Commit
·
4108e31
1
Parent(s):
e8efc25
End of training
Browse files- checkpoint-1000/README.md +19 -0
- checkpoint-1000/adapter_config.json +3 -3
- checkpoint-1000/adapter_model.safetensors +2 -2
- checkpoint-1000/optimizer.pt +1 -1
- checkpoint-1000/rng_state.pth +1 -1
- checkpoint-1000/scheduler.pt +1 -1
- checkpoint-1000/trainer_state.json +33 -1173
- checkpoint-1000/training_args.bin +1 -1
- checkpoint-1500/README.md +220 -0
- checkpoint-1500/adapter_config.json +23 -0
- checkpoint-1500/adapter_model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +109 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/README.md +220 -0
- checkpoint-2000/adapter_config.json +23 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +139 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/README.md +220 -0
- checkpoint-2500/adapter_config.json +23 -0
- checkpoint-2500/adapter_model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +169 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-500/README.md +19 -0
- checkpoint-500/adapter_config.json +3 -3
- checkpoint-500/adapter_model.safetensors +2 -2
- checkpoint-500/optimizer.pt +1 -1
- checkpoint-500/rng_state.pth +1 -1
- checkpoint-500/scheduler.pt +1 -1
- checkpoint-500/trainer_state.json +13 -583
- checkpoint-500/training_args.bin +1 -1
- runs/Nov22_05-17-44_3ed78d352be3/events.out.tfevents.1700630265.3ed78d352be3.3950.0 +3 -0
checkpoint-1000/README.md
CHANGED
|
@@ -236,4 +236,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 236 |
### Framework versions
|
| 237 |
|
| 238 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 239 |
- PEFT 0.6.2
|
|
|
|
| 236 |
### Framework versions
|
| 237 |
|
| 238 |
|
| 239 |
+
- PEFT 0.6.2
|
| 240 |
+
## Training procedure
|
| 241 |
+
|
| 242 |
+
|
| 243 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 244 |
+
- quant_method: bitsandbytes
|
| 245 |
+
- load_in_8bit: False
|
| 246 |
+
- load_in_4bit: True
|
| 247 |
+
- llm_int8_threshold: 6.0
|
| 248 |
+
- llm_int8_skip_modules: None
|
| 249 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 250 |
+
- llm_int8_has_fp16_weight: False
|
| 251 |
+
- bnb_4bit_quant_type: nf4
|
| 252 |
+
- bnb_4bit_use_double_quant: True
|
| 253 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 254 |
+
|
| 255 |
+
### Framework versions
|
| 256 |
+
|
| 257 |
+
|
| 258 |
- PEFT 0.6.2
|
checkpoint-1000/adapter_config.json
CHANGED
|
@@ -12,12 +12,12 @@
|
|
| 12 |
"lora_dropout": 0.1,
|
| 13 |
"modules_to_save": null,
|
| 14 |
"peft_type": "LORA",
|
| 15 |
-
"r":
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
|
|
|
| 12 |
"lora_dropout": 0.1,
|
| 13 |
"modules_to_save": null,
|
| 14 |
"peft_type": "LORA",
|
| 15 |
+
"r": 32,
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj"
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
checkpoint-1000/adapter_model.safetensors
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:fccc42f58dd6336fe96ad118dab74bd05fc22a9ec9e489b7c256c1d765119072
|
| 3 |
+
size 67126104
|
checkpoint-1000/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69ae342b4b17dffa0a39133642cb4bbf35a75e266c539638c16718cb4101dbc
|
| 3 |
size 1384
|
checkpoint-1000/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 sha256:9916ccdf4a2c96f9abbaa93c24f261f87e3221b0d797f7d306707640c909c82d
|
| 3 |
size 14244
|
checkpoint-1000/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 sha256:78da2ad4b9ca31898b45b1311417fe63cc13ba94ce9477e40d7f195675677450
|
| 3 |
size 1064
|
checkpoint-1000/trainer_state.json
CHANGED
|
@@ -9,1211 +9,71 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss":
|
| 15 |
-
"step":
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"epoch": 0.01,
|
| 19 |
-
"learning_rate": 0.0,
|
| 20 |
-
"loss": 0.0,
|
| 21 |
-
"step": 10
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.01,
|
| 25 |
-
"learning_rate": 0.0,
|
| 26 |
-
"loss": 16.3471,
|
| 27 |
-
"step": 15
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.02,
|
| 31 |
-
"learning_rate": 0.0,
|
| 32 |
-
"loss": 0.0,
|
| 33 |
-
"step": 20
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.02,
|
| 37 |
-
"learning_rate": 0.0,
|
| 38 |
-
"loss": 0.0,
|
| 39 |
-
"step": 25
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.02,
|
| 43 |
-
"learning_rate": 0.0,
|
| 44 |
-
"loss": 0.4615,
|
| 45 |
-
"step": 30
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.03,
|
| 49 |
-
"learning_rate": 0.0,
|
| 50 |
-
"loss": 0.194,
|
| 51 |
-
"step": 35
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.03,
|
| 55 |
-
"learning_rate": 0.0,
|
| 56 |
-
"loss": 0.0,
|
| 57 |
-
"step": 40
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.04,
|
| 61 |
-
"learning_rate": 0.0,
|
| 62 |
-
"loss": 0.0,
|
| 63 |
-
"step": 45
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.04,
|
| 67 |
-
"learning_rate": 0.0,
|
| 68 |
-
"loss": 0.9551,
|
| 69 |
-
"step": 50
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.04,
|
| 73 |
-
"learning_rate": 0.0,
|
| 74 |
-
"loss": 0.0,
|
| 75 |
-
"step": 55
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.05,
|
| 79 |
-
"learning_rate": 0.0,
|
| 80 |
-
"loss": 0.2261,
|
| 81 |
-
"step": 60
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.05,
|
| 85 |
-
"learning_rate": 0.0,
|
| 86 |
-
"loss": 0.0,
|
| 87 |
-
"step": 65
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.06,
|
| 91 |
-
"learning_rate": 0.0,
|
| 92 |
-
"loss": 0.0,
|
| 93 |
-
"step": 70
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.06,
|
| 97 |
-
"learning_rate": 0.0,
|
| 98 |
-
"loss": 0.0,
|
| 99 |
-
"step": 75
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.06,
|
| 103 |
-
"learning_rate": 0.0,
|
| 104 |
-
"loss": 0.0,
|
| 105 |
-
"step": 80
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.07,
|
| 109 |
-
"learning_rate": 0.0,
|
| 110 |
-
"loss": 1.9869,
|
| 111 |
-
"step": 85
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.07,
|
| 115 |
-
"learning_rate": 0.0,
|
| 116 |
-
"loss": 0.0,
|
| 117 |
-
"step": 90
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 0.08,
|
| 121 |
-
"learning_rate": 0.0,
|
| 122 |
-
"loss": 0.0,
|
| 123 |
-
"step": 95
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 0.08,
|
| 127 |
-
"learning_rate": 0.0,
|
| 128 |
-
"loss": 1.6293,
|
| 129 |
-
"step": 100
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.08,
|
| 133 |
-
"learning_rate": 0.0,
|
| 134 |
-
"loss": 0.0,
|
| 135 |
-
"step": 105
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.09,
|
| 139 |
-
"learning_rate": 0.0,
|
| 140 |
-
"loss": 0.0,
|
| 141 |
-
"step": 110
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 0.09,
|
| 145 |
-
"learning_rate": 0.0,
|
| 146 |
-
"loss": 0.0,
|
| 147 |
-
"step": 115
|
| 148 |
-
},
|
| 149 |
-
{
|
| 150 |
-
"epoch": 0.1,
|
| 151 |
-
"learning_rate": 0.0,
|
| 152 |
-
"loss": 2.0245,
|
| 153 |
-
"step": 120
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 0.1,
|
| 157 |
-
"learning_rate": 0.0,
|
| 158 |
-
"loss": 0.0,
|
| 159 |
-
"step": 125
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 0.1,
|
| 163 |
-
"learning_rate": 0.0,
|
| 164 |
-
"loss": 0.0,
|
| 165 |
-
"step": 130
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.11,
|
| 169 |
-
"learning_rate": 0.0,
|
| 170 |
-
"loss": 0.0,
|
| 171 |
-
"step": 135
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.11,
|
| 175 |
-
"learning_rate": 0.0,
|
| 176 |
-
"loss": 1.8265,
|
| 177 |
-
"step": 140
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.12,
|
| 181 |
-
"learning_rate": 0.0,
|
| 182 |
-
"loss": 0.0,
|
| 183 |
-
"step": 145
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 0.12,
|
| 187 |
-
"learning_rate": 0.0,
|
| 188 |
-
"loss": 0.5536,
|
| 189 |
-
"step": 150
