Commit
•
db7c33c
1
Parent(s):
cc14b49
Update fine-tuned model
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +410 -165
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"k_proj",
|
| 27 |
-
"gate_proj",
|
| 28 |
"q_proj",
|
| 29 |
-
"
|
|
|
|
| 30 |
"v_proj",
|
| 31 |
"up_proj",
|
| 32 |
-
"
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"q_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
"v_proj",
|
| 30 |
"up_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"gate_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae7d6124db2999b66ba36817f8c2d2311a0f4f6fb36106ec14c0bc5b31769573
|
| 3 |
size 159967880
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 852876198
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60e76bf5ab8ae5b9e9260b0b8905e5be77afb63ceeab61da8f715e051ae9ec5
|
| 3 |
size 852876198
|
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 sha256:841c3d2e9b5e46e8a77c6c9e705dba80a96ae5b9084634adc158035e3d78011a
|
| 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:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,298 +1,543 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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": 0.
|
| 22 |
-
"loss":
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss":
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss":
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss":
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch":
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 0.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 0.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch":
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch":
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch":
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
}
|
| 291 |
],
|
| 292 |
"logging_steps": 1,
|
| 293 |
-
"max_steps":
|
| 294 |
"num_input_tokens_seen": 0,
|
| 295 |
-
"num_train_epochs":
|
| 296 |
"save_steps": 500,
|
| 297 |
"stateful_callbacks": {
|
| 298 |
"TrainerControl": {
|
|
@@ -306,7 +551,7 @@
|
|
| 306 |
"attributes": {}
|
| 307 |
}
|
| 308 |
},
|
| 309 |
-
"total_flos":
|
| 310 |
"train_batch_size": 1,
|
| 311 |
"trial_name": null,
|
| 312 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 1.728904366493225,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 0.7312,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 1.7350375652313232,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 0.7843,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 1.4805001020431519,
|
| 28 |
+
"learning_rate": 0.00015000000000000001,
|
| 29 |
+
"loss": 0.6772,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 1.0534298419952393,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.6122,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 0.8123345375061035,
|
| 42 |
+
"learning_rate": 0.00019990212265199738,
|
| 43 |
+
"loss": 0.5329,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.6635419130325317,
|
| 49 |
+
"learning_rate": 0.00019960868220749448,
|
| 50 |
+
"loss": 0.4878,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 0.6072973608970642,
|
| 56 |
+
"learning_rate": 0.00019912025308994148,
|
| 57 |
+
"loss": 0.4836,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 0.5697150826454163,
|
| 63 |
+
"learning_rate": 0.00019843779142227256,
|
| 64 |
+
"loss": 0.5162,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 0.5166112780570984,
|
| 70 |
+
"learning_rate": 0.0001975626331552507,
|
| 71 |
+
"loss": 0.4825,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 0.5054742097854614,
|
| 77 |
+
"learning_rate": 0.00019649649145228102,
|
| 78 |
+
"loss": 0.4564,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 0.4537505805492401,
|
| 84 |
+
"learning_rate": 0.00019524145333581317,
|
| 85 |
+
"loss": 0.4383,
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 0.4296068251132965,
|
| 91 |
+
"learning_rate": 0.00019379997560189675,
|
| 92 |
+
"loss": 0.4529,
