Upload 8 files
Browse files- README.md +9 -13
- all_results.json +12 -12
- eval_results.json +6 -6
- model.safetensors +1 -1
- train_results.json +6 -6
- trainer_state.json +220 -1032
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,26 +1,22 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
base_model: agentlans/multilingual-e5-small-aligned
|
| 4 |
-
language:
|
| 5 |
-
- multilingual
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
-
- name: multilingual-e5-small-aligned-
|
| 10 |
results: []
|
| 11 |
-
datasets:
|
| 12 |
-
- agentlans/en-translations
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
-
# multilingual-e5-small-aligned-
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [agentlans/multilingual-e5-small-aligned](https://huggingface.co/agentlans/multilingual-e5-small-aligned) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
-
- Mse: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -40,7 +36,7 @@ More information needed
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 5e-05
|
| 43 |
-
- train_batch_size:
|
| 44 |
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
@@ -51,9 +47,9 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Mse |
|
| 53 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
@@ -61,4 +57,4 @@ The following hyperparameters were used during training:
|
|
| 61 |
- Transformers 4.46.3
|
| 62 |
- Pytorch 2.5.1+cu124
|
| 63 |
- Datasets 3.1.0
|
| 64 |
-
- Tokenizers 0.20.3
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
base_model: agentlans/multilingual-e5-small-aligned
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
+
- name: multilingual-e5-small-aligned-quality-20241214-new
|
| 8 |
results: []
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# multilingual-e5-small-aligned-quality-20241214-new
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [agentlans/multilingual-e5-small-aligned](https://huggingface.co/agentlans/multilingual-e5-small-aligned) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1958
|
| 19 |
+
- Mse: 0.1958
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 128
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss | Mse |
|
| 49 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 50 |
+
| 0.2436 | 1.0 | 7813 | 0.2296 | 0.2296 |
|
| 51 |
+
| 0.1927 | 2.0 | 15626 | 0.2079 | 0.2079 |
|
| 52 |
+
| 0.1615 | 3.0 | 23439 | 0.1958 | 0.1958 |
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 57 |
- Transformers 4.46.3
|
| 58 |
- Pytorch 2.5.1+cu124
|
| 59 |
- Datasets 3.1.0
|
| 60 |
+
- Tokenizers 0.20.3
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_mse": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"total_flos": 4.
|
| 10 |
-
"train_loss": 0.
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples":
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second":
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.19583497941493988,
|
| 4 |
+
"eval_mse": 0.19583499065839644,
|
| 5 |
+
"eval_runtime": 99.5388,
|
| 6 |
+
"eval_samples": 182111,
|
| 7 |
+
"eval_samples_per_second": 1829.547,
|
| 8 |
+
"eval_steps_per_second": 228.695,
|
| 9 |
+
"total_flos": 4.9403660544e+16,
|
| 10 |
+
"train_loss": 0.21201796470442558,
|
| 11 |
+
"train_runtime": 3304.0326,
|
| 12 |
+
"train_samples": 1000000,
|
| 13 |
+
"train_samples_per_second": 907.981,
|
| 14 |
+
"train_steps_per_second": 7.094
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_mse": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.19583497941493988,
|
| 4 |
+
"eval_mse": 0.19583499065839644,
|
| 5 |
+
"eval_runtime": 99.5388,
|
| 6 |
+
"eval_samples": 182111,
|
| 7 |
+
"eval_samples_per_second": 1829.547,
|
| 8 |
+
"eval_steps_per_second": 228.695
|
| 9 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 470640124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fb2b10048a4dbfcb9f9a0c7afece210a37c49fe8c498d4fb7774a0b9162d16e
|
| 3 |
size 470640124
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"total_flos": 4.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples":
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.9403660544e+16,
|
| 4 |
+
"train_loss": 0.21201796470442558,
|
| 5 |
+
"train_runtime": 3304.0326,
|
| 6 |
+
"train_samples": 1000000,
|
| 7 |
+
"train_samples_per_second": 907.981,
|
| 8 |
+
"train_steps_per_second": 7.094
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1186 +1,374 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "multilingual-e5-small-aligned-
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 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": 1.
|
| 14 |
-
"learning_rate": 4.
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate": 4.
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
-
"learning_rate": 4.
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 1500
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 4.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 2000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 4.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 2500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 4.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 3000
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 4.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 3500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
-
"learning_rate": 4.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 4000
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 4.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 4500
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 5000
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 5500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 6000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 6500
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 7000
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 7500
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
"step": 8000
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 8500
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm": 1.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 9000