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 0.12,
|
| 193 |
-
"learning_rate": 0.0,
|
| 194 |
-
"loss": 0.0,
|
| 195 |
-
"step": 155
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.13,
|
| 199 |
-
"learning_rate": 0.0,
|
| 200 |
-
"loss": 2.0011,
|
| 201 |
-
"step": 160
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.13,
|
| 205 |
-
"learning_rate": 0.0,
|
| 206 |
-
"loss": 0.0,
|
| 207 |
-
"step": 165
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.14,
|
| 211 |
-
"learning_rate": 0.0,
|
| 212 |
-
"loss": 0.0,
|
| 213 |
-
"step": 170
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.14,
|
| 217 |
-
"learning_rate": 0.0,
|
| 218 |
-
"loss": 0.1846,
|
| 219 |
-
"step": 175
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.14,
|
| 223 |
-
"learning_rate": 0.0,
|
| 224 |
-
"loss": 2.3248,
|
| 225 |
-
"step": 180
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.15,
|
| 229 |
-
"learning_rate": 0.0,
|
| 230 |
-
"loss": 3.966,
|
| 231 |
-
"step": 185
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 0.15,
|
| 235 |
-
"learning_rate": 0.0,
|
| 236 |
-
"loss": 0.0,
|
| 237 |
-
"step": 190
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 0.16,
|
| 241 |
-
"learning_rate": 0.0,
|
| 242 |
-
"loss": 0.0,
|
| 243 |
-
"step": 195
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 0.16,
|
| 247 |
-
"learning_rate": 0.0,
|
| 248 |
-
"loss": 49.8341,
|
| 249 |
-
"step": 200
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.16,
|
| 253 |
-
"learning_rate": 0.0,
|
| 254 |
-
"loss": 0.0,
|
| 255 |
-
"step": 205
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.17,
|
| 259 |
-
"learning_rate": 0.0,
|
| 260 |
-
"loss": 0.0,
|
| 261 |
-
"step": 210
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.17,
|
| 265 |
-
"learning_rate": 0.0,
|
| 266 |
-
"loss": 0.0,
|
| 267 |
-
"step": 215
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.18,
|
| 271 |
-
"learning_rate": 0.0,
|
| 272 |
-
"loss": 4.7387,
|
| 273 |
-
"step": 220
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.18,
|
| 277 |
-
"learning_rate": 0.0,
|
| 278 |
-
"loss": 27.6091,
|
| 279 |
-
"step": 225
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.18,
|
| 283 |
-
"learning_rate": 0.0,
|
| 284 |
-
"loss": 0.0,
|
| 285 |
-
"step": 230
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 0.19,
|
| 289 |
-
"learning_rate": 0.0,
|
| 290 |
-
"loss": 0.0,
|
| 291 |
-
"step": 235
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.19,
|
| 295 |
-
"learning_rate": 0.0,
|
| 296 |
-
"loss": 0.0,
|
| 297 |
-
"step": 240
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.2,
|
| 301 |
-
"learning_rate": 0.0,
|
| 302 |
-
"loss": 0.7769,
|
| 303 |
-
"step": 245
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.2,
|
| 307 |
-
"learning_rate": 0.0,
|
| 308 |
-
"loss": 1.2832,
|
| 309 |
-
"step": 250
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.2,
|
| 313 |
-
"learning_rate": 0.0,
|
| 314 |
-
"loss": 28.6253,
|
| 315 |
-
"step": 255
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.21,
|
| 319 |
-
"learning_rate": 0.0,
|
| 320 |
-
"loss": 0.0,
|
| 321 |
-
"step": 260
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.21,
|
| 325 |
-
"learning_rate": 0.0,
|
| 326 |
-
"loss": 1.311,
|
| 327 |
-
"step": 265
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.22,
|
| 331 |
-
"learning_rate": 0.0,
|
| 332 |
-
"loss": 0.0,
|
| 333 |
-
"step": 270
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.22,
|
| 337 |
-
"learning_rate": 0.0,
|
| 338 |
-
"loss": 0.0,
|
| 339 |
-
"step": 275
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.22,
|
| 343 |
-
"learning_rate": 0.0,
|
| 344 |
-
"loss": 0.0,
|
| 345 |
-
"step": 280
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.23,
|
| 349 |
-
"learning_rate": 0.0,
|
| 350 |
-
"loss": 0.0,
|
| 351 |
-
"step": 285
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 0.23,
|
| 355 |
-
"learning_rate": 0.0,
|
| 356 |
-
"loss": 1.0543,
|
| 357 |
-
"step": 290
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 0.24,
|
| 361 |
-
"learning_rate": 0.0,
|
| 362 |
-
"loss": 0.0,
|
| 363 |
-
"step": 295
|
| 364 |
-
},
|
| 365 |
-
{
|
| 366 |
-
"epoch": 0.24,
|
| 367 |
-
"learning_rate": 0.0,
|
| 368 |
-
"loss": 0.0,
|
| 369 |
-
"step": 300
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.24,
|
| 373 |
-
"learning_rate": 0.0,
|
| 374 |
-
"loss": 4.1379,
|
| 375 |
-
"step": 305
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.25,
|
| 379 |
-
"learning_rate": 0.0,
|
| 380 |
-
"loss": 0.0,
|
| 381 |
-
"step": 310
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.25,
|
| 385 |
-
"learning_rate": 0.0,
|
| 386 |
-
"loss": 0.2084,
|
| 387 |
-
"step": 315
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 0.26,
|
| 391 |
-
"learning_rate": 0.0,
|
| 392 |
-
"loss": 0.0,
|
| 393 |
-
"step": 320
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"epoch": 0.26,
|
| 397 |
-
"learning_rate": 0.0,
|
| 398 |
-
"loss": 0.0999,
|
| 399 |
-
"step": 325
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 0.26,
|
| 403 |
-
"learning_rate": 0.0,
|
| 404 |
-
"loss": 0.0,
|
| 405 |
-
"step": 330
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.27,
|
| 409 |
-
"learning_rate": 0.0,
|
| 410 |
-
"loss": 0.0,
|
| 411 |
-
"step": 335
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.27,
|
| 415 |
-
"learning_rate": 0.0,
|
| 416 |
-
"loss": 0.0,
|
| 417 |
-
"step": 340
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.28,
|
| 421 |
-
"learning_rate": 0.0,
|
| 422 |
-
"loss": 0.2186,
|
| 423 |
-
"step": 345
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.28,
|
| 427 |
-
"learning_rate": 0.0,
|
| 428 |
-
"loss": 0.0,
|
| 429 |
-
"step": 350
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.28,
|
| 433 |
-
"learning_rate": 0.0,
|
| 434 |
-
"loss": 0.6567,
|
| 435 |
-
"step": 355
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.29,
|
| 439 |
-
"learning_rate": 0.0,
|
| 440 |
-
"loss": 0.1897,
|
| 441 |
-
"step": 360
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.29,
|
| 445 |
-
"learning_rate": 0.0,
|
| 446 |
-
"loss": 0.0,
|
| 447 |
-
"step": 365
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 0.3,
|
| 451 |
-
"learning_rate": 0.0,
|
| 452 |
-
"loss": 0.0,
|
| 453 |
-
"step": 370
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.3,
|
| 457 |
-
"learning_rate": 0.0,
|
| 458 |
-
"loss": 0.0,
|
| 459 |
-
"step": 375
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 0.3,
|
| 463 |
-
"learning_rate": 0.0,
|
| 464 |
-
"loss": 1.1873,
|
| 465 |
-
"step": 380
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 0.31,
|
| 469 |
-
"learning_rate": 0.0,
|
| 470 |
-
"loss": 0.5393,
|
| 471 |
-
"step": 385
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 0.31,
|
| 475 |
-
"learning_rate": 0.0,
|
| 476 |
-
"loss": 0.0,
|
| 477 |
-
"step": 390
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 0.32,
|
| 481 |
-
"learning_rate": 0.0,
|
| 482 |
-
"loss": 0.0,
|
| 483 |
-
"step": 395
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 0.32,
|
| 487 |
-
"learning_rate": 0.0,
|
| 488 |
-
"loss": 0.0,
|
| 489 |
-
"step": 400
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.32,
|
| 493 |
-
"learning_rate": 0.0,
|
| 494 |
-
"loss": 0.0,
|
| 495 |
-
"step": 405
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 0.33,
|
| 499 |
-
"learning_rate": 0.0,
|
| 500 |
-
"loss": 0.0,
|
| 501 |
-
"step": 410
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.33,
|
| 505 |
-
"learning_rate": 0.0,
|
| 506 |
-
"loss": 0.0,
|
| 507 |
-
"step": 415
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 0.34,
|
| 511 |
-
"learning_rate": 0.0,
|
| 512 |
-
"loss": 0.0,
|
| 513 |
-
"step": 420
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.34,