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 0.44367527961730957,
|
| 98 |
+
"learning_rate": 0.00019217488001088784,
|
| 99 |
+
"loss": 0.4545,
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 0.4168623685836792,
|
| 105 |
+
"learning_rate": 0.0001903693477637204,
|
| 106 |
+
"loss": 0.418,
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 0.4231944680213928,
|
| 112 |
+
"learning_rate": 0.0001883869132745561,
|
| 113 |
+
"loss": 0.435,
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 0.4075939953327179,
|
| 119 |
+
"learning_rate": 0.00018623145725200278,
|
| 120 |
+
"loss": 0.4274,
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 0.36284372210502625,
|
| 126 |
+
"learning_rate": 0.00018390719910244487,
|
| 127 |
+
"loss": 0.3972,
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 0.3902932405471802,
|
| 133 |
+
"learning_rate": 0.00018141868867035745,
|
| 134 |
+
"loss": 0.3953,
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 0.38837161660194397,
|
| 140 |
+
"learning_rate": 0.00017877079733177184,
|
| 141 |
+
"loss": 0.4294,
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 0.38330700993537903,
|
| 147 |
+
"learning_rate": 0.0001759687084583285,
|
| 148 |
+
"loss": 0.4155,
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 0.3897230625152588,
|
| 154 |
+
"learning_rate": 0.00017301790727058345,
|
| 155 |
+
"loss": 0.3791,
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 0.40314897894859314,
|
| 161 |
+
"learning_rate": 0.00016992417010043142,
|
| 162 |
+
"loss": 0.4018,
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 0.4068446755409241,
|
| 168 |
+
"learning_rate": 0.0001666935530836651,
|
| 169 |
+
"loss": 0.3801,
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 0.40863823890686035,
|
| 175 |
+
"learning_rate": 0.0001633323803048047,
|
| 176 |
+
"loss": 0.3879,
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 0.3958357274532318,
|
| 182 |
+
"learning_rate": 0.00015984723141740576,
|
| 183 |
+
"loss": 0.3929,
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 1.04,
|
| 188 |
+
"grad_norm": 0.3210630416870117,
|
| 189 |
+
"learning_rate": 0.0001562449287640781,
|
| 190 |
+
"loss": 0.2722,
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 1.08,
|
| 195 |
+
"grad_norm": 0.34723371267318726,
|
| 196 |
+
"learning_rate": 0.00015253252402142988,
|
| 197 |
+
"loss": 0.2701,
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 1.12,
|
| 202 |
+
"grad_norm": 0.3267146050930023,
|
| 203 |
+
"learning_rate": 0.00014871728439607966,
|
| 204 |
+
"loss": 0.2654,
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 1.16,
|
| 209 |
+
"grad_norm": 0.3217560350894928,
|
| 210 |
+
"learning_rate": 0.00014480667839875786,
|
| 211 |
+
"loss": 0.2653,
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"grad_norm": 0.3129405975341797,
|
| 217 |
+
"learning_rate": 0.0001408083612243465,
|
| 218 |
+
"loss": 0.2495,
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 1.24,
|
| 223 |
+
"grad_norm": 0.3169604241847992,
|
| 224 |
+
"learning_rate": 0.00013673015976647568,
|
| 225 |
+
"loss": 0.2783,
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 1.28,
|
| 230 |
+
"grad_norm": 0.3302832543849945,
|
| 231 |
+
"learning_rate": 0.00013258005729601177,
|
| 232 |
+
"loss": 0.2589,
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 1.32,
|
| 237 |
+
"grad_norm": 0.3463418781757355,
|
| 238 |
+
"learning_rate": 0.0001283661778334297,
|
| 239 |
+
"loss": 0.2453,
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 1.3599999999999999,
|
| 244 |
+
"grad_norm": 0.3463260531425476,
|
| 245 |
+
"learning_rate": 0.00012409677024566144,
|
| 246 |
+
"loss": 0.242,
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 1.4,
|
| 251 |
+
"grad_norm": 0.3702252209186554,
|
| 252 |
+
"learning_rate": 0.00011978019209855174,
|
| 253 |
+
"loss": 0.264,
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 1.44,
|
| 258 |
+
"grad_norm": 0.3509206771850586,