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 9500
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 10000
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 10500
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm": 2.
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 11000
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 11500
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 12000
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 12500
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 13000
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"grad_norm": 1.
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 13500
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"grad_norm":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 14000
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"grad_norm": 1.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 14500
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"grad_norm":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 15000
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 15500
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch": 0
|
| 230 |
-
"
|
| 231 |
-
"
|
| 232 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
"step": 16000
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 16500
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"grad_norm":
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 17000
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch":
|
| 251 |
-
"grad_norm":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 17500
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"grad_norm":
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 18000
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"grad_norm":
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 18500
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch":
|
| 272 |
-
"grad_norm":
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 19000
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
-
"grad_norm":
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 19500
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"grad_norm":
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 20000
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch":
|
| 293 |
-
"grad_norm":
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 20500
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"grad_norm":
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 21000
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"grad_norm":
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 21500
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch":
|
| 314 |
-
"grad_norm":
|
| 315 |
-
"learning_rate": 3.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 22000
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch":
|
| 321 |
-
"grad_norm":
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 22500
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
-
"grad_norm":
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 23000
|
| 332 |
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 0.8672866843814585,
|
| 335 |
-
"grad_norm": 3.147702932357788,
|
| 336 |
-
"learning_rate": 3.554522192697569e-05,
|
| 337 |
-
"loss": 0.2923,
|
| 338 |
-
"step": 23500
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 0.8857395925597874,
|
| 342 |
-
"grad_norm": 2.4293417930603027,
|
| 343 |
-
"learning_rate": 3.5237673457336876e-05,
|
| 344 |
-
"loss": 0.2962,
|
| 345 |
-
"step": 24000
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.9041925007381163,
|
| 349 |
-
"grad_norm": 1.7400178909301758,
|
| 350 |
-
"learning_rate": 3.493012498769807e-05,
|
| 351 |
-
"loss": 0.3017,
|
| 352 |
-
"step": 24500
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 0.9226454089164452,
|
| 356 |
-
"grad_norm": 2.229633331298828,
|
| 357 |
-
"learning_rate": 3.4622576518059246e-05,
|
| 358 |
-
"loss": 0.2961,
|
| 359 |
-
"step": 25000
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 0.9410983170947741,
|
| 363 |
-
"grad_norm": 2.479665517807007,
|
| 364 |
-
"learning_rate": 3.431502804842043e-05,
|
| 365 |
-
"loss": 0.2961,
|
| 366 |
-
"step": 25500
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 0.959551225273103,
|
| 370 |
-
"grad_norm": 2.990281820297241,
|
| 371 |
-
"learning_rate": 3.400747957878162e-05,
|
| 372 |
-
"loss": 0.2932,
|
| 373 |
-
"step": 26000
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 0.978004133451432,
|
| 377 |
-
"grad_norm": 2.545665979385376,
|
| 378 |
-
"learning_rate": 3.36999311091428e-05,
|
| 379 |
-
"loss": 0.3006,
|
| 380 |
-
"step": 26500
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 0.9964570416297609,
|
| 384 |
-
"grad_norm": 3.353132486343384,
|
| 385 |
-
"learning_rate": 3.3392382639503986e-05,
|
| 386 |
-
"loss": 0.2949,
|
| 387 |
-
"step": 27000
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 1.0,
|
| 391 |
-
"eval_loss": 0.2873324751853943,
|
| 392 |
-
"eval_mse": 0.28733249980634695,
|
| 393 |
-
"eval_runtime": 59.3439,
|
| 394 |
-
"eval_samples_per_second": 1623.385,
|
| 395 |
-
"eval_steps_per_second": 202.936,
|
| 396 |
-
"step": 27096
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 1.0149099498080898,
|
| 400 |
-
"grad_norm": 1.8382848501205444,
|
| 401 |
-
"learning_rate": 3.308483416986517e-05,
|
| 402 |
-
"loss": 0.2532,
|
| 403 |
-
"step": 27500
|
| 404 |
-
},
|
| 405 |
-
{
|
| 406 |
-
"epoch": 1.0333628579864187,
|
| 407 |
-
"grad_norm": 2.252268075942993,
|
| 408 |
-
"learning_rate": 3.277728570022636e-05,
|
| 409 |
-
"loss": 0.2366,
|
| 410 |
-
"step": 28000
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 1.0518157661647476,
|
| 414 |
-
"grad_norm": 2.4993882179260254,
|
| 415 |
-
"learning_rate": 3.246973723058754e-05,
|
| 416 |
-
"loss": 0.2431,
|
| 417 |
-
"step": 28500
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 1.0702686743430765,
|
| 421 |
-
"grad_norm": 2.5144221782684326,
|
| 422 |
-
"learning_rate": 3.216218876094873e-05,
|
| 423 |
-
"loss": 0.2421,
|
| 424 |
-
"step": 29000