|
| 517 |
-
"learning_rate": 0.0,
|
| 518 |
-
"loss": 0.0,
|
| 519 |
-
"step": 425
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 0.34,
|
| 523 |
-
"learning_rate": 0.0,
|
| 524 |
-
"loss": 0.0,
|
| 525 |
-
"step": 430
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 0.35,
|
| 529 |
-
"learning_rate": 0.0,
|
| 530 |
-
"loss": 0.0,
|
| 531 |
-
"step": 435
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.35,
|
| 535 |
-
"learning_rate": 0.0,
|
| 536 |
-
"loss": 0.0,
|
| 537 |
-
"step": 440
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.36,
|
| 541 |
-
"learning_rate": 0.0,
|
| 542 |
-
"loss": 0.0,
|
| 543 |
-
"step": 445
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 0.36,
|
| 547 |
-
"learning_rate": 0.0,
|
| 548 |
-
"loss": 0.0,
|
| 549 |
-
"step": 450
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 0.36,
|
| 553 |
-
"learning_rate": 0.0,
|
| 554 |
-
"loss": 0.6623,
|
| 555 |
-
"step": 455
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 0.37,
|
| 559 |
-
"learning_rate": 0.0,
|
| 560 |
-
"loss": 7.193,
|
| 561 |
-
"step": 460
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 0.37,
|
| 565 |
-
"learning_rate": 0.0,
|
| 566 |
-
"loss": 62.3001,
|
| 567 |
-
"step": 465
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 0.38,
|
| 571 |
-
"learning_rate": 0.0,
|
| 572 |
-
"loss": 1.6018,
|
| 573 |
-
"step": 470
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.38,
|
| 577 |
-
"learning_rate": 0.0,
|
| 578 |
-
"loss": 0.0,
|
| 579 |
-
"step": 475
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 0.38,
|
| 583 |
-
"learning_rate": 0.0,
|
| 584 |
-
"loss": 0.0,
|
| 585 |
-
"step": 480
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.39,
|
| 589 |
-
"learning_rate": 0.0,
|
| 590 |
-
"loss": 0.1079,
|
| 591 |
-
"step": 485
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.39,
|
| 595 |
-
"learning_rate": 0.0,
|
| 596 |
-
"loss": 0.0,
|
| 597 |
-
"step": 490
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 0.4,
|
| 601 |
-
"learning_rate": 0.0,
|
| 602 |
-
"loss": 1.2356,
|
| 603 |
-
"step": 495
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 0.4,
|
| 607 |
-
"learning_rate": 0.0,
|
| 608 |
-
"loss": 0.0,
|
| 609 |
-
"step": 500
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 0.4,
|
| 613 |
-
"learning_rate": 0.0,
|
| 614 |
-
"loss": 0.0,
|
| 615 |
-
"step": 505
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"epoch": 0.41,
|
| 619 |
-
"learning_rate": 0.0,
|
| 620 |
-
"loss": 0.0,
|
| 621 |
-
"step": 510
|
| 622 |
-
},
|
| 623 |
-
{
|
| 624 |
-
"epoch": 0.41,
|
| 625 |
-
"learning_rate": 0.0,
|
| 626 |
-
"loss": 0.0,
|
| 627 |
-
"step": 515
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 0.42,
|
| 631 |
-
"learning_rate": 0.0,
|
| 632 |
-
"loss": 0.7136,
|
| 633 |
-
"step": 520
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 0.42,
|
| 637 |
-
"learning_rate": 0.0,
|
| 638 |
-
"loss": 0.6036,
|
| 639 |
-
"step": 525
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 0.42,
|
| 643 |
-
"learning_rate": 0.0,
|
| 644 |
-
"loss": 0.0,
|
| 645 |
-
"step": 530
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"epoch": 0.43,
|
| 649 |
-
"learning_rate": 0.0,
|
| 650 |
-
"loss": 0.1166,
|
| 651 |
-
"step": 535
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 0.43,
|
| 655 |
-
"learning_rate": 0.0,
|
| 656 |
-
"loss": 0.0,
|
| 657 |
-
"step": 540
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 0.44,
|
| 661 |
-
"learning_rate": 0.0,
|
| 662 |
-
"loss": 0.1405,
|
| 663 |
-
"step": 545
|
| 664 |
-
},
|
| 665 |
-
{
|
| 666 |
-
"epoch": 0.44,
|
| 667 |
-
"learning_rate": 0.0,
|
| 668 |
-
"loss": 0.0857,
|
| 669 |
-
"step": 550
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 0.44,
|
| 673 |
-
"learning_rate": 0.0,
|
| 674 |
-
"loss": 5.0663,
|
| 675 |
-
"step": 555
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 0.45,
|
| 679 |
-
"learning_rate": 0.0,
|
| 680 |
-
"loss": 0.0,
|
| 681 |
-
"step": 560
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 0.45,
|
| 685 |
-
"learning_rate": 0.0,
|
| 686 |
-
"loss": 0.0,
|
| 687 |
-
"step": 565
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 0.46,
|
| 691 |
-
"learning_rate": 0.0,
|
| 692 |
-
"loss": 0.4088,
|
| 693 |
-
"step": 570
|
| 694 |
-
},
|
| 695 |
-
{
|
| 696 |
-
"epoch": 0.46,
|
| 697 |
-
"learning_rate": 0.0,
|
| 698 |
-
"loss": 0.0,
|
| 699 |
-
"step": 575
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"epoch": 0.
|
| 703 |
-
"learning_rate": 0.
|
| 704 |
-
"loss": 0.
|
| 705 |
-
"step":
|
| 706 |
},
|
| 707 |
{
|
| 708 |
-
"epoch": 0.
|
| 709 |
-
"learning_rate": 0.
|
| 710 |
-
"loss":
|
| 711 |
-
"step":
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch": 0.
|
| 715 |
-
"learning_rate": 0.
|
| 716 |
"loss": 0.0,
|
| 717 |
-
"step":
|
| 718 |
},
|
| 719 |
{
|
| 720 |
-
"epoch": 0.
|
| 721 |
-
"learning_rate": 0.
|
| 722 |
-
"loss":
|
| 723 |
-
"step":
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.48,
|
| 727 |
-
"learning_rate": 0.
|
| 728 |
-
"loss":
|
| 729 |
"step": 600
|
| 730 |
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 0.48,
|
| 733 |
-
"learning_rate": 0.0,
|
| 734 |
-
"loss": 0.0,
|
| 735 |
-
"step": 605
|
| 736 |
-
},
|
| 737 |
-
{
|
| 738 |
-
"epoch": 0.49,
|
| 739 |
-
"learning_rate": 0.0,
|
| 740 |
-
"loss": 0.0,
|
| 741 |
-
"step": 610
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 0.49,
|
| 745 |
-
"learning_rate": 0.0,
|
| 746 |
-
"loss": 0.2691,
|
| 747 |
-
"step": 615
|
| 748 |
-
},
|
| 749 |
-
{
|
| 750 |
-
"epoch": 0.5,
|
| 751 |
-
"learning_rate": 0.0,
|
| 752 |
-
"loss": 0.0,
|
| 753 |
-
"step": 620
|
| 754 |
-
},
|
| 755 |
-
{
|
| 756 |
-
"epoch": 0.5,
|
| 757 |
-
"learning_rate": 0.0,
|
| 758 |
-
"loss": 0.0,
|
| 759 |
-
"step": 625
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 0.5,
|
| 763 |
-
"learning_rate": 0.0,
|
| 764 |
-
"loss": 0.0,
|
| 765 |
-
"step": 630
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 0.51,
|
| 769 |
-
"learning_rate": 0.0,
|
| 770 |
-
"loss": 4.2892,
|
| 771 |
-
"step": 635
|
| 772 |
-
},
|
| 773 |
-
{
|
| 774 |
-
"epoch": 0.51,
|
| 775 |
-
"learning_rate": 0.0,
|
| 776 |
-
"loss": 0.0,
|
| 777 |
-
"step": 640
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 0.52,
|
| 781 |
-
"learning_rate": 0.0,
|
| 782 |
-
"loss": 1.1384,
|
| 783 |
-
"step": 645
|
| 784 |
-
},
|
| 785 |
-
{
|
| 786 |
-
"epoch": 0.52,
|
| 787 |
-
"learning_rate": 0.0,
|
| 788 |
-
"loss": 13.9341,
|
| 789 |
-
"step": 650
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 0.52,
|
| 793 |
-
"learning_rate": 0.0,
|
| 794 |
-
"loss": 6.6407,
|
| 795 |
-
"step": 655
|
| 796 |
-
},
|
| 797 |
-
{
|
| 798 |
-
"epoch": 0.53,
|
| 799 |
-
"learning_rate": 0.0,
|
| 800 |
-
"loss": 0.0,
|
| 801 |
-
"step": 660
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 0.53,
|
| 805 |
-
"learning_rate": 0.0,
|
| 806 |
-
"loss": 0.0,
|
| 807 |
-
"step": 665
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 0.54,
|
| 811 |
-
"learning_rate": 0.0,
|
| 812 |
-
"loss": 0.0,
|
| 813 |
-
"step": 670
|
| 814 |
-
},
|
| 815 |
-
{
|
| 816 |
-
"epoch": 0.54,
|
| 817 |
-
"learning_rate": 0.0,
|
| 818 |
-
"loss": 5.8702,
|
| 819 |
-
"step": 675
|
| 820 |
-
},
|
| 821 |
-
{
|
| 822 |
-
"epoch": 0.54,
|
| 823 |
-
"learning_rate": 0.0,
|
| 824 |
-
"loss": 0.9148,
|
| 825 |
-
"step": 680
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 0.55,
|
| 829 |
-
"learning_rate": 0.0,
|
| 830 |
-
"loss": 0.8692,
|
| 831 |
-
"step": 685
|
| 832 |
-
},
|
| 833 |
-
{
|
| 834 |
-
"epoch": 0.55,
|
| 835 |
-
"learning_rate": 0.0,
|
| 836 |
-
"loss": 0.0,
|
| 837 |
-
"step": 690
|
| 838 |
-
},
|
| 839 |
{
|
| 840 |
"epoch": 0.56,
|
| 841 |
-
"learning_rate": 0.
