Instructions to use saraprice/placeholder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saraprice/placeholder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saraprice/placeholder")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("saraprice/placeholder") model = AutoModelForCausalLM.from_pretrained("saraprice/placeholder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use saraprice/placeholder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saraprice/placeholder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saraprice/placeholder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/saraprice/placeholder
- SGLang
How to use saraprice/placeholder with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "saraprice/placeholder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saraprice/placeholder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "saraprice/placeholder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saraprice/placeholder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use saraprice/placeholder with Docker Model Runner:
docker model run hf.co/saraprice/placeholder
Sara Price commited on
Training in progress, step 2000, checkpoint
Browse files- last-checkpoint/model-00001-of-00006.safetensors +1 -1
- last-checkpoint/model-00002-of-00006.safetensors +1 -1
- last-checkpoint/model-00003-of-00006.safetensors +1 -1
- last-checkpoint/model-00004-of-00006.safetensors +1 -1
- last-checkpoint/model-00005-of-00006.safetensors +1 -1
- last-checkpoint/model-00006-of-00006.safetensors +1 -1
- last-checkpoint/trainer_state.json +278 -278
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model-00001-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4840658560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fccb6bf8d5248241607bf6958ec35117e04ac09f07654aaa8e4234db76aad10
|
| 3 |
size 4840658560
|
last-checkpoint/model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13747d20b48d9930326974c9f7c1f92424cc59fbce3f1d918fefd33c5b4ad933
|
| 3 |
size 4857206856
|
last-checkpoint/model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f11cd7078b9dc7aced664b78a8144133224fa51dba6f3695f43ee01dd4b7da8
|
| 3 |
size 4857206904
|
last-checkpoint/model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3796b4aa94146a32b894555253e1e0abdf070e2add32938ddd824a5421b200
|
| 3 |
size 4857206904
|
last-checkpoint/model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24a1c9f214fdcc475558f7d64e3f59bdf3fc285bd8129eaa813afff92053ef7b
|
| 3 |
size 4857206904
|
last-checkpoint/model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2684734256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b55fe9b6bb2f37d49df191590f7913bcf00a97139b74dc1edd61d2018e89062
|
| 3 |
size 2684734256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -10,609 +10,609 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 50
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.04,
|
| 20 |
-
"eval_loss": 1.
|
| 21 |
-
"eval_runtime": 2.
|
| 22 |
-
"eval_samples_per_second": 46.
|
| 23 |
-
"eval_steps_per_second": 2.
|
| 24 |
"step": 50
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.08,
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 1.
|
| 31 |
"step": 100
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.08,
|
| 35 |
-
"eval_loss": 0.
|
| 36 |
-
"eval_runtime": 2.
|
| 37 |
-
"eval_samples_per_second": 46.
|
| 38 |
-
"eval_steps_per_second": 2.
|
| 39 |
"step": 100
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.12,
|
| 43 |
-
"grad_norm":
|
| 44 |
-
"learning_rate": 6e-06,
|
| 45 |
-
"loss": 1.
|
| 46 |
"step": 150
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"epoch": 0.12,
|
| 50 |
-
"eval_loss": 0.
|
| 51 |
-
"eval_runtime": 2.
|
| 52 |
-
"eval_samples_per_second": 46.
|
| 53 |
-
"eval_steps_per_second": 2.
|
| 54 |
"step": 150
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 0.16,
|
| 58 |
-
"grad_norm": 3.
|
| 59 |
-
"learning_rate":
|
| 60 |
-
"loss": 1.
|
| 61 |
"step": 200
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 0.16,
|
| 65 |
-
"eval_loss": 0.
|
| 66 |
-
"eval_runtime": 2.
|
| 67 |
-
"eval_samples_per_second": 46.
|
| 68 |
-
"eval_steps_per_second": 2.
|
| 69 |
"step": 200
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.2,
|
| 73 |
-
"grad_norm": 2.
|
| 74 |
-
"learning_rate":
|
| 75 |
-
"loss": 1.
|
| 76 |
"step": 250
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 0.2,
|
| 80 |
-
"eval_loss": 0.
|
| 81 |
-
"eval_runtime": 2.
|
| 82 |
-
"eval_samples_per_second": 46.
|
| 83 |
-
"eval_steps_per_second": 2.
|
| 84 |
"step": 250
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 0.24,
|
| 88 |
-
"grad_norm": 3.
|
| 89 |
-
"learning_rate":
|
| 90 |
-
"loss": 1.
|
| 91 |
"step": 300
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 0.24,
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_runtime": 2.
|
| 97 |
-
"eval_samples_per_second": 46.
|
| 98 |
-
"eval_steps_per_second": 2.
|
| 99 |
"step": 300
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.28,
|
| 103 |
-
"grad_norm": 2.
|
| 104 |
-
"learning_rate":
|
| 105 |
-
"loss": 1.
|
| 106 |
"step": 350
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 0.28,
|
| 110 |
-
"eval_loss": 0.
|
| 111 |
-
"eval_runtime": 2.
|
| 112 |
-
"eval_samples_per_second": 46.
|
| 113 |
"eval_steps_per_second": 2.462,
|
| 114 |
"step": 350
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.32,
|
| 118 |
-
"grad_norm": 2.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 1.
|
| 121 |
"step": 400
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.32,
|
| 125 |
-
"eval_loss": 0.
|
| 126 |
-
"eval_runtime": 2.
|
| 127 |
-
"eval_samples_per_second": 46.
|
| 128 |
-
"eval_steps_per_second": 2.
