1.096,
|
| 1384 |
-
"step": 405
|
| 1385 |
-
},
|
| 1386 |
-
{
|
| 1387 |
-
"epoch": 0.606508875739645,
|
| 1388 |
-
"grad_norm": 0.660113771455314,
|
| 1389 |
-
"learning_rate": 2.151720345511491e-05,
|
| 1390 |
-
"loss": 0.8483,
|
| 1391 |
-
"step": 410
|
| 1392 |
-
},
|
| 1393 |
-
{
|
| 1394 |
-
"epoch": 0.606508875739645,
|
| 1395 |
-
"eval_loss": 0.8721917867660522,
|
| 1396 |
-
"eval_runtime": 4.7031,
|
| 1397 |
-
"eval_samples_per_second": 113.756,
|
| 1398 |
-
"eval_steps_per_second": 1.063,
|
| 1399 |
-
"step": 410
|
| 1400 |
-
},
|
| 1401 |
-
{
|
| 1402 |
-
"epoch": 0.613905325443787,
|
| 1403 |
-
"grad_norm": 0.6554745701701462,
|
| 1404 |
-
"learning_rate": 2.0988352802142352e-05,
|
| 1405 |
-
"loss": 0.8344,
|
| 1406 |
-
"step": 415
|
| 1407 |
-
},
|
| 1408 |
-
{
|
| 1409 |
-
"epoch": 0.613905325443787,
|
| 1410 |
-
"eval_loss": 0.8716893792152405,
|
| 1411 |
-
"eval_runtime": 4.6708,
|
| 1412 |
-
"eval_samples_per_second": 114.541,
|
| 1413 |
-
"eval_steps_per_second": 1.07,
|
| 1414 |
-
"step": 415
|
| 1415 |
-
},
|
| 1416 |
-
{
|
| 1417 |
-
"epoch": 0.621301775147929,
|
| 1418 |
-
"grad_norm": 0.6532273385705507,
|
| 1419 |
-
"learning_rate": 2.0463400122779307e-05,
|
| 1420 |
-
"loss": 0.8336,
|
| 1421 |
-
"step": 420
|
| 1422 |
-
},
|
| 1423 |
-
{
|
| 1424 |
-
"epoch": 0.621301775147929,
|
| 1425 |
-
"eval_loss": 0.871632993221283,
|
| 1426 |
-
"eval_runtime": 4.6552,
|
| 1427 |
-
"eval_samples_per_second": 114.924,
|
| 1428 |
-
"eval_steps_per_second": 1.074,
|
| 1429 |
-
"step": 420
|
| 1430 |
-
},
|
| 1431 |
-
{
|
| 1432 |
-
"epoch": 0.628698224852071,
|
| 1433 |
-
"grad_norm": 0.6375832377334109,
|
| 1434 |
-
"learning_rate": 1.994265966189012e-05,
|
| 1435 |
-
"loss": 0.8452,
|
| 1436 |
-
"step": 425
|
| 1437 |
-
},
|
| 1438 |
-
{
|
| 1439 |
-
"epoch": 0.628698224852071,
|
| 1440 |
-
"eval_loss": 0.8717252016067505,
|
| 1441 |
-
"eval_runtime": 4.5491,
|
| 1442 |
-
"eval_samples_per_second": 117.607,
|
| 1443 |
-
"eval_steps_per_second": 1.099,
|
| 1444 |
-
"step": 425
|
| 1445 |
-
},
|
| 1446 |
-
{
|
| 1447 |
-
"epoch": 0.636094674556213,
|
| 1448 |
-
"grad_norm": 0.6981207777177686,
|
| 1449 |
-
"learning_rate": 1.9426443142839447e-05,
|
| 1450 |
-
"loss": 0.8429,
|
| 1451 |
-
"step": 430
|
| 1452 |
-
},
|
| 1453 |
-
{
|
| 1454 |
-
"epoch": 0.636094674556213,
|
| 1455 |
-
"eval_loss": 0.8708469271659851,
|
| 1456 |
-
"eval_runtime": 4.5282,
|
| 1457 |
-
"eval_samples_per_second": 118.148,
|
| 1458 |
-
"eval_steps_per_second": 1.104,
|
| 1459 |
-
"step": 430
|
| 1460 |
-
},
|
| 1461 |
-
{
|
| 1462 |
-
"epoch": 0.643491124260355,
|
| 1463 |
-
"grad_norm": 0.652634344146103,
|
| 1464 |
-
"learning_rate": 1.891505958088977e-05,
|
| 1465 |
-
"loss": 0.8405,
|
| 1466 |
-
"step": 435
|
| 1467 |
-
},
|
| 1468 |
-
{
|
| 1469 |
-
"epoch": 0.643491124260355,
|
| 1470 |
-
"eval_loss": 0.8699945211410522,
|
| 1471 |
-
"eval_runtime": 4.5588,
|
| 1472 |
-
"eval_samples_per_second": 117.354,
|
| 1473 |
-
"eval_steps_per_second": 1.097,
|
| 1474 |
-
"step": 435
|
| 1475 |
-
},
|
| 1476 |
-
{
|
| 1477 |
-
"epoch": 0.650887573964497,
|
| 1478 |
-
"grad_norm": 0.6201611689922387,
|
| 1479 |
-
"learning_rate": 1.8408815098220043e-05,
|
| 1480 |
-
"loss": 0.8566,
|
| 1481 |
-
"step": 440
|
| 1482 |
-
},
|
| 1483 |
-
{
|
| 1484 |
-
"epoch": 0.650887573964497,
|
| 1485 |
-
"eval_loss": 0.8690354228019714,
|
| 1486 |
-
"eval_runtime": 4.5688,
|
| 1487 |
-
"eval_samples_per_second": 117.098,
|
| 1488 |
-
"eval_steps_per_second": 1.094,
|
| 1489 |
-
"step": 440
|
| 1490 |
-
},
|
| 1491 |
-
{
|
| 1492 |
-
"epoch": 0.658284023668639,
|
| 1493 |
-
"grad_norm": 0.6371435519919459,
|
| 1494 |
-
"learning_rate": 1.7908012740676195e-05,
|
| 1495 |
-
"loss": 0.8412,
|
| 1496 |
-
"step": 445
|
| 1497 |
-
},
|
| 1498 |
-
{
|
| 1499 |
-
"epoch": 0.658284023668639,
|
| 1500 |
-
"eval_loss": 0.8690587282180786,
|
| 1501 |
-
"eval_runtime": 4.5404,
|
| 1502 |
-
"eval_samples_per_second": 117.832,
|
| 1503 |
-
"eval_steps_per_second": 1.101,
|
| 1504 |
-
"step": 445
|
| 1505 |
-
},
|
| 1506 |
-
{
|
| 1507 |
-
"epoch": 0.665680473372781,
|
| 1508 |
-
"grad_norm": 0.6528979398382087,
|
| 1509 |
-
"learning_rate": 1.7412952296363133e-05,
|
| 1510 |
-
"loss": 0.8395,
|
| 1511 |
-
"step": 450
|
| 1512 |
-
},
|
| 1513 |
-
{
|
| 1514 |
-
"epoch": 0.665680473372781,
|
| 1515 |
-
"eval_loss": 0.8680040240287781,
|
| 1516 |
-
"eval_runtime": 4.4831,
|
| 1517 |
-
"eval_samples_per_second": 119.337,
|
| 1518 |
-
"eval_steps_per_second": 1.115,
|
| 1519 |
-
"step": 450
|