|
| 842 |
-
"loss":
|
| 843 |
-
"step": 695
|
| 844 |
-
},
|
| 845 |
-
{
|
| 846 |
-
"epoch": 0.56,
|
| 847 |
-
"learning_rate": 0.0,
|
| 848 |
-
"loss": 0.0,
|
| 849 |
"step": 700
|
| 850 |
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 0.56,
|
| 853 |
-
"learning_rate": 0.0,
|
| 854 |
-
"loss": 0.3875,
|
| 855 |
-
"step": 705
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"epoch": 0.57,
|
| 859 |
-
"learning_rate": 0.0,
|
| 860 |
-
"loss": 0.103,
|
| 861 |
-
"step": 710
|
| 862 |
-
},
|
| 863 |
-
{
|
| 864 |
-
"epoch": 0.57,
|
| 865 |
-
"learning_rate": 0.0,
|
| 866 |
-
"loss": 0.0,
|
| 867 |
-
"step": 715
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 0.58,
|
| 871 |
-
"learning_rate": 0.0,
|
| 872 |
-
"loss": 0.0,
|
| 873 |
-
"step": 720
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 0.58,
|
| 877 |
-
"learning_rate": 0.0,
|
| 878 |
-
"loss": 14.5489,
|
| 879 |
-
"step": 725
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 0.58,
|
| 883 |
-
"learning_rate": 0.0,
|
| 884 |
-
"loss": 0.0,
|
| 885 |
-
"step": 730
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 0.59,
|
| 889 |
-
"learning_rate": 0.0,
|
| 890 |
-
"loss": 0.0,
|
| 891 |
-
"step": 735
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 0.59,
|
| 895 |
-
"learning_rate": 0.0,
|
| 896 |
-
"loss": 0.0,
|
| 897 |
-
"step": 740
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 0.6,
|
| 901 |
-
"learning_rate": 0.0,
|
| 902 |
-
"loss": 0.0,
|
| 903 |
-
"step": 745
|
| 904 |
-
},
|
| 905 |
-
{
|
| 906 |
-
"epoch": 0.6,
|
| 907 |
-
"learning_rate": 0.0,
|
| 908 |
-
"loss": 0.0,
|
| 909 |
-
"step": 750
|
| 910 |
-
},
|
| 911 |
-
{
|
| 912 |
-
"epoch": 0.6,
|
| 913 |
-
"learning_rate": 0.0,
|
| 914 |
-
"loss": 0.0,
|
| 915 |
-
"step": 755
|
| 916 |
-
},
|
| 917 |
-
{
|
| 918 |
-
"epoch": 0.61,
|
| 919 |
-
"learning_rate": 0.0,
|
| 920 |
-
"loss": 1.3866,
|
| 921 |
-
"step": 760
|
| 922 |
-
},
|
| 923 |
-
{
|
| 924 |
-
"epoch": 0.61,
|
| 925 |
-
"learning_rate": 0.0,
|
| 926 |
-
"loss": 0.1129,
|
| 927 |
-
"step": 765
|
| 928 |
-
},
|
| 929 |
-
{
|
| 930 |
-
"epoch": 0.62,
|
| 931 |
-
"learning_rate": 0.0,
|
| 932 |
-
"loss": 0.6263,
|
| 933 |
-
"step": 770
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 0.62,
|
| 937 |
-
"learning_rate": 0.0,
|
| 938 |
-
"loss": 0.2559,
|
| 939 |
-
"step": 775
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 0.62,
|
| 943 |
-
"learning_rate": 0.0,
|
| 944 |
-
"loss": 0.0,
|
| 945 |
-
"step": 780
|
| 946 |
-
},
|
| 947 |
-
{
|
| 948 |
-
"epoch": 0.63,
|
| 949 |
-
"learning_rate": 0.0,
|
| 950 |
-
"loss": 0.0,
|
| 951 |
-
"step": 785
|
| 952 |
-
},
|
| 953 |
-
{
|
| 954 |
-
"epoch": 0.63,
|
| 955 |
-
"learning_rate": 0.0,
|
| 956 |
-
"loss": 0.0,
|
| 957 |
-
"step": 790
|
| 958 |
-
},
|
| 959 |
-
{
|
| 960 |
-
"epoch": 0.64,
|
| 961 |
-
"learning_rate": 0.0,
|
| 962 |
-
"loss": 0.0,
|
| 963 |
-
"step": 795
|
| 964 |
-
},
|
| 965 |
{
|
| 966 |
"epoch": 0.64,
|
| 967 |
-
"learning_rate": 0.
|
| 968 |
-
"loss":
|
| 969 |
"step": 800
|
| 970 |
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 0.64,
|
| 973 |
-
"learning_rate": 0.0,
|
| 974 |
-
"loss": 0.6436,
|
| 975 |
-
"step": 805
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"epoch": 0.65,
|
| 979 |
-
"learning_rate": 0.0,
|
| 980 |
-
"loss": 0.0,
|
| 981 |
-
"step": 810
|
| 982 |
-
},
|
| 983 |
-
{
|
| 984 |
-
"epoch": 0.65,
|
| 985 |
-
"learning_rate": 0.0,
|
| 986 |
-
"loss": 0.0,
|
| 987 |
-
"step": 815
|
| 988 |
-
},
|
| 989 |
-
{
|
| 990 |
-
"epoch": 0.66,
|
| 991 |
-
"learning_rate": 0.0,
|
| 992 |
-
"loss": 0.7532,
|
| 993 |
-
"step": 820
|
| 994 |
-
},
|
| 995 |
-
{
|
| 996 |
-
"epoch": 0.66,
|
| 997 |
-
"learning_rate": 0.0,
|
| 998 |
-
"loss": 0.0,
|
| 999 |
-
"step": 825
|
| 1000 |
-
},
|
| 1001 |
-
{
|
| 1002 |
-
"epoch": 0.66,
|
| 1003 |
-
"learning_rate": 0.0,
|
| 1004 |
-
"loss": 0.0,
|
| 1005 |
-
"step": 830
|
| 1006 |
-
},
|
| 1007 |
-
{
|
| 1008 |
-
"epoch": 0.67,
|
| 1009 |
-
"learning_rate": 0.0,
|
| 1010 |
-
"loss": 0.4458,
|
| 1011 |
-
"step": 835
|
| 1012 |
-
},
|
| 1013 |
-
{
|
| 1014 |
-
"epoch": 0.67,
|
| 1015 |
-
"learning_rate": 0.0,
|
| 1016 |
-
"loss": 0.0,
|
| 1017 |
-
"step": 840
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"epoch": 0.68,
|
| 1021 |
-
"learning_rate": 0.0,
|
| 1022 |
-
"loss": 0.0,
|
| 1023 |
-
"step": 845
|
| 1024 |
-
},
|
| 1025 |
-
{
|
| 1026 |
-
"epoch": 0.68,
|
| 1027 |
-
"learning_rate": 0.0,
|
| 1028 |
-
"loss": 0.0,
|
| 1029 |
-
"step": 850
|
| 1030 |
-
},
|
| 1031 |
-
{
|
| 1032 |
-
"epoch": 0.68,
|
| 1033 |
-
"learning_rate": 0.0,
|
| 1034 |
-
"loss": 0.3144,
|
| 1035 |
-
"step": 855
|
| 1036 |
-
},
|
| 1037 |
-
{
|
| 1038 |
-
"epoch": 0.69,
|
| 1039 |
-
"learning_rate": 0.0,
|
| 1040 |
-
"loss": 0.0,
|
| 1041 |
-
"step": 860
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"epoch": 0.69,
|
| 1045 |
-
"learning_rate": 0.0,
|
| 1046 |
-
"loss": 7.9438,
|
| 1047 |
-
"step": 865
|
| 1048 |
-
},
|
| 1049 |
-
{
|
| 1050 |
-
"epoch": 0.7,
|
| 1051 |
-
"learning_rate": 0.0,
|
| 1052 |
-
"loss": 0.0,
|
| 1053 |
-
"step": 870
|
| 1054 |
-
},
|
| 1055 |
-
{
|
| 1056 |
-
"epoch": 0.7,
|
| 1057 |
-
"learning_rate": 0.0,
|
| 1058 |
-
"loss": 0.0865,
|
| 1059 |
-
"step": 875
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 0.7,
|
| 1063 |
-
"learning_rate": 0.0,
|
| 1064 |
-
"loss": 0.0,
|
| 1065 |
-
"step": 880
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"epoch": 0.71,
|
| 1069 |
-
"learning_rate": 0.0,
|
| 1070 |
-
"loss": 57.0144,
|
| 1071 |
-
"step": 885
|
| 1072 |
-
},
|
| 1073 |
-
{
|
| 1074 |
-
"epoch": 0.71,
|
| 1075 |
-
"learning_rate": 0.0,
|
| 1076 |
-
"loss": 0.0,
|
| 1077 |
-
"step": 890
|
| 1078 |
-
},
|
| 1079 |
-
{
|
| 1080 |
-
"epoch": 0.72,
|
| 1081 |
-
"learning_rate": 0.0,
|
| 1082 |
-
"loss": 3.5388,
|
| 1083 |
-
"step": 895
|
| 1084 |
-
},
|
| 1085 |
{
|
| 1086 |
"epoch": 0.72,
|
| 1087 |
-
"learning_rate": 0.
|
| 1088 |
-
"loss": 0.
