ikno
commited on
Commit
•
c0f1f7e
1
Parent(s):
0795eee
Model save
Browse files- README.md +7 -11
- all_results.json +5 -10
- config.json +1 -1
- model-00001-of-00006.safetensors +1 -1
- model-00002-of-00006.safetensors +1 -1
- model-00003-of-00006.safetensors +1 -1
- model-00004-of-00006.safetensors +1 -1
- model-00005-of-00006.safetensors +1 -1
- model-00006-of-00006.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +1207 -185
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,15 +1,11 @@
|
|
| 1 |
---
|
| 2 |
base_model: OrionStarAI/Orion-14B-Chat
|
| 3 |
tags:
|
| 4 |
-
- alignment-handbook
|
| 5 |
-
- trl
|
| 6 |
-
- sft
|
| 7 |
-
- generated_from_trainer
|
| 8 |
- trl
|
| 9 |
- sft
|
| 10 |
- generated_from_trainer
|
| 11 |
datasets:
|
| 12 |
-
-
|
| 13 |
model-index:
|
| 14 |
- name: rinko-test
|
| 15 |
results: []
|
|
@@ -20,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
# rinko-test
|
| 22 |
|
| 23 |
-
This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
-
- Loss:
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -41,7 +37,7 @@ More information needed
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
-
- learning_rate:
|
| 45 |
- train_batch_size: 1
|
| 46 |
- eval_batch_size: 1
|
| 47 |
- seed: 42
|
|
@@ -59,9 +55,9 @@ The following hyperparameters were used during training:
|
|
| 59 |
|
| 60 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 61 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
base_model: OrionStarAI/Orion-14B-Chat
|
| 3 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- trl
|
| 5 |
- sft
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
+
- generator
|
| 9 |
model-index:
|
| 10 |
- name: rinko-test
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# rinko-test
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1385
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-07
|
| 41 |
- train_batch_size: 1
|
| 42 |
- eval_batch_size: 1
|
| 43 |
- seed: 42
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
+
| 1.1777 | 1.0 | 305 | 1.1992 |
|
| 59 |
+
| 1.1046 | 2.0 | 611 | 1.1458 |
|
| 60 |
+
| 1.1129 | 3.0 | 915 | 1.1385 |
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"eval_samples": 442,
|
| 6 |
-
"eval_samples_per_second": 0.274,
|
| 7 |
-
"eval_steps_per_second": 0.069,
|
| 8 |
-
"train_loss": 0.3222779505034929,
|
| 9 |
-
"train_runtime": 18917.8994,
|
| 10 |
"train_samples": 5850,
|
| 11 |
-
"train_samples_per_second": 0.
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.2146218933042934,
|
| 4 |
+
"train_runtime": 75011.8955,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"train_samples": 5850,
|
| 6 |
+
"train_samples_per_second": 0.098,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 8 |
}
|
config.json
CHANGED
|
@@ -28,6 +28,6 @@
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.38.2",
|
| 31 |
-
"use_cache":
|
| 32 |
"vocab_size": 84608
|
| 33 |
}
|
|
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.38.2",
|
| 31 |
+
"use_cache": false,
|
| 32 |
"vocab_size": 84608
|
| 33 |
}
|
model-00001-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4956085824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:872d4d9e59411a02a34efe2a6317a0b3b51373c460bd6a44b9a1ccc13c9a4a9f
|
| 3 |
size 4956085824
|
model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4981032096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dc91ca31d512351dc69b1d68ffe8e530d965c0d6afaf2edb67aabbbea494e51
|
| 3 |
size 4981032096
|
model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4928602984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4532de965f51ebdf97f3672e3d4d658526461471c4e6922bb1bf1da22bbf3fd
|
| 3 |
size 4928602984
|
model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4928602976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5401498c6d08d08e849b474bcca596b3697531d5a91f3dc920d7576d996822f9
|
| 3 |
size 4928602976
|
model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4981073320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f262e1d5ed3a678b12aa9a89bbfcf6e7f9ff5c024b4247df676e12c0b2133eb
|
| 3 |
size 4981073320
|
model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4222060984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74f117fa0211eceb4a2ef4b7a3f268615ae803eee801f13c9de2f126db7a0e32
|
| 3 |
size 4222060984
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 5850,
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.2146218933042934,
|
| 4 |
+
"train_runtime": 75011.8955,
|
| 5 |
"train_samples": 5850,
|
| 6 |
+
"train_samples_per_second": 0.098,
|
| 7 |
+
"train_steps_per_second": 0.012
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,319 +1,1341 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 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":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 1.
|
| 43 |
-
"loss":
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 1.
|
| 50 |
-
"loss":
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 1.
|
| 57 |
-
"loss":
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 1.
|
| 64 |
-
"loss":
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss":
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss":
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"eval_steps_per_second": 0.069,
|
| 108 |
-
"step": 62
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 1.04,
|
| 112 |
-
"grad_norm": 1.2392330789677268,
|
| 113 |
-
"learning_rate": 1.6483745493805867e-07,
|
| 114 |
-
"loss": 0.3216,
|
| 115 |
"step": 65
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch":
|
| 119 |
-
"grad_norm":
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss":
|
| 122 |
"step": 70
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"grad_norm":
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss":
|
| 129 |
"step": 75
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"grad_norm":
|
| 134 |
-
"learning_rate":
|
| 135 |
-
"loss":
|
| 136 |
"step": 80
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch":
|
| 140 |
-
"grad_norm":
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss":
|
| 143 |
"step": 85
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"grad_norm":
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss":
|
| 150 |
"step": 90
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch":
|
| 154 |
-
"grad_norm":
|
| 155 |
-
"learning_rate":
|
| 156 |
-
"loss":
|
| 157 |
"step": 95
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch":
|
| 161 |
-
"grad_norm": 1.
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
"step": 100
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"grad_norm": 1.
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss":
|
| 171 |
"step": 105
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"grad_norm": 1.
|
| 176 |
-
"learning_rate":
|
| 177 |
-
"loss":
|
| 178 |
"step": 110
|
| 179 |
},
|
| 180 |
{
|
| 181 |
-
"epoch":
|
| 182 |
-
"grad_norm": 1.
|
| 183 |
-
"learning_rate":
|
| 184 |
-
"loss":
|
| 185 |
"step": 115
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch":
|
| 189 |
-
"grad_norm": 1.
|
| 190 |
-
"learning_rate":
|
| 191 |
-
"loss":
|
| 192 |
"step": 120
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"epoch":
|
| 196 |
-
"grad_norm": 1.
|
| 197 |
-
"learning_rate":
|
| 198 |
-
"loss":
|
| 199 |
-
"step": 125
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 2.0,
|
| 203 |
-
"eval_loss": 0.18834702670574188,
|
| 204 |
-
"eval_runtime": 131.135,
|
| 205 |
-
"eval_samples_per_second": 0.275,
|
| 206 |
-
"eval_steps_per_second": 0.069,
|
| 207 |
"step": 125
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"grad_norm": 1.
|
| 212 |
-
"learning_rate":
|
| 213 |
-
"loss":
|
| 214 |
"step": 130
|
| 215 |
},
|
| 216 |
{
|
| 217 |
-
"epoch":
|
| 218 |
-
"grad_norm": 1.
|
| 219 |
-
"learning_rate": 4.
|
| 220 |
-
"loss":
|
| 221 |
"step": 135
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch":
|
| 225 |
-
"grad_norm": 1.