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 1.0887215825214054,
|
| 428 |
-
"grad_norm": 2.1316707134246826,
|
| 429 |
-
"learning_rate": 3.185464029130991e-05,
|
| 430 |
-
"loss": 0.2401,
|
| 431 |
-
"step": 29500
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 1.1071744906997343,
|
| 435 |
-
"grad_norm": 2.0435242652893066,
|
| 436 |
-
"learning_rate": 3.15470918216711e-05,
|
| 437 |
-
"loss": 0.2339,
|
| 438 |
-
"step": 30000
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 1.1256273988780632,
|
| 442 |
-
"grad_norm": 3.039565086364746,
|
| 443 |
-
"learning_rate": 3.123954335203228e-05,
|
| 444 |
-
"loss": 0.2424,
|
| 445 |
-
"step": 30500
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 1.144080307056392,
|
| 449 |
-
"grad_norm": 2.4302680492401123,
|
| 450 |
-
"learning_rate": 3.093199488239347e-05,
|
| 451 |
-
"loss": 0.239,
|
| 452 |
-
"step": 31000
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 1.162533215234721,
|
| 456 |
-
"grad_norm": 2.2677814960479736,
|
| 457 |
-
"learning_rate": 3.062444641275465e-05,
|
| 458 |
-
"loss": 0.2394,
|
| 459 |
-
"step": 31500
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 1.1809861234130499,
|
| 463 |
-
"grad_norm": 3.0901999473571777,
|
| 464 |
-
"learning_rate": 3.0316897943115834e-05,
|
| 465 |
-
"loss": 0.2323,
|
| 466 |
-
"step": 32000
|
| 467 |
-
},
|
| 468 |
-
{
|
| 469 |
-
"epoch": 1.1994390315913788,
|
| 470 |
-
"grad_norm": 2.9839725494384766,
|
| 471 |
-
"learning_rate": 3.0009349473477023e-05,
|
| 472 |
-
"loss": 0.2387,
|
| 473 |
-
"step": 32500
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 1.2178919397697077,
|
| 477 |
-
"grad_norm": 2.2191145420074463,
|
| 478 |
-
"learning_rate": 2.9701801003838208e-05,
|
| 479 |
-
"loss": 0.2388,
|
| 480 |
-
"step": 33000
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 1.2363448479480366,
|
| 484 |
-
"grad_norm": 2.5112791061401367,
|
| 485 |
-
"learning_rate": 2.939425253419939e-05,
|
| 486 |
-
"loss": 0.2378,
|
| 487 |
-
"step": 33500
|
| 488 |
-
},
|
| 489 |
-
{
|
| 490 |
-
"epoch": 1.2547977561263655,
|
| 491 |
-
"grad_norm": 2.370722770690918,
|
| 492 |
-
"learning_rate": 2.9086704064560578e-05,
|
| 493 |
-
"loss": 0.2414,
|
| 494 |
-
"step": 34000
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 1.2732506643046944,
|
| 498 |
-
"grad_norm": 3.031116247177124,
|
| 499 |
-
"learning_rate": 2.877915559492176e-05,
|
| 500 |
-
"loss": 0.2349,
|
| 501 |
-
"step": 34500
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 1.2917035724830233,
|
| 505 |
-
"grad_norm": 3.356889247894287,
|
| 506 |
-
"learning_rate": 2.8471607125282945e-05,
|
| 507 |
-
"loss": 0.2364,
|
| 508 |
-
"step": 35000
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 1.3101564806613522,
|
| 512 |
-
"grad_norm": 3.58608078956604,
|
| 513 |
-
"learning_rate": 2.8164058655644134e-05,
|
| 514 |
-
"loss": 0.2435,
|
| 515 |
-
"step": 35500
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 1.328609388839681,
|
| 519 |
-
"grad_norm": 3.02878999710083,
|
| 520 |
-
"learning_rate": 2.7856510186005312e-05,
|
| 521 |
-
"loss": 0.2419,
|
| 522 |
-
"step": 36000
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 1.34706229701801,
|
| 526 |
-
"grad_norm": 2.696791648864746,
|
| 527 |
-
"learning_rate": 2.75489617163665e-05,
|
| 528 |
-
"loss": 0.2335,
|
| 529 |
-
"step": 36500
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 1.3655152051963388,
|
| 533 |
-
"grad_norm": 3.62918758392334,
|
| 534 |
-
"learning_rate": 2.7241413246727686e-05,
|
| 535 |
-
"loss": 0.2335,
|
| 536 |
-
"step": 37000
|
| 537 |
-
},
|
| 538 |
-
{
|
| 539 |
-
"epoch": 1.3839681133746677,
|
| 540 |
-
"grad_norm": 2.1558516025543213,
|
| 541 |
-
"learning_rate": 2.6933864777088867e-05,
|
| 542 |
-
"loss": 0.2312,
|
| 543 |
-
"step": 37500
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 1.4024210215529966,
|
| 547 |
-
"grad_norm": 2.8393824100494385,
|
| 548 |
-
"learning_rate": 2.6626316307450056e-05,
|
| 549 |
-
"loss": 0.2366,
|
| 550 |
-
"step": 38000
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 1.4208739297313255,
|
| 554 |
-
"grad_norm": 4.011019229888916,
|
| 555 |
-
"learning_rate": 2.631876783781124e-05,
|
| 556 |
-
"loss": 0.2341,
|
| 557 |
-
"step": 38500
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"epoch": 1.4393268379096544,
|
| 561 |
-
"grad_norm": 2.1811978816986084,
|
| 562 |
-
"learning_rate": 2.6011219368172423e-05,
|
| 563 |
-
"loss": 0.2367,
|
| 564 |
-
"step": 39000
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 1.4577797460879833,
|
| 568 |
-
"grad_norm": 2.3741202354431152,
|
| 569 |
-
"learning_rate": 2.570367089853361e-05,
|
| 570 |
-
"loss": 0.2357,
|
| 571 |
-
"step": 39500
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"epoch": 1.4762326542663124,
|
| 575 |
-
"grad_norm": 1.7879256010055542,
|
| 576 |
-
"learning_rate": 2.5396122428894797e-05,
|
| 577 |
-
"loss": 0.2383,
|
| 578 |
-
"step": 40000
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 1.4946855624446413,
|
| 582 |
-
"grad_norm": 2.9185972213745117,
|
| 583 |
-
"learning_rate": 2.508857395925598e-05,
|
| 584 |
-
"loss": 0.2383,
|
| 585 |
-
"step": 40500
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 1.51313847062297,
|
| 589 |
-
"grad_norm": 2.2389113903045654,
|
| 590 |
-
"learning_rate": 2.4781025489617167e-05,
|
| 591 |
-
"loss": 0.2365,
|
| 592 |
-
"step": 41000
|
| 593 |
-
},
|
| 594 |
-
{
|
| 595 |
-
"epoch": 1.531591378801299,
|
| 596 |
-
"grad_norm": 3.312300205230713,
|
| 597 |
-
"learning_rate": 2.447347701997835e-05,
|
| 598 |
-
"loss": 0.235,
|
| 599 |
-
"step": 41500
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 1.550044286979628,
|
| 603 |
-
"grad_norm": 1.933483362197876,
|
| 604 |
-
"learning_rate": 2.4165928550339534e-05,
|
| 605 |
-
"loss": 0.2328,
|
| 606 |
-
"step": 42000
|
| 607 |
-
},
|
| 608 |
-
{
|
| 609 |
-
"epoch": 1.568497195157957,
|
| 610 |
-
"grad_norm": 3.212892532348633,
|
| 611 |
-
"learning_rate": 2.3858380080700722e-05,
|
| 612 |
-
"loss": 0.2298,
|
| 613 |
-
"step": 42500
|
| 614 |
-
},
|
| 615 |
-
{
|
| 616 |