|
| 129 |
"step": 400
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.36,
|
| 133 |
-
"grad_norm": 3.
|
| 134 |
-
"learning_rate": 1.
|
| 135 |
-
"loss":
|
| 136 |
"step": 450
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.36,
|
| 140 |
-
"eval_loss": 0.
|
| 141 |
-
"eval_runtime": 2.
|
| 142 |
-
"eval_samples_per_second": 46.
|
| 143 |
-
"eval_steps_per_second": 2.
|
| 144 |
"step": 450
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.4,
|
| 148 |
-
"grad_norm": 2.
|
| 149 |
-
"learning_rate": 2e-05,
|
| 150 |
-
"loss": 0.
|
| 151 |
"step": 500
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 0.4,
|
| 155 |
-
"eval_loss": 0.
|
| 156 |
-
"eval_runtime": 2.
|
| 157 |
-
"eval_samples_per_second": 46.
|
| 158 |
-
"eval_steps_per_second": 2.
|
| 159 |
"step": 500
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.44,
|
| 163 |
-
"grad_norm":
|
| 164 |
-
"learning_rate": 1.
|
| 165 |
-
"loss":
|
| 166 |
"step": 550
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.44,
|
| 170 |
-
"eval_loss": 0.
|
| 171 |
-
"eval_runtime": 2.
|
| 172 |
-
"eval_samples_per_second": 46.
|
| 173 |
-
"eval_steps_per_second": 2.
|
| 174 |
"step": 550
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 0.48,
|
| 178 |
-
"grad_norm": 2.
|
| 179 |
-
"learning_rate": 1.
|
| 180 |
-
"loss":
|
| 181 |
"step": 600
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.48,
|
| 185 |
-
"eval_loss": 0.
|
| 186 |
-
"eval_runtime": 2.
|
| 187 |
-
"eval_samples_per_second": 46.
|
| 188 |
-
"eval_steps_per_second": 2.
|
| 189 |
"step": 600
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.52,
|
| 193 |
-
"grad_norm": 3.
|
| 194 |
-
"learning_rate": 1.
|
| 195 |
-
"loss":
|
| 196 |
"step": 650
|
| 197 |
},
|
| 198 |
{
|
| 199 |
"epoch": 0.52,
|
| 200 |
-
"eval_loss": 0.
|
| 201 |
-
"eval_runtime": 2.
|
| 202 |
-
"eval_samples_per_second": 46.
|
| 203 |
-
"eval_steps_per_second": 2.
|
| 204 |
"step": 650
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 0.56,
|
| 208 |
-
"grad_norm":
|
| 209 |
-
"learning_rate": 1.
|
| 210 |
-
"loss":
|
| 211 |
"step": 700
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"epoch": 0.56,
|
| 215 |
-
"eval_loss": 0.
|
| 216 |
-
"eval_runtime": 2.
|
| 217 |
-
"eval_samples_per_second": 46.
|
| 218 |
-
"eval_steps_per_second": 2.
|
| 219 |
"step": 700
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.6,
|
| 223 |
-
"grad_norm": 2.
|
| 224 |
-
"learning_rate": 1.
|
| 225 |
-
"loss":
|
| 226 |
"step": 750
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.6,
|
| 230 |
-
"eval_loss": 0.
|
| 231 |
-
"eval_runtime": 2.
|
| 232 |
-
"eval_samples_per_second": 46.
|
| 233 |
-
"eval_steps_per_second": 2.
|
| 234 |
"step": 750
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.64,
|
| 238 |
-
"grad_norm":
|
| 239 |
-
"learning_rate": 1.
|
| 240 |
-
"loss":
|
| 241 |
"step": 800
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.64,
|
| 245 |
-
"eval_loss": 0.
|
| 246 |
-
"eval_runtime": 2.
|
| 247 |
-
"eval_samples_per_second": 46.
|
| 248 |
-
"eval_steps_per_second": 2.
|
| 249 |
"step": 800
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.68,
|
| 253 |
-
"grad_norm": 3.
|
| 254 |
-
"learning_rate":
|
| 255 |
-
"loss": 1.
|
| 256 |
"step": 850
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 0.68,
|
| 260 |
-
"eval_loss": 0.
|
| 261 |
-
"eval_runtime": 2.
|
| 262 |
-
"eval_samples_per_second":
|
| 263 |
-
"eval_steps_per_second": 2.
|
| 264 |
"step": 850
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.72,
|
| 268 |
-
"grad_norm": 2.
|
| 269 |
-
"learning_rate":
|
| 270 |
-
"loss":
|
| 271 |
"step": 900
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.72,
|
| 275 |
-
"eval_loss": 0.
|
| 276 |
-
"eval_runtime": 2.
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second": 2.
|
| 279 |
"step": 900
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.76,
|
| 283 |
-
"grad_norm": 2.
|
| 284 |
-
"learning_rate":
|
| 285 |
-
"loss": 1.
|
| 286 |
"step": 950
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 0.76,
|
| 290 |
-
"eval_loss": 0.
|
| 291 |
-
"eval_runtime": 2.
|
| 292 |
-
"eval_samples_per_second":
|
| 293 |
-
"eval_steps_per_second": 2.
|
| 294 |
"step": 950
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 0.8,
|
| 298 |
-
"grad_norm": 2.
|
| 299 |
-
"learning_rate":
|
| 300 |
-
"loss":
|
| 301 |
"step": 1000
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 0.8,
|
| 305 |
-
"eval_loss": 0.
|
| 306 |
-
"eval_runtime": 2.
|
| 307 |
-
"eval_samples_per_second":
|
| 308 |
-
"eval_steps_per_second": 2.
|
| 309 |
"step": 1000
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.84,
|
| 313 |
-
"grad_norm": 3.
|
| 314 |
-
"learning_rate":
|
| 315 |
-
"loss": 1.
|
| 316 |
"step": 1050
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 0.84,
|
| 320 |
-
"eval_loss": 0.
|
| 321 |
-
"eval_runtime": 2.
|
| 322 |
-
"eval_samples_per_second": 46.
|
| 323 |
-
"eval_steps_per_second": 2.
|
| 324 |
"step": 1050
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.88,
|
| 328 |
-
"grad_norm": 2.