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss":
|
| 228 |
"step": 140
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch":
|
| 232 |
-
"grad_norm": 1.
|
| 233 |
-
"learning_rate":
|
| 234 |
-
"loss":
|
| 235 |
"step": 145
|
| 236 |
},
|
| 237 |
{
|
| 238 |
-
"epoch":
|
| 239 |
-
"grad_norm": 1.
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss":
|
| 242 |
"step": 150
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"grad_norm": 1.
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss":
|
| 249 |
"step": 155
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"grad_norm": 1.
|
| 254 |
-
"learning_rate":
|
| 255 |
-
"loss":
|
| 256 |
"step": 160
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch":
|
| 260 |
-
"grad_norm": 1.
|
| 261 |
-
"learning_rate":
|
| 262 |
-
"loss":
|
| 263 |
"step": 165
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch":
|
| 267 |
-
"grad_norm": 1.
|
| 268 |
-
"learning_rate": 4.
|
| 269 |
-
"loss":
|
| 270 |
"step": 170
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"epoch":
|
| 274 |
-
"grad_norm": 1.
|
| 275 |
-
"learning_rate":
|
| 276 |
-
"loss":
|
| 277 |
"step": 175
|
| 278 |
},
|
| 279 |
{
|
| 280 |
-
"epoch":
|
| 281 |
-
"grad_norm": 1.
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss":
|
| 284 |
"step": 180
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"grad_norm": 1.
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss":
|
| 291 |
"step": 185
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch":
|
| 295 |
-
"
|
| 296 |
-
"
|
| 297 |
-
"
|
| 298 |
-
"
|
| 299 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 2.98,
|
| 303 |
-
"
|
| 304 |
-
"
|
| 305 |
-
"
|
| 306 |
-
"
|
| 307 |
-
|
| 308 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 309 |
}
|
| 310 |
],
|
| 311 |
"logging_steps": 5,
|
| 312 |
-
"max_steps":
|
| 313 |
"num_input_tokens_seen": 0,
|
| 314 |
"num_train_epochs": 3,
|
| 315 |
-
"save_steps":
|
| 316 |
-
"total_flos":
|
| 317 |
"train_batch_size": 1,
|
| 318 |
"trial_name": null,
|
| 319 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9950900163666123,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 915,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 16.716502969210488,
|
| 14 |
+
"learning_rate": 5.4347826086956515e-09,
|
| 15 |
+
"loss": 2.043,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 15.483069924073853,
|
| 21 |
+
"learning_rate": 2.717391304347826e-08,
|
| 22 |
+
"loss": 2.0144,
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 14.970955440826483,
|
| 28 |
+
"learning_rate": 5.434782608695652e-08,
|
| 29 |
+
"loss": 2.0252,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.05,
|
| 34 |
+
"grad_norm": 16.409859521687437,
|
| 35 |
+
"learning_rate": 8.152173913043478e-08,
|
| 36 |
+
"loss": 2.0317,
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.07,
|
| 41 |
+
"grad_norm": 15.119202061638624,
|
| 42 |
+
"learning_rate": 1.0869565217391303e-07,
|
| 43 |
+
"loss": 2.0122,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.08,
|
| 48 |
+
"grad_norm": 14.957507881730114,
|
| 49 |
+
"learning_rate": 1.358695652173913e-07,
|
| 50 |
+
"loss": 1.9709,
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"grad_norm": 13.274098507749727,
|
| 56 |
+
"learning_rate": 1.6304347826086955e-07,
|
| 57 |
+
"loss": 1.9688,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.11,
|
| 62 |
+
"grad_norm": 14.11477451327087,
|
| 63 |
+
"learning_rate": 1.9021739130434784e-07,
|
| 64 |
+
"loss": 1.9494,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.13,
|
| 69 |
+
"grad_norm": 8.88731632748161,
|
| 70 |
+
"learning_rate": 2.1739130434782607e-07,
|
| 71 |
+
"loss": 1.9168,
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.15,
|
| 76 |
+
"grad_norm": 7.911411675554511,
|
| 77 |
+
"learning_rate": 2.445652173913043e-07,
|
| 78 |
+
"loss": 1.8351,
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.16,
|
| 83 |
+
"grad_norm": 7.272959783180739,
|
| 84 |
+
"learning_rate": 2.717391304347826e-07,
|
| 85 |
+
"loss": 1.796,
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.18,
|
| 90 |
+
"grad_norm": 6.735025921958398,
|
| 91 |
+
"learning_rate": 2.9891304347826084e-07,
|
| 92 |
+
"loss": 1.756,
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.2,
|
| 97 |
+
"grad_norm": 4.788928779270596,
|
| 98 |
+
"learning_rate": 3.260869565217391e-07,
|
| 99 |
+
"loss": 1.7134,
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.21,
|
| 104 |
+
"grad_norm": 3.8456380127229584,
|
| 105 |
+
"learning_rate": 3.532608695652174e-07,
|
| 106 |
+
"loss": 1.654,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.23,
|
| 111 |
+
"grad_norm": 3.513598430455612,
|
| 112 |
+
"learning_rate": 3.8043478260869567e-07,
|
| 113 |
+
"loss": 1.62,
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.25,
|
| 118 |
+
"grad_norm": 3.2709987769023225,
|
| 119 |
+
"learning_rate": 4.076086956521739e-07,
|
| 120 |
+
"loss": 1.6021,
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.26,
|
| 125 |
+
"grad_norm": 2.6615496338038342,
|
| 126 |
+
"learning_rate": 4.3478260869565214e-07,
|
| 127 |
+
"loss": 1.5568,
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.28,
|
| 132 |
+
"grad_norm": 2.164065581831568,
|
| 133 |
+
"learning_rate": 4.619565217391304e-07,
|
| 134 |
+
"loss": 1.528,
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"grad_norm": 2.0800819028364823,
|
| 140 |
+
"learning_rate": 4.891304347826087e-07,
|
| 141 |
+
"loss": 1.4875,
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.31,
|
| 146 |
+
"grad_norm": 2.011052602558943,
|
| 147 |
+
"learning_rate": 4.999836073996402e-07,
|
| 148 |
+
"loss": 1.5089,