-
"epoch": 1.5869501033362858,
|
| 617 |
-
"grad_norm": 2.561583995819092,
|
| 618 |
-
"learning_rate": 2.3550831611061904e-05,
|
| 619 |
-
"loss": 0.2334,
|
| 620 |
-
"step": 43000
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 1.6054030115146147,
|
| 624 |
-
"grad_norm": 3.2696096897125244,
|
| 625 |
-
"learning_rate": 2.324328314142309e-05,
|
| 626 |
-
"loss": 0.239,
|
| 627 |
-
"step": 43500
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 1.6238559196929436,
|
| 631 |
-
"grad_norm": 2.1827101707458496,
|
| 632 |
-
"learning_rate": 2.2935734671784274e-05,
|
| 633 |
-
"loss": 0.2305,
|
| 634 |
-
"step": 44000
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 1.6423088278712725,
|
| 638 |
-
"grad_norm": 2.3663787841796875,
|
| 639 |
-
"learning_rate": 2.262818620214546e-05,
|
| 640 |
-
"loss": 0.2282,
|
| 641 |
-
"step": 44500
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 1.6607617360496014,
|
| 645 |
-
"grad_norm": 2.3439533710479736,
|
| 646 |
-
"learning_rate": 2.2320637732506645e-05,
|
| 647 |
-
"loss": 0.2319,
|
| 648 |
-
"step": 45000
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 1.6792146442279303,
|
| 652 |
-
"grad_norm": 1.9831467866897583,
|
| 653 |
-
"learning_rate": 2.201308926286783e-05,
|
| 654 |
-
"loss": 0.2301,
|
| 655 |
-
"step": 45500
|
| 656 |
-
},
|
| 657 |
-
{
|
| 658 |
-
"epoch": 1.6976675524062592,
|
| 659 |
-
"grad_norm": 2.6936724185943604,
|
| 660 |
-
"learning_rate": 2.1705540793229015e-05,
|
| 661 |
-
"loss": 0.229,
|
| 662 |
-
"step": 46000
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 1.7161204605845881,
|
| 666 |
-
"grad_norm": 2.882948160171509,
|
| 667 |
-
"learning_rate": 2.13979923235902e-05,
|
| 668 |
-
"loss": 0.2312,
|
| 669 |
-
"step": 46500
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 1.734573368762917,
|
| 673 |
-
"grad_norm": 2.604907274246216,
|
| 674 |
-
"learning_rate": 2.1090443853951382e-05,
|
| 675 |
-
"loss": 0.2251,
|
| 676 |
-
"step": 47000
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 1.753026276941246,
|
| 680 |
-
"grad_norm": 2.0118274688720703,
|
| 681 |
-
"learning_rate": 2.0782895384312567e-05,
|
| 682 |
-
"loss": 0.2298,
|
| 683 |
-
"step": 47500
|
| 684 |
-
},
|
| 685 |
-
{
|
| 686 |
-
"epoch": 1.7714791851195748,
|
| 687 |
-
"grad_norm": 3.394923448562622,
|
| 688 |
-
"learning_rate": 2.0475346914673755e-05,
|
| 689 |
-
"loss": 0.235,
|
| 690 |
-
"step": 48000
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 1.7899320932979037,
|
| 694 |
-
"grad_norm": 2.554750919342041,
|
| 695 |
-
"learning_rate": 2.0167798445034937e-05,
|
| 696 |
-
"loss": 0.2336,
|
| 697 |
-
"step": 48500
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"epoch": 1.8083850014762326,
|
| 701 |
-
"grad_norm": 2.264559030532837,
|
| 702 |
-
"learning_rate": 1.9860249975396122e-05,
|
| 703 |
-
"loss": 0.2252,
|
| 704 |
-
"step": 49000
|
| 705 |
-
},
|
| 706 |
-
{
|
| 707 |
-
"epoch": 1.8268379096545617,
|
| 708 |
-
"grad_norm": 3.1084542274475098,
|
| 709 |
-
"learning_rate": 1.955270150575731e-05,
|
| 710 |
-
"loss": 0.228,
|
| 711 |
-
"step": 49500
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 1.8452908178328906,
|
| 715 |
-
"grad_norm": 3.497529983520508,
|
| 716 |
-
"learning_rate": 1.9245153036118493e-05,
|
| 717 |
-
"loss": 0.2262,
|
| 718 |
-
"step": 50000
|
| 719 |
-
},
|
| 720 |
-
{
|
| 721 |
-
"epoch": 1.8637437260112195,
|
| 722 |
-
"grad_norm": 2.686687707901001,
|
| 723 |
-
"learning_rate": 1.8937604566479678e-05,
|
| 724 |
-
"loss": 0.2238,
|
| 725 |
-
"step": 50500
|
| 726 |
-
},
|
| 727 |
-
{
|
| 728 |
-
"epoch": 1.8821966341895484,
|
| 729 |
-
"grad_norm": 3.541355609893799,
|
| 730 |
-
"learning_rate": 1.8630056096840863e-05,
|
| 731 |
-
"loss": 0.2273,
|
| 732 |
-
"step": 51000
|
| 733 |
-
},
|
| 734 |
-
{
|
| 735 |
-
"epoch": 1.9006495423678773,
|
| 736 |
-
"grad_norm": 2.5415749549865723,
|
| 737 |
-
"learning_rate": 1.8322507627202048e-05,
|
| 738 |
-
"loss": 0.2298,
|
| 739 |
-
"step": 51500
|
| 740 |
-
},
|
| 741 |
-
{
|
| 742 |
-
"epoch": 1.9191024505462062,
|
| 743 |
-
"grad_norm": 2.017357349395752,
|
| 744 |
-
"learning_rate": 1.8014959157563233e-05,
|
| 745 |
-
"loss": 0.2285,
|
| 746 |
-
"step": 52000
|
| 747 |
-
},
|
| 748 |
-
{
|
| 749 |
-
"epoch": 1.937555358724535,
|
| 750 |
-
"grad_norm": 2.1992979049682617,
|
| 751 |
-
"learning_rate": 1.7707410687924418e-05,
|
| 752 |
-
"loss": 0.2322,
|
| 753 |
-
"step": 52500
|
| 754 |
-
},
|
| 755 |
-
{
|
| 756 |
-
"epoch": 1.956008266902864,
|
| 757 |
-
"grad_norm": 3.5973832607269287,
|
| 758 |
-
"learning_rate": 1.7399862218285603e-05,
|
| 759 |
-
"loss": 0.2282,
|
| 760 |
-
"step": 53000
|
| 761 |
-
},
|
| 762 |
-
{
|
| 763 |
-
"epoch": 1.974461175081193,
|
| 764 |
-
"grad_norm": 2.55898380279541,
|
| 765 |
-
"learning_rate": 1.709231374864679e-05,
|
| 766 |
-
"loss": 0.2257,
|
| 767 |
-
"step": 53500
|
| 768 |
-
},
|
| 769 |
-
{
|
| 770 |
-
"epoch": 1.9929140832595218,
|
| 771 |
-
"grad_norm": 1.7618777751922607,
|
| 772 |
-
"learning_rate": 1.678476527900797e-05,
|
| 773 |
-
"loss": 0.2239,
|
| 774 |
-
"step": 54000
|
| 775 |
-
},
|
| 776 |
-
{
|
| 777 |
-
"epoch": 2.0,
|
| 778 |
-
"eval_loss": 0.2671372890472412,
|
| 779 |
-
"eval_mse": 0.2671373049978385,
|
| 780 |
-
"eval_runtime": 53.3061,
|
| 781 |
-
"eval_samples_per_second": 1807.261,
|
| 782 |
-
"eval_steps_per_second": 225.922,
|
| 783 |
-
"step": 54192
|
| 784 |
-
},
|
| 785 |
-
{
|
| 786 |
-
"epoch": 2.0113669914378507,
|
| 787 |
-
"grad_norm": 1.9996424913406372,
|
| 788 |
-
"learning_rate": 1.647721680936916e-05,
|
| 789 |
-
"loss": 0.2054,
|
| 790 |
-
"step": 54500
|
| 791 |
-
},
|
| 792 |
-
{
|
| 793 |
-
"epoch": 2.0298198996161796,
|
| 794 |
-
"grad_norm": 3.9520423412323,
|
| 795 |
-
"learning_rate": 1.6169668339730344e-05,
|
| 796 |
-
"loss": 0.1834,
|
| 797 |
-
"step": 55000
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 2.0482728077945085,
|
| 801 |
-
"grad_norm": 2.5493485927581787,
|
| 802 |
-
"learning_rate": 1.5862119870091526e-05,
|
| 803 |
-
"loss": 0.183,
|
| 804 |
-
"step": 55500
|
| 805 |
-
},
|
| 806 |
-
{
|
| 807 |