| 1520 |
-
},
|
| 1521 |
-
{
|
| 1522 |
-
"epoch": 0.6730769230769231,
|
| 1523 |
-
"grad_norm": 0.7567869297925619,
|
| 1524 |
-
"learning_rate": 1.6923930116186907e-05,
|
| 1525 |
-
"loss": 0.8481,
|
| 1526 |
-
"step": 455
|
| 1527 |
-
},
|
| 1528 |
-
{
|
| 1529 |
-
"epoch": 0.6730769230769231,
|
| 1530 |
-
"eval_loss": 0.867551863193512,
|
| 1531 |
-
"eval_runtime": 4.4437,
|
| 1532 |
-
"eval_samples_per_second": 120.395,
|
| 1533 |
-
"eval_steps_per_second": 1.125,
|
| 1534 |
-
"step": 455
|
| 1535 |
-
},
|
| 1536 |
-
{
|
| 1537 |
-
"epoch": 0.6804733727810651,
|
| 1538 |
-
"grad_norm": 0.6773475295723909,
|
| 1539 |
-
"learning_rate": 1.644123893645448e-05,
|
| 1540 |
-
"loss": 0.8605,
|
| 1541 |
-
"step": 460
|
| 1542 |
-
},
|
| 1543 |
-
{
|
| 1544 |
-
"epoch": 0.6804733727810651,
|
| 1545 |
-
"eval_loss": 0.8671652674674988,
|
| 1546 |
-
"eval_runtime": 4.5312,
|
| 1547 |
-
"eval_samples_per_second": 118.069,
|
| 1548 |
-
"eval_steps_per_second": 1.103,
|
| 1549 |
-
"step": 460
|
| 1550 |
-
},
|
| 1551 |
-
{
|
| 1552 |
-
"epoch": 0.6878698224852071,
|
| 1553 |
-
"grad_norm": 0.7010338732044618,
|
| 1554 |
-
"learning_rate": 1.5965167703637124e-05,
|
| 1555 |
-
"loss": 0.8395,
|
| 1556 |
-
"step": 465
|
| 1557 |
-
},
|
| 1558 |
-
{
|
| 1559 |
-
"epoch": 0.6878698224852071,
|
| 1560 |
-
"eval_loss": 0.8658307790756226,
|
| 1561 |
-
"eval_runtime": 4.586,
|
| 1562 |
-
"eval_samples_per_second": 116.659,
|
| 1563 |
-
"eval_steps_per_second": 1.09,
|
| 1564 |
-
"step": 465
|
| 1565 |
-
},
|
| 1566 |
-
{
|
| 1567 |
-
"epoch": 0.6952662721893491,
|
| 1568 |
-
"grad_norm": 0.6702003501907882,
|
| 1569 |
-
"learning_rate": 1.5496001401402644e-05,
|
| 1570 |
-
"loss": 0.8418,
|
| 1571 |
-
"step": 470
|
| 1572 |
-
},
|
| 1573 |
-
{
|
| 1574 |
-
"epoch": 0.6952662721893491,
|
| 1575 |
-
"eval_loss": 0.8654137253761292,
|
| 1576 |
-
"eval_runtime": 4.4934,
|
| 1577 |
-
"eval_samples_per_second": 119.062,
|
| 1578 |
-
"eval_steps_per_second": 1.113,
|
| 1579 |
-
"step": 470
|
| 1580 |
-
},
|
| 1581 |
-
{
|
| 1582 |
-
"epoch": 0.7026627218934911,
|
| 1583 |
-
"grad_norm": 0.6408882433617089,
|
| 1584 |
-
"learning_rate": 1.5034020880019619e-05,
|
| 1585 |
-
"loss": 0.8528,
|
| 1586 |
-
"step": 475
|
| 1587 |
-
},
|
| 1588 |
-
{
|
| 1589 |
-
"epoch": 0.7026627218934911,
|
| 1590 |
-
"eval_loss": 0.8655184507369995,
|
| 1591 |
-
"eval_runtime": 4.427,
|
| 1592 |
-
"eval_samples_per_second": 120.85,
|
| 1593 |
-
"eval_steps_per_second": 1.129,
|
| 1594 |
-
"step": 475
|
| 1595 |
-
},
|
| 1596 |
-
{
|
| 1597 |
-
"epoch": 0.7100591715976331,
|
| 1598 |
-
"grad_norm": 0.6451588589935744,
|
| 1599 |
-
"learning_rate": 1.4579502688236146e-05,
|
| 1600 |
-
"loss": 0.856,
|
| 1601 |
-
"step": 480
|
| 1602 |
-
},
|
| 1603 |
-
{
|
| 1604 |
-
"epoch": 0.7100591715976331,
|
| 1605 |
-
"eval_loss": 0.8649392127990723,
|
| 1606 |
-
"eval_runtime": 4.5976,
|
| 1607 |
-
"eval_samples_per_second": 116.366,
|
| 1608 |
-
"eval_steps_per_second": 1.088,
|
| 1609 |
-
"step": 480
|
| 1610 |
-
},
|
| 1611 |
-
{
|
| 1612 |
-
"epoch": 0.7174556213017751,
|
| 1613 |
-
"grad_norm": 0.6270246011748759,
|
| 1614 |
-
"learning_rate": 1.4132718907733361e-05,
|
| 1615 |
-
"loss": 0.8361,
|
| 1616 |
-
"step": 485
|
| 1617 |
-
},
|
| 1618 |
-
{
|
| 1619 |
-
"epoch": 0.7174556213017751,
|
| 1620 |
-
"eval_loss": 0.864596962928772,
|
| 1621 |
-
"eval_runtime": 4.5791,
|
| 1622 |
-
"eval_samples_per_second": 116.835,
|
| 1623 |
-
"eval_steps_per_second": 1.092,
|
| 1624 |
-
"step": 485
|
| 1625 |
-
},
|
| 1626 |
-
{
|
| 1627 |
-
"epoch": 0.7248520710059172,
|
| 1628 |
-
"grad_norm": 0.7162779140578355,
|
| 1629 |
-
"learning_rate": 1.3693936990253142e-05,
|
| 1630 |
-
"loss": 0.8391,
|
| 1631 |
-
"step": 490
|
| 1632 |
-
},
|
| 1633 |
-
{
|
| 1634 |
-
"epoch": 0.7248520710059172,
|
| 1635 |
-
"eval_loss": 0.8636202216148376,
|
| 1636 |
-
"eval_runtime": 4.8532,
|
| 1637 |
-
"eval_samples_per_second": 110.238,
|
| 1638 |
-
"eval_steps_per_second": 1.03,
|
| 1639 |
-
"step": 490
|
| 1640 |
-
},
|
| 1641 |
-
{
|
| 1642 |
-
"epoch": 0.7322485207100592,
|
| 1643 |
-
"grad_norm": 0.6264415975109302,
|
| 1644 |
-
"learning_rate": 1.326341959749731e-05,
|
| 1645 |
-
"loss": 0.8402,
|
| 1646 |
-
"step": 495
|
| 1647 |
-
},
|
| 1648 |
-
{
|
| 1649 |
-
"epoch": 0.7322485207100592,
|
| 1650 |
-
"eval_loss": 0.8627746105194092,
|
| 1651 |
-
"eval_runtime": 4.5577,
|
| 1652 |
-
"eval_samples_per_second": 117.385,
|
| 1653 |
-
"eval_steps_per_second": 1.097,
|
| 1654 |
-
"step": 495
|
| 1655 |
-
},
|
| 1656 |