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.33,
|
| 153 |
+
"grad_norm": 1.7314022698124276,
|
| 154 |
+
"learning_rate": 4.998834381823981e-07,
|
| 155 |
+
"loss": 1.4765,
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.34,
|
| 160 |
+
"grad_norm": 1.698172314244185,
|
| 161 |
+
"learning_rate": 4.99692243192814e-07,
|
| 162 |
+
"loss": 1.479,
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.36,
|
| 167 |
+
"grad_norm": 1.5924897184805729,
|
| 168 |
+
"learning_rate": 4.994100920780472e-07,
|
| 169 |
+
"loss": 1.4313,
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.38,
|
| 174 |
+
"grad_norm": 1.6198237756392246,
|
| 175 |
+
"learning_rate": 4.99037087618111e-07,
|
| 176 |
+
"loss": 1.405,
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.39,
|
| 181 |
+
"grad_norm": 1.6433214339592699,
|
| 182 |
+
"learning_rate": 4.985733656884334e-07,
|
| 183 |
+
"loss": 1.4268,
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.41,
|
| 188 |
+
"grad_norm": 1.585215905595777,
|
| 189 |
+
"learning_rate": 4.980190952103605e-07,
|
| 190 |
+
"loss": 1.4092,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.43,
|
| 195 |
+
"grad_norm": 1.6305731412306417,
|
| 196 |
+
"learning_rate": 4.973744780896238e-07,
|
| 197 |
+
"loss": 1.3617,
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.44,
|
| 202 |
+
"grad_norm": 1.583823751699642,
|
| 203 |
+
"learning_rate": 4.966397491427908e-07,
|
| 204 |
+
"loss": 1.3597,
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.46,
|
| 209 |
+
"grad_norm": 1.484959829645435,
|
| 210 |
+
"learning_rate": 4.958151760117285e-07,
|
| 211 |
+
"loss": 1.3353,
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.47,
|
| 216 |
+
"grad_norm": 1.4342113311109135,
|
| 217 |
+
"learning_rate": 4.949010590661078e-07,
|
| 218 |
+
"loss": 1.3029,
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.49,
|
| 223 |
+
"grad_norm": 1.379625137958501,
|
| 224 |
+
"learning_rate": 4.938977312939872e-07,
|
| 225 |
+
"loss": 1.2749,
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.51,
|
| 230 |
+
"grad_norm": 1.2678627597286303,
|
| 231 |
+
"learning_rate": 4.928055581805149e-07,
|
| 232 |
+
"loss": 1.2539,
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.52,
|
| 237 |
+
"grad_norm": 1.1977112273152672,
|
| 238 |
+
"learning_rate": 4.916249375747916e-07,
|
| 239 |
+
"loss": 1.2506,
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.54,
|
| 244 |
+
"grad_norm": 1.2424603760621953,
|
| 245 |
+
"learning_rate": 4.903562995449452e-07,
|
| 246 |
+
"loss": 1.2563,
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.56,
|
| 251 |
+
"grad_norm": 1.1271206534398783,
|
| 252 |
+
"learning_rate": 4.890001062214688e-07,
|
| 253 |
+
"loss": 1.2476,
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.57,
|
| 258 |
+
"grad_norm": 1.1518448899554141,
|
| 259 |
+
"learning_rate": 4.875568516288789e-07,
|
| 260 |
+
"loss": 1.2349,
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.59,
|
| 265 |
+
"grad_norm": 1.1817144244682463,
|
| 266 |
+
"learning_rate": 4.860270615057555e-07,
|
| 267 |
+
"loss": 1.2165,
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.61,
|
| 272 |
+
"grad_norm": 1.1263459506930984,
|
| 273 |
+
"learning_rate": 4.844112931132302e-07,
|
| 274 |
+
"loss": 1.2187,
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.62,
|
| 279 |
+
"grad_norm": 1.0547482535639097,
|
| 280 |
+
"learning_rate": 4.827101350319902e-07,
|
| 281 |
+
"loss": 1.2125,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.64,
|
| 286 |
+
"grad_norm": 1.1000431029318167,
|
| 287 |
+
"learning_rate": 4.809242069478755e-07,
|
| 288 |
+
"loss": 1.2012,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.65,
|
| 293 |
+
"grad_norm": 1.1158408603050054,
|
| 294 |
+
"learning_rate": 4.790541594261431e-07,
|
| 295 |
+
"loss": 1.2363,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.67,
|
| 300 |
+
"grad_norm": 1.1038133372547887,
|
| 301 |
+
"learning_rate": 4.771006736744841e-07,
|
| 302 |
+
"loss": 1.2126,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.69,
|
| 307 |
+
"grad_norm": 1.0325798408972995,
|
| 308 |
+
"learning_rate": 4.7506446129487827e-07,
|
| 309 |
+
"loss": 1.1925,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7,
|
| 314 |
+
"grad_norm": 1.0244158176654672,
|
| 315 |
+
"learning_rate": 4.7294626402437656e-07,
|
| 316 |
+
"loss": 1.2129,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.72,
|
| 321 |
+
"grad_norm": 1.004472026312722,
|
| 322 |
+
"learning_rate": 4.707468534649062e-07,
|
| 323 |
+
"loss": 1.1808,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.74,
|
| 328 |
+
"grad_norm": 1.0183080167380476,
|
| 329 |
+
"learning_rate": 4.684670308021974e-07,
|
| 330 |
+
"loss": 1.1993,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.75,
|
| 335 |
+
"grad_norm": 0.9917433442773201,
|
| 336 |
+
"learning_rate": 4.6610762651393285e-07,
|
| 337 |
+
"loss": 1.2014,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.77,
|
| 342 |
+
"grad_norm": 0.9652304321103495,
|
| 343 |
+
"learning_rate": 4.6366950006722716e-07,
|
| 344 |
+
"loss": 1.1899,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.79,
|
| 349 |
+
"grad_norm": 1.0030899254957348,
|
| 350 |
+
"learning_rate": 4.611535396055463e-07,
|
| 351 |
+
"loss": 1.1807,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8,
|
| 356 |
+
"grad_norm": 0.9792294017825395,
|
| 357 |
+
"learning_rate": 4.58560661625181e-07,
|
| 358 |
+
"loss": 1.1865,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.82,
|
| 363 |
+
"grad_norm": 1.0234204375359932,
|
| 364 |
+
"learning_rate": 4.5589181064139187e-07,
|
| 365 |
+
"loss": 1.1911,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.83,