-
"epoch": 2.0667257159728374,
|
| 808 |
-
"grad_norm": 2.3871965408325195,
|
| 809 |
-
"learning_rate": 1.555457140045271e-05,
|
| 810 |
-
"loss": 0.182,
|
| 811 |
-
"step": 56000
|
| 812 |
-
},
|
| 813 |
-
{
|
| 814 |
-
"epoch": 2.0851786241511663,
|
| 815 |
-
"grad_norm": 2.607405185699463,
|
| 816 |
-
"learning_rate": 1.5247022930813898e-05,
|
| 817 |
-
"loss": 0.1831,
|
| 818 |
-
"step": 56500
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 2.103631532329495,
|
| 822 |
-
"grad_norm": 3.14758038520813,
|
| 823 |
-
"learning_rate": 1.4939474461175081e-05,
|
| 824 |
-
"loss": 0.1802,
|
| 825 |
-
"step": 57000
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 2.122084440507824,
|
| 829 |
-
"grad_norm": 2.3298392295837402,
|
| 830 |
-
"learning_rate": 1.4631925991536266e-05,
|
| 831 |
-
"loss": 0.1886,
|
| 832 |
-
"step": 57500
|
| 833 |
-
},
|
| 834 |
-
{
|
| 835 |
-
"epoch": 2.140537348686153,
|
| 836 |
-
"grad_norm": 2.356092929840088,
|
| 837 |
-
"learning_rate": 1.4324377521897453e-05,
|
| 838 |
-
"loss": 0.1866,
|
| 839 |
-
"step": 58000
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 2.158990256864482,
|
| 843 |
-
"grad_norm": 2.599311113357544,
|
| 844 |
-
"learning_rate": 1.4016829052258637e-05,
|
| 845 |
-
"loss": 0.1799,
|
| 846 |
-
"step": 58500
|
| 847 |
-
},
|
| 848 |
-
{
|
| 849 |
-
"epoch": 2.1774431650428108,
|
| 850 |
-
"grad_norm": 2.818366050720215,
|
| 851 |
-
"learning_rate": 1.3709280582619822e-05,
|
| 852 |
-
"loss": 0.1885,
|
| 853 |
-
"step": 59000
|
| 854 |
-
},
|
| 855 |
-
{
|
| 856 |
-
"epoch": 2.1958960732211397,
|
| 857 |
-
"grad_norm": 2.1913158893585205,
|
| 858 |
-
"learning_rate": 1.3401732112981005e-05,
|
| 859 |
-
"loss": 0.1817,
|
| 860 |
-
"step": 59500
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 2.2143489813994686,
|
| 864 |
-
"grad_norm": 1.8911914825439453,
|
| 865 |
-
"learning_rate": 1.3094183643342192e-05,
|
| 866 |
-
"loss": 0.1837,
|
| 867 |
-
"step": 60000
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 2.2328018895777975,
|
| 871 |
-
"grad_norm": 1.7305101156234741,
|
| 872 |
-
"learning_rate": 1.2786635173703375e-05,
|
| 873 |
-
"loss": 0.18,
|
| 874 |
-
"step": 60500
|
| 875 |
-
},
|
| 876 |
-
{
|
| 877 |
-
"epoch": 2.2512547977561264,
|
| 878 |
-
"grad_norm": 2.5203235149383545,
|
| 879 |
-
"learning_rate": 1.2479086704064562e-05,
|
| 880 |
-
"loss": 0.1874,
|
| 881 |
-
"step": 61000
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 2.2697077059344553,
|
| 885 |
-
"grad_norm": 2.4888010025024414,
|
| 886 |
-
"learning_rate": 1.2171538234425746e-05,
|
| 887 |
-
"loss": 0.1834,
|
| 888 |
-
"step": 61500
|
| 889 |
-
},
|
| 890 |
-
{
|
| 891 |
-
"epoch": 2.288160614112784,
|
| 892 |
-
"grad_norm": 2.570237159729004,
|
| 893 |
-
"learning_rate": 1.186398976478693e-05,
|
| 894 |
-
"loss": 0.1845,
|
| 895 |
-
"step": 62000
|
| 896 |
-
},
|
| 897 |
-
{
|
| 898 |
-
"epoch": 2.306613522291113,
|
| 899 |
-
"grad_norm": 3.0238893032073975,
|
| 900 |
-
"learning_rate": 1.1556441295148116e-05,
|
| 901 |
-
"loss": 0.1862,
|
| 902 |
-
"step": 62500
|
| 903 |
-
},
|
| 904 |
-
{
|
| 905 |
-
"epoch": 2.325066430469442,
|
| 906 |
-
"grad_norm": 2.6648924350738525,
|
| 907 |
-
"learning_rate": 1.1248892825509301e-05,
|
| 908 |
-
"loss": 0.1858,
|
| 909 |
-
"step": 63000
|
| 910 |
-
},
|
| 911 |
-
{
|
| 912 |
-
"epoch": 2.343519338647771,
|
| 913 |
-
"grad_norm": 2.760099411010742,
|
| 914 |
-
"learning_rate": 1.0941344355870485e-05,
|
| 915 |
-
"loss": 0.1836,
|
| 916 |
-
"step": 63500
|
| 917 |
-
},
|
| 918 |
-
{
|
| 919 |
-
"epoch": 2.3619722468260997,
|
| 920 |
-
"grad_norm": 2.4213175773620605,
|
| 921 |
-
"learning_rate": 1.0633795886231671e-05,
|
| 922 |
-
"loss": 0.1798,
|
| 923 |
-
"step": 64000
|
| 924 |
-
},
|
| 925 |
-
{
|
| 926 |
-
"epoch": 2.3804251550044286,
|
| 927 |
-
"grad_norm": 3.6033475399017334,
|
| 928 |
-
"learning_rate": 1.0326247416592857e-05,
|
| 929 |
-
"loss": 0.1811,
|
| 930 |
-
"step": 64500
|
| 931 |
-
},
|
| 932 |
-
{
|
| 933 |
-
"epoch": 2.3988780631827575,
|
| 934 |
-
"grad_norm": 2.590794086456299,
|
| 935 |
-
"learning_rate": 1.001869894695404e-05,
|
| 936 |
-
"loss": 0.1784,
|
| 937 |
-
"step": 65000
|
| 938 |
-
},
|
| 939 |
-
{
|
| 940 |
-
"epoch": 2.4173309713610864,
|
| 941 |
-
"grad_norm": 2.297030448913574,
|
| 942 |
-
"learning_rate": 9.711150477315225e-06,
|
| 943 |
-
"loss": 0.177,
|
| 944 |
-
"step": 65500
|
| 945 |
-
},
|
| 946 |
-
{
|
| 947 |
-
"epoch": 2.4357838795394153,
|
| 948 |
-
"grad_norm": 2.6488535404205322,
|
| 949 |
-
"learning_rate": 9.40360200767641e-06,
|
| 950 |
-
"loss": 0.1804,
|
| 951 |
-
"step": 66000
|
| 952 |
-
},
|
| 953 |
-
{
|
| 954 |
-
"epoch": 2.4542367877177442,
|
| 955 |
-
"grad_norm": 2.314232349395752,
|
| 956 |
-
"learning_rate": 9.096053538037595e-06,
|
| 957 |
-
"loss": 0.1808,
|
| 958 |
-
"step": 66500
|
| 959 |
-
},
|
| 960 |
-
{
|
| 961 |
-
"epoch": 2.472689695896073,
|
| 962 |
-
"grad_norm": 2.5361621379852295,
|
| 963 |
-
"learning_rate": 8.78850506839878e-06,
|
| 964 |
-
"loss": 0.1814,
|
| 965 |
-
"step": 67000
|
| 966 |
-
},
|
| 967 |
-
{
|
| 968 |
-
"epoch": 2.491142604074402,
|
| 969 |
-
"grad_norm": 1.9473010301589966,
|
| 970 |
-
"learning_rate": 8.480956598759966e-06,
|
| 971 |
-
"loss": 0.1819,
|
| 972 |
-
"step": 67500
|
| 973 |
-
},
|
| 974 |
-
{
|
| 975 |
-
"epoch": 2.509595512252731,
|
| 976 |
-
"grad_norm": 1.6078424453735352,
|
| 977 |
-
"learning_rate": 8.17340812912115e-06,
|
| 978 |
-
"loss": 0.1821,
|
| 979 |
-
"step": 68000
|
| 980 |
-
},
|
| 981 |
-
{
|
| 982 |
-
"epoch": 2.52804842043106,
|
| 983 |
-
"grad_norm": 2.9577689170837402,
|
| 984 |
-
"learning_rate": 7.865859659482334e-06,
|
| 985 |
-
"loss": 0.1816,
|
| 986 |
-
"step": 68500
|
| 987 |
-
},
|
| 988 |
-
{
|
| 989 |
-
"epoch": 2.5465013286093887,
|
| 990 |
-
"grad_norm": 2.314099073410034,
|
| 991 |
-
"learning_rate": 7.55831118984352e-06,
|
| 992 |
-
"loss": 0.1813,
|
| 993 |
-
"step": 69000
|
| 994 |
-
},
|
| 995 |
-
{
|
| 996 |
-
"epoch": 2.5649542367877176,
|
| 997 |
-
"grad_norm": 2.1542553901672363,
|
| 998 |
-
"learning_rate": 7.250762720204704e-06,