-
{
|
| 1657 |
-
"epoch": 0.7396449704142012,
|
| 1658 |
-
"grad_norm": 0.5999441934467236,
|
| 1659 |
-
"learning_rate": 1.2841424443894246e-05,
|
| 1660 |
-
"loss": 0.8356,
|
| 1661 |
-
"step": 500
|
| 1662 |
-
},
|
| 1663 |
-
{
|
| 1664 |
-
"epoch": 0.7396449704142012,
|
| 1665 |
-
"eval_loss": 0.8623146414756775,
|
| 1666 |
-
"eval_runtime": 4.5802,
|
| 1667 |
-
"eval_samples_per_second": 116.807,
|
| 1668 |
-
"eval_steps_per_second": 1.092,
|
| 1669 |
-
"step": 500
|
| 1670 |
-
},
|
| 1671 |
-
{
|
| 1672 |
-
"epoch": 0.7470414201183432,
|
| 1673 |
-
"grad_norm": 0.6129410145276629,
|
| 1674 |
-
"learning_rate": 1.2428204142327e-05,
|
| 1675 |
-
"loss": 0.8462,
|
| 1676 |
-
"step": 505
|
| 1677 |
-
},
|
| 1678 |
-
{
|
| 1679 |
-
"epoch": 0.7470414201183432,
|
| 1680 |
-
"eval_loss": 0.86202472448349,
|
| 1681 |
-
"eval_runtime": 4.5046,
|
| 1682 |
-
"eval_samples_per_second": 118.766,
|
| 1683 |
-
"eval_steps_per_second": 1.11,
|
| 1684 |
-
"step": 505
|
| 1685 |
-
},
|
| 1686 |
-
{
|
| 1687 |
-
"epoch": 0.7544378698224852,
|
| 1688 |
-
"grad_norm": 0.8356836512352364,
|
| 1689 |
-
"learning_rate": 1.2024006052915295e-05,
|
| 1690 |
-
"loss": 0.8276,
|
| 1691 |
-
"step": 510
|
| 1692 |
-
},
|
| 1693 |
-
{
|
| 1694 |
-
"epoch": 0.7544378698224852,
|
| 1695 |
-
"eval_loss": 0.8616589903831482,
|
| 1696 |
-
"eval_runtime": 4.5743,
|
| 1697 |
-
"eval_samples_per_second": 116.957,
|
| 1698 |
-
"eval_steps_per_second": 1.093,
|
| 1699 |
-
"step": 510
|
| 1700 |
-
},
|
| 1701 |
-
{
|
| 1702 |
-
"epoch": 0.7618343195266272,
|
| 1703 |
-
"grad_norm": 0.5779272740478268,
|
| 1704 |
-
"learning_rate": 1.1629072134941883e-05,
|
| 1705 |
-
"loss": 0.8478,
|
| 1706 |
-
"step": 515
|
| 1707 |
-
},
|
| 1708 |
-
{
|
| 1709 |
-
"epoch": 0.7618343195266272,
|
| 1710 |
-
"eval_loss": 0.8606404066085815,
|
| 1711 |
-
"eval_runtime": 4.6303,
|
| 1712 |
-
"eval_samples_per_second": 115.544,
|
| 1713 |
-
"eval_steps_per_second": 1.08,
|
| 1714 |
-
"step": 515
|
| 1715 |
-
},
|
| 1716 |
-
{
|
| 1717 |
-
"epoch": 0.7692307692307693,
|
| 1718 |
-
"grad_norm": 0.6069493343307135,
|
| 1719 |
-
"learning_rate": 1.1243638802011954e-05,
|
| 1720 |
-
"loss": 0.8438,
|
| 1721 |
-
"step": 520
|
| 1722 |
-
},
|
| 1723 |
-
{
|
| 1724 |
-
"epoch": 0.7692307692307693,
|
| 1725 |
-
"eval_loss": 0.8605805039405823,
|
| 1726 |
-
"eval_runtime": 4.5932,
|
| 1727 |
-
"eval_samples_per_second": 116.477,
|
| 1728 |
-
"eval_steps_per_second": 1.089,
|
| 1729 |
-
"step": 520
|
| 1730 |
-
},
|
| 1731 |
-
{
|
| 1732 |
-
"epoch": 0.7766272189349113,
|
| 1733 |
-
"grad_norm": 0.6125533080147663,
|
| 1734 |
-
"learning_rate": 1.0867936780532248e-05,
|
| 1735 |
-
"loss": 0.8439,
|
| 1736 |
-
"step": 525
|
| 1737 |
-
},
|
| 1738 |
-
{
|
| 1739 |
-
"epoch": 0.7766272189349113,
|
| 1740 |
-
"eval_loss": 0.8604384064674377,
|
| 1741 |
-
"eval_runtime": 4.6021,
|
| 1742 |
-
"eval_samples_per_second": 116.25,
|
| 1743 |
-
"eval_steps_per_second": 1.086,
|
| 1744 |
-
"step": 525
|
| 1745 |
-
},
|
| 1746 |
-
{
|
| 1747 |
-
"epoch": 0.7840236686390533,
|
| 1748 |
-
"grad_norm": 0.6452403926195849,
|
| 1749 |
-
"learning_rate": 1.0502190971594672e-05,
|
| 1750 |
-
"loss": 0.8424,
|
| 1751 |
-
"step": 530
|
| 1752 |
-
},
|
| 1753 |
-
{
|
| 1754 |
-
"epoch": 0.7840236686390533,
|
| 1755 |
-
"eval_loss": 0.859944760799408,
|
| 1756 |
-
"eval_runtime": 4.5374,
|
| 1757 |
-
"eval_samples_per_second": 117.91,
|
| 1758 |
-
"eval_steps_per_second": 1.102,
|
| 1759 |
-
"step": 530
|
| 1760 |
-
},
|
| 1761 |
-
{
|
| 1762 |
-
"epoch": 0.7914201183431953,
|
| 1763 |
-
"grad_norm": 0.5745825978672692,
|
| 1764 |
-
"learning_rate": 1.014662031634692e-05,
|
| 1765 |
-
"loss": 0.8235,
|
| 1766 |
-
"step": 535
|
| 1767 |
-
},
|
| 1768 |
-
{
|
| 1769 |
-
"epoch": 0.7914201183431953,
|
| 1770 |
-
"eval_loss": 0.8596252202987671,
|
| 1771 |
-
"eval_runtime": 4.4046,
|
| 1772 |
-
"eval_samples_per_second": 121.465,
|
| 1773 |
-
"eval_steps_per_second": 1.135,
|
| 1774 |
-
"step": 535
|
| 1775 |
-
},
|
| 1776 |
-
{
|
| 1777 |
-
"epoch": 0.7988165680473372,
|
| 1778 |
-
"grad_norm": 0.5837129035152734,
|
| 1779 |
-
"learning_rate": 9.80143766493097e-06,
|
| 1780 |
-
"loss": 0.8289,
|
| 1781 |
-
"step": 540
|
| 1782 |
-
},
|
| 1783 |
-
{
|
| 1784 |
-
"epoch": 0.7988165680473372,
|
| 1785 |
-
"eval_loss": 0.8592759966850281,
|
| 1786 |
-
"eval_runtime": 4.5322,
|
| 1787 |
-
"eval_samples_per_second": 118.044,
|
| 1788 |
-
"eval_steps_per_second": 1.103,
|
| 1789 |
-
"step": 540
|
| 1790 |
-
},
|
| 1791 |
-
{
|
| 1792 |
-