|
| 370 |
+
"grad_norm": 1.001857550343514,
|
| 371 |
+
"learning_rate": 4.531479588443483e-07,
|
| 372 |
+
"loss": 1.1784,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.85,
|
| 377 |
+
"grad_norm": 1.0265204712627047,
|
| 378 |
+
"learning_rate": 4.503301057449855e-07,
|
| 379 |
+
"loss": 1.1776,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.87,
|
| 384 |
+
"grad_norm": 0.9768188781212096,
|
| 385 |
+
"learning_rate": 4.474392778109101e-07,
|
| 386 |
+
"loss": 1.205,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.88,
|
| 391 |
+
"grad_norm": 0.9711825909852003,
|
| 392 |
+
"learning_rate": 4.444765280924855e-07,
|
| 393 |
+
"loss": 1.1848,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9,
|
| 398 |
+
"grad_norm": 1.0406571418053925,
|
| 399 |
+
"learning_rate": 4.4144293583923455e-07,
|
| 400 |
+
"loss": 1.172,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.92,
|
| 405 |
+
"grad_norm": 0.9599694708712767,
|
| 406 |
+
"learning_rate": 4.383396061066974e-07,
|
| 407 |
+
"loss": 1.1803,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.93,
|
| 412 |
+
"grad_norm": 0.9804601001635962,
|
| 413 |
+
"learning_rate": 4.351676693538906e-07,
|
| 414 |
+
"loss": 1.1799,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.95,
|
| 419 |
+
"grad_norm": 0.9277200983575595,
|
| 420 |
+
"learning_rate": 4.319282810315109e-07,
|
| 421 |
+
"loss": 1.1757,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.97,
|
| 426 |
+
"grad_norm": 0.9052931929609641,
|
| 427 |
+
"learning_rate": 4.286226211610358e-07,
|
| 428 |
+
"loss": 1.1647,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.98,
|
| 433 |
+
"grad_norm": 0.9475606426644578,
|
| 434 |
+
"learning_rate": 4.2525189390487403e-07,
|
| 435 |
+
"loss": 1.1868,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.0,
|
| 440 |
+
"grad_norm": 0.9480095438475787,
|
| 441 |
+
"learning_rate": 4.2181732712772155e-07,
|
| 442 |
+
"loss": 1.1777,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0,
|
| 447 |
+
"eval_loss": 1.1991753578186035,
|
| 448 |
+
"eval_runtime": 552.5832,
|
| 449 |
+
"eval_samples_per_second": 0.385,
|
| 450 |
+
"eval_steps_per_second": 0.098,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.01,
|
| 455 |
+
"grad_norm": 0.9649853251126954,
|
| 456 |
+
"learning_rate": 4.183201719492837e-07,
|
| 457 |
+
"loss": 1.1908,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.03,
|
| 462 |
+
"grad_norm": 0.9307973686987313,
|
| 463 |
+
"learning_rate": 4.147617022885261e-07,
|
| 464 |
+
"loss": 1.1392,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.05,
|
| 469 |
+
"grad_norm": 0.9374655856787941,
|
| 470 |
+
"learning_rate": 4.1114321439962085e-07,
|
| 471 |
+
"loss": 1.1333,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.06,
|
| 476 |
+
"grad_norm": 0.9496571637434005,
|
| 477 |
+
"learning_rate": 4.0746602639975547e-07,
|
| 478 |
+
"loss": 1.1656,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.08,
|
| 483 |
+
"grad_norm": 0.9262061183605496,
|
| 484 |
+
"learning_rate": 4.037314777889792e-07,
|
| 485 |
+
"loss": 1.1466,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.1,
|
| 490 |
+
"grad_norm": 0.921853250947036,
|
| 491 |
+
"learning_rate": 3.999409289622591e-07,
|
| 492 |
+
"loss": 1.1178,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.11,
|
| 497 |
+
"grad_norm": 0.921849981902405,
|
| 498 |
+
"learning_rate": 3.9609576071392493e-07,
|
| 499 |
+
"loss": 1.1624,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.13,
|
| 504 |
+
"grad_norm": 0.9093850424200817,
|
| 505 |
+
"learning_rate": 3.921973737346832e-07,
|
| 506 |
+
"loss": 1.1383,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.15,
|
| 511 |
+
"grad_norm": 0.9486739204504845,
|
| 512 |
+
"learning_rate": 3.8824718810138367e-07,
|
| 513 |
+
"loss": 1.1391,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.16,
|
| 518 |
+
"grad_norm": 0.9765974188105699,
|
| 519 |
+
"learning_rate": 3.8424664275972345e-07,
|
| 520 |
+
"loss": 1.1773,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.18,
|
| 525 |
+
"grad_norm": 0.9573534898626346,
|
| 526 |
+
"learning_rate": 3.801971950000783e-07,
|
| 527 |
+
"loss": 1.1564,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.19,
|
| 532 |
+
"grad_norm": 0.91608560372732,
|
| 533 |
+
"learning_rate": 3.7610031992665106e-07,
|
| 534 |
+
"loss": 1.1595,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.21,
|
| 539 |
+
"grad_norm": 0.922365401205156,
|
| 540 |
+
"learning_rate": 3.719575099201309e-07,
|
| 541 |
+
"loss": 1.1458,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.23,
|
| 546 |
+
"grad_norm": 0.8960246173391375,
|
| 547 |
+
"learning_rate": 3.677702740940603e-07,
|
| 548 |
+
"loss": 1.1707,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.24,
|
| 553 |
+
"grad_norm": 0.9375786732342487,
|
| 554 |
+
"learning_rate": 3.6354013774510455e-07,
|
| 555 |
+
"loss": 1.1816,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.26,
|
| 560 |
+
"grad_norm": 0.9357396217542764,
|
| 561 |
+
"learning_rate": 3.5926864179742864e-07,
|
| 562 |
+
"loss": 1.1486,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.28,
|
| 567 |
+
"grad_norm": 0.9231104901219429,
|
| 568 |
+
"learning_rate": 3.549573422413795e-07,
|
| 569 |
+
"loss": 1.1499,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.29,
|
| 574 |
+
"grad_norm": 0.871929206362279,
|
| 575 |
+
"learning_rate": 3.506078095666812e-07,
|
| 576 |
+
"loss": 1.1392,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.31,
|
| 581 |
+
"grad_norm": 0.9066352806550632,
|
| 582 |
+
"learning_rate": 3.4622162819034807e-07,
|
| 583 |
+
"loss": 1.1309,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.33,