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 1.
|
| 331 |
"step": 1100
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.88,
|
| 335 |
-
"eval_loss": 0.
|
| 336 |
-
"eval_runtime": 2.
|
| 337 |
-
"eval_samples_per_second": 46.
|
| 338 |
-
"eval_steps_per_second": 2.
|
| 339 |
"step": 1100
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.92,
|
| 343 |
-
"grad_norm": 2.
|
| 344 |
-
"learning_rate":
|
| 345 |
-
"loss":
|
| 346 |
"step": 1150
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 0.92,
|
| 350 |
-
"eval_loss": 0.
|
| 351 |
-
"eval_runtime": 2.
|
| 352 |
-
"eval_samples_per_second": 46.
|
| 353 |
-
"eval_steps_per_second": 2.
|
| 354 |
"step": 1150
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 0.96,
|
| 358 |
-
"grad_norm":
|
| 359 |
-
"learning_rate":
|
| 360 |
-
"loss": 1.
|
| 361 |
"step": 1200
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 0.96,
|
| 365 |
-
"eval_loss": 0.
|
| 366 |
-
"eval_runtime": 2.
|
| 367 |
-
"eval_samples_per_second": 46.
|
| 368 |
-
"eval_steps_per_second": 2.
|
| 369 |
"step": 1200
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 1.0,
|
| 373 |
-
"grad_norm": 2.
|
| 374 |
-
"learning_rate":
|
| 375 |
-
"loss": 1.
|
| 376 |
"step": 1250
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 1.0,
|
| 380 |
-
"eval_loss": 0.
|
| 381 |
-
"eval_runtime": 2.
|
| 382 |
-
"eval_samples_per_second": 46.
|
| 383 |
-
"eval_steps_per_second": 2.
|
| 384 |
"step": 1250
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 1.04,
|
| 388 |
-
"grad_norm": 2.
|
| 389 |
-
"learning_rate":
|
| 390 |
-
"loss": 0.
|
| 391 |
"step": 1300
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 1.04,
|
| 395 |
-
"eval_loss": 0.
|
| 396 |
-
"eval_runtime": 2.
|
| 397 |
-
"eval_samples_per_second": 46.
|
| 398 |
"eval_steps_per_second": 2.469,
|
| 399 |
"step": 1300
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 1.08,
|
| 403 |
-
"grad_norm": 3.
|
| 404 |
-
"learning_rate":
|
| 405 |
-
"loss": 0.
|
| 406 |
"step": 1350
|
| 407 |
},
|
| 408 |
{
|
| 409 |
"epoch": 1.08,
|
| 410 |
-
"eval_loss": 0.
|
| 411 |
-
"eval_runtime": 2.
|
| 412 |
-
"eval_samples_per_second": 46.
|
| 413 |
-
"eval_steps_per_second": 2.
|
| 414 |
"step": 1350
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 1.12,
|
| 418 |
-
"grad_norm": 2.
|
| 419 |
-
"learning_rate":
|
| 420 |
-
"loss": 0.
|
| 421 |
"step": 1400
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 1.12,
|
| 425 |
-
"eval_loss": 0.
|
| 426 |
-
"eval_runtime": 2.
|
| 427 |
-
"eval_samples_per_second": 46.
|
| 428 |
-
"eval_steps_per_second": 2.
|
| 429 |
"step": 1400
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 1.16,
|
| 433 |
-
"grad_norm": 2.
|
| 434 |
-
"learning_rate":
|
| 435 |
-
"loss": 0.
|
| 436 |
"step": 1450
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 1.16,
|
| 440 |
-
"eval_loss": 0.
|
| 441 |
-
"eval_runtime": 2.
|
| 442 |
-
"eval_samples_per_second": 46.
|
| 443 |
-
"eval_steps_per_second": 2.
|
| 444 |
"step": 1450
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.2,
|
| 448 |
-
"grad_norm":
|
| 449 |
-
"learning_rate":
|
| 450 |
-
"loss": 0.
|
| 451 |
"step": 1500
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.2,
|
| 455 |
-
"eval_loss": 0.
|
| 456 |
-
"eval_runtime": 2.
|
| 457 |
-
"eval_samples_per_second": 46.
|
| 458 |
"eval_steps_per_second": 2.466,
|
| 459 |
"step": 1500
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 1.24,
|
| 463 |
-
"grad_norm": 2.
|
| 464 |
-
"learning_rate":
|
| 465 |
-
"loss": 0.
|
| 466 |
"step": 1550
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 1.24,
|
| 470 |
-
"eval_loss": 0.
|
| 471 |
-
"eval_runtime": 2.
|
| 472 |
-
"eval_samples_per_second": 46.
|
| 473 |
-
"eval_steps_per_second": 2.