|
| 999 |
-
"loss": 0.1771,
|
| 1000 |
-
"step": 69500
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"epoch": 2.5834071449660465,
|
| 1004 |
-
"grad_norm": 2.126908540725708,
|
| 1005 |
-
"learning_rate": 6.94321425056589e-06,
|
| 1006 |
-
"loss": 0.1807,
|
| 1007 |
-
"step": 70000
|
| 1008 |
-
},
|
| 1009 |
-
{
|
| 1010 |
-
"epoch": 2.6018600531443754,
|
| 1011 |
-
"grad_norm": 2.9939024448394775,
|
| 1012 |
-
"learning_rate": 6.635665780927075e-06,
|
| 1013 |
-
"loss": 0.1792,
|
| 1014 |
-
"step": 70500
|
| 1015 |
-
},
|
| 1016 |
-
{
|
| 1017 |
-
"epoch": 2.6203129613227043,
|
| 1018 |
-
"grad_norm": 3.436375856399536,
|
| 1019 |
-
"learning_rate": 6.328117311288259e-06,
|
| 1020 |
-
"loss": 0.1801,
|
| 1021 |
-
"step": 71000
|
| 1022 |
-
},
|
| 1023 |
-
{
|
| 1024 |
-
"epoch": 2.638765869501033,
|
| 1025 |
-
"grad_norm": 2.515270233154297,
|
| 1026 |
-
"learning_rate": 6.020568841649444e-06,
|
| 1027 |
-
"loss": 0.1805,
|
| 1028 |
-
"step": 71500
|
| 1029 |
-
},
|
| 1030 |
-
{
|
| 1031 |
-
"epoch": 2.657218777679362,
|
| 1032 |
-
"grad_norm": 2.924694061279297,
|
| 1033 |
-
"learning_rate": 5.713020372010629e-06,
|
| 1034 |
-
"loss": 0.1782,
|
| 1035 |
-
"step": 72000
|
| 1036 |
-
},
|
| 1037 |
-
{
|
| 1038 |
-
"epoch": 2.675671685857691,
|
| 1039 |
-
"grad_norm": 2.6601603031158447,
|
| 1040 |
-
"learning_rate": 5.4054719023718145e-06,
|
| 1041 |
-
"loss": 0.1821,
|
| 1042 |
-
"step": 72500
|
| 1043 |
-
},
|
| 1044 |
-
{
|
| 1045 |
-
"epoch": 2.69412459403602,
|
| 1046 |
-
"grad_norm": 2.6807141304016113,
|
| 1047 |
-
"learning_rate": 5.097923432732999e-06,
|
| 1048 |
-
"loss": 0.1793,
|
| 1049 |
-
"step": 73000
|
| 1050 |
-
},
|
| 1051 |
-
{
|
| 1052 |
-
"epoch": 2.712577502214349,
|
| 1053 |
-
"grad_norm": 3.814213991165161,
|
| 1054 |
-
"learning_rate": 4.790374963094184e-06,
|
| 1055 |
-
"loss": 0.1814,
|
| 1056 |
-
"step": 73500
|
| 1057 |
-
},
|
| 1058 |
-
{
|
| 1059 |
-
"epoch": 2.7310304103926777,
|
| 1060 |
-
"grad_norm": 2.8295676708221436,
|
| 1061 |
-
"learning_rate": 4.482826493455368e-06,
|
| 1062 |
-
"loss": 0.1761,
|
| 1063 |
-
"step": 74000
|
| 1064 |
-
},
|
| 1065 |
-
{
|
| 1066 |
-
"epoch": 2.7494833185710066,
|
| 1067 |
-
"grad_norm": 3.3659756183624268,
|
| 1068 |
-
"learning_rate": 4.175278023816553e-06,
|
| 1069 |
-
"loss": 0.1823,
|
| 1070 |
-
"step": 74500
|
| 1071 |
-
},
|
| 1072 |
-
{
|
| 1073 |
-
"epoch": 2.7679362267493355,
|
| 1074 |
-
"grad_norm": 2.6024508476257324,
|
| 1075 |
-
"learning_rate": 3.8677295541777385e-06,
|
| 1076 |
-
"loss": 0.1805,
|
| 1077 |
-
"step": 75000
|
| 1078 |
-
},
|
| 1079 |
-
{
|
| 1080 |
-
"epoch": 2.7863891349276644,
|
| 1081 |
-
"grad_norm": 2.8737952709198,
|
| 1082 |
-
"learning_rate": 3.5601810845389237e-06,
|
| 1083 |
-
"loss": 0.173,
|
| 1084 |
-
"step": 75500
|
| 1085 |
-
},
|
| 1086 |
-
{
|
| 1087 |
-
"epoch": 2.8048420431059933,
|
| 1088 |
-
"grad_norm": 2.042231559753418,
|
| 1089 |
-
"learning_rate": 3.2526326149001084e-06,
|
| 1090 |
-
"loss": 0.1748,
|
| 1091 |
-
"step": 76000
|
| 1092 |
-
},
|
| 1093 |
-
{
|
| 1094 |
-
"epoch": 2.823294951284322,
|
| 1095 |
-
"grad_norm": 2.5914924144744873,
|
| 1096 |
-
"learning_rate": 2.945084145261293e-06,
|
| 1097 |
-
"loss": 0.1796,
|
| 1098 |
-
"step": 76500
|
| 1099 |
-
},
|
| 1100 |
-
{
|
| 1101 |
-
"epoch": 2.841747859462651,
|
| 1102 |
-
"grad_norm": 2.8601739406585693,
|
| 1103 |
-
"learning_rate": 2.6375356756224782e-06,
|
| 1104 |
-
"loss": 0.178,
|
| 1105 |
-
"step": 77000
|
| 1106 |
-
},
|
| 1107 |
-
{
|
| 1108 |
-
"epoch": 2.86020076764098,
|
| 1109 |
-
"grad_norm": 2.323885917663574,
|
| 1110 |
-
"learning_rate": 2.3299872059836634e-06,
|
| 1111 |
-
"loss": 0.179,
|
| 1112 |
-
"step": 77500
|
| 1113 |
-
},
|
| 1114 |
-
{
|
| 1115 |
-
"epoch": 2.878653675819309,
|
| 1116 |
-
"grad_norm": 3.8116016387939453,
|
| 1117 |
-
"learning_rate": 2.022438736344848e-06,
|
| 1118 |
-
"loss": 0.1793,
|
| 1119 |
-
"step": 78000
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 2.8971065839976378,
|
| 1123 |
-
"grad_norm": 3.1566436290740967,
|
| 1124 |
-
"learning_rate": 1.7148902667060328e-06,
|
| 1125 |
-
"loss": 0.1733,
|
| 1126 |
-
"step": 78500
|
| 1127 |
-
},
|
| 1128 |
-
{
|
| 1129 |
-
"epoch": 2.9155594921759667,
|
| 1130 |
-
"grad_norm": 2.2577366828918457,
|
| 1131 |
-
"learning_rate": 1.4073417970672177e-06,
|
| 1132 |
-
"loss": 0.1757,
|
| 1133 |
-
"step": 79000
|
| 1134 |
-
},
|
| 1135 |
-
{
|
| 1136 |
-
"epoch": 2.934012400354296,
|
| 1137 |
-
"grad_norm": 2.2155442237854004,
|
| 1138 |
-
"learning_rate": 1.0997933274284029e-06,
|
| 1139 |
-
"loss": 0.1805,
|
| 1140 |
-
"step": 79500
|
| 1141 |
-
},
|
| 1142 |
-
{
|
| 1143 |
-
"epoch": 2.952465308532625,
|
| 1144 |
-
"grad_norm": 1.9121520519256592,
|
| 1145 |
-
"learning_rate": 7.922448577895876e-07,
|
| 1146 |
-
"loss": 0.1775,
|
| 1147 |
-
"step": 80000
|
| 1148 |
-
},
|
| 1149 |
-
{
|
| 1150 |
-
"epoch": 2.970918216710954,
|
| 1151 |
-
"grad_norm": 3.8823773860931396,
|
| 1152 |
-
"learning_rate": 4.846963881507725e-07,
|
| 1153 |
-
"loss": 0.1808,
|
| 1154 |
-
"step": 80500
|
| 1155 |
-
},
|
| 1156 |
-
{
|
| 1157 |
-
"epoch": 2.9893711248892827,
|
| 1158 |
-
"grad_norm": 2.4405837059020996,
|
| 1159 |
-
"learning_rate": 1.771479185119575e-07,
|
| 1160 |
-
"loss": 0.1789,
|
| 1161 |
-
"step": 81000
|
| 1162 |
-
},
|
| 1163 |
{
|
| 1164 |
"epoch": 3.0,
|
| 1165 |
-
"eval_loss": 0.
|
| 1166 |
-
"eval_mse": 0.
|
| 1167 |
-
"eval_runtime":
|
| 1168 |
-
"eval_samples_per_second":
|
| 1169 |
-
"eval_steps_per_second": 227.
|
| 1170 |
-
"step":
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
"epoch": 3.0,
|
| 1174 |
-
"step":
|
| 1175 |
-
"total_flos": 4.
|
| 1176 |
-
"train_loss": 0.
|
| 1177 |
-
"train_runtime":
|
| 1178 |
-
"train_samples_per_second":
|
| 1179 |
-
"train_steps_per_second":
|
| 1180 |
}
|
| 1181 |
],
|
| 1182 |
"logging_steps": 500,
|
| 1183 |
-
"max_steps":
|
| 1184 |
"num_input_tokens_seen": 0,
|
| 1185 |
"num_train_epochs": 3,
|
| 1186 |
"save_steps": 500,
|
|
@@ -1196,8 +384,8 @@
|
|
| 1196 |
"attributes": {}
|
| 1197 |
}
|
| 1198 |
},
|
| 1199 |
-
"total_flos": 4.
