Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +0 -9
- tokenizer_config.json +1 -9
- trainer_state.json +70 -172
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -19,10 +19,10 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"dense_h_to_4h",
|
| 23 |
"query_key_value",
|
|
|
|
| 24 |
"dense",
|
| 25 |
-
"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"query_key_value",
|
| 23 |
+
"dense_4h_to_h",
|
| 24 |
"dense",
|
| 25 |
+
"dense_h_to_4h"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134235712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def4bf80bf800e02179b9887cbcfe611765a18dfd835dfc8332a02edd88f2afd
|
| 3 |
size 134235712
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268514874
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c82e563048bc7c11c1b1313f30a9179de4fafc980081c6a57a63f364b3e9fa90
|
| 3 |
size 268514874
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2267f321ff44f0478eb689f1b92fd3a803bb3057326a871a1ce82488f0f0d08
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
|
| 3 |
size 1064
|
special_tokens_map.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -232,15 +232,6 @@
|
|
| 232 |
"rstrip": false,
|
| 233 |
"normalized": true,
|
| 234 |
"special": false
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"id": 50277,
|
| 238 |
-
"content": "[PAD]",
|
| 239 |
-
"single_word": false,
|
| 240 |
-
"lstrip": false,
|
| 241 |
-
"rstrip": false,
|
| 242 |
-
"normalized": false,
|
| 243 |
-
"special": true
|
| 244 |
}
|
| 245 |
],
|
| 246 |
"normalizer": {
|
|
|
|
| 232 |
"rstrip": false,
|
| 233 |
"normalized": true,
|
| 234 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 235 |
}
|
| 236 |
],
|
| 237 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -200,21 +200,13 @@
|
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
"special": false
|
| 203 |
-
},
|
| 204 |
-
"50277": {
|
| 205 |
-
"content": "[PAD]",
|
| 206 |
-
"lstrip": false,
|
| 207 |
-
"normalized": false,
|
| 208 |
-
"rstrip": false,
|
| 209 |
-
"single_word": false,
|
| 210 |
-
"special": true
|
| 211 |
}
|
| 212 |
},
|
| 213 |
"bos_token": "<|endoftext|>",
|
| 214 |
"clean_up_tokenization_spaces": true,
|
| 215 |
"eos_token": "<|endoftext|>",
|
| 216 |
"model_max_length": 1000000000000000019884624838656,
|
| 217 |
-
"pad_token": "
|
| 218 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 219 |
"unk_token": "<|endoftext|>"
|
| 220 |
}
|
|
|
|
| 200 |
"rstrip": false,
|
| 201 |
"single_word": false,
|
| 202 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
}
|
| 204 |
},
|
| 205 |
"bos_token": "<|endoftext|>",
|
| 206 |
"clean_up_tokenization_spaces": true,
|
| 207 |
"eos_token": "<|endoftext|>",
|
| 208 |
"model_max_length": 1000000000000000019884624838656,
|
| 209 |
+
"pad_token": "<|endoftext|>",
|
| 210 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 211 |
"unk_token": "<|endoftext|>"
|
| 212 |
}
|
trainer_state.json
CHANGED
|
@@ -1,320 +1,218 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 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 |
"learning_rate": 0.0002,
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
"learning_rate": 0.0002,
|
| 20 |
-
"loss":
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
"learning_rate": 0.0002,
|
| 26 |
-
"loss":
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
"learning_rate": 0.0002,
|
| 32 |
-
"loss":
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
"learning_rate": 0.0002,
|
| 38 |
-
"loss":
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
"learning_rate": 0.0002,
|
| 44 |
-
"loss":
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
-
"loss":
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
"learning_rate": 0.0002,
|
| 56 |
-
"loss":
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
"learning_rate": 0.0002,
|
| 62 |
-
"loss": 2.
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
"learning_rate": 0.0002,
|
| 68 |
-
"loss":
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
"learning_rate": 0.0002,
|
| 74 |
-
"loss":
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
"learning_rate": 0.0002,
|
| 80 |
-
"loss":
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
"learning_rate": 0.0002,
|
| 86 |
-
"loss":
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
"learning_rate": 0.0002,
|
| 92 |
-
"loss":
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
"learning_rate": 0.0002,
|
| 98 |
-
"loss":
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
"learning_rate": 0.0002,
|
| 104 |
-
"loss":
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
"learning_rate": 0.0002,
|
| 110 |
-
"loss": 2.