"epoch": 0.8062130177514792,
|
| 1793 |
-
"grad_norm": 0.5813377576331795,
|
| 1794 |
-
"learning_rate": 9.466849649067596e-06,
|
| 1795 |
-
"loss": 0.83,
|
| 1796 |
-
"step": 545
|
| 1797 |
-
},
|
| 1798 |
-
{
|
| 1799 |
-
"epoch": 0.8062130177514792,
|
| 1800 |
-
"eval_loss": 0.8585328459739685,
|
| 1801 |
-
"eval_runtime": 4.5627,
|
| 1802 |
-
"eval_samples_per_second": 117.254,
|
| 1803 |
-
"eval_steps_per_second": 1.096,
|
| 1804 |
-
"step": 545
|
| 1805 |
-
},
|
| 1806 |
-
{
|
| 1807 |
-
"epoch": 0.8136094674556213,
|
| 1808 |
-
"grad_norm": 0.6039721338817958,
|
| 1809 |
-
"learning_rate": 9.143056558363463e-06,
|
| 1810 |
-
"loss": 0.8363,
|
| 1811 |
-
"step": 550
|
| 1812 |
-
},
|
| 1813 |
-
{
|
| 1814 |
-
"epoch": 0.8136094674556213,
|
| 1815 |
-
"eval_loss": 0.8581274747848511,
|
| 1816 |
-
"eval_runtime": 4.6357,
|
| 1817 |
-
"eval_samples_per_second": 115.408,
|
| 1818 |
-
"eval_steps_per_second": 1.079,
|
| 1819 |
-
"step": 550
|
| 1820 |
-
},
|
| 1821 |
-
{
|
| 1822 |
-
"epoch": 0.8210059171597633,
|
| 1823 |
-
"grad_norm": 0.5888712234714697,
|
| 1824 |
-
"learning_rate": 8.83025222041459e-06,
|
| 1825 |
-
"loss": 0.8403,
|
| 1826 |
-
"step": 555
|
| 1827 |
-
},
|
| 1828 |
-
{
|
| 1829 |
-
"epoch": 0.8210059171597633,
|
| 1830 |
-
"eval_loss": 0.8580217361450195,
|
| 1831 |
-
"eval_runtime": 4.5942,
|
| 1832 |
-
"eval_samples_per_second": 116.45,
|
| 1833 |
-
"eval_steps_per_second": 1.088,
|
| 1834 |
-
"step": 555
|
| 1835 |
-
},
|
| 1836 |
-
{
|
| 1837 |
-
"epoch": 0.8284023668639053,
|
| 1838 |
-
"grad_norm": 0.6337569313224579,
|
| 1839 |
-
"learning_rate": 8.528623884778144e-06,
|
| 1840 |
-
"loss": 0.8517,
|
| 1841 |
-
"step": 560
|
| 1842 |
-
},
|
| 1843 |
-
{
|
| 1844 |
-
"epoch": 0.8284023668639053,
|
| 1845 |
-
"eval_loss": 0.8578224182128906,
|
| 1846 |
-
"eval_runtime": 4.9197,
|
| 1847 |
-
"eval_samples_per_second": 108.747,
|
| 1848 |
-
"eval_steps_per_second": 1.016,
|
| 1849 |
-
"step": 560
|
| 1850 |
-
},
|
| 1851 |
-
{
|
| 1852 |
-
"epoch": 0.8357988165680473,
|
| 1853 |
-
"grad_norm": 0.5656560440585017,
|
| 1854 |
-
"learning_rate": 8.238352110881945e-06,
|
| 1855 |
-
"loss": 0.8286,
|
| 1856 |
-
"step": 565
|
| 1857 |
-
},
|
| 1858 |
-
{
|
| 1859 |
-
"epoch": 0.8357988165680473,
|
| 1860 |
-
"eval_loss": 0.857262372970581,
|
| 1861 |
-
"eval_runtime": 4.4021,
|
| 1862 |
-
"eval_samples_per_second": 121.533,
|
| 1863 |
-
"eval_steps_per_second": 1.136,
|
| 1864 |
-
"step": 565
|
| 1865 |
-
},
|
| 1866 |
-
{
|
| 1867 |
-
"epoch": 0.8431952662721893,
|
| 1868 |
-
"grad_norm": 0.6428278413031142,
|
| 1869 |
-
"learning_rate": 7.959610659938765e-06,
|
| 1870 |
-
"loss": 0.8341,
|
| 1871 |
-
"step": 570
|
| 1872 |
-
},
|
| 1873 |
-
{
|
| 1874 |
-
"epoch": 0.8431952662721893,
|
| 1875 |
-
"eval_loss": 0.8569393157958984,
|
| 1876 |
-
"eval_runtime": 4.5023,
|
| 1877 |
-
"eval_samples_per_second": 118.829,
|
| 1878 |
-
"eval_steps_per_second": 1.111,
|
| 1879 |
-
"step": 570
|
| 1880 |
-
},
|
| 1881 |
-
{
|
| 1882 |
-
"epoch": 0.8505917159763313,
|
| 1883 |
-
"grad_norm": 0.5744234711786275,
|
| 1884 |
-
"learning_rate": 7.69256639093015e-06,
|
| 1885 |
-
"loss": 0.8262,
|
| 1886 |
-
"step": 575
|
| 1887 |
-
},
|
| 1888 |
-
{
|
| 1889 |
-
"epoch": 0.8505917159763313,
|
| 1890 |
-
"eval_loss": 0.8566195368766785,
|
| 1891 |
-
"eval_runtime": 4.558,
|
| 1892 |
-
"eval_samples_per_second": 117.375,
|
| 1893 |
-
"eval_steps_per_second": 1.097,
|
| 1894 |
-
"step": 575
|
| 1895 |
-
},
|
| 1896 |
-
{
|
| 1897 |
-
"epoch": 0.8579881656804734,
|
| 1898 |
-
"grad_norm": 0.578200912437047,
|
| 1899 |
-
"learning_rate": 7.4373791607220455e-06,
|
| 1900 |
-
"loss": 0.8351,
|
| 1901 |
-
"step": 580
|
| 1902 |
-
},
|
| 1903 |
-
{
|
| 1904 |
-
"epoch": 0.8579881656804734,
|
| 1905 |
-
"eval_loss": 0.8565072417259216,
|
| 1906 |
-
"eval_runtime": 4.5104,
|
| 1907 |
-
"eval_samples_per_second": 118.615,
|
| 1908 |
-
"eval_steps_per_second": 1.109,
|
| 1909 |
-
"step": 580
|
| 1910 |
-
},
|
| 1911 |
-
{
|
| 1912 |
-
"epoch": 0.8653846153846154,
|
| 1913 |
-
"grad_norm": 0.5778075441668177,
|
| 1914 |
-
"learning_rate": 7.194201728371964e-06,
|
| 1915 |
-
"loss": 0.8329,
|
| 1916 |
-
"step": 585
|
| 1917 |
-
},
|
| 1918 |
-
{
|
| 1919 |
-
"epoch": 0.8653846153846154,
|
| 1920 |
-
"eval_loss": 0.8561302423477173,
|
| 1921 |
-
"eval_runtime": 4.5476,
|
| 1922 |
-
"eval_samples_per_second": 117.646,
|
| 1923 |
-
"eval_steps_per_second": 1.099,
|
| 1924 |
-
"step": 585
|
| 1925 |
-
},
|
| 1926 |
-
{
|
| 1927 |
-
"epoch": 0.8727810650887574,
|