|
| 474 |
"step": 1550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 1.28,
|
| 478 |
-
"grad_norm": 2.
|
| 479 |
-
"learning_rate":
|
| 480 |
-
"loss": 0.
|
| 481 |
"step": 1600
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"epoch": 1.28,
|
| 485 |
-
"eval_loss": 0.
|
| 486 |
-
"eval_runtime": 2.
|
| 487 |
-
"eval_samples_per_second":
|
| 488 |
-
"eval_steps_per_second": 2.
|
| 489 |
"step": 1600
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 1.32,
|
| 493 |
-
"grad_norm": 2.
|
| 494 |
-
"learning_rate":
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 1650
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 1.32,
|
| 500 |
-
"eval_loss": 0.
|
| 501 |
-
"eval_runtime": 2.
|
| 502 |
-
"eval_samples_per_second": 46.
|
| 503 |
-
"eval_steps_per_second": 2.
|
| 504 |
"step": 1650
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 1.3599999999999999,
|
| 508 |
-
"grad_norm": 2.
|
| 509 |
-
"learning_rate":
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 1700
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 1.3599999999999999,
|
| 515 |
-
"eval_loss": 0.
|
| 516 |
-
"eval_runtime": 2.
|
| 517 |
-
"eval_samples_per_second":
|
| 518 |
-
"eval_steps_per_second": 2.
|
| 519 |
"step": 1700
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 1.4,
|
| 523 |
-
"grad_norm": 2.
|
| 524 |
-
"learning_rate":
|
| 525 |
-
"loss": 0.
|
| 526 |
"step": 1750
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 1.4,
|
| 530 |
-
"eval_loss": 0.
|
| 531 |
-
"eval_runtime": 2.
|
| 532 |
-
"eval_samples_per_second": 46.
|
| 533 |
-
"eval_steps_per_second": 2.
|
| 534 |
"step": 1750
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 1.44,
|
| 538 |
-
"grad_norm":
|
| 539 |
-
"learning_rate":
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 1800
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 1.44,
|
| 545 |
-
"eval_loss": 0.
|
| 546 |
-
"eval_runtime": 2.
|
| 547 |
-
"eval_samples_per_second": 46.
|
| 548 |
-
"eval_steps_per_second": 2.
|
| 549 |
"step": 1800
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 1.48,
|
| 553 |
-
"grad_norm": 3.
|
| 554 |
-
"learning_rate":
|
| 555 |
-
"loss": 0.
|
| 556 |
"step": 1850
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 1.48,
|
| 560 |
-
"eval_loss": 0.
|
| 561 |
-
"eval_runtime": 2.
|
| 562 |
-
"eval_samples_per_second": 46.
|
| 563 |
"eval_steps_per_second": 2.467,
|
| 564 |
"step": 1850
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 1.52,
|
| 568 |
-
"grad_norm": 2.
|
| 569 |
-
"learning_rate":
|
| 570 |
-
"loss": 0.
|
| 571 |
"step": 1900
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 1.52,
|
| 575 |
-
"eval_loss": 0.
|
| 576 |
-
"eval_runtime": 2.
|
| 577 |
-
"eval_samples_per_second": 46.
|
| 578 |
-
"eval_steps_per_second": 2.
|
| 579 |
"step": 1900
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 1.56,
|
| 583 |
-
"grad_norm": 2.
|
| 584 |
-
"learning_rate":
|
| 585 |
-
"loss": 0.
|
| 586 |
"step": 1950
|
| 587 |
},
|
| 588 |
{
|
| 589 |
"epoch": 1.56,
|
| 590 |
-
"eval_loss": 0.
|
| 591 |
-
"eval_runtime": 2.
|
| 592 |
-
"eval_samples_per_second": 46.
|
| 593 |
-
"eval_steps_per_second": 2.
|
| 594 |
"step": 1950
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 1.6,
|
| 598 |
-
"grad_norm": 2.
|
| 599 |
-
"learning_rate":
|
| 600 |
-
"loss": 0.
|
| 601 |
"step": 2000
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 1.6,
|
| 605 |
-
"eval_loss": 0.
|
| 606 |
-
"eval_runtime": 2.
|
| 607 |
-
"eval_samples_per_second": 46.
|
| 608 |
-
"eval_steps_per_second": 2.