|
| 259 |
+
"learning_rate": 0.00011542489329653024,
|
| 260 |
+
"loss": 0.2593,
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 1.48,
|
| 265 |
+
"grad_norm": 0.3612159490585327,
|
| 266 |
+
"learning_rate": 0.000111039399541527,
|
| 267 |
+
"loss": 0.2411,
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 1.52,
|
| 272 |
+
"grad_norm": 0.3651520609855652,
|
| 273 |
+
"learning_rate": 0.00010663229564351041,
|
| 274 |
+
"loss": 0.2378,
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 1.56,
|
| 279 |
+
"grad_norm": 0.3665476441383362,
|
| 280 |
+
"learning_rate": 0.00010221220871531869,
|
| 281 |
+
"loss": 0.2334,
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 1.6,
|
| 286 |
+
"grad_norm": 0.34961438179016113,
|
| 287 |
+
"learning_rate": 9.778779128468132e-05,
|
| 288 |
+
"loss": 0.2307,
|
| 289 |
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6400000000000001,
|
| 293 |
+
"grad_norm": 0.379111111164093,
|
| 294 |
+
"learning_rate": 9.336770435648964e-05,
|
| 295 |
+
"loss": 0.2212,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6800000000000002,
|
| 300 |
+
"grad_norm": 0.38593631982803345,
|
| 301 |
+
"learning_rate": 8.896060045847304e-05,
|
| 302 |
+
"loss": 0.2335,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.72,
|
| 307 |
+
"grad_norm": 0.37961545586586,
|
| 308 |
+
"learning_rate": 8.457510670346976e-05,
|
| 309 |
+
"loss": 0.2306,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.76,
|
| 314 |
+
"grad_norm": 0.3735259771347046,
|
| 315 |
+
"learning_rate": 8.021980790144827e-05,
|
| 316 |
+
"loss": 0.2499,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.8,
|
| 321 |
+
"grad_norm": 0.40170496702194214,
|
| 322 |
+
"learning_rate": 7.590322975433857e-05,
|
| 323 |
+
"loss": 0.2275,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8399999999999999,
|
| 328 |
+
"grad_norm": 0.3875046372413635,
|
| 329 |
+
"learning_rate": 7.163382216657034e-05,
|
| 330 |
+
"loss": 0.218,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.88,
|
| 335 |
+
"grad_norm": 0.37028905749320984,
|
| 336 |
+
"learning_rate": 6.741994270398826e-05,
|
| 337 |
+
"loss": 0.2422,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.92,
|
| 342 |
+
"grad_norm": 0.3737669289112091,
|
| 343 |
+
"learning_rate": 6.326984023352435e-05,
|
| 344 |
+
"loss": 0.2195,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.96,
|
| 349 |
+
"grad_norm": 0.3924426734447479,
|
| 350 |
+
"learning_rate": 5.91916387756535e-05,
|
| 351 |
+
"loss": 0.2235,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0,
|
| 356 |
+
"grad_norm": 0.36921918392181396,
|
| 357 |
+
"learning_rate": 5.5193321601242156e-05,
|
| 358 |
+
"loss": 0.2141,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.04,
|
| 363 |
+
"grad_norm": 0.28800830245018005,
|
| 364 |
+
"learning_rate": 5.1282715603920374e-05,
|
| 365 |
+
"loss": 0.1736,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.08,
|
| 370 |
+
"grad_norm": 0.31100502610206604,
|
| 371 |
+
"learning_rate": 4.746747597857014e-05,
|
| 372 |
+
"loss": 0.1578,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.12,
|
| 377 |
+
"grad_norm": 0.3049222528934479,
|
| 378 |
+
"learning_rate": 4.375507123592194e-05,
|
| 379 |
+
"loss": 0.1771,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.16,
|
| 384 |
+
"grad_norm": 0.28219300508499146,
|
| 385 |
+
"learning_rate": 4.015276858259427e-05,
|
| 386 |
+
"loss": 0.1476,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.2,
|
| 391 |
+
"grad_norm": 0.3022613525390625,
|
| 392 |
+
"learning_rate": 3.6667619695195285e-05,
|
| 393 |
+
"loss": 0.1779,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.24,
|
| 398 |
+
"grad_norm": 0.2823966443538666,
|
| 399 |
+
"learning_rate": 3.330644691633492e-05,
|
| 400 |
+
"loss": 0.1501,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.2800000000000002,
|
| 405 |
+
"grad_norm": 0.28174689412117004,
|
| 406 |
+
"learning_rate": 3.0075829899568597e-05,