| 1928 |
-
"grad_norm": 0.5935938929493908,
|
| 1929 |
-
"learning_rate": 6.96317966368506e-06,
|
| 1930 |
-
"loss": 0.841,
|
| 1931 |
-
"step": 590
|
| 1932 |
-
},
|
| 1933 |
-
{
|
| 1934 |
-
"epoch": 0.8727810650887574,
|
| 1935 |
-
"eval_loss": 0.8557109832763672,
|
| 1936 |
-
"eval_runtime": 4.567,
|
| 1937 |
-
"eval_samples_per_second": 117.145,
|
| 1938 |
-
"eval_steps_per_second": 1.095,
|
| 1939 |
-
"step": 590
|
| 1940 |
-
},
|
| 1941 |
-
{
|
| 1942 |
-
"epoch": 0.8801775147928994,
|
| 1943 |
-
"grad_norm": 0.6038472885423796,
|
| 1944 |
-
"learning_rate": 6.744451260073718e-06,
|
| 1945 |
-
"loss": 0.8286,
|
| 1946 |
-
"step": 595
|
| 1947 |
-
},
|
| 1948 |
-
{
|
| 1949 |
-
"epoch": 0.8801775147928994,
|
| 1950 |
-
"eval_loss": 0.8555126786231995,
|
| 1951 |
-
"eval_runtime": 4.5524,
|
| 1952 |
-
"eval_samples_per_second": 117.519,
|
| 1953 |
-
"eval_steps_per_second": 1.098,
|
| 1954 |
-
"step": 595
|
| 1955 |
-
},
|
| 1956 |
-
{
|
| 1957 |
-
"epoch": 0.8875739644970414,
|
| 1958 |
-
"grad_norm": 0.5943088695918576,
|
| 1959 |
-
"learning_rate": 6.538147451773029e-06,
|
| 1960 |
-
"loss": 0.835,
|
| 1961 |
-
"step": 600
|
| 1962 |
-
},
|
| 1963 |
-
{
|
| 1964 |
-
"epoch": 0.8875739644970414,
|
| 1965 |
-
"eval_loss": 0.8550283312797546,
|
| 1966 |
-
"eval_runtime": 4.4943,
|
| 1967 |
-
"eval_samples_per_second": 119.039,
|
| 1968 |
-
"eval_steps_per_second": 1.113,
|
| 1969 |
-
"step": 600
|
| 1970 |
-
},
|
| 1971 |
-
{
|
| 1972 |
-
"epoch": 0.8949704142011834,
|
| 1973 |
-
"grad_norm": 0.6151479841904817,
|
| 1974 |
-
"learning_rate": 6.3443917354614466e-06,
|
| 1975 |
-
"loss": 0.8313,
|
| 1976 |
-
"step": 605
|
| 1977 |
-
},
|
| 1978 |
-
{
|
| 1979 |
-
"epoch": 0.8949704142011834,
|
| 1980 |
-
"eval_loss": 0.8547914028167725,
|
| 1981 |
-
"eval_runtime": 4.5869,
|
| 1982 |
-
"eval_samples_per_second": 116.638,
|
| 1983 |
-
"eval_steps_per_second": 1.09,
|
| 1984 |
-
"step": 605
|
| 1985 |
-
},
|
| 1986 |
-
{
|
| 1987 |
-
"epoch": 0.9023668639053254,
|
| 1988 |
-
"grad_norm": 0.5914893004098631,
|
| 1989 |
-
"learning_rate": 6.163300096333806e-06,
|
| 1990 |
-
"loss": 0.8276,
|
| 1991 |
-
"step": 610
|
| 1992 |
-
},
|
| 1993 |
-
{
|
| 1994 |
-
"epoch": 0.9023668639053254,
|
| 1995 |
-
"eval_loss": 0.8543236255645752,
|
| 1996 |
-
"eval_runtime": 4.5789,
|
| 1997 |
-
"eval_samples_per_second": 116.84,
|
| 1998 |
-
"eval_steps_per_second": 1.092,
|
| 1999 |
-
"step": 610
|
| 2000 |
-
},
|
| 2001 |
-
{
|
| 2002 |
-
"epoch": 0.9097633136094675,
|
| 2003 |
-
"grad_norm": 0.5915554024359355,
|
| 2004 |
-
"learning_rate": 5.9949809386707394e-06,
|
| 2005 |
-
"loss": 0.8252,
|
| 2006 |
-
"step": 615
|
| 2007 |
-
},
|
| 2008 |
-
{
|
| 2009 |
-
"epoch": 0.9097633136094675,
|
| 2010 |
-
"eval_loss": 0.8538296818733215,
|
| 2011 |
-
"eval_runtime": 4.7415,
|
| 2012 |
-
"eval_samples_per_second": 112.832,
|
| 2013 |
-
"eval_steps_per_second": 1.055,
|
| 2014 |
-
"step": 615
|
| 2015 |
-
},
|
| 2016 |
-
{
|
| 2017 |
-
"epoch": 0.9171597633136095,
|
| 2018 |
-
"grad_norm": 0.5682950068319568,
|
| 2019 |
-
"learning_rate": 5.839535020946193e-06,
|
| 2020 |
-
"loss": 0.8177,
|
| 2021 |
-
"step": 620
|
| 2022 |
-
},
|
| 2023 |
-
{
|
| 2024 |
-
"epoch": 0.9171597633136095,
|
| 2025 |
-
"eval_loss": 0.8535985946655273,
|
| 2026 |
-
"eval_runtime": 4.5719,
|
| 2027 |
-
"eval_samples_per_second": 117.02,
|
| 2028 |
-
"eval_steps_per_second": 1.094,
|
| 2029 |
-
"step": 620
|
| 2030 |
-
},
|
| 2031 |
-
{
|
| 2032 |
-
"epoch": 0.9245562130177515,
|
| 2033 |
-
"grad_norm": 0.5863960670439361,
|
| 2034 |
-
"learning_rate": 5.697055395511836e-06,
|
| 2035 |
-
"loss": 0.8342,
|
| 2036 |
-
"step": 625
|
| 2037 |
-
},
|
| 2038 |
-
{
|
| 2039 |
-
"epoch": 0.9245562130177515,
|
| 2040 |
-
"eval_loss": 0.8532615303993225,
|
| 2041 |
-
"eval_runtime": 4.5376,
|
| 2042 |
-
"eval_samples_per_second": 117.903,
|
| 2043 |
-
"eval_steps_per_second": 1.102,
|
| 2044 |
-
"step": 625
|
| 2045 |
-
},
|
| 2046 |
-
{
|
| 2047 |
-
"epoch": 0.9319526627218935,
|
| 2048 |
-
"grad_norm": 0.5531562271776167,
|
| 2049 |
-
"learning_rate": 5.567627352894467e-06,
|
| 2050 |
-
"loss": 0.8402,
|
| 2051 |
-
"step": 630
|
| 2052 |
-
},
|
| 2053 |
-
{
|
| 2054 |
-
"epoch": 0.9319526627218935,
|
| 2055 |
-
"eval_loss": 0.8529289960861206,
|
| 2056 |
-
"eval_runtime": 4.5667,
|
| 2057 |
-
"eval_samples_per_second": 117.152,
|
| 2058 |
-
"eval_steps_per_second": 1.095,
|
| 2059 |
-
"step": 630
|
| 2060 |
-
},
|
| 2061 |
-
{
|
| 2062 |
-
"epoch": 0.9393491124260355,
|
| 2063 |
-
"grad_norm": 0.595496303433799,