|
| 588 |
+
"grad_norm": 0.9173513698176368,
|
| 589 |
+
"learning_rate": 3.418003958795243e-07,
|
| 590 |
+
"loss": 1.1397,
|
| 591 |
+
"step": 405
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.34,
|
| 595 |
+
"grad_norm": 0.9113976210277046,
|
| 596 |
+
"learning_rate": 3.3734572316946073e-07,
|
| 597 |
+
"loss": 1.1575,
|
| 598 |
+
"step": 410
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.36,
|
| 602 |
+
"grad_norm": 0.9178151730113013,
|
| 603 |
+
"learning_rate": 3.328592327768405e-07,
|
| 604 |
+
"loss": 1.1377,
|
| 605 |
+
"step": 415
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.37,
|
| 609 |
+
"grad_norm": 0.9007526310368873,
|
| 610 |
+
"learning_rate": 3.2834255900866716e-07,
|
| 611 |
+
"loss": 1.1319,
|
| 612 |
+
"step": 420
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.39,
|
| 616 |
+
"grad_norm": 0.9174055759076049,
|
| 617 |
+
"learning_rate": 3.2379734716693075e-07,
|
| 618 |
+
"loss": 1.1325,
|
| 619 |
+
"step": 425
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.41,
|
| 623 |
+
"grad_norm": 0.8949717617571301,
|
| 624 |
+
"learning_rate": 3.1922525294926936e-07,
|
| 625 |
+
"loss": 1.1248,
|
| 626 |
+
"step": 430
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.42,
|
| 630 |
+
"grad_norm": 0.9421266219905364,
|
| 631 |
+
"learning_rate": 3.146279418458428e-07,
|
| 632 |
+
"loss": 1.1356,
|
| 633 |
+
"step": 435
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.44,
|
| 637 |
+
"grad_norm": 0.939956376079189,
|
| 638 |
+
"learning_rate": 3.100070885326395e-07,
|
| 639 |
+
"loss": 1.1333,
|
| 640 |
+
"step": 440
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.46,
|
| 644 |
+
"grad_norm": 0.8908860472024647,
|
| 645 |
+
"learning_rate": 3.053643762614381e-07,
|
| 646 |
+
"loss": 1.1244,
|
| 647 |
+
"step": 445
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.47,
|
| 651 |
+
"grad_norm": 0.854957997046981,
|
| 652 |
+
"learning_rate": 3.0070149624664367e-07,
|
| 653 |
+
"loss": 1.116,
|
| 654 |
+
"step": 450
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.49,
|
| 658 |
+
"grad_norm": 0.9824002406797512,
|
| 659 |
+
"learning_rate": 2.9602014704922413e-07,
|
| 660 |
+
"loss": 1.1351,
|
| 661 |
+
"step": 455
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.51,
|
| 665 |
+
"grad_norm": 0.9473931201675668,
|
| 666 |
+
"learning_rate": 2.913220339579712e-07,
|
| 667 |
+
"loss": 1.1486,
|
| 668 |
+
"step": 460
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.52,
|
| 672 |
+
"grad_norm": 0.9614723238274686,
|
| 673 |
+
"learning_rate": 2.866088683683088e-07,
|
| 674 |
+
"loss": 1.1278,
|
| 675 |
+
"step": 465
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.54,
|
| 679 |
+
"grad_norm": 0.8966403120315597,
|
| 680 |
+
"learning_rate": 2.8188236715887897e-07,
|
| 681 |
+
"loss": 1.1502,
|
| 682 |
+
"step": 470
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.55,
|
| 686 |
+
"grad_norm": 0.9113074954319733,
|
| 687 |
+
"learning_rate": 2.7714425206612884e-07,
|
| 688 |
+
"loss": 1.1477,
|
| 689 |
+
"step": 475
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.57,
|
| 693 |
+
"grad_norm": 0.9277072403986325,
|
| 694 |
+
"learning_rate": 2.7239624905712885e-07,
|
| 695 |
+
"loss": 1.1326,
|
| 696 |
+
"step": 480
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.59,
|
| 700 |
+
"grad_norm": 0.8933150404518155,
|
| 701 |
+
"learning_rate": 2.6764008770084986e-07,
|
| 702 |
+
"loss": 1.1122,
|
| 703 |
+
"step": 485
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6,
|
| 707 |
+
"grad_norm": 0.9423200783026597,
|
| 708 |
+
"learning_rate": 2.6287750053812746e-07,
|
| 709 |
+
"loss": 1.1319,
|
| 710 |
+
"step": 490
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.62,
|
| 714 |
+
"grad_norm": 0.9138649347681606,
|
| 715 |
+
"learning_rate": 2.581102224505449e-07,
|
| 716 |
+
"loss": 1.0938,
|
| 717 |
+
"step": 495
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.64,
|
| 721 |
+
"grad_norm": 0.9218456828673846,
|
| 722 |
+
"learning_rate": 2.5333999002846235e-07,
|
| 723 |
+
"loss": 1.124,
|
| 724 |
+
"step": 500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.65,
|
| 728 |
+
"grad_norm": 0.8863039794287404,
|
| 729 |
+
"learning_rate": 2.4856854093842373e-07,
|
| 730 |
+
"loss": 1.1149,
|
| 731 |
+
"step": 505
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.67,
|
| 735 |
+
"grad_norm": 0.8502000094018759,
|
| 736 |
+
"learning_rate": 2.4379761329017255e-07,
|
| 737 |
+
"loss": 1.1067,
|
| 738 |
+
"step": 510
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.69,
|
| 742 |
+
"grad_norm": 0.9252138466436688,
|
| 743 |
+
"learning_rate": 2.3902894500350516e-07,
|
| 744 |
+
"loss": 1.1103,
|
| 745 |
+
"step": 515
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.7,
|
| 749 |
+
"grad_norm": 0.8961237196153136,
|
| 750 |
+
"learning_rate": 2.342642731751933e-07,
|
| 751 |
+
"loss": 1.0985,
|
| 752 |
+
"step": 520
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.72,
|
| 756 |
+
"grad_norm": 0.869866335392851,
|
| 757 |
+
"learning_rate": 2.2950533344620754e-07,
|
| 758 |
+
"loss": 1.1104,
|
| 759 |
+
"step": 525
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.73,
|
| 763 |
+
"grad_norm": 0.9315973913649565,
|
| 764 |
+
"learning_rate": 2.247538593694695e-07,
|
| 765 |
+
"loss": 1.0717,
|
| 766 |
+
"step": 530
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.75,
|
| 770 |
+
"grad_norm": 0.8902726821310524,
|
| 771 |
+
"learning_rate": 2.2001158177836596e-07,
|
| 772 |
+
"loss": 1.129,
|
| 773 |
+
"step": 535
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.77,
|
| 777 |
+
"grad_norm": 0.9195027929003787,
|
| 778 |
+