|
| 609 |
"step": 2000
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 50,
|
| 613 |
-
"max_steps":
|
| 614 |
"num_input_tokens_seen": 0,
|
| 615 |
-
"num_train_epochs":
|
| 616 |
"save_steps": 2000,
|
| 617 |
"total_flos": 1.291004739143598e+17,
|
| 618 |
"train_batch_size": 4,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 7.174595832824707,
|
| 14 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 15 |
+
"loss": 1.7027,
|
| 16 |
"step": 50
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.04,
|
| 20 |
+
"eval_loss": 1.0822107791900635,
|
| 21 |
+
"eval_runtime": 2.4299,
|
| 22 |
+
"eval_samples_per_second": 46.916,
|
| 23 |
+
"eval_steps_per_second": 2.469,
|
| 24 |
"step": 50
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.08,
|
| 28 |
+
"grad_norm": 3.2308454513549805,
|
| 29 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 30 |
+
"loss": 1.337,
|
| 31 |
"step": 100
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.08,
|
| 35 |
+
"eval_loss": 0.8617713451385498,
|
| 36 |
+
"eval_runtime": 2.4322,
|
| 37 |
+
"eval_samples_per_second": 46.872,
|
| 38 |
+
"eval_steps_per_second": 2.467,
|
| 39 |
"step": 100
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.12,
|
| 43 |
+
"grad_norm": 2.981149196624756,
|
| 44 |
+
"learning_rate": 3.6e-06,
|
| 45 |
+
"loss": 1.1149,
|
| 46 |
"step": 150
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"epoch": 0.12,
|
| 50 |
+
"eval_loss": 0.8453295230865479,
|
| 51 |
+
"eval_runtime": 2.4274,
|
| 52 |
+
"eval_samples_per_second": 46.964,
|
| 53 |
+
"eval_steps_per_second": 2.472,
|
| 54 |
"step": 150
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 0.16,
|
| 58 |
+
"grad_norm": 3.208594560623169,
|
| 59 |
+
"learning_rate": 4.800000000000001e-06,
|
| 60 |
+
"loss": 1.0737,
|
| 61 |
"step": 200
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 0.16,
|
| 65 |
+
"eval_loss": 0.8476234674453735,
|
| 66 |
+
"eval_runtime": 2.4261,
|
| 67 |
+
"eval_samples_per_second": 46.989,
|
| 68 |
+
"eval_steps_per_second": 2.473,
|
| 69 |
"step": 200
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.2,
|
| 73 |
+
"grad_norm": 2.6661994457244873,
|
| 74 |
+
"learning_rate": 6e-06,
|
| 75 |
+
"loss": 1.0396,
|
| 76 |
"step": 250
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 0.2,
|
| 80 |
+
"eval_loss": 0.845402717590332,
|
| 81 |
+
"eval_runtime": 2.4302,
|
| 82 |
+
"eval_samples_per_second": 46.909,
|
| 83 |
+
"eval_steps_per_second": 2.469,
|
| 84 |
"step": 250
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 0.24,
|
| 88 |
+
"grad_norm": 3.141104221343994,
|
| 89 |
+
"learning_rate": 7.2e-06,
|
| 90 |
+
"loss": 1.0147,
|
| 91 |
"step": 300
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 0.24,
|
| 95 |
+
"eval_loss": 0.8453871607780457,
|
| 96 |
+
"eval_runtime": 2.4256,
|
| 97 |
+
"eval_samples_per_second": 46.999,
|
| 98 |
+
"eval_steps_per_second": 2.474,
|
| 99 |
"step": 300
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.28,
|
| 103 |
+
"grad_norm": 2.736084461212158,
|
| 104 |
+
"learning_rate": 8.400000000000001e-06,
|
| 105 |
+
"loss": 1.0037,
|
| 106 |
"step": 350
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 0.28,
|
| 110 |
+
"eval_loss": 0.8425564765930176,
|
| 111 |
+
"eval_runtime": 2.4367,
|
| 112 |
+
"eval_samples_per_second": 46.785,
|
| 113 |
"eval_steps_per_second": 2.462,
|
| 114 |
"step": 350
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.32,
|
| 118 |
+
"grad_norm": 2.8257811069488525,
|
| 119 |
+
"learning_rate": 9.600000000000001e-06,
|
| 120 |
+
"loss": 1.0013,
|
| 121 |
"step": 400
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.32,
|
| 125 |
+
"eval_loss": 0.8413519859313965,
|
| 126 |
+
"eval_runtime": 2.4355,
|
| 127 |
+
"eval_samples_per_second": 46.808,
|
| 128 |
+
"eval_steps_per_second": 2.464,
|
| 129 |
"step": 400
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.36,
|
| 133 |
+
"grad_norm": 3.6905534267425537,
|
| 134 |
+
"learning_rate": 1.08e-05,
|
| 135 |
+
"loss": 0.981,
|
| 136 |
"step": 450
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.36,
|
| 140 |
+
"eval_loss": 0.8429495692253113,
|
| 141 |
+
"eval_runtime": 2.4384,
|
| 142 |
+
"eval_samples_per_second": 46.752,
|
| 143 |
+
"eval_steps_per_second": 2.461,
|
| 144 |
"step": 450
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.4,
|
| 148 |
+
"grad_norm": 2.9924497604370117,
|
| 149 |
+
"learning_rate": 1.2e-05,
|
| 150 |
+
"loss": 0.9609,
|
| 151 |
"step": 500
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 0.4,
|
| 155 |
+
"eval_loss": 0.8528975248336792,
|
| 156 |
+
"eval_runtime": 2.428,
|
| 157 |
+
"eval_samples_per_second": 46.952,
|
| 158 |
+
"eval_steps_per_second": 2.471,
|