|
| 407 |
+
"loss": 0.1511,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.32,
|
| 412 |
+
"grad_norm": 0.2776714861392975,
|
| 413 |
+
"learning_rate": 2.6982092729416587e-05,
|
| 414 |
+
"loss": 0.1568,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.36,
|
| 419 |
+
"grad_norm": 0.2745690643787384,
|
| 420 |
+
"learning_rate": 2.403129154167153e-05,
|
| 421 |
+
"loss": 0.1393,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.4,
|
| 426 |
+
"grad_norm": 0.2862659692764282,
|
| 427 |
+
"learning_rate": 2.1229202668228197e-05,
|
| 428 |
+
"loss": 0.1568,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.44,
|
| 433 |
+
"grad_norm": 0.30168795585632324,
|
| 434 |
+
"learning_rate": 1.858131132964259e-05,
|
| 435 |
+
"loss": 0.164,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.48,
|
| 440 |
+
"grad_norm": 0.30739548802375793,
|
| 441 |
+
"learning_rate": 1.609280089755515e-05,
|
| 442 |
+
"loss": 0.1595,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.52,
|
| 447 |
+
"grad_norm": 0.2983320355415344,
|
| 448 |
+
"learning_rate": 1.3768542747997215e-05,
|
| 449 |
+
"loss": 0.174,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.56,
|
| 454 |
+
"grad_norm": 0.30526575446128845,
|
| 455 |
+
"learning_rate": 1.161308672544389e-05,
|
| 456 |
+
"loss": 0.168,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.6,
|
| 461 |
+
"grad_norm": 0.28905755281448364,
|
| 462 |
+
"learning_rate": 9.630652236279625e-06,
|
| 463 |
+
"loss": 0.1557,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.64,
|
| 468 |
+
"grad_norm": 0.29685401916503906,
|
| 469 |
+
"learning_rate": 7.825119989112173e-06,
|
| 470 |
+
"loss": 0.1531,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.68,
|
| 475 |
+
"grad_norm": 0.309733510017395,
|
| 476 |
+
"learning_rate": 6.200024398103255e-06,
|
| 477 |
+
"loss": 0.1538,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.7199999999999998,
|
| 482 |
+
"grad_norm": 0.31325626373291016,
|
| 483 |
+
"learning_rate": 4.758546664186869e-06,
|
| 484 |
+
"loss": 0.16,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.76,
|
| 489 |
+
"grad_norm": 0.29155057668685913,
|
| 490 |
+
"learning_rate": 3.5035085477190143e-06,
|
| 491 |
+
"loss": 0.1612,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.8,
|
| 496 |
+
"grad_norm": 0.31043997406959534,
|
| 497 |
+
"learning_rate": 2.4373668447493224e-06,
|
| 498 |
+
"loss": 0.1655,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.84,
|
| 503 |
+
"grad_norm": 0.30450770258903503,
|
| 504 |
+
"learning_rate": 1.562208577727442e-06,
|
| 505 |
+
"loss": 0.1581,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.88,
|
| 510 |
+
"grad_norm": 0.2816106677055359,
|
| 511 |
+
"learning_rate": 8.797469100585431e-07,
|
| 512 |
+
"loss": 0.1369,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.92,
|
| 517 |
+
"grad_norm": 0.3166625201702118,
|
| 518 |
+
"learning_rate": 3.913177925055189e-07,
|
| 519 |
+
"loss": 0.1724,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.96,
|
| 524 |
+
"grad_norm": 0.30547070503234863,
|
| 525 |
+
"learning_rate": 9.78773480026396e-08,
|
| 526 |
+
"loss": 0.1555,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.0,
|
| 531 |
+
"grad_norm": 0.29624301195144653,
|
| 532 |
+
"learning_rate": 0.0,
|
| 533 |
+
"loss": 0.1598,
|
| 534 |
+
"step": 75
|
| 535 |
}
|
| 536 |
],
|
| 537 |
"logging_steps": 1,
|
| 538 |
+
"max_steps": 75,
|
| 539 |
"num_input_tokens_seen": 0,
|
| 540 |
+
"num_train_epochs": 3,
|
| 541 |
"save_steps": 500,
|
| 542 |
"stateful_callbacks": {
|
| 543 |
"TrainerControl": {
|
|
|
|
| 551 |
"attributes": {}
|
| 552 |
}
|
| 553 |
},
|
| 554 |
+
"total_flos": 9.106714169779814e+16,
|
| 555 |
"train_batch_size": 1,
|
| 556 |
"trial_name": null,
|
| 557 |
"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 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c82f1076477830c5279e886b1bb2af3d8f3ef16a462c5c5df5187f2aded327b7
|
| 3 |
size 5240
|