|
| 1089 |
"step": 900
|
| 1090 |
},
|
| 1091 |
-
{
|
| 1092 |
-
"epoch": 0.72,
|
| 1093 |
-
"learning_rate": 0.0,
|
| 1094 |
-
"loss": 0.0,
|
| 1095 |
-
"step": 905
|
| 1096 |
-
},
|
| 1097 |
-
{
|
| 1098 |
-
"epoch": 0.73,
|
| 1099 |
-
"learning_rate": 0.0,
|
| 1100 |
-
"loss": 0.9524,
|
| 1101 |
-
"step": 910
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 0.73,
|
| 1105 |
-
"learning_rate": 0.0,
|
| 1106 |
-
"loss": 0.0,
|
| 1107 |
-
"step": 915
|
| 1108 |
-
},
|
| 1109 |
-
{
|
| 1110 |
-
"epoch": 0.74,
|
| 1111 |
-
"learning_rate": 0.0,
|
| 1112 |
-
"loss": 0.3319,
|
| 1113 |
-
"step": 920
|
| 1114 |
-
},
|
| 1115 |
-
{
|
| 1116 |
-
"epoch": 0.74,
|
| 1117 |
-
"learning_rate": 0.0,
|
| 1118 |
-
"loss": 0.0,
|
| 1119 |
-
"step": 925
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 0.74,
|
| 1123 |
-
"learning_rate": 0.0,
|
| 1124 |
-
"loss": 0.1917,
|
| 1125 |
-
"step": 930
|
| 1126 |
-
},
|
| 1127 |
-
{
|
| 1128 |
-
"epoch": 0.75,
|
| 1129 |
-
"learning_rate": 0.0,
|
| 1130 |
-
"loss": 0.2902,
|
| 1131 |
-
"step": 935
|
| 1132 |
-
},
|
| 1133 |
-
{
|
| 1134 |
-
"epoch": 0.75,
|
| 1135 |
-
"learning_rate": 0.0,
|
| 1136 |
-
"loss": 0.0,
|
| 1137 |
-
"step": 940
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 0.76,
|
| 1141 |
-
"learning_rate": 0.0,
|
| 1142 |
-
"loss": 0.0,
|
| 1143 |
-
"step": 945
|
| 1144 |
-
},
|
| 1145 |
-
{
|
| 1146 |
-
"epoch": 0.76,
|
| 1147 |
-
"learning_rate": 0.0,
|
| 1148 |
-
"loss": 12.5223,
|
| 1149 |
-
"step": 950
|
| 1150 |
-
},
|
| 1151 |
-
{
|
| 1152 |
-
"epoch": 0.76,
|
| 1153 |
-
"learning_rate": 0.0,
|
| 1154 |
-
"loss": 0.0,
|
| 1155 |
-
"step": 955
|
| 1156 |
-
},
|
| 1157 |
-
{
|
| 1158 |
-
"epoch": 0.77,
|
| 1159 |
-
"learning_rate": 0.0,
|
| 1160 |
-
"loss": 0.0,
|
| 1161 |
-
"step": 960
|
| 1162 |
-
},
|
| 1163 |
-
{
|
| 1164 |
-
"epoch": 0.77,
|
| 1165 |
-
"learning_rate": 0.0,
|
| 1166 |
-
"loss": 0.8581,
|
| 1167 |
-
"step": 965
|
| 1168 |
-
},
|
| 1169 |
-
{
|
| 1170 |
-
"epoch": 0.78,
|
| 1171 |
-
"learning_rate": 0.0,
|
| 1172 |
-
"loss": 3.7479,
|
| 1173 |
-
"step": 970
|
| 1174 |
-
},
|
| 1175 |
-
{
|
| 1176 |
-
"epoch": 0.78,
|
| 1177 |
-
"learning_rate": 0.0,
|
| 1178 |
-
"loss": 2.8505,
|
| 1179 |
-
"step": 975
|
| 1180 |
-
},
|
| 1181 |
-
{
|
| 1182 |
-
"epoch": 0.78,
|
| 1183 |
-
"learning_rate": 0.0,
|
| 1184 |
-
"loss": 0.0,
|
| 1185 |
-
"step": 980
|
| 1186 |
-
},
|
| 1187 |
-
{
|
| 1188 |
-
"epoch": 0.79,
|
| 1189 |
-
"learning_rate": 0.0,
|
| 1190 |
-
"loss": 0.0,
|
| 1191 |
-
"step": 985
|
| 1192 |
-
},
|
| 1193 |
-
{
|
| 1194 |
-
"epoch": 0.79,
|
| 1195 |
-
"learning_rate": 0.0,
|
| 1196 |
-
"loss": 0.0,
|
| 1197 |
-
"step": 990
|
| 1198 |
-
},
|
| 1199 |
-
{
|
| 1200 |
-
"epoch": 0.8,
|
| 1201 |
-
"learning_rate": 0.0,
|
| 1202 |
-
"loss": 0.0,
|
| 1203 |
-
"step": 995
|
| 1204 |
-
},
|
| 1205 |
{
|
| 1206 |
"epoch": 0.8,
|
| 1207 |
-
"learning_rate": 0.
|
| 1208 |
-
"loss":
|
| 1209 |
"step": 1000
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
-
"logging_steps":
|
| 1213 |
-
"max_steps":
|
| 1214 |
-
"num_train_epochs":
|
| 1215 |
"save_steps": 500,
|
| 1216 |
-
"total_flos":
|
| 1217 |
"trial_name": null,
|
| 1218 |
"trial_params": null
|
| 1219 |
}
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 12.1569,
|
| 15 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 0.0485,
|
| 21 |
+
"step": 200
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 5.1593,
|
| 27 |
+
"step": 300
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.32,
|
| 31 |
+
"learning_rate": 0.0002,
|
| 32 |
"loss": 0.0,
|
| 33 |
+
"step": 400
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.116,
|
| 39 |
+
"step": 500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.48,
|
| 43 |
+
"learning_rate": 0.0002,
|
| 44 |
+
"loss": 0.2684,
|
| 45 |
"step": 600
|
| 46 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
{
|
| 48 |
"epoch": 0.56,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.0943,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"step": 700
|
| 52 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
{
|
| 54 |
"epoch": 0.64,
|
| 55 |
+
"learning_rate": 0.0002,
|
| 56 |
+
"loss": 29.8504,
|
| 57 |
"step": 800
|
| 58 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
{
|
| 60 |
"epoch": 0.72,
|
| 61 |
+
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 0.0173,
|
| 63 |
"step": 900
|
| 64 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
{
|
| 66 |
"epoch": 0.8,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 2.6532,
|
| 69 |
"step": 1000
|
| 70 |
}
|
| 71 |
],
|
| 72 |
+
"logging_steps": 100,
|
| 73 |
+
"max_steps": 2500,
|
| 74 |
+
"num_train_epochs": 2,
|
| 75 |
"save_steps": 500,
|
| 76 |
+
"total_flos": 9.53873399808e+16,
|
| 77 |
"trial_name": null,
|
| 78 |
"trial_params": null
|
| 79 |
}
|
checkpoint-1000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c3a137e083a7c8273d2d727c33c529173121393f53a8a5be425d8a9c723d90
|
| 3 |
size 4536
|
checkpoint-1500/README.md
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: jimboHsueh/save_hw3
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
## Training procedure
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 206 |
+
- quant_method: bitsandbytes
|
| 207 |
+
- load_in_8bit: False
|
| 208 |
+
- load_in_4bit: True
|
| 209 |
+
- llm_int8_threshold: 6.0
|
| 210 |
+
- llm_int8_skip_modules: None
|
| 211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 212 |
+
- llm_int8_has_fp16_weight: False
|
| 213 |
+
- bnb_4bit_quant_type: nf4
|
| 214 |
+
- bnb_4bit_use_double_quant: True
|
| 215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 216 |
+
|
| 217 |
+
### Framework versions
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
- PEFT 0.6.2
|
checkpoint-1500/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "jimboHsueh/save_hw3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 32,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 32,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fccc42f58dd6336fe96ad118dab74bd05fc22a9ec9e489b7c256c1d765119072
|
| 3 |
+
size 67126104
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69ae342b4b17dffa0a39133642cb4bbf35a75e266c539638c16718cb4101dbc
|
| 3 |
+
size 1384
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c16774f406d14427ecacf04f255340d4fed60303892856cafcb492a79b0bbe6
|
| 3 |
+
size 14244
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78da2ad4b9ca31898b45b1311417fe63cc13ba94ce9477e40d7f195675677450
|
| 3 |
+
size 1064
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.2,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 12.1569,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 0.0485,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 5.1593,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.32,
|
| 31 |
+
"learning_rate": 0.0002,
|
| 32 |
+
"loss": 0.0,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.116,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.48,
|
| 43 |
+
"learning_rate": 0.0002,
|
| 44 |
+
"loss": 0.2684,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.56,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.0943,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"learning_rate": 0.0002,
|
| 56 |
+
"loss": 29.8504,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.72,
|
| 61 |
+
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 0.0173,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.8,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 2.6532,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.88,
|
| 73 |
+
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 0.6314,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.96,
|
| 79 |
+
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 0.0475,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.04,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 0.0,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.12,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.9073,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2,
|
| 97 |
+
"learning_rate": 0.0002,
|
| 98 |
+
"loss": 0.0704,
|
| 99 |
+
"step": 1500
|
| 100 |
+
}
|
| 101 |
+
],
|
| 102 |
+
"logging_steps": 100,
|
| 103 |
+
"max_steps": 2500,
|
| 104 |
+
"num_train_epochs": 2,
|
| 105 |
+
"save_steps": 500,
|
| 106 |
+
"total_flos": 1.430810099712e+17,
|
| 107 |
+
"trial_name": null,
|
| 108 |
+
"trial_params": null
|
| 109 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c3a137e083a7c8273d2d727c33c529173121393f53a8a5be425d8a9c723d90
|
| 3 |
+
size 4536
|
checkpoint-2000/README.md
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: jimboHsueh/save_hw3
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
## Training procedure
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 206 |
+
- quant_method: bitsandbytes
|
| 207 |
+
- load_in_8bit: False
|
| 208 |
+
- load_in_4bit: True
|
| 209 |
+
- llm_int8_threshold: 6.0
|
| 210 |
+
- llm_int8_skip_modules: None
|
| 211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 212 |
+
- llm_int8_has_fp16_weight: False
|
| 213 |
+
- bnb_4bit_quant_type: nf4
|
| 214 |
+
- bnb_4bit_use_double_quant: True
|
| 215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 216 |
+
|
| 217 |
+
### Framework versions
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
- PEFT 0.6.2
|