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
"learning_rate": 0.0002,
|
| 116 |
-
"loss":
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
"learning_rate": 0.0002,
|
| 122 |
-
"loss":
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
"learning_rate": 0.0002,
|
| 128 |
-
"loss":
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
"learning_rate": 0.0002,
|
| 134 |
-
"loss":
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
"learning_rate": 0.0002,
|
| 140 |
-
"loss": 1.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
"learning_rate": 0.0002,
|
| 146 |
-
"loss":
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
"learning_rate": 0.0002,
|
| 152 |
-
"loss":
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
"learning_rate": 0.0002,
|
| 158 |
-
"loss": 2.
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
"learning_rate": 0.0002,
|
| 164 |
-
"loss":
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
"learning_rate": 0.0002,
|
| 170 |
-
"loss":
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
"learning_rate": 0.0002,
|
| 176 |
-
"loss":
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
"learning_rate": 0.0002,
|
| 182 |
-
"loss":
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 0.
|
| 187 |
"learning_rate": 0.0002,
|
| 188 |
-
"loss":
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 0.
|
| 193 |
"learning_rate": 0.0002,
|
| 194 |
-
"loss":
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 0.
|
| 199 |
"learning_rate": 0.0002,
|
| 200 |
-
"loss":
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 0.
|
| 205 |
"learning_rate": 0.0002,
|
| 206 |
-
"loss":
|
| 207 |
"step": 66
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.68,
|
| 211 |
-
"learning_rate": 0.0002,
|
| 212 |
-
"loss": 2.1555,
|
| 213 |
-
"step": 68
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.7,
|
| 217 |
-
"learning_rate": 0.0002,
|
| 218 |
-
"loss": 1.9828,
|
| 219 |
-
"step": 70
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.72,
|
| 223 |
-
"learning_rate": 0.0002,
|
| 224 |
-
"loss": 2.2447,
|
| 225 |
-
"step": 72
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.74,
|
| 229 |
-
"learning_rate": 0.0002,
|
| 230 |
-
"loss": 2.0942,
|
| 231 |
-
"step": 74
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 0.76,
|
| 235 |
-
"learning_rate": 0.0002,
|
| 236 |
-
"loss": 2.1352,
|
| 237 |
-
"step": 76
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 0.78,
|
| 241 |
-
"learning_rate": 0.0002,
|
| 242 |
-
"loss": 2.1952,
|
| 243 |
-
"step": 78
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 0.8,
|
| 247 |
-
"learning_rate": 0.0002,
|
| 248 |
-
"loss": 2.3201,
|
| 249 |
-
"step": 80
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.82,
|
| 253 |
-
"learning_rate": 0.0002,
|
| 254 |
-
"loss": 2.2092,
|
| 255 |
-
"step": 82
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.84,
|
| 259 |
-
"learning_rate": 0.0002,
|
| 260 |
-
"loss": 2.2096,
|
| 261 |
-
"step": 84
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.86,
|
| 265 |
-
"learning_rate": 0.0002,
|
| 266 |
-
"loss": 2.3016,
|
| 267 |
-
"step": 86
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.88,
|
| 271 |
-
"learning_rate": 0.0002,
|
| 272 |
-
"loss": 2.2513,
|
| 273 |
-
"step": 88
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.89,
|
| 277 |
-
"learning_rate": 0.0002,
|
| 278 |
-
"loss": 2.0121,
|
| 279 |
-
"step": 90
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.91,
|
| 283 |
-
"learning_rate": 0.0002,
|
| 284 |
-
"loss": 2.068,
|
| 285 |
-
"step": 92
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 0.93,
|
| 289 |
-
"learning_rate": 0.0002,
|
| 290 |
-
"loss": 2.0854,
|
| 291 |
-
"step": 94
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.95,
|
| 295 |
-
"learning_rate": 0.0002,
|
| 296 |
-
"loss": 1.94,
|
| 297 |
-
"step": 96
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.97,
|
| 301 |
-
"learning_rate": 0.0002,
|
| 302 |
-
"loss": 2.1028,
|
| 303 |
-
"step": 98
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.99,
|
| 307 |
-
"learning_rate": 0.0002,
|
| 308 |
-
"loss": 1.9648,
|
| 309 |
-
"step": 100
|
| 310 |
}
|
| 311 |
],
|
| 312 |
"logging_steps": 2,
|
| 313 |
-
"max_steps":
|
| 314 |
"num_input_tokens_seen": 0,
|
| 315 |
"num_train_epochs": 1,
|
| 316 |
"save_steps": 500,
|
| 317 |
-
"total_flos":
|
| 318 |
"train_batch_size": 1,
|
| 319 |
"trial_name": null,
|