|
| 2064 |
-
"learning_rate": 5.451328370739774e-06,
|
| 2065 |
-
"loss": 0.8233,
|
| 2066 |
-
"step": 635
|
| 2067 |
-
},
|
| 2068 |
-
{
|
| 2069 |
-
"epoch": 0.9393491124260355,
|
| 2070 |
-
"eval_loss": 0.8527988195419312,
|
| 2071 |
-
"eval_runtime": 4.6311,
|
| 2072 |
-
"eval_samples_per_second": 115.523,
|
| 2073 |
-
"eval_steps_per_second": 1.08,
|
| 2074 |
-
"step": 635
|
| 2075 |
-
},
|
| 2076 |
-
{
|
| 2077 |
-
"epoch": 0.9467455621301775,
|
| 2078 |
-
"grad_norm": 0.62602812517354,
|
| 2079 |
-
"learning_rate": 5.3482280674330136e-06,
|
| 2080 |
-
"loss": 0.8183,
|
| 2081 |
-
"step": 640
|
| 2082 |
-
},
|
| 2083 |
-
{
|
| 2084 |
-
"epoch": 0.9467455621301775,
|
| 2085 |
-
"eval_loss": 0.852441668510437,
|
| 2086 |
-
"eval_runtime": 4.5774,
|
| 2087 |
-
"eval_samples_per_second": 116.877,
|
| 2088 |
-
"eval_steps_per_second": 1.092,
|
| 2089 |
-
"step": 640
|
| 2090 |
-
},
|
| 2091 |
-
{
|
| 2092 |
-
"epoch": 0.9541420118343196,
|
| 2093 |
-
"grad_norm": 0.5716364859992062,
|
| 2094 |
-
"learning_rate": 5.25838816042435e-06,
|
| 2095 |
-
"loss": 0.822,
|
| 2096 |
-
"step": 645
|
| 2097 |
-
},
|
| 2098 |
-
{
|
| 2099 |
-
"epoch": 0.9541420118343196,
|
| 2100 |
-
"eval_loss": 0.8520421385765076,
|
| 2101 |
-
"eval_runtime": 4.5908,
|
| 2102 |
-
"eval_samples_per_second": 116.537,
|
| 2103 |
-
"eval_steps_per_second": 1.089,
|
| 2104 |
-
"step": 645
|
| 2105 |
-
},
|
| 2106 |
-
{
|
| 2107 |
-
"epoch": 0.9615384615384616,
|
| 2108 |
-
"grad_norm": 0.5973178018451643,
|
| 2109 |
-
"learning_rate": 5.1818624292838275e-06,
|
| 2110 |
-
"loss": 0.8326,
|
| 2111 |
-
"step": 650
|
| 2112 |
-
},
|
| 2113 |
-
{
|
| 2114 |
-
"epoch": 0.9615384615384616,
|
| 2115 |
-
"eval_loss": 0.8517911434173584,
|
| 2116 |
-
"eval_runtime": 4.5169,
|
| 2117 |
-
"eval_samples_per_second": 118.444,
|
| 2118 |
-
"eval_steps_per_second": 1.107,
|
| 2119 |
-
"step": 650
|
| 2120 |
-
},
|
| 2121 |
-
{
|
| 2122 |
-
"epoch": 0.9689349112426036,
|
| 2123 |
-
"grad_norm": 0.5848676320077507,
|
| 2124 |
-
"learning_rate": 5.118696683508087e-06,
|
| 2125 |
-
"loss": 0.8224,
|
| 2126 |
-
"step": 655
|
| 2127 |
-
},
|
| 2128 |
-
{
|
| 2129 |
-
"epoch": 0.9689349112426036,
|
| 2130 |
-
"eval_loss": 0.8514999151229858,
|
| 2131 |
-
"eval_runtime": 4.6466,
|
| 2132 |
-
"eval_samples_per_second": 115.137,
|
| 2133 |
-
"eval_steps_per_second": 1.076,
|
| 2134 |
-
"step": 655
|
| 2135 |
-
},
|
| 2136 |
-
{
|
| 2137 |
-
"epoch": 0.9763313609467456,
|
| 2138 |
-
"grad_norm": 0.584823125278116,
|
| 2139 |
-
"learning_rate": 5.0689287350980886e-06,
|
| 2140 |
-
"loss": 0.823,
|
| 2141 |
-
"step": 660
|
| 2142 |
-
},
|
| 2143 |
-
{
|
| 2144 |
-
"epoch": 0.9763313609467456,
|
| 2145 |
-
"eval_loss": 0.8514819741249084,
|
| 2146 |
-
"eval_runtime": 4.4836,
|
| 2147 |
-
"eval_samples_per_second": 119.325,
|
| 2148 |
-
"eval_steps_per_second": 1.115,
|
| 2149 |
-
"step": 660
|
| 2150 |
-
},
|
| 2151 |
-
{
|
| 2152 |
-
"epoch": 0.9837278106508875,
|
| 2153 |
-
"grad_norm": 0.5887341532281551,
|
| 2154 |
-
"learning_rate": 5.03258837592424e-06,
|
| 2155 |
-
"loss": 0.8366,
|
| 2156 |
-
"step": 665
|
| 2157 |
-
},
|
| 2158 |
-
{
|
| 2159 |
-
"epoch": 0.9837278106508875,
|
| 2160 |
-
"eval_loss": 0.8512169718742371,
|
| 2161 |
-
"eval_runtime": 4.4841,
|
| 2162 |
-
"eval_samples_per_second": 119.311,
|
| 2163 |
-
"eval_steps_per_second": 1.115,
|
| 2164 |
-
"step": 665
|
| 2165 |
-
},
|
| 2166 |
-
{
|
| 2167 |
-
"epoch": 0.9911242603550295,
|
| 2168 |
-
"grad_norm": 0.6312074358327011,
|
| 2169 |
-
"learning_rate": 5.009697359892536e-06,
|
| 2170 |
-
"loss": 0.82,
|
| 2171 |
-
"step": 670
|
| 2172 |
-
},
|
| 2173 |
-
{
|
| 2174 |
-
"epoch": 0.9911242603550295,
|
| 2175 |
-
"eval_loss": 0.8510258197784424,
|
| 2176 |
-
"eval_runtime": 4.5807,
|
| 2177 |
-
"eval_samples_per_second": 116.794,
|
| 2178 |
-
"eval_steps_per_second": 1.092,
|
| 2179 |
-
"step": 670
|
| 2180 |
-
},
|
| 2181 |
-
{
|
| 2182 |
-
"epoch": 0.9985207100591716,
|
| 2183 |
-
"grad_norm": 0.6109741913754086,
|
| 2184 |
-
"learning_rate": 5.0002693899223325e-06,
|
| 2185 |
-
"loss": 0.8494,
|
| 2186 |
-
"step": 675
|
| 2187 |
-
},
|
| 2188 |
-
{
|
| 2189 |
-
"epoch": 0.9985207100591716,
|
| 2190 |
-
"eval_loss": 0.8508756160736084,
|
| 2191 |
-
"eval_runtime": 4.5433,
|
| 2192 |
-
"eval_samples_per_second": 117.755,
|
| 2193 |
-
"eval_steps_per_second": 1.101,
|
| 2194 |
-
"step": 675
|
| 2195 |
-
},
|
| 2196 |
{
|
| 2197 |
"epoch": 1.0,
|
| 2198 |
-
"step":
|
| 2199 |
-
"total_flos":
|
| 2200 |
-
"train_loss": 0.