"learning_rate": 2.1528022815625303e-07,
|
| 779 |
+
"loss": 1.1016,
|
| 780 |
+
"step": 540
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.78,
|
| 784 |
+
"grad_norm": 0.8626744756177651,
|
| 785 |
+
"learning_rate": 2.1056152200718018e-07,
|
| 786 |
+
"loss": 1.118,
|
| 787 |
+
"step": 545
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.8,
|
| 791 |
+
"grad_norm": 0.8633291274404195,
|
| 792 |
+
"learning_rate": 2.0585718222806528e-07,
|
| 793 |
+
"loss": 1.0894,
|
| 794 |
+
"step": 550
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.82,
|
| 798 |
+
"grad_norm": 0.9198499710986737,
|
| 799 |
+
"learning_rate": 2.0116892248254639e-07,
|
| 800 |
+
"loss": 1.1263,
|
| 801 |
+
"step": 555
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.83,
|
| 805 |
+
"grad_norm": 0.8725009093818972,
|
| 806 |
+
"learning_rate": 1.964984505767405e-07,
|
| 807 |
+
"loss": 1.0881,
|
| 808 |
+
"step": 560
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.85,
|
| 812 |
+
"grad_norm": 0.8481882368797279,
|
| 813 |
+
"learning_rate": 1.91847467837136e-07,
|
| 814 |
+
"loss": 1.0855,
|
| 815 |
+
"step": 565
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.87,
|
| 819 |
+
"grad_norm": 0.9323691915343033,
|
| 820 |
+
"learning_rate": 1.8721766849084592e-07,
|
| 821 |
+
"loss": 1.1097,
|
| 822 |
+
"step": 570
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.88,
|
| 826 |
+
"grad_norm": 0.9005669510238986,
|
| 827 |
+
"learning_rate": 1.8261073904844626e-07,
|
| 828 |
+
"loss": 1.1016,
|
| 829 |
+
"step": 575
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.9,
|
| 833 |
+
"grad_norm": 0.9505847371717607,
|
| 834 |
+
"learning_rate": 1.7802835768962628e-07,
|
| 835 |
+
"loss": 1.0998,
|
| 836 |
+
"step": 580
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.91,
|
| 840 |
+
"grad_norm": 0.9020674746183535,
|
| 841 |
+
"learning_rate": 1.7347219365187282e-07,
|
| 842 |
+
"loss": 1.1284,
|
| 843 |
+
"step": 585
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.93,
|
| 847 |
+
"grad_norm": 0.8913471215755544,
|
| 848 |
+
"learning_rate": 1.689439066224122e-07,
|
| 849 |
+
"loss": 1.1095,
|
| 850 |
+
"step": 590
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.95,
|
| 854 |
+
"grad_norm": 0.9156453302935215,
|
| 855 |
+
"learning_rate": 1.6444514613363143e-07,
|
| 856 |
+
"loss": 1.1152,
|
| 857 |
+
"step": 595
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.96,
|
| 861 |
+
"grad_norm": 0.8754536183127603,
|
| 862 |
+
"learning_rate": 1.5997755096219792e-07,
|
| 863 |
+
"loss": 1.0841,
|
| 864 |
+
"step": 600
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.98,
|
| 868 |
+
"grad_norm": 0.8389293727280541,
|
| 869 |
+
"learning_rate": 1.5554274853209775e-07,
|
| 870 |
+
"loss": 1.1028,
|
| 871 |
+
"step": 605
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.0,
|
| 875 |
+
"grad_norm": 0.91364223904081,
|
| 876 |
+
"learning_rate": 1.5114235432180879e-07,
|
| 877 |
+
"loss": 1.1046,
|
| 878 |
+
"step": 610
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"eval_loss": 1.1457586288452148,
|
| 883 |
+
"eval_runtime": 552.4602,
|
| 884 |
+
"eval_samples_per_second": 0.386,
|
| 885 |
+
"eval_steps_per_second": 0.098,
|
| 886 |
+
"step": 611
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.01,
|
| 890 |
+
"grad_norm": 0.8685324682917593,
|
| 891 |
+
"learning_rate": 1.4677797127582592e-07,
|
| 892 |
+
"loss": 1.1065,
|
| 893 |
+
"step": 615
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.03,
|
| 897 |
+
"grad_norm": 0.881396936654864,
|
| 898 |
+
"learning_rate": 1.4245118922075167e-07,
|
| 899 |
+
"loss": 1.1062,
|
| 900 |
+
"step": 620
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.05,
|
| 904 |
+
"grad_norm": 0.8605768115061145,
|
| 905 |
+
"learning_rate": 1.3816358428616555e-07,
|
| 906 |
+
"loss": 1.1139,
|
| 907 |
+
"step": 625
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.06,
|
| 911 |
+
"grad_norm": 0.8695988343532115,
|
| 912 |
+
"learning_rate": 1.3391671833048222e-07,
|
| 913 |
+
"loss": 1.1026,
|
| 914 |
+
"step": 630
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.08,
|
| 918 |
+
"grad_norm": 0.9277463151512839,
|
| 919 |
+
"learning_rate": 1.2971213837200966e-07,
|
| 920 |
+
"loss": 1.1171,
|
| 921 |
+
"step": 635
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.09,
|
| 925 |
+
"grad_norm": 0.8936560541708038,
|
| 926 |
+
"learning_rate": 1.255513760254111e-07,
|
| 927 |
+
"loss": 1.1141,
|
| 928 |
+
"step": 640
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.11,
|
| 932 |
+
"grad_norm": 0.8783043744127691,
|
| 933 |
+
"learning_rate": 1.2143594694378035e-07,
|
| 934 |
+
"loss": 1.0913,
|
| 935 |
+
"step": 645
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.13,
|
| 939 |
+
"grad_norm": 0.8926718750269779,
|
| 940 |
+
"learning_rate": 1.1736735026652975e-07,
|
| 941 |
+
"loss": 1.0963,
|
| 942 |
+
"step": 650
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.14,
|
| 946 |
+
"grad_norm": 0.8891415780653408,
|
| 947 |
+
"learning_rate": 1.133470680732943e-07,
|
| 948 |
+
"loss": 1.1072,
|
| 949 |
+
"step": 655
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.16,
|
| 953 |
+
"grad_norm": 0.9510568294433623,
|
| 954 |
+
"learning_rate": 1.0937656484405083e-07,
|
| 955 |
+
"loss": 1.0701,
|
| 956 |
+
"step": 660
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.18,
|
| 960 |
+
"grad_norm": 0.8861055353381297,
|
| 961 |
+
"learning_rate": 1.0545728692564632e-07,
|
| 962 |
+
"loss": 1.1009,
|
| 963 |
+
"step": 665
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.19,
|
| 967 |
+
"grad_norm": 0.9135875600693542,
|
| 968 |
+
"learning_rate": 1.015906620049343e-07,
|
| 969 |
+
"loss": 1.0917,