|
| 1200 |
-
"train_batch_size":
|
| 1201 |
"trial_name": null,
|
| 1202 |
"trial_params": null
|
| 1203 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.19583497941493988,
|
| 3 |
+
"best_model_checkpoint": "multilingual-e5-small-aligned-quality-20241214-new/checkpoint-23439",
|
| 4 |
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 23439,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.06399590426212723,
|
| 13 |
+
"grad_norm": 1.3940926790237427,
|
| 14 |
+
"learning_rate": 4.8933401595631215e-05,
|
| 15 |
+
"loss": 0.3708,
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.12799180852425446,
|
| 20 |
+
"grad_norm": 1.3164088726043701,
|
| 21 |
+
"learning_rate": 4.786680319126243e-05,
|
| 22 |
+
"loss": 0.3132,
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.19198771278638166,
|
| 27 |
+
"grad_norm": 1.3515187501907349,
|
| 28 |
+
"learning_rate": 4.680020478689364e-05,
|
| 29 |
+
"loss": 0.2973,
|
| 30 |
"step": 1500
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.2559836170485089,
|
| 34 |
+
"grad_norm": 1.7389737367630005,
|
| 35 |
+
"learning_rate": 4.573360638252485e-05,
|
| 36 |
+
"loss": 0.2877,
|
| 37 |
"step": 2000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.3199795213106361,
|
| 41 |
+
"grad_norm": 1.2677313089370728,
|
| 42 |
+
"learning_rate": 4.4667007978156063e-05,
|
| 43 |
+
"loss": 0.2803,
|
| 44 |
"step": 2500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.3839754255727633,
|
| 48 |
+
"grad_norm": 1.3927785158157349,
|
| 49 |
+
"learning_rate": 4.360040957378728e-05,
|
| 50 |
+
"loss": 0.2743,
|
| 51 |
"step": 3000
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.4479713298348906,
|
| 55 |
+
"grad_norm": 1.628334879875183,
|
| 56 |
+
"learning_rate": 4.2533811169418495e-05,
|
| 57 |
+
"loss": 0.2747,
|
| 58 |
"step": 3500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.5119672340970178,
|
| 62 |
+
"grad_norm": 1.4009227752685547,
|
| 63 |
+
"learning_rate": 4.146721276504971e-05,
|
| 64 |
+
"loss": 0.2672,
|
| 65 |
"step": 4000
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.575963138359145,
|
| 69 |
+
"grad_norm": 1.4522840976715088,
|
| 70 |
+
"learning_rate": 4.040061436068092e-05,
|
| 71 |
+
"loss": 0.264,
|
| 72 |
"step": 4500
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.6399590426212722,
|
| 76 |
+
"grad_norm": 1.5413362979888916,
|
| 77 |
+
"learning_rate": 3.933401595631213e-05,
|
| 78 |
+
"loss": 0.2588,
|
| 79 |
"step": 5000
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.7039549468833994,
|
| 83 |
+
"grad_norm": 1.2421332597732544,
|
| 84 |
+
"learning_rate": 3.8267417551943344e-05,
|
| 85 |
+
"loss": 0.253,
|
| 86 |
"step": 5500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.7679508511455266,
|
| 90 |
+
"grad_norm": 1.3509016036987305,
|
| 91 |
+
"learning_rate": 3.7200819147574556e-05,
|
| 92 |
+
"loss": 0.2539,
|
| 93 |
"step": 6000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.831946755407654,
|
| 97 |
+
"grad_norm": 1.9007371664047241,
|
| 98 |
+
"learning_rate": 3.613422074320577e-05,
|
| 99 |
+
"loss": 0.2516,
|
| 100 |
"step": 6500
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.8959426596697811,
|
| 104 |
+
"grad_norm": 1.3137174844741821,
|
| 105 |
+
"learning_rate": 3.506762233883698e-05,
|
| 106 |
+
"loss": 0.2464,
|
| 107 |
"step": 7000
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.9599385639319084,
|
| 111 |
+
"grad_norm": 1.5280767679214478,
|
| 112 |
+
"learning_rate": 3.400102393446819e-05,
|
| 113 |
+
"loss": 0.2436,
|
| 114 |
"step": 7500
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 1.0,
|
| 118 |
+
"eval_loss": 0.2296382337808609,
|
| 119 |
+
"eval_mse": 0.22963822030546574,
|
| 120 |
+
"eval_runtime": 103.0849,
|
| 121 |
+
"eval_samples_per_second": 1766.611,
|
| 122 |
+
"eval_steps_per_second": 220.828,
|
| 123 |
+
"step": 7813
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0239344681940357,
|
| 127 |
+
"grad_norm": 1.2579801082611084,
|
| 128 |
+
"learning_rate": 3.293442553009941e-05,
|
| 129 |
+
"loss": 0.2307,
|
| 130 |
"step": 8000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 1.0879303724561629,
|
| 134 |
+
"grad_norm": 1.494954228401184,
|
| 135 |
+
"learning_rate": 3.1867827125730624e-05,
|
| 136 |
+
"loss": 0.2053,
|
| 137 |
"step": 8500
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.15192627671829,
|
| 141 |
+
"grad_norm": 1.6762491464614868,
|
| 142 |
+
"learning_rate": 3.0801228721361836e-05,
|
| 143 |
+
"loss": 0.2021,
|
| 144 |
"step": 9000
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.2159221809804173,
|
| 148 |
+
"grad_norm": 1.3708257675170898,
|
| 149 |
+
"learning_rate": 2.9734630316993045e-05,
|
| 150 |
+
"loss": 0.2034,
|
| 151 |
"step": 9500
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.2799180852425445,
|
| 155 |
+
"grad_norm": 1.57413649559021,
|
| 156 |
+
"learning_rate": 2.866803191262426e-05,
|
| 157 |
+
"loss": 0.2016,
|
| 158 |
"step": 10000
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 1.3439139895046717,
|
| 162 |
+
"grad_norm": 1.1981782913208008,
|
| 163 |
+
"learning_rate": 2.7601433508255476e-05,
|
| 164 |
+
"loss": 0.2014,
|
| 165 |
"step": 10500
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.4079098937667989,
|
| 169 |
+
"grad_norm": 2.0707337856292725,
|
| 170 |
+
"learning_rate": 2.6534835103886685e-05,
|
| 171 |
+
"loss": 0.1996,
|
| 172 |
"step": 11000
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 1.471905798028926,
|
| 176 |
+
"grad_norm": 1.3037790060043335,
|
| 177 |
+
"learning_rate": 2.54682366995179e-05,
|
| 178 |
+
"loss": 0.1998,
|
| 179 |
"step": 11500
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 1.5359017022910533,
|
| 183 |
+
"grad_norm": 1.331900715827942,
|
| 184 |
+
"learning_rate": 2.4401638295149112e-05,
|
| 185 |
+
"loss": 0.1995,
|
| 186 |
"step": 12000
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 1.5998976065531805,
|
| 190 |
+
"grad_norm": 1.6664810180664062,
|
| 191 |
+
"learning_rate": 2.3335039890780325e-05,
|
| 192 |
+
"loss": 0.1995,
|
| 193 |
"step": 12500