|
| 2201 |
-
"train_runtime":
|
| 2202 |
-
"train_samples_per_second":
|
| 2203 |
-
"train_steps_per_second":
|
| 2204 |
}
|
| 2205 |
],
|
| 2206 |
"logging_steps": 5,
|
|
@@ -2220,8 +406,8 @@
|
|
| 2220 |
"attributes": {}
|
| 2221 |
}
|
| 2222 |
},
|
| 2223 |
-
"total_flos":
|
| 2224 |
-
"train_batch_size":
|
| 2225 |
"trial_name": null,
|
| 2226 |
"trial_params": null
|
| 2227 |
}
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 268,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.018656716417910446,
|
| 13 |
+
"grad_norm": 1.8357123991549114,
|
| 14 |
+
"learning_rate": 1.785714285714286e-05,
|
| 15 |
+
"loss": 0.8456,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.03731343283582089,
|
| 20 |
+
"grad_norm": 0.7888674392020409,
|
| 21 |
+
"learning_rate": 3.571428571428572e-05,
|
| 22 |
+
"loss": 0.7682,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.055970149253731345,
|
| 27 |
+
"grad_norm": 0.5088001784298014,
|
| 28 |
+
"learning_rate": 4.999827900623038e-05,
|
| 29 |
+
"loss": 0.7026,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.07462686567164178,
|
| 34 |
+
"grad_norm": 0.3967331836313917,
|
| 35 |
+
"learning_rate": 4.993807186343243e-05,
|
| 36 |
+
"loss": 0.6745,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.09328358208955224,
|
| 41 |
+
"grad_norm": 0.38953492827269537,
|
| 42 |
+
"learning_rate": 4.979207812402531e-05,
|
| 43 |
+
"loss": 0.6436,
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.11194029850746269,
|
| 48 |
+
"grad_norm": 0.3056894462367877,
|
| 49 |
+
"learning_rate": 4.956085596012407e-05,
|
| 50 |
+
"loss": 0.6362,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.13059701492537312,
|
| 55 |
+
"grad_norm": 0.2848383986273845,
|
| 56 |
+
"learning_rate": 4.924528939432311e-05,
|
| 57 |
+
"loss": 0.6199,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.14925373134328357,
|
| 62 |
+
"grad_norm": 0.24821786610124724,
|
| 63 |
+
"learning_rate": 4.884658491984735e-05,
|
| 64 |
+
"loss": 0.6106,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.16791044776119404,
|
| 69 |
+
"grad_norm": 0.21630773743864942,
|
| 70 |
+
"learning_rate": 4.8366266887814235e-05,
|
| 71 |
+
"loss": 0.6112,
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.1865671641791045,
|
| 76 |
+
"grad_norm": 0.2542614286063211,
|
| 77 |
+
"learning_rate": 4.780617167924209e-05,
|
| 78 |
+
"loss": 0.5939,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.20522388059701493,
|
| 83 |
+
"grad_norm": 0.273652684856057,
|
| 84 |
+
"learning_rate": 4.716844068408693e-05,
|
| 85 |
+
"loss": 0.5965,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"step": 55
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.22388059701492538,
|
| 90 |
+
"grad_norm": 0.2919315422944058,
|
| 91 |
+
"learning_rate": 4.6455512114150546e-05,
|
| 92 |
+
"loss": 0.5919,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.24253731343283583,
|
| 97 |
+
"grad_norm": 0.4896363894073648,
|
| 98 |
+
"learning_rate": 4.5670111681161296e-05,
|
| 99 |
+
"loss": 0.5829,
|
| 100 |
"step": 65
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.26119402985074625,
|
| 104 |
+
"grad_norm": 0.35893234362656307,
|
| 105 |
+
"learning_rate": 4.481524217566783e-05,
|
| 106 |
+
"loss": 0.5799,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.2798507462686567,
|
| 111 |
+
"grad_norm": 0.47821339713150723,
|
| 112 |
+
"learning_rate": 4.3894171986588217e-05,
|
| 113 |
+
"loss": 0.5787,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
"step": 75
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.29850746268656714,
|
| 118 |
+
"grad_norm": 0.42779548633021597,
|
| 119 |
+
"learning_rate": 4.29104226053073e-05,
|
| 120 |
+
"loss": 0.5775,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.31716417910447764,
|
| 125 |
+
"grad_norm": 0.34493135242732464,
|
| 126 |
+
"learning_rate": 4.186775516209732e-05,
|
| 127 |
+
"loss": 0.5728,
|
| 128 |
"step": 85
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.3358208955223881,
|
| 132 |
+
"grad_norm": 0.3450752761118264,
|
| 133 |
+
"learning_rate": 4.077015604633669e-05,
|
| 134 |
+
"loss": 0.5752,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.35447761194029853,
|
| 139 |
+
"grad_norm": 0.3254883369412446,
|
| 140 |
+
"learning_rate": 3.962182166550441e-05,
|
| 141 |
+
"loss": 0.5737,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142 |
"step": 95
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.373134328358209,
|
| 146 |
+
"grad_norm": 0.3021937652365121,
|
| 147 |
+
"learning_rate": 3.8427142401220634e-05,
|
| 148 |
+
"loss": 0.5697,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.3917910447761194,
|
| 153 |
+
"grad_norm": 0.22543629034027707,
|
| 154 |
+
"learning_rate": 3.71906858236735e-05,
|
| 155 |
+
"loss": 0.566,
|
| 156 |
"step": 105
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.41044776119402987,
|
| 160 |
+
"grad_norm": 0.26150626383864994,
|
| 161 |
+
"learning_rate": 3.591717922860785e-05,
|
| 162 |
+
"loss": 0.5733,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
"step": 110
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.4291044776119403,
|
| 167 |
+
"grad_norm": 0.25406069172974854,
|
| 168 |
+
"learning_rate": 3.46114915636416e-05,
|
| 169 |
+
"loss": 0.5641,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 170 |
"step": 115
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.44776119402985076,
|
| 174 |
+
"grad_norm": 0.2761171780274853,
|
| 175 |
+
"learning_rate": 3.3278614813010034e-05,
|
| 176 |
+
"loss": 0.565,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
"step": 120
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.4664179104477612,
|
| 181 |
+
"grad_norm": 0.27444350076630936,
|
| 182 |
+
"learning_rate": 3.1923644911909e-05,
|
| 183 |
+
"loss": 0.5619,
|
| 184 |
"step": 125
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.48507462686567165,
|
| 188 |
+
"grad_norm": 0.22218188459643629,
|
| 189 |
+
"learning_rate": 3.0551762263406576e-05,
|
| 190 |
+
"loss": 0.5606,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 191 |
"step": 130
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.503731343283582,
|
| 195 |
+
"grad_norm": 0.23885769537130422,
|
| 196 |
+
"learning_rate": 2.9168211932412042e-05,
|
| 197 |
+
"loss": 0.5579,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
"step": 135
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.5223880597014925,
|
| 202 |
+
"grad_norm": 0.19581242444906968,
|
| 203 |
+
"learning_rate": 2.777828359242567e-05,
|
| 204 |
+
"loss": 0.5632,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
"step": 140
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.5410447761194029,
|
| 209 |
+
"grad_norm": 0.23903378838505404,
|
| 210 |
+
"learning_rate": 2.6387291301738377e-05,
|
| 211 |