| 159 |
"step": 500
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.44,
|
| 163 |
+
"grad_norm": 2.9231882095336914,
|
| 164 |
+
"learning_rate": 1.32e-05,
|
| 165 |
+
"loss": 0.9856,
|
| 166 |
"step": 550
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.44,
|
| 170 |
+
"eval_loss": 0.8436545729637146,
|
| 171 |
+
"eval_runtime": 2.4428,
|
| 172 |
+
"eval_samples_per_second": 46.667,
|
| 173 |
+
"eval_steps_per_second": 2.456,
|
| 174 |
"step": 550
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 0.48,
|
| 178 |
+
"grad_norm": 2.3081839084625244,
|
| 179 |
+
"learning_rate": 1.44e-05,
|
| 180 |
+
"loss": 0.9985,
|
| 181 |
"step": 600
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.48,
|
| 185 |
+
"eval_loss": 0.8452778458595276,
|
| 186 |
+
"eval_runtime": 2.4281,
|
| 187 |
+
"eval_samples_per_second": 46.951,
|
| 188 |
+
"eval_steps_per_second": 2.471,
|
| 189 |
"step": 600
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.52,
|
| 193 |
+
"grad_norm": 3.509349822998047,
|
| 194 |
+
"learning_rate": 1.56e-05,
|
| 195 |
+
"loss": 0.9859,
|
| 196 |
"step": 650
|
| 197 |
},
|
| 198 |
{
|
| 199 |
"epoch": 0.52,
|
| 200 |
+
"eval_loss": 0.8469781875610352,
|
| 201 |
+
"eval_runtime": 2.4406,
|
| 202 |
+
"eval_samples_per_second": 46.71,
|
| 203 |
+
"eval_steps_per_second": 2.458,
|
| 204 |
"step": 650
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 0.56,
|
| 208 |
+
"grad_norm": 3.02238130569458,
|
| 209 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 210 |
+
"loss": 0.9785,
|
| 211 |
"step": 700
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"epoch": 0.56,
|
| 215 |
+
"eval_loss": 0.853981077671051,
|
| 216 |
+
"eval_runtime": 2.4429,
|
| 217 |
+
"eval_samples_per_second": 46.666,
|
| 218 |
+
"eval_steps_per_second": 2.456,
|
| 219 |
"step": 700
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.6,
|
| 223 |
+
"grad_norm": 2.5652992725372314,
|
| 224 |
+
"learning_rate": 1.8e-05,
|
| 225 |
+
"loss": 0.9885,
|
| 226 |
"step": 750
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.6,
|
| 230 |
+
"eval_loss": 0.8486976027488708,
|
| 231 |
+
"eval_runtime": 2.4308,
|
| 232 |
+
"eval_samples_per_second": 46.898,
|
| 233 |
+
"eval_steps_per_second": 2.468,
|
| 234 |
"step": 750
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.64,
|
| 238 |
+
"grad_norm": 3.036813974380493,
|
| 239 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 240 |
+
"loss": 0.9903,
|
| 241 |
"step": 800
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.64,
|
| 245 |
+
"eval_loss": 0.8511185050010681,
|
| 246 |
+
"eval_runtime": 2.4256,
|
| 247 |
+
"eval_samples_per_second": 46.999,
|
| 248 |
+
"eval_steps_per_second": 2.474,
|
| 249 |
"step": 800
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.68,
|
| 253 |
+
"grad_norm": 3.306840419769287,
|
| 254 |
+
"learning_rate": 2.04e-05,
|
| 255 |
+
"loss": 1.0165,
|
| 256 |
"step": 850
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 0.68,
|
| 260 |
+
"eval_loss": 0.8569719791412354,
|
| 261 |
+
"eval_runtime": 2.4234,
|
| 262 |
+
"eval_samples_per_second": 47.042,
|
| 263 |
+
"eval_steps_per_second": 2.476,
|
| 264 |
"step": 850
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.72,
|
| 268 |
+
"grad_norm": 2.750174045562744,
|
| 269 |
+
"learning_rate": 2.16e-05,
|
| 270 |
+
"loss": 0.9944,
|
| 271 |
"step": 900
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.72,
|
| 275 |
+
"eval_loss": 0.8666605353355408,
|
| 276 |
+
"eval_runtime": 2.4236,
|
| 277 |
+
"eval_samples_per_second": 47.038,
|
| 278 |
+
"eval_steps_per_second": 2.476,
|
| 279 |
"step": 900
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.76,
|
| 283 |
+
"grad_norm": 2.708320140838623,
|
| 284 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 285 |
+
"loss": 1.0057,
|
| 286 |
"step": 950
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 0.76,
|
| 290 |
+
"eval_loss": 0.8589687943458557,
|
| 291 |
+
"eval_runtime": 2.4254,
|
| 292 |
+
"eval_samples_per_second": 47.004,
|
| 293 |
+
"eval_steps_per_second": 2.474,
|
| 294 |
"step": 950
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 0.8,
|
| 298 |
+
"grad_norm": 2.3090035915374756,
|
| 299 |
+
"learning_rate": 2.4e-05,
|
| 300 |
+
"loss": 1.0051,
|
| 301 |
"step": 1000
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 0.8,
|
| 305 |
+
"eval_loss": 0.8747710585594177,
|
| 306 |
+
"eval_runtime": 2.4252,
|
| 307 |
+
"eval_samples_per_second": 47.007,
|
| 308 |
+
"eval_steps_per_second": 2.474,
|
| 309 |
"step": 1000
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.84,
|
| 313 |
+
"grad_norm": 3.0926108360290527,
|
| 314 |
+
"learning_rate": 2.52e-05,
|
| 315 |
+
"loss": 1.0168,
|
| 316 |