| 320 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9990680335507922,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 67,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 2.5917,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 1.801,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.09,
|
| 25 |
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 1.8031,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.12,
|
| 31 |
"learning_rate": 0.0002,
|
| 32 |
+
"loss": 1.8163,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.15,
|
| 37 |
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 1.5103,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.18,
|
| 43 |
"learning_rate": 0.0002,
|
| 44 |
+
"loss": 1.7491,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.21,
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 1.6798,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.24,
|
| 55 |
"learning_rate": 0.0002,
|
| 56 |
+
"loss": 1.4741,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.27,
|
| 61 |
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 2.49,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.3,
|
| 67 |
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 1.8303,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.33,
|
| 73 |
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 1.6824,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.36,
|
| 79 |
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 1.5503,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.39,
|
| 85 |
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 1.3722,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.42,
|
| 91 |
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 1.5678,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.45,
|
| 97 |
"learning_rate": 0.0002,
|
| 98 |
+
"loss": 1.6044,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.48,
|
| 103 |
"learning_rate": 0.0002,
|
| 104 |
+
"loss": 1.4898,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.51,
|
| 109 |
"learning_rate": 0.0002,
|
| 110 |
+
"loss": 2.3578,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.54,
|
| 115 |
"learning_rate": 0.0002,
|
| 116 |
+
"loss": 1.681,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.57,
|
| 121 |
"learning_rate": 0.0002,
|
| 122 |
+
"loss": 1.6899,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.6,
|
| 127 |
"learning_rate": 0.0002,
|
| 128 |
+
"loss": 1.7208,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.63,
|
| 133 |
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 1.4426,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.66,
|
| 139 |
"learning_rate": 0.0002,
|
| 140 |
+
"loss": 1.4401,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.69,
|
| 145 |
"learning_rate": 0.0002,
|
| 146 |
+
"loss": 1.5496,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.72,
|
| 151 |
"learning_rate": 0.0002,
|
| 152 |
+
"loss": 1.3325,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.75,
|
| 157 |
"learning_rate": 0.0002,
|
| 158 |
+
"loss": 2.1736,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.78,
|
| 163 |
"learning_rate": 0.0002,
|
| 164 |
+
"loss": 1.7819,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.81,
|
| 169 |
"learning_rate": 0.0002,
|
| 170 |
+
"loss": 1.7129,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.84,
|
| 175 |
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 1.6788,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.86,
|
| 181 |
"learning_rate": 0.0002,
|
| 182 |
+
"loss": 1.5192,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 0.89,
|
| 187 |
"learning_rate": 0.0002,
|
| 188 |
+
"loss": 1.2892,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.92,
|
| 193 |
"learning_rate": 0.0002,
|
| 194 |
+
"loss": 1.5028,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.95,
|
| 199 |
"learning_rate": 0.0002,
|
| 200 |
+
"loss": 1.1439,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.98,
|
| 205 |
"learning_rate": 0.0002,
|
| 206 |
+
"loss": 1.6148,
|
| 207 |
"step": 66
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
}
|
| 209 |
],
|
| 210 |
"logging_steps": 2,
|
| 211 |
+
"max_steps": 67,
|
| 212 |
"num_input_tokens_seen": 0,
|
| 213 |
"num_train_epochs": 1,
|
| 214 |
"save_steps": 500,
|
| 215 |
+
"total_flos": 3079120462749696.0,
|
| 216 |
"train_batch_size": 1,
|
| 217 |
"trial_name": null,
|
| 218 |
"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 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2297ef3d3b4b6285e02eddcb6c86542c844a3ba7ac6f2da0f6de09ae9d0a5274
|
| 3 |
size 4728
|