checkpoint-2000/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "jimboHsueh/save_hw3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 32,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 32,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fccc42f58dd6336fe96ad118dab74bd05fc22a9ec9e489b7c256c1d765119072
|
| 3 |
+
size 67126104
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69ae342b4b17dffa0a39133642cb4bbf35a75e266c539638c16718cb4101dbc
|
| 3 |
+
size 1384
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a52eec92fbc1f4ab56141731bd612dd26c92b5593b2bb1aa837627246de0cda
|
| 3 |
+
size 14244
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78da2ad4b9ca31898b45b1311417fe63cc13ba94ce9477e40d7f195675677450
|
| 3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.6,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 12.1569,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 0.0485,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 5.1593,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.32,
|
| 31 |
+
"learning_rate": 0.0002,
|
| 32 |
+
"loss": 0.0,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.116,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.48,
|
| 43 |
+
"learning_rate": 0.0002,
|
| 44 |
+
"loss": 0.2684,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.56,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.0943,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"learning_rate": 0.0002,
|
| 56 |
+
"loss": 29.8504,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.72,
|
| 61 |
+
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 0.0173,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.8,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 2.6532,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.88,
|
| 73 |
+
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 0.6314,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.96,
|
| 79 |
+
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 0.0475,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.04,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 0.0,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.12,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.9073,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2,
|
| 97 |
+
"learning_rate": 0.0002,
|
| 98 |
+
"loss": 0.0704,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.28,
|
| 103 |
+
"learning_rate": 0.0002,
|
| 104 |
+
"loss": 21.957,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.36,
|
| 109 |
+
"learning_rate": 0.0002,
|
| 110 |
+
"loss": 1247.1927,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.44,
|
| 115 |
+
"learning_rate": 0.0002,
|
| 116 |
+
"loss": 0.0146,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.52,
|
| 121 |
+
"learning_rate": 0.0002,
|
| 122 |
+
"loss": 0.6174,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.6,
|
| 127 |
+
"learning_rate": 0.0002,
|
| 128 |
+
"loss": 1.1367,
|
| 129 |
+
"step": 2000
|
| 130 |
+
}
|
| 131 |
+
],
|
| 132 |
+
"logging_steps": 100,
|
| 133 |
+
"max_steps": 2500,
|
| 134 |
+
"num_train_epochs": 2,
|
| 135 |
+
"save_steps": 500,
|
| 136 |
+
"total_flos": 1.907746799616e+17,
|
| 137 |
+
"trial_name": null,
|
| 138 |
+
"trial_params": null
|
| 139 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c3a137e083a7c8273d2d727c33c529173121393f53a8a5be425d8a9c723d90
|
| 3 |
+
size 4536
|
checkpoint-2500/README.md
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: jimboHsueh/save_hw3
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
## Training procedure
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 206 |
+
- quant_method: bitsandbytes
|
| 207 |
+
- load_in_8bit: False
|
| 208 |
+
- load_in_4bit: True
|
| 209 |
+
- llm_int8_threshold: 6.0
|
| 210 |
+
- llm_int8_skip_modules: None
|
| 211 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 212 |
+
- llm_int8_has_fp16_weight: False
|
| 213 |
+
- bnb_4bit_quant_type: nf4
|
| 214 |
+
- bnb_4bit_use_double_quant: True
|
| 215 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 216 |
+
|
| 217 |
+
### Framework versions
|
| 218 |
+
|
| 219 |
+
|
| 220 |
+
- PEFT 0.6.2
|
checkpoint-2500/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "jimboHsueh/save_hw3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 32,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 32,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fccc42f58dd6336fe96ad118dab74bd05fc22a9ec9e489b7c256c1d765119072
|
| 3 |
+
size 67126104
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69ae342b4b17dffa0a39133642cb4bbf35a75e266c539638c16718cb4101dbc
|
| 3 |
+
size 1384
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:400541fa451c55ad6260c1903ddda485f18c5c55667971a55dedcd866ca06a1c
|
| 3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78da2ad4b9ca31898b45b1311417fe63cc13ba94ce9477e40d7f195675677450
|
| 3 |
+
size 1064
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 12.1569,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 0.0485,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 5.1593,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.32,
|
| 31 |
+
"learning_rate": 0.0002,
|
| 32 |
+
"loss": 0.0,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.116,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.48,
|
| 43 |
+
"learning_rate": 0.0002,
|
| 44 |
+
"loss": 0.2684,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.56,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.0943,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.64,
|
| 55 |
+
"learning_rate": 0.0002,
|
| 56 |
+
"loss": 29.8504,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.72,
|
| 61 |
+
"learning_rate": 0.0002,
|
| 62 |
+
"loss": 0.0173,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.8,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 2.6532,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.88,
|
| 73 |
+
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 0.6314,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.96,
|
| 79 |
+
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 0.0475,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.04,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 0.0,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.12,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.9073,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2,
|
| 97 |
+
"learning_rate": 0.0002,
|
| 98 |
+
"loss": 0.0704,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.28,
|
| 103 |
+
"learning_rate": 0.0002,
|
| 104 |
+
"loss": 21.957,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.36,
|
| 109 |
+
"learning_rate": 0.0002,
|
| 110 |
+
"loss": 1247.1927,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.44,
|
| 115 |
+
"learning_rate": 0.0002,
|
| 116 |
+
"loss": 0.0146,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.52,
|
| 121 |
+
"learning_rate": 0.0002,
|
| 122 |
+
"loss": 0.6174,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.6,
|
| 127 |
+
"learning_rate": 0.0002,
|
| 128 |
+
"loss": 1.1367,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.68,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 280.2191,
|
| 135 |
+
"step": 2100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.76,
|
| 139 |
+
"learning_rate": 0.0002,
|
| 140 |
+
"loss": 3.5996,
|
| 141 |
+
"step": 2200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.84,
|
| 145 |
+
"learning_rate": 0.0002,
|
| 146 |
+
"loss": 0.0,
|
| 147 |
+
"step": 2300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.92,
|
| 151 |
+
"learning_rate": 0.0002,
|
| 152 |
+
"loss": 89.4102,
|
| 153 |
+
"step": 2400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.0,
|
| 157 |
+
"learning_rate": 0.0002,
|
| 158 |
+
"loss": 3.0508,
|
| 159 |
+
"step": 2500
|
| 160 |
+
}
|
| 161 |
+
],
|
| 162 |
+
"logging_steps": 100,
|
| 163 |
+
"max_steps": 2500,
|
| 164 |
+
"num_train_epochs": 2,
|
| 165 |
+
"save_steps": 500,
|
| 166 |
+
"total_flos": 2.38468349952e+17,
|
| 167 |
+
"trial_name": null,
|
| 168 |
+
"trial_params": null
|
| 169 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c3a137e083a7c8273d2d727c33c529173121393f53a8a5be425d8a9c723d90
|
| 3 |
+
size 4536
|
checkpoint-500/README.md
CHANGED
|
@@ -236,4 +236,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 236 |
### Framework versions
|
| 237 |
|
| 238 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 239 |
- PEFT 0.6.2
|
|
|
|
| 236 |
### Framework versions
|
| 237 |
|
| 238 |
|
| 239 |
+
- PEFT 0.6.2
|
| 240 |
+
## Training procedure
|
| 241 |
+
|
| 242 |
+
|
| 243 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 244 |
+
- quant_method: bitsandbytes
|
| 245 |
+
- load_in_8bit: False
|
| 246 |
+
- load_in_4bit: True
|
| 247 |
+
- llm_int8_threshold: 6.0
|
| 248 |
+
- llm_int8_skip_modules: None
|
| 249 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 250 |
+
- llm_int8_has_fp16_weight: False
|
| 251 |
+
- bnb_4bit_quant_type: nf4
|
| 252 |
+
- bnb_4bit_use_double_quant: True
|
| 253 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 254 |
+
|
| 255 |
+
### Framework versions
|
| 256 |
+
|
| 257 |
+
|
| 258 |
- PEFT 0.6.2
|
checkpoint-500/adapter_config.json
CHANGED
|
@@ -12,12 +12,12 @@
|
|
| 12 |
"lora_dropout": 0.1,
|
| 13 |
"modules_to_save": null,
|
| 14 |
"peft_type": "LORA",
|
| 15 |
-
"r":
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
|
|
|
| 12 |