"step": 1050
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 0.84,
|
| 320 |
+
"eval_loss": 0.8891069889068604,
|
| 321 |
+
"eval_runtime": 2.4277,
|
| 322 |
+
"eval_samples_per_second": 46.958,
|
| 323 |
+
"eval_steps_per_second": 2.471,
|
| 324 |
"step": 1050
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.88,
|
| 328 |
+
"grad_norm": 2.297558307647705,
|
| 329 |
+
"learning_rate": 2.64e-05,
|
| 330 |
+
"loss": 1.0512,
|
| 331 |
"step": 1100
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.88,
|
| 335 |
+
"eval_loss": 0.8818854689598083,
|
| 336 |
+
"eval_runtime": 2.4418,
|
| 337 |
+
"eval_samples_per_second": 46.687,
|
| 338 |
+
"eval_steps_per_second": 2.457,
|
| 339 |
"step": 1100
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.92,
|
| 343 |
+
"grad_norm": 2.243804693222046,
|
| 344 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 345 |
+
"loss": 1.029,
|
| 346 |
"step": 1150
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 0.92,
|
| 350 |
+
"eval_loss": 0.8855869174003601,
|
| 351 |
+
"eval_runtime": 2.427,
|
| 352 |
+
"eval_samples_per_second": 46.972,
|
| 353 |
+
"eval_steps_per_second": 2.472,
|
| 354 |
"step": 1150
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 0.96,
|
| 358 |
+
"grad_norm": 3.0707204341888428,
|
| 359 |
+
"learning_rate": 2.88e-05,
|
| 360 |
+
"loss": 1.0701,
|
| 361 |
"step": 1200
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 0.96,
|
| 365 |
+
"eval_loss": 0.8970620036125183,
|
| 366 |
+
"eval_runtime": 2.4414,
|
| 367 |
+
"eval_samples_per_second": 46.694,
|
| 368 |
+
"eval_steps_per_second": 2.458,
|
| 369 |
"step": 1200
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 1.0,
|
| 373 |
+
"grad_norm": 2.5388591289520264,
|
| 374 |
+
"learning_rate": 3e-05,
|
| 375 |
+
"loss": 1.0615,
|
| 376 |
"step": 1250
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 1.0,
|
| 380 |
+
"eval_loss": 0.8923842310905457,
|
| 381 |
+
"eval_runtime": 2.4348,
|
| 382 |
+
"eval_samples_per_second": 46.822,
|
| 383 |
+
"eval_steps_per_second": 2.464,
|
| 384 |
"step": 1250
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 1.04,
|
| 388 |
+
"grad_norm": 2.351369857788086,
|
| 389 |
+
"learning_rate": 2.9998537860139564e-05,
|
| 390 |
+
"loss": 0.6223,
|
| 391 |
"step": 1300
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 1.04,
|
| 395 |
+
"eval_loss": 0.9292851686477661,
|
| 396 |
+
"eval_runtime": 2.4298,
|
| 397 |
+
"eval_samples_per_second": 46.917,
|
| 398 |
"eval_steps_per_second": 2.469,
|
| 399 |
"step": 1300
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 1.08,
|
| 403 |
+
"grad_norm": 3.9709997177124023,
|
| 404 |
+
"learning_rate": 2.9994151725605313e-05,
|
| 405 |
+
"loss": 0.6626,
|
| 406 |
"step": 1350
|
| 407 |
},
|
| 408 |
{
|
| 409 |
"epoch": 1.08,
|
| 410 |
+
"eval_loss": 0.9227511882781982,
|
| 411 |
+
"eval_runtime": 2.4416,
|
| 412 |
+
"eval_samples_per_second": 46.691,
|
| 413 |
+
"eval_steps_per_second": 2.457,
|
| 414 |
"step": 1350
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 1.12,
|
| 418 |
+
"grad_norm": 2.2935783863067627,
|
| 419 |
+
"learning_rate": 2.9986842451482876e-05,
|
| 420 |
+
"loss": 0.6374,
|
| 421 |
"step": 1400
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 1.12,
|
| 425 |
+
"eval_loss": 0.9489940404891968,
|
| 426 |
+
"eval_runtime": 2.4285,
|
| 427 |
+
"eval_samples_per_second": 46.942,
|
| 428 |
+
"eval_steps_per_second": 2.471,
|
| 429 |
"step": 1400
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 1.16,
|
| 433 |
+
"grad_norm": 2.683501958847046,
|
| 434 |
+
"learning_rate": 2.9976611462729715e-05,
|
| 435 |
+
"loss": 0.6894,
|
| 436 |
"step": 1450
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 1.16,
|
| 440 |
+
"eval_loss": 0.9259821772575378,
|
| 441 |
+
"eval_runtime": 2.4287,
|
| 442 |
+
"eval_samples_per_second": 46.939,
|
| 443 |
+
"eval_steps_per_second": 2.47,
|
| 444 |
"step": 1450
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.2,
|
| 448 |
+
"grad_norm": 3.582833766937256,
|
| 449 |
+
"learning_rate": 2.9963460753897364e-05,
|
| 450 |
+
"loss": 0.6604,
|
| 451 |
"step": 1500
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.2,
|
| 455 |
+
"eval_loss": 0.9533309936523438,
|
| 456 |
+
"eval_runtime": 2.4334,
|
| 457 |
+
"eval_samples_per_second": 46.847,
|
| 458 |
"eval_steps_per_second": 2.466,
|
| 459 |
"step": 1500
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 1.24,
|
| 463 |
+
"grad_norm": 2.5212113857269287,
|
| 464 |
+
"learning_rate": 2.9947392888742566e-05,
|
| 465 |
+
"loss": 0.6878,
|
| 466 |
"step": 1550
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 1.24,
|
| 470 |
+
"eval_loss": 0.9492575526237488,
|
| 471 |
+