|
| 970 |
+
"step": 670
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.21,
|
| 974 |
+
"grad_norm": 0.8715772657210394,
|
| 975 |
+
"learning_rate": 9.777809858870623e-08,
|
| 976 |
+
"loss": 1.0873,
|
| 977 |
+
"step": 675
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.23,
|
| 981 |
+
"grad_norm": 0.8496453955301547,
|
| 982 |
+
"learning_rate": 9.402098549061083e-08,
|
| 983 |
+
"loss": 1.0874,
|
| 984 |
+
"step": 680
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.24,
|
| 988 |
+
"grad_norm": 0.8627541455935185,
|
| 989 |
+
"learning_rate": 9.032069132524728e-08,
|
| 990 |
+
"loss": 1.0828,
|
| 991 |
+
"step": 685
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.26,
|
| 995 |
+
"grad_norm": 0.8953058627119301,
|
| 996 |
+
"learning_rate": 8.667856400961507e-08,
|
| 997 |
+
"loss": 1.0636,
|
| 998 |
+
"step": 690
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.27,
|
| 1002 |
+
"grad_norm": 0.9074456406630441,
|
| 1003 |
+
"learning_rate": 8.309593027210543e-08,
|
| 1004 |
+
"loss": 1.0984,
|
| 1005 |
+
"step": 695
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.29,
|
| 1009 |
+
"grad_norm": 0.885202959051119,
|
| 1010 |
+
"learning_rate": 7.957409516920921e-08,
|
| 1011 |
+
"loss": 1.0898,
|
| 1012 |
+
"step": 700
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.31,
|
| 1016 |
+
"grad_norm": 0.8664959542867797,
|
| 1017 |
+
"learning_rate": 7.611434161012045e-08,
|
| 1018 |
+
"loss": 1.1019,
|
| 1019 |
+
"step": 705
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.32,
|
| 1023 |
+
"grad_norm": 0.8687463126064324,
|
| 1024 |
+
"learning_rate": 7.271792988940755e-08,
|
| 1025 |
+
"loss": 1.0725,
|
| 1026 |
+
"step": 710
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.34,
|
| 1030 |
+
"grad_norm": 0.9668961175895807,
|
| 1031 |
+
"learning_rate": 6.93860972279214e-08,
|
| 1032 |
+
"loss": 1.1063,
|
| 1033 |
+
"step": 715
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.36,
|
| 1037 |
+
"grad_norm": 0.9709686806435888,
|
| 1038 |
+
"learning_rate": 6.612005732211015e-08,
|
| 1039 |
+
"loss": 1.1057,
|
| 1040 |
+
"step": 720
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.37,
|
| 1044 |
+
"grad_norm": 0.8789480605794918,
|
| 1045 |
+
"learning_rate": 6.292099990190178e-08,
|
| 1046 |
+
"loss": 1.1014,
|
| 1047 |
+
"step": 725
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.39,
|
| 1051 |
+
"grad_norm": 0.8557651308313651,
|
| 1052 |
+
"learning_rate": 5.979009029731789e-08,
|
| 1053 |
+
"loss": 1.099,
|
| 1054 |
+
"step": 730
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.41,
|
| 1058 |
+
"grad_norm": 0.821933575062032,
|
| 1059 |
+
"learning_rate": 5.6728469013975876e-08,
|
| 1060 |
+
"loss": 1.0876,
|
| 1061 |
+
"step": 735
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.42,
|
| 1065 |
+
"grad_norm": 0.9104274652488417,
|
| 1066 |
+
"learning_rate": 5.373725131763287e-08,
|
| 1067 |
+
"loss": 1.0894,
|
| 1068 |
+
"step": 740
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.44,
|
| 1072 |
+
"grad_norm": 0.881443701968621,
|
| 1073 |
+
"learning_rate": 5.081752682792542e-08,
|
| 1074 |
+
"loss": 1.087,
|
| 1075 |
+
"step": 745
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.45,
|
| 1079 |
+
"grad_norm": 0.9159497602891767,
|
| 1080 |
+
"learning_rate": 4.7970359121449924e-08,
|
| 1081 |
+
"loss": 1.121,
|
| 1082 |
+
"step": 750
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.47,
|
| 1086 |
+
"grad_norm": 0.8506596006190186,
|
| 1087 |
+
"learning_rate": 4.519678534433088e-08,
|
| 1088 |
+
"loss": 1.108,
|
| 1089 |
+
"step": 755
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.49,
|
| 1093 |
+
"grad_norm": 0.8568944137130331,
|
| 1094 |
+
"learning_rate": 4.249781583441644e-08,
|
| 1095 |
+
"loss": 1.0897,
|
| 1096 |
+
"step": 760
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.5,
|
| 1100 |
+
"grad_norm": 0.8910416600450194,
|
| 1101 |
+
"learning_rate": 3.9874433753239427e-08,
|
| 1102 |
+
"loss": 1.1024,
|
| 1103 |
+
"step": 765
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.52,
|
| 1107 |
+
"grad_norm": 0.904643756401202,
|
| 1108 |
+
"learning_rate": 3.732759472787894e-08,
|
| 1109 |
+
"loss": 1.1059,
|
| 1110 |
+
"step": 770
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.54,
|
| 1114 |
+
"grad_norm": 0.8802351411972301,
|
| 1115 |
+
"learning_rate": 3.485822650285042e-08,
|
| 1116 |
+
"loss": 1.1208,
|
| 1117 |
+
"step": 775
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.55,
|
| 1121 |
+
"grad_norm": 0.952490522578208,
|
| 1122 |
+
"learning_rate": 3.246722860215414e-08,
|
| 1123 |
+
"loss": 1.1187,
|
| 1124 |
+
"step": 780
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.57,
|
| 1128 |
+
"grad_norm": 0.8914026126857395,
|
| 1129 |
+
"learning_rate": 3.0155472001602486e-08,
|
| 1130 |
+
"loss": 1.1034,
|
| 1131 |
+
"step": 785
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.59,
|
| 1135 |
+
"grad_norm": 0.8960856771418554,
|
| 1136 |
+
"learning_rate": 2.7923798811547105e-08,
|
| 1137 |
+
"loss": 1.106,
|
| 1138 |
+
"step": 790
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.6,
|
| 1142 |
+
"grad_norm": 0.8524261428700936,
|
| 1143 |
+
"learning_rate": 2.5773021970121266e-08,
|
| 1144 |
+
"loss": 1.1115,
|
| 1145 |
+
"step": 795
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.62,
|
| 1149 |
+
"grad_norm": 0.8753031757673515,
|
| 1150 |
+
"learning_rate": 2.3703924947108044e-08,
|
| 1151 |
+
"loss": 1.1139,
|
| 1152 |
+
"step": 800
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.64,
|
| 1156 |
+
"grad_norm": 0.889260017399631,
|
| 1157 |
+
"learning_rate": 2.1717261458543912e-08,
|
| 1158 |
+
"loss": 1.1165,