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 1.6638935108153077,
|
| 197 |
+
"grad_norm": 1.518689751625061,
|
| 198 |
+
"learning_rate": 2.2268441486411537e-05,
|
| 199 |
+
"loss": 0.1981,
|
| 200 |
"step": 13000
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 1.727889415077435,
|
| 204 |
+
"grad_norm": 1.4883790016174316,
|
| 205 |
+
"learning_rate": 2.120184308204275e-05,
|
| 206 |
+
"loss": 0.1954,
|
| 207 |
"step": 13500
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 1.7918853193395623,
|
| 211 |
+
"grad_norm": 1.3662298917770386,
|
| 212 |
+
"learning_rate": 2.0135244677673965e-05,
|
| 213 |
+
"loss": 0.1957,
|
| 214 |
"step": 14000
|
| 215 |
},
|
| 216 |
{
|
| 217 |
+
"epoch": 1.8558812236016895,
|
| 218 |
+
"grad_norm": 1.4358400106430054,
|
| 219 |
+
"learning_rate": 1.9068646273305177e-05,
|
| 220 |
+
"loss": 0.1943,
|
| 221 |
"step": 14500
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 1.9198771278638167,
|
| 225 |
+
"grad_norm": 1.3663334846496582,
|
| 226 |
+
"learning_rate": 1.800204786893639e-05,
|
| 227 |
+
"loss": 0.1959,
|
| 228 |
"step": 15000
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 1.983873032125944,
|
| 232 |
+
"grad_norm": 1.3956917524337769,
|
| 233 |
+
"learning_rate": 1.69354494645676e-05,
|
| 234 |
+
"loss": 0.1927,
|
| 235 |
"step": 15500
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 2.0,
|
| 239 |
+
"eval_loss": 0.2078620195388794,
|
| 240 |
+
"eval_mse": 0.20786202507040266,
|
| 241 |
+
"eval_runtime": 99.6454,
|
| 242 |
+
"eval_samples_per_second": 1827.591,
|
| 243 |
+
"eval_steps_per_second": 228.45,
|
| 244 |
+
"step": 15626
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.0478689363880713,
|
| 248 |
+
"grad_norm": 1.112040638923645,
|
| 249 |
+
"learning_rate": 1.5868851060198814e-05,
|
| 250 |
+
"loss": 0.1722,
|
| 251 |
"step": 16000
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 2.1118648406501985,
|
| 255 |
+
"grad_norm": 1.627584457397461,
|
| 256 |
+
"learning_rate": 1.480225265583003e-05,
|
| 257 |
+
"loss": 0.1648,
|
| 258 |
"step": 16500
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"epoch": 2.1758607449123257,
|
| 262 |
+
"grad_norm": 1.6189327239990234,
|
| 263 |
+
"learning_rate": 1.3735654251461241e-05,
|
| 264 |
+
"loss": 0.1637,
|
| 265 |
"step": 17000
|
| 266 |
},
|
| 267 |
{
|
| 268 |
+
"epoch": 2.239856649174453,
|
| 269 |
+
"grad_norm": 1.2161808013916016,
|
| 270 |
+
"learning_rate": 1.2669055847092454e-05,
|
| 271 |
+
"loss": 0.1644,
|
| 272 |
"step": 17500
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 2.30385255343658,
|
| 276 |
+
"grad_norm": 1.4423365592956543,
|
| 277 |
+
"learning_rate": 1.1602457442723666e-05,
|
| 278 |
+
"loss": 0.163,
|
| 279 |
"step": 18000
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 2.3678484576987073,
|
| 283 |
+
"grad_norm": 1.298816204071045,
|
| 284 |
+
"learning_rate": 1.053585903835488e-05,
|
| 285 |
+
"loss": 0.1626,
|
| 286 |
"step": 18500
|
| 287 |
},
|
| 288 |
{
|
| 289 |
+
"epoch": 2.4318443619608345,
|
| 290 |
+
"grad_norm": 1.2976384162902832,
|
| 291 |
+
"learning_rate": 9.469260633986092e-06,
|
| 292 |
+
"loss": 0.1627,
|
| 293 |
"step": 19000
|
| 294 |
},
|
| 295 |
{
|
| 296 |
+
"epoch": 2.4958402662229617,
|
| 297 |
+
"grad_norm": 1.39438796043396,
|
| 298 |
+
"learning_rate": 8.402662229617304e-06,
|
| 299 |
+
"loss": 0.1633,
|
| 300 |
"step": 19500
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"epoch": 2.559836170485089,
|
| 304 |
+
"grad_norm": 1.342234492301941,
|
| 305 |
+
"learning_rate": 7.336063825248518e-06,
|
| 306 |
+
"loss": 0.162,
|
| 307 |
"step": 20000
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 2.623832074747216,
|
| 311 |
+
"grad_norm": 1.3450177907943726,
|
| 312 |
+
"learning_rate": 6.26946542087973e-06,
|
| 313 |
+
"loss": 0.1619,
|
| 314 |
"step": 20500
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 2.6878279790093433,
|
| 318 |
+
"grad_norm": 1.3149842023849487,
|
| 319 |
+
"learning_rate": 5.202867016510943e-06,
|
| 320 |
+
"loss": 0.1608,
|
| 321 |
"step": 21000
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 2.7518238832714705,
|
| 325 |
+
"grad_norm": 1.3171745538711548,
|
| 326 |
+
"learning_rate": 4.1362686121421564e-06,
|
| 327 |
+
"loss": 0.1622,
|
| 328 |
"step": 21500
|
| 329 |
},
|
| 330 |
{
|
| 331 |
+
"epoch": 2.8158197875335977,
|
| 332 |
+
"grad_norm": 1.0992498397827148,
|
| 333 |
+
"learning_rate": 3.069670207773369e-06,
|
| 334 |
+
"loss": 0.1608,
|
| 335 |
"step": 22000
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 2.879815691795725,
|
| 339 |
+
"grad_norm": 1.3956327438354492,
|
| 340 |
+
"learning_rate": 2.003071803404582e-06,
|
| 341 |
+
"loss": 0.161,
|
| 342 |
"step": 22500
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 2.943811596057852,
|
| 346 |
+
"grad_norm": 1.531733512878418,
|
| 347 |
+
"learning_rate": 9.364733990357951e-07,
|
| 348 |
+
"loss": 0.1615,
|
| 349 |
"step": 23000
|
| 350 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 351 |
{
|
| 352 |
"epoch": 3.0,
|
| 353 |
+
"eval_loss": 0.19583497941493988,
|
| 354 |
+
"eval_mse": 0.19583499065839644,
|
| 355 |
+
"eval_runtime": 99.9929,
|
| 356 |
+
"eval_samples_per_second": 1821.239,
|
| 357 |
+
"eval_steps_per_second": 227.656,
|
| 358 |
+
"step": 23439
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 3.0,
|
| 362 |
+
"step": 23439,
|
| 363 |
+
"total_flos": 4.9403660544e+16,
|
| 364 |
+
"train_loss": 0.21201796470442558,
|
| 365 |
+
"train_runtime": 3304.0326,
|
| 366 |
+
"train_samples_per_second": 907.981,
|
| 367 |
+
"train_steps_per_second": 7.094
|
| 368 |
}
|
| 369 |
],
|
| 370 |
"logging_steps": 500,
|
| 371 |
+
"max_steps": 23439,
|
| 372 |
"num_input_tokens_seen": 0,
|
| 373 |
"num_train_epochs": 3,
|
| 374 |
"save_steps": 500,
|
|
|
|
| 384 |
"attributes": {}
|
| 385 |
}
|
| 386 |
},
|
| 387 |
+
"total_flos": 4.9403660544e+16,
|
| 388 |
+
"train_batch_size": 128,
|
| 389 |
"trial_name": null,
|
| 390 |
"trial_params": null
|
| 391 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dc970f588e7b3f3c91f44dc7ac64c322e7c274490920c7b98653ebce45b58fc
|
| 3 |
size 5368
|