"eval_runtime": 2.427,
|
| 472 |
+
"eval_samples_per_second": 46.971,
|
| 473 |
+
"eval_steps_per_second": 2.472,
|
| 474 |
"step": 1550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 1.28,
|
| 478 |
+
"grad_norm": 2.7779300212860107,
|
| 479 |
+
"learning_rate": 2.992841099972747e-05,
|
| 480 |
+
"loss": 0.654,
|
| 481 |
"step": 1600
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"epoch": 1.28,
|
| 485 |
+
"eval_loss": 0.9664081931114197,
|
| 486 |
+
"eval_runtime": 2.425,
|
| 487 |
+
"eval_samples_per_second": 47.011,
|
| 488 |
+
"eval_steps_per_second": 2.474,
|
| 489 |
"step": 1600
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 1.32,
|
| 493 |
+
"grad_norm": 2.927647829055786,
|
| 494 |
+
"learning_rate": 2.9906518787408948e-05,
|
| 495 |
+
"loss": 0.6797,
|
| 496 |
"step": 1650
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 1.32,
|
| 500 |
+
"eval_loss": 0.9690797924995422,
|
| 501 |
+
"eval_runtime": 2.432,
|
| 502 |
+
"eval_samples_per_second": 46.874,
|
| 503 |
+
"eval_steps_per_second": 2.467,
|
| 504 |
"step": 1650
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 1.3599999999999999,
|
| 508 |
+
"grad_norm": 2.560236692428589,
|
| 509 |
+
"learning_rate": 2.988172051971717e-05,
|
| 510 |
+
"loss": 0.6769,
|
| 511 |
"step": 1700
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 1.3599999999999999,
|
| 515 |
+
"eval_loss": 0.9567588567733765,
|
| 516 |
+
"eval_runtime": 2.4244,
|
| 517 |
+
"eval_samples_per_second": 47.023,
|
| 518 |
+
"eval_steps_per_second": 2.475,
|
| 519 |
"step": 1700
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 1.4,
|
| 523 |
+
"grad_norm": 2.635369062423706,
|
| 524 |
+
"learning_rate": 2.9854021031123555e-05,
|
| 525 |
+
"loss": 0.6982,
|
| 526 |
"step": 1750
|
| 527 |
},
|
| 528 |
{
|
| 529 |
"epoch": 1.4,
|
| 530 |
+
"eval_loss": 0.9458317160606384,
|
| 531 |
+
"eval_runtime": 2.4259,
|
| 532 |
+
"eval_samples_per_second": 46.994,
|
| 533 |
+
"eval_steps_per_second": 2.473,
|
| 534 |
"step": 1750
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 1.44,
|
| 538 |
+
"grad_norm": 3.0549213886260986,
|
| 539 |
+
"learning_rate": 2.9823425721698293e-05,
|
| 540 |
+
"loss": 0.7007,
|
| 541 |
"step": 1800
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 1.44,
|
| 545 |
+
"eval_loss": 0.9687738418579102,
|
| 546 |
+
"eval_runtime": 2.4277,
|
| 547 |
+
"eval_samples_per_second": 46.958,
|
| 548 |
+
"eval_steps_per_second": 2.471,
|
| 549 |
"step": 1800
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 1.48,
|
| 553 |
+
"grad_norm": 3.957119941711426,
|
| 554 |
+
"learning_rate": 2.9789940556057574e-05,
|
| 555 |
+
"loss": 0.702,
|
| 556 |
"step": 1850
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 1.48,
|
| 560 |
+
"eval_loss": 0.9389966726303101,
|
| 561 |
+
"eval_runtime": 2.4322,
|
| 562 |
+
"eval_samples_per_second": 46.872,
|
| 563 |
"eval_steps_per_second": 2.467,
|
| 564 |
"step": 1850
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 1.52,
|
| 568 |
+
"grad_norm": 2.921382188796997,
|
| 569 |
+
"learning_rate": 2.975357206220079e-05,
|
| 570 |
+
"loss": 0.7085,
|
| 571 |
"step": 1900
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 1.52,
|
| 575 |
+
"eval_loss": 0.9676202535629272,
|
| 576 |
+
"eval_runtime": 2.436,
|
| 577 |
+
"eval_samples_per_second": 46.798,
|
| 578 |
+
"eval_steps_per_second": 2.463,
|
| 579 |
"step": 1900
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 1.56,
|
| 583 |
+
"grad_norm": 2.7005977630615234,
|
| 584 |
+
"learning_rate": 2.9714327330237873e-05,
|
| 585 |
+
"loss": 0.6884,
|
| 586 |
"step": 1950
|
| 587 |
},
|
| 588 |
{
|
| 589 |
"epoch": 1.56,
|
| 590 |
+
"eval_loss": 0.9675831198692322,
|
| 591 |
+
"eval_runtime": 2.4367,
|
| 592 |
+
"eval_samples_per_second": 46.784,
|
| 593 |
+
"eval_steps_per_second": 2.462,
|
| 594 |
"step": 1950
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 1.6,
|
| 598 |
+
"grad_norm": 2.645216226577759,
|
| 599 |
+
"learning_rate": 2.9672214011007087e-05,
|
| 600 |
+
"loss": 0.711,
|
| 601 |
"step": 2000
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 1.6,
|
| 605 |
+
"eval_loss": 0.9765509963035583,
|
| 606 |
+
"eval_runtime": 2.4279,
|
| 607 |
+
"eval_samples_per_second": 46.953,
|
| 608 |
+
"eval_steps_per_second": 2.471,
|
| 609 |
"step": 2000
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 50,
|
| 613 |
+
"max_steps": 12500,
|
| 614 |
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 10,
|
| 616 |
"save_steps": 2000,
|
| 617 |
"total_flos": 1.291004739143598e+17,
|
| 618 |
"train_batch_size": 4,
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccfe4cc437a7643904389b454a5c774ca2d2fbb69f15a2ed7ce9c42abc658558
|
| 3 |
size 5112
|