+
"loss": 0.5559,
|
| 212 |
"step": 145
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.5597014925373134,
|
| 216 |
+
"grad_norm": 0.22131995247320724,
|
| 217 |
+
"learning_rate": 2.50005531864019e-05,
|
| 218 |
+
"loss": 0.5537,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
"step": 150
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.5783582089552238,
|
| 223 |
+
"grad_norm": 0.20388629120046767,
|
| 224 |
+
"learning_rate": 2.362337110764688e-05,
|
| 225 |
+
"loss": 0.554,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 226 |
"step": 155
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.5970149253731343,
|
| 230 |
+
"grad_norm": 0.19865451240052354,
|
| 231 |
+
"learning_rate": 2.226101039148557e-05,
|
| 232 |
+
"loss": 0.5523,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
"step": 160
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.6156716417910447,
|
| 237 |
+
"grad_norm": 0.21792292980419078,
|
| 238 |
+
"learning_rate": 2.0918679697998252e-05,
|
| 239 |
+
"loss": 0.5511,
|
| 240 |
"step": 165
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.6343283582089553,
|
| 244 |
+
"grad_norm": 0.20734976300061925,
|
| 245 |
+
"learning_rate": 1.9601511107268255e-05,
|
| 246 |
+
"loss": 0.5516,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
"step": 170
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.6529850746268657,
|
| 251 |
+
"grad_norm": 0.1990824685948915,
|
| 252 |
+
"learning_rate": 1.8314540498102216e-05,
|
| 253 |
+
"loss": 0.5512,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 254 |
"step": 175
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.6716417910447762,
|
| 258 |
+
"grad_norm": 0.1759699937325297,
|
| 259 |
+
"learning_rate": 1.7062688294552992e-05,
|
| 260 |
+
"loss": 0.5433,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 261 |
"step": 180
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.6902985074626866,
|
| 265 |
+
"grad_norm": 0.19952904233106478,
|
| 266 |
+
"learning_rate": 1.5850740653856096e-05,
|
| 267 |
+
"loss": 0.5467,
|
| 268 |
"step": 185
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.7089552238805971,
|
| 272 |
+
"grad_norm": 0.17940456799398388,
|
| 273 |
+
"learning_rate": 1.4683331167703218e-05,
|
| 274 |
+
"loss": 0.5503,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 275 |
"step": 190
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.7276119402985075,
|
| 279 |
+
"grad_norm": 0.17212507506796912,
|
| 280 |
+
"learning_rate": 1.356492314681356e-05,
|
| 281 |
+
"loss": 0.5531,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 282 |
"step": 195
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 0.746268656716418,
|
| 286 |
+
"grad_norm": 0.16216686994925128,
|
| 287 |
+
"learning_rate": 1.2499792556533716e-05,
|
| 288 |
+
"loss": 0.5474,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 289 |
"step": 200
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.7649253731343284,
|
| 293 |
+
"grad_norm": 0.17719961464188644,
|
| 294 |
+
"learning_rate": 1.1492011668707753e-05,
|
| 295 |
+
"loss": 0.5449,
|
| 296 |
"step": 205
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.7835820895522388,
|
| 300 |
+
"grad_norm": 0.17440876918971734,
|
| 301 |
+
"learning_rate": 1.0545433492320603e-05,
|
| 302 |
+
"loss": 0.5501,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 303 |
"step": 210
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.8022388059701493,
|
| 307 |
+
"grad_norm": 0.1578415381103267,
|
| 308 |
+
"learning_rate": 9.663677042440537e-06,
|
| 309 |
+
"loss": 0.5444,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 310 |
"step": 215
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 0.8208955223880597,
|
| 314 |
+
"grad_norm": 0.16294954656469435,
|
| 315 |
+
"learning_rate": 8.850113503781367e-06,
|
| 316 |
+
"loss": 0.5443,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 317 |
"step": 220
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.8395522388059702,
|
| 321 |
+
"grad_norm": 0.14550383873413048,
|
| 322 |
+
"learning_rate": 8.107853341784671e-06,
|
| 323 |
+
"loss": 0.5507,
|
| 324 |
"step": 225
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.8582089552238806,
|
| 328 |
+
"grad_norm": 0.1571896983780636,
|
| 329 |
+
"learning_rate": 7.439734410499752e-06,
|
| 330 |
+
"loss": 0.547,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 331 |
"step": 230
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.8768656716417911,
|
| 335 |
+
"grad_norm": 0.1811708441839716,
|
| 336 |
+
"learning_rate": 6.848311102728011e-06,
|
| 337 |
+
"loss": 0.5472,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 338 |
"step": 235
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.8955223880597015,
|
| 342 |
+
"grad_norm": 0.1768578492896203,
|
| 343 |
+
"learning_rate": 6.335844583913515e-06,
|
| 344 |
+
"loss": 0.5433,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 345 |
"step": 240
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.914179104477612,
|
| 349 |
+
"grad_norm": 0.14375585775141816,
|
| 350 |
+
"learning_rate": 5.904294147118193e-06,
|
| 351 |
+
"loss": 0.547,
|
| 352 |
"step": 245
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 0.9328358208955224,
|
| 356 |
+
"grad_norm": 0.14507740115855672,
|
| 357 |
+
"learning_rate": 5.555309722133842e-06,
|
| 358 |
+
"loss": 0.5436,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 359 |
"step": 250
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.9514925373134329,
|
| 363 |
+
"grad_norm": 0.14189135037515943,
|
| 364 |
+
"learning_rate": 5.290225567370509e-06,
|
| 365 |
+
"loss": 0.5396,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 366 |
"step": 255
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 0.9701492537313433,
|
| 370 |
+
"grad_norm": 0.15104419515678771,
|
| 371 |
+
"learning_rate": 5.110055168638854e-06,
|
| 372 |
+
"loss": 0.5433,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 373 |
"step": 260
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 0.9888059701492538,
|
| 377 |
+
"grad_norm": 0.14422216331517992,
|
| 378 |
+
"learning_rate": 5.0154873643297575e-06,
|
| 379 |
+
"loss": 0.547,
|
| 380 |
"step": 265
|
| 381 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 382 |
{
|
| 383 |
"epoch": 1.0,
|
| 384 |
+
"step": 268,
|
| 385 |
+
"total_flos": 487709642588160.0,
|
| 386 |
+
"train_loss": 0.5792717831348305,
|
| 387 |
+
"train_runtime": 20654.3187,
|
| 388 |
+
"train_samples_per_second": 1.661,
|
| 389 |
+
"train_steps_per_second": 0.013
|
| 390 |
}
|
| 391 |
],
|
| 392 |
"logging_steps": 5,
|
|
|
|
| 406 |
"attributes": {}
|
| 407 |
}
|
| 408 |
},
|
| 409 |
+
"total_flos": 487709642588160.0,
|
| 410 |
+
"train_batch_size": 8,
|
| 411 |
"trial_name": null,
|
| 412 |
"trial_params": null
|
| 413 |
}
|