|
| 1159 |
+
"step": 805
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.65,
|
| 1163 |
+
"grad_norm": 0.8951574525353929,
|
| 1164 |
+
"learning_rate": 1.9813755192159803e-08,
|
| 1165 |
+
"loss": 1.0916,
|
| 1166 |
+
"step": 810
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.67,
|
| 1170 |
+
"grad_norm": 0.8577854322715776,
|
| 1171 |
+
"learning_rate": 1.7994099543761993e-08,
|
| 1172 |
+
"loss": 1.0743,
|
| 1173 |
+
"step": 815
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.68,
|
| 1177 |
+
"grad_norm": 0.8772006513774372,
|
| 1178 |
+
"learning_rate": 1.625895736464622e-08,
|
| 1179 |
+
"loss": 1.125,
|
| 1180 |
+
"step": 820
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.7,
|
| 1184 |
+
"grad_norm": 0.8752419885342775,
|
| 1185 |
+
"learning_rate": 1.4608960720139063e-08,
|
| 1186 |
+
"loss": 1.1034,
|
| 1187 |
+
"step": 825
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.72,
|
| 1191 |
+
"grad_norm": 0.8573911472670636,
|
| 1192 |
+
"learning_rate": 1.304471065935389e-08,
|
| 1193 |
+
"loss": 1.0972,
|
| 1194 |
+
"step": 830
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.73,
|
| 1198 |
+
"grad_norm": 0.8899464128181873,
|
| 1199 |
+
"learning_rate": 1.156677699624442e-08,
|
| 1200 |
+
"loss": 1.08,
|
| 1201 |
+
"step": 835
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.75,
|
| 1205 |
+
"grad_norm": 0.900376288519936,
|
| 1206 |
+
"learning_rate": 1.0175698102037473e-08,
|
| 1207 |
+
"loss": 1.0898,
|
| 1208 |
+
"step": 840
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.77,
|
| 1212 |
+
"grad_norm": 0.8624497890591514,
|
| 1213 |
+
"learning_rate": 8.87198070911857e-09,
|
| 1214 |
+
"loss": 1.0796,
|
| 1215 |
+
"step": 845
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.78,
|
| 1219 |
+
"grad_norm": 0.8848072665534406,
|
| 1220 |
+
"learning_rate": 7.656099726443071e-09,
|
| 1221 |
+
"loss": 1.1282,
|
| 1222 |
+
"step": 850
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.8,
|
| 1226 |
+
"grad_norm": 0.9099776946050603,
|
| 1227 |
+
"learning_rate": 6.528498066539962e-09,
|
| 1228 |
+
"loss": 1.1028,
|
| 1229 |
+
"step": 855
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.82,
|
| 1233 |
+
"grad_norm": 0.8819666433395044,
|
| 1234 |
+
"learning_rate": 5.4895864841703335e-09,
|
| 1235 |
+
"loss": 1.1041,
|
| 1236 |
+
"step": 860
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.83,
|
| 1240 |
+
"grad_norm": 0.864829653067709,
|
| 1241 |
+
"learning_rate": 4.539743426701048e-09,
|
| 1242 |
+
"loss": 1.0925,
|
| 1243 |
+
"step": 865
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.85,
|
| 1247 |
+
"grad_norm": 0.9179363157687722,
|
| 1248 |
+
"learning_rate": 3.6793148962462607e-09,
|
| 1249 |
+
"loss": 1.0937,
|
| 1250 |
+
"step": 870
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.86,
|
| 1254 |
+
"grad_norm": 0.8348352435305063,
|
| 1255 |
+
"learning_rate": 2.9086143236283225e-09,
|
| 1256 |
+
"loss": 1.0668,
|
| 1257 |
+
"step": 875
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.88,
|
| 1261 |
+
"grad_norm": 0.873330764161282,
|
| 1262 |
+
"learning_rate": 2.227922454203529e-09,
|
| 1263 |
+
"loss": 1.0824,
|
| 1264 |
+
"step": 880
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.9,
|
| 1268 |
+
"grad_norm": 0.8710437274036247,
|
| 1269 |
+
"learning_rate": 1.6374872455939547e-09,
|
| 1270 |
+
"loss": 1.0772,
|
| 1271 |
+
"step": 885
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.91,
|
| 1275 |
+
"grad_norm": 0.8778769609639595,
|
| 1276 |
+
"learning_rate": 1.1375237773633973e-09,
|
| 1277 |
+
"loss": 1.0961,
|
| 1278 |
+
"step": 890
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.93,
|
| 1282 |
+
"grad_norm": 0.8825077843421442,
|
| 1283 |
+
"learning_rate": 7.282141726696334e-10,
|
| 1284 |
+
"loss": 1.1155,
|
| 1285 |
+
"step": 895
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.95,
|
| 1289 |
+
"grad_norm": 0.8557847842209891,
|
| 1290 |
+
"learning_rate": 4.0970753192190456e-10,
|
| 1291 |
+
"loss": 1.0864,
|
| 1292 |
+
"step": 900
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.96,
|
| 1296 |
+
"grad_norm": 0.8808858637432918,
|
| 1297 |
+
"learning_rate": 1.8211987846766807e-10,
|
| 1298 |
+
"loss": 1.0782,
|
| 1299 |
+
"step": 905
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 2.98,
|
| 1303 |
+
"grad_norm": 0.8609393480980289,
|
| 1304 |
+
"learning_rate": 4.553411632840509e-11,
|
| 1305 |
+
"loss": 1.0913,
|
| 1306 |
+
"step": 910
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 3.0,
|
| 1310 |
+
"grad_norm": 0.8627091171927345,
|
| 1311 |
+
"learning_rate": 0.0,
|
| 1312 |
+
"loss": 1.1129,
|
| 1313 |
+
"step": 915
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 3.0,
|
| 1317 |
+
"eval_loss": 1.1385215520858765,
|
| 1318 |
+
"eval_runtime": 551.1914,
|
| 1319 |
+
"eval_samples_per_second": 0.386,
|
| 1320 |
+
"eval_steps_per_second": 0.098,
|
| 1321 |
+
"step": 915
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 3.0,
|
| 1325 |
+
"step": 915,
|
| 1326 |
+
"total_flos": 149131666391040.0,
|
| 1327 |
+
"train_loss": 1.2146218933042934,
|
| 1328 |
+
"train_runtime": 75011.8955,
|
| 1329 |
+
"train_samples_per_second": 0.098,
|
| 1330 |
+
"train_steps_per_second": 0.012
|
| 1331 |
}
|
| 1332 |
],
|
| 1333 |
"logging_steps": 5,
|
| 1334 |
+
"max_steps": 915,
|
| 1335 |
"num_input_tokens_seen": 0,
|
| 1336 |
"num_train_epochs": 3,
|
| 1337 |
+
"save_steps": 458,
|
| 1338 |
+
"total_flos": 149131666391040.0,
|
| 1339 |
"train_batch_size": 1,
|
| 1340 |
"trial_name": null,
|
| 1341 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f56f6327739e6f75b04736e33313f0b61fd3af750e41cfe0e9f87074e2d6793e
|
| 3 |
+
size 6136
|