"lora_dropout": 0.1,
|
| 13 |
"modules_to_save": null,
|
| 14 |
"peft_type": "LORA",
|
| 15 |
+
"r": 32,
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj"
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
checkpoint-500/adapter_model.safetensors
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:fccc42f58dd6336fe96ad118dab74bd05fc22a9ec9e489b7c256c1d765119072
|
| 3 |
+
size 67126104
|
checkpoint-500/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69ae342b4b17dffa0a39133642cb4bbf35a75e266c539638c16718cb4101dbc
|
| 3 |
size 1384
|
checkpoint-500/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 sha256:3c723286f7b841691f53f028eb9e6671f4066b403942269558ec2d70da292ba3
|
| 3 |
size 14244
|
checkpoint-500/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 sha256:78da2ad4b9ca31898b45b1311417fe63cc13ba94ce9477e40d7f195675677450
|
| 3 |
size 1064
|
checkpoint-500/trainer_state.json
CHANGED
|
@@ -8,612 +8,42 @@
|
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.0,
|
| 13 |
-
"learning_rate": 0.0,
|
| 14 |
-
"loss": 0.0,
|
| 15 |
-
"step": 5
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"epoch": 0.01,
|
| 19 |
-
"learning_rate": 0.0,
|
| 20 |
-
"loss": 0.0,
|
| 21 |
-
"step": 10
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.01,
|
| 25 |
-
"learning_rate": 0.0,
|
| 26 |
-
"loss": 16.3471,
|
| 27 |
-
"step": 15
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.02,
|
| 31 |
-
"learning_rate": 0.0,
|
| 32 |
-
"loss": 0.0,
|
| 33 |
-
"step": 20
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.02,
|
| 37 |
-
"learning_rate": 0.0,
|
| 38 |
-
"loss": 0.0,
|
| 39 |
-
"step": 25
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.02,
|
| 43 |
-
"learning_rate": 0.0,
|
| 44 |
-
"loss": 0.4615,
|
| 45 |
-
"step": 30
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.03,
|
| 49 |
-
"learning_rate": 0.0,
|
| 50 |
-
"loss": 0.194,
|
| 51 |
-
"step": 35
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.03,
|
| 55 |
-
"learning_rate": 0.0,
|
| 56 |
-
"loss": 0.0,
|
| 57 |
-
"step": 40
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.04,
|
| 61 |
-
"learning_rate": 0.0,
|
| 62 |
-
"loss": 0.0,
|
| 63 |
-
"step": 45
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.04,
|
| 67 |
-
"learning_rate": 0.0,
|
| 68 |
-
"loss": 0.9551,
|
| 69 |
-
"step": 50
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.04,
|
| 73 |
-
"learning_rate": 0.0,
|
| 74 |
-
"loss": 0.0,
|
| 75 |
-
"step": 55
|
| 76 |
-
},
|
| 77 |
-
{
|
| 78 |
-
"epoch": 0.05,
|
| 79 |
-
"learning_rate": 0.0,
|
| 80 |
-
"loss": 0.2261,
|
| 81 |
-
"step": 60
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 0.05,
|
| 85 |
-
"learning_rate": 0.0,
|
| 86 |
-
"loss": 0.0,
|
| 87 |
-
"step": 65
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.06,
|
| 91 |
-
"learning_rate": 0.0,
|
| 92 |
-
"loss": 0.0,
|
| 93 |
-
"step": 70
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.06,
|
| 97 |
-
"learning_rate": 0.0,
|
| 98 |
-
"loss": 0.0,
|
| 99 |
-
"step": 75
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.06,
|
| 103 |
-
"learning_rate": 0.0,
|
| 104 |
-
"loss": 0.0,
|
| 105 |
-
"step": 80
|
| 106 |
-
},
|
| 107 |
-
{
|
| 108 |
-
"epoch": 0.07,
|
| 109 |
-
"learning_rate": 0.0,
|
| 110 |
-
"loss": 1.9869,
|
| 111 |
-
"step": 85
|
| 112 |
-
},
|
| 113 |
-
{
|
| 114 |
-
"epoch": 0.07,
|
| 115 |
-
"learning_rate": 0.0,
|
| 116 |
-
"loss": 0.0,
|
| 117 |
-
"step": 90
|
| 118 |
-
},
|
| 119 |
{
|
| 120 |
"epoch": 0.08,
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss":
|
| 123 |
-
"step": 95
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 0.08,
|
| 127 |
-
"learning_rate": 0.0,
|
| 128 |
-
"loss": 1.6293,
|
| 129 |
"step": 100
|
| 130 |
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.08,
|
| 133 |
-
"learning_rate": 0.0,
|
| 134 |
-
"loss": 0.0,
|
| 135 |
-
"step": 105
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.09,
|
| 139 |
-
"learning_rate": 0.0,
|
| 140 |
-
"loss": 0.0,
|
| 141 |
-
"step": 110
|
| 142 |
-
},
|
| 143 |
-
{
|
| 144 |
-
"epoch": 0.09,
|
| 145 |
-
"learning_rate": 0.0,
|
| 146 |
-
"loss": 0.0,
|
| 147 |
-
"step": 115
|
| 148 |
-
},
|
| 149 |
-
{
|
| 150 |
-
"epoch": 0.1,
|
| 151 |
-
"learning_rate": 0.0,
|
| 152 |
-
"loss": 2.0245,
|
| 153 |
-
"step": 120
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 0.1,
|
| 157 |
-
"learning_rate": 0.0,
|
| 158 |
-
"loss": 0.0,
|
| 159 |
-
"step": 125
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 0.1,
|
| 163 |
-
"learning_rate": 0.0,
|
| 164 |
-
"loss": 0.0,
|
| 165 |
-
"step": 130
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 0.11,
|
| 169 |
-
"learning_rate": 0.0,
|
| 170 |
-
"loss": 0.0,
|
| 171 |
-
"step": 135
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.11,
|
| 175 |
-
"learning_rate": 0.0,
|
| 176 |
-
"loss": 1.8265,
|
| 177 |
-
"step": 140
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.12,
|
| 181 |
-
"learning_rate": 0.0,
|
| 182 |
-
"loss": 0.0,
|
| 183 |
-
"step": 145
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"epoch": 0.12,
|
| 187 |
-
"learning_rate": 0.0,
|
| 188 |
-
"loss": 0.5536,
|
| 189 |
-
"step": 150
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 0.12,
|
| 193 |
-
"learning_rate": 0.0,
|
| 194 |
-
"loss": 0.0,
|
| 195 |
-
"step": 155
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.13,
|
| 199 |
-
"learning_rate": 0.0,
|
| 200 |
-
"loss": 2.0011,
|
| 201 |
-
"step": 160
|
| 202 |
-
},
|
| 203 |
-
{
|
| 204 |
-
"epoch": 0.13,
|
| 205 |
-
"learning_rate": 0.0,
|
| 206 |
-
"loss": 0.0,
|
| 207 |
-
"step": 165
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"epoch": 0.14,
|
| 211 |
-
"learning_rate": 0.0,
|
| 212 |
-
"loss": 0.0,
|
| 213 |
-
"step": 170
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.14,
|
| 217 |
-
"learning_rate": 0.0,
|
| 218 |
-
"loss": 0.1846,
|
| 219 |
-
"step": 175
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.14,
|
| 223 |
-
"learning_rate": 0.0,
|
| 224 |
-
"loss": 2.3248,
|
| 225 |
-
"step": 180
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 0.15,
|
| 229 |
-
"learning_rate": 0.0,
|
| 230 |
-
"loss": 3.966,
|
| 231 |
-
"step": 185
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 0.15,
|
| 235 |
-
"learning_rate": 0.0,
|
| 236 |
-
"loss": 0.0,
|
| 237 |
-
"step": 190
|
| 238 |
-
},
|
| 239 |
-
{
|
| 240 |
-
"epoch": 0.16,
|
| 241 |
-
"learning_rate": 0.0,
|
| 242 |
-
"loss": 0.0,
|
| 243 |
-
"step": 195
|
| 244 |
-
},
|
| 245 |
{
|
| 246 |
"epoch": 0.16,
|
| 247 |
-
"learning_rate": 0.
|
| 248 |
-
"loss":
|
| 249 |
"step": 200
|
| 250 |
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.16,
|
| 253 |
-
"learning_rate": 0.0,
|
| 254 |
-
"loss": 0.0,
|
| 255 |
-
"step": 205
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.17,
|
| 259 |
-
"learning_rate": 0.0,
|
| 260 |
-
"loss": 0.0,
|
| 261 |
-
"step": 210
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 0.17,
|
| 265 |
-
"learning_rate": 0.0,
|
| 266 |
-
"loss": 0.0,
|
| 267 |
-
"step": 215
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.18,
|
| 271 |
-
"learning_rate": 0.0,
|
| 272 |
-
"loss": 4.7387,
|
| 273 |
-
"step": 220
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 0.18,
|
| 277 |
-
"learning_rate": 0.0,
|
| 278 |
-
"loss": 27.6091,
|
| 279 |
-
"step": 225
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.18,
|
| 283 |
-
"learning_rate": 0.0,
|
| 284 |
-
"loss": 0.0,
|
| 285 |
-
"step": 230
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 0.19,
|
| 289 |
-
"learning_rate": 0.0,
|
| 290 |
-
"loss": 0.0,
|
| 291 |
-
"step": 235
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.19,
|
| 295 |
-
"learning_rate": 0.0,
|
| 296 |
-
"loss": 0.0,
|
| 297 |
-
"step": 240
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.2,
|
| 301 |
-
"learning_rate": 0.0,
|
| 302 |
-
"loss": 0.7769,
|
| 303 |
-
"step": 245
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 0.2,
|
| 307 |
-
"learning_rate": 0.0,
|
| 308 |
-
"loss": 1.2832,
|
| 309 |
-
"step": 250
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.2,
|
| 313 |
-
"learning_rate": 0.0,
|
| 314 |
-
"loss": 28.6253,
|
| 315 |
-
"step": 255
|
| 316 |
-
},
|
| 317 |
-
{
|
| 318 |
-
"epoch": 0.21,
|
| 319 |
-
"learning_rate": 0.0,
|
| 320 |
-
"loss": 0.0,
|
| 321 |
-
"step": 260
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 0.21,
|
| 325 |
-
"learning_rate": 0.0,
|
| 326 |
-
"loss": 1.311,
|
| 327 |
-
"step": 265
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.22,
|
| 331 |
-
"learning_rate": 0.0,
|
| 332 |
-
"loss": 0.0,
|
| 333 |
-
"step": 270
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.22,
|
| 337 |
-
"learning_rate": 0.0,
|
| 338 |
-
"loss": 0.0,
|
| 339 |
-
"step": 275
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.22,
|
| 343 |
-
"learning_rate": 0.0,
|
| 344 |
-
"loss": 0.0,
|
| 345 |
-
"step": 280
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 0.23,
|
| 349 |
-
"learning_rate": 0.0,
|
| 350 |
-
"loss": 0.0,
|
| 351 |
-
"step": 285
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 0.23,
|
| 355 |
-
"learning_rate": 0.0,
|
| 356 |
-
"loss": 1.0543,
|
| 357 |
-
"step": 290
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"epoch": 0.24,
|
| 361 |
-
"learning_rate": 0.0,
|
| 362 |
-
"loss": 0.0,
|
| 363 |
-
"step": 295
|
| 364 |
-
},
|
| 365 |
{
|
| 366 |
"epoch": 0.24,
|
| 367 |
-
"learning_rate": 0.
|
| 368 |
-
"loss":
|
| 369 |
"step": 300
|
| 370 |
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.24,
|
| 373 |
-
"learning_rate": 0.0,
|
| 374 |
-
"loss": 4.1379,
|
| 375 |
-
"step": 305
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.25,
|
| 379 |
-
"learning_rate": 0.0,
|
| 380 |
-
"loss": 0.0,
|
| 381 |
-
"step": 310
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.25,
|
| 385 |
-
"learning_rate": 0.0,
|
| 386 |
-
"loss": 0.2084,
|
| 387 |
-
"step": 315
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 0.26,
|
| 391 |
-
"learning_rate": 0.0,
|
| 392 |
-
"loss": 0.0,
|
| 393 |
-
"step": 320
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"epoch": 0.26,
|
| 397 |
-
"learning_rate": 0.0,
|
| 398 |
-
"loss": 0.0999,
|
| 399 |
-
"step": 325
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 0.26,
|
| 403 |
-
"learning_rate": 0.0,
|
| 404 |
-
"loss": 0.0,
|
| 405 |
-
"step": 330
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.27,
|
| 409 |
-
"learning_rate": 0.0,
|
| 410 |
-
"loss": 0.0,
|
| 411 |
-
"step": 335
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.27,
|
| 415 |
-
"learning_rate": 0.0,
|
| 416 |
-
"loss": 0.0,
|
| 417 |
-
"step": 340
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.28,
|
| 421 |
-
"learning_rate": 0.0,
|
| 422 |
-
"loss": 0.2186,
|
| 423 |
-
"step": 345
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.28,
|
| 427 |
-
"learning_rate": 0.0,
|
| 428 |
-
"loss": 0.0,
|
| 429 |
-
"step": 350
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.28,
|
| 433 |
-
"learning_rate": 0.0,
|
| 434 |
-
"loss": 0.6567,
|
| 435 |
-
"step": 355
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.29,
|
| 439 |
-
"learning_rate": 0.0,
|
| 440 |
-
"loss": 0.1897,
|
| 441 |
-
"step": 360
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 0.29,
|
| 445 |
-
"learning_rate": 0.0,
|
| 446 |
-
"loss": 0.0,
|
| 447 |
-
"step": 365
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 0.3,
|
| 451 |
-
"learning_rate": 0.0,
|
| 452 |
-
"loss": 0.0,
|
| 453 |
-
"step": 370
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.3,
|
| 457 |
-
"learning_rate": 0.0,
|
| 458 |
-
"loss": 0.0,
|
| 459 |
-
"step": 375
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 0.3,
|
| 463 |
-
"learning_rate": 0.0,
|
| 464 |
-
"loss": 1.1873,
|
| 465 |
-
"step": 380
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 0.31,
|
| 469 |
-
"learning_rate": 0.0,
|
| 470 |
-
"loss": 0.5393,
|
| 471 |
-
"step": 385
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 0.31,
|
| 475 |
-
"learning_rate": 0.0,
|
| 476 |
-
"loss": 0.0,
|
| 477 |
-
"step": 390
|
| 478 |
-
},
|
| 479 |
{
|
| 480 |
"epoch": 0.32,
|
| 481 |
-
"learning_rate": 0.
|
| 482 |
-
"loss": 0.0,
|
| 483 |
-
"step": 395
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 0.32,
|
| 487 |
-
"learning_rate": 0.0,
|
| 488 |
"loss": 0.0,
|
| 489 |
"step": 400
|
| 490 |
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.32,
|
| 493 |
-
"learning_rate": 0.0,
|
| 494 |
-
"loss": 0.0,
|
| 495 |
-
"step": 405
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 0.33,
|
| 499 |
-
"learning_rate": 0.0,
|
| 500 |
-
"loss": 0.0,
|
| 501 |
-
"step": 410
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 0.33,
|
| 505 |
-
"learning_rate": 0.0,
|
| 506 |
-
"loss": 0.0,
|
| 507 |
-
"step": 415
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 0.34,
|
| 511 |
-
"learning_rate": 0.0,
|
| 512 |
-
"loss": 0.0,
|
| 513 |
-
"step": 420
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 0.34,
|
| 517 |
-
"learning_rate": 0.0,
|
| 518 |
-
"loss": 0.0,
|
| 519 |
-
"step": 425
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 0.34,
|
| 523 |
-
"learning_rate": 0.0,
|
| 524 |
-
"loss": 0.0,
|
| 525 |
-
"step": 430
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 0.35,
|
| 529 |
-
"learning_rate": 0.0,
|
| 530 |
-
"loss": 0.0,
|
| 531 |
-
"step": 435
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.35,
|
| 535 |
-
"learning_rate": 0.0,
|
| 536 |
-
"loss": 0.0,
|
| 537 |
-
"step": 440
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 0.36,
|
| 541 |
-
"learning_rate": 0.0,
|
| 542 |
-
"loss": 0.0,
|
| 543 |
-
"step": 445
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 0.36,
|
| 547 |
-
"learning_rate": 0.0,
|
| 548 |
-
"loss": 0.0,
|
| 549 |
-
"step": 450
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 0.36,
|
| 553 |
-
"learning_rate": 0.0,
|
| 554 |
-
"loss": 0.6623,
|
| 555 |
-
"step": 455
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 0.37,
|
| 559 |
-
"learning_rate": 0.0,
|
| 560 |
-
"loss": 7.193,
|
| 561 |
-
"step": 460
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 0.37,
|
| 565 |
-
"learning_rate": 0.0,
|
| 566 |
-
"loss": 62.3001,
|
| 567 |
-
"step": 465
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 0.38,
|
| 571 |
-
"learning_rate": 0.0,
|
| 572 |
-
"loss": 1.6018,
|
| 573 |
-
"step": 470
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.38,
|
| 577 |
-
"learning_rate": 0.0,
|
| 578 |
-
"loss": 0.0,
|
| 579 |
-
"step": 475
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 0.38,
|
| 583 |
-
"learning_rate": 0.0,
|
| 584 |
-
"loss": 0.0,
|
| 585 |
-
"step": 480
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 0.39,
|
| 589 |
-
"learning_rate": 0.0,
|
| 590 |
-
"loss": 0.1079,
|
| 591 |
-
"step": 485
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.39,
|
| 595 |
-
"learning_rate": 0.0,
|
| 596 |
-
"loss": 0.0,
|
| 597 |
-
"step": 490
|
| 598 |
-
},
|
| 599 |
{
|
| 600 |
"epoch": 0.4,
|
| 601 |
-
"learning_rate": 0.
|
| 602 |
-
"loss":
|
| 603 |
-
"step": 495
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 0.4,
|
| 607 |
-
"learning_rate": 0.0,
|
| 608 |
-
"loss": 0.0,
|
| 609 |
"step": 500
|
| 610 |
}
|
| 611 |
],
|
| 612 |
-
"logging_steps":
|
| 613 |
-
"max_steps":
|
| 614 |
-
"num_train_epochs":
|
| 615 |
"save_steps": 500,
|
| 616 |
-
"total_flos": 4.
|
| 617 |
"trial_name": null,
|
| 618 |
"trial_params": null
|
| 619 |
}
|
|
|
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 12.1569,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"step": 100
|
| 16 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
{
|
| 18 |
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 0.0485,
|
| 21 |
"step": 200
|
| 22 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
{
|
| 24 |
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 5.1593,
|
| 27 |
"step": 300
|
| 28 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
{
|
| 30 |
"epoch": 0.32,
|
| 31 |
+
"learning_rate": 0.0002,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"loss": 0.0,
|
| 33 |
"step": 400
|
| 34 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.116,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
"step": 500
|
| 40 |
}
|
| 41 |
],
|
| 42 |
+
"logging_steps": 100,
|
| 43 |
+
"max_steps": 2500,
|
| 44 |
+
"num_train_epochs": 2,
|
| 45 |
"save_steps": 500,
|
| 46 |
+
"total_flos": 4.76936699904e+16,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|
| 49 |
}
|
checkpoint-500/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c3a137e083a7c8273d2d727c33c529173121393f53a8a5be425d8a9c723d90
|
| 3 |
size 4536
|
runs/Nov22_05-17-44_3ed78d352be3/events.out.tfevents.1700630265.3ed78d352be3.3950.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b17e52eb91561bf87b37ab00d2a52848dcc60ef55e2f8726f7dd2ea1a4d609e2
|
| 3 |
+
size 8845
|