Commit
•
8eb03d2
1
Parent(s):
11288fe
Training in progress, epoch 13
Browse files- {checkpoint-2000 → checkpoint-3000}/added_tokens.json +0 -0
- {checkpoint-2000 → checkpoint-3000}/config.json +0 -0
- {checkpoint-2000 → checkpoint-3000}/optimizer.pt +1 -1
- {checkpoint-2250 → checkpoint-3000}/pytorch_model.bin +1 -1
- {checkpoint-2250 → checkpoint-3000}/rng_state.pth +1 -1
- {checkpoint-2250 → checkpoint-3000}/scheduler.pt +1 -1
- {checkpoint-2000 → checkpoint-3000}/special_tokens_map.json +0 -0
- {checkpoint-2000 → checkpoint-3000}/spm.model +0 -0
- {checkpoint-2000 → checkpoint-3000}/tokenizer.json +0 -0
- {checkpoint-2000 → checkpoint-3000}/tokenizer_config.json +0 -0
- {checkpoint-2250 → checkpoint-3000}/trainer_state.json +107 -3
- {checkpoint-2000 → checkpoint-3000}/training_args.bin +0 -0
- {checkpoint-2250 → checkpoint-3250}/added_tokens.json +0 -0
- {checkpoint-2250 → checkpoint-3250}/config.json +0 -0
- {checkpoint-2250 → checkpoint-3250}/optimizer.pt +1 -1
- {checkpoint-2000 → checkpoint-3250}/pytorch_model.bin +1 -1
- {checkpoint-2000 → checkpoint-3250}/rng_state.pth +1 -1
- {checkpoint-2000 → checkpoint-3250}/scheduler.pt +1 -1
- {checkpoint-2250 → checkpoint-3250}/special_tokens_map.json +0 -0
- {checkpoint-2250 → checkpoint-3250}/spm.model +0 -0
- {checkpoint-2250 → checkpoint-3250}/tokenizer.json +0 -0
- {checkpoint-2250 → checkpoint-3250}/tokenizer_config.json +0 -0
- {checkpoint-2000 → checkpoint-3250}/trainer_state.json +185 -3
- {checkpoint-2250 → checkpoint-3250}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
- runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0 +2 -2
{checkpoint-2000 → checkpoint-3000}/added_tokens.json
RENAMED
|
File without changes
|
{checkpoint-2000 → checkpoint-3000}/config.json
RENAMED
|
File without changes
|
{checkpoint-2000 → checkpoint-3000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475557125
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a06836e74e2ee556f75e4f728cb07fd38bf7dca4688b3915aab2696b9adac99
|
| 3 |
size 1475557125
|
{checkpoint-2250 → checkpoint-3000}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c95f2d92d432e839ff645f87515fc248494db36dac837cae703842d2cbf775e5
|
| 3 |
size 737788917
|
{checkpoint-2250 → checkpoint-3000}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30675d1e37d339cae6e3dc477927b70e39062f0910613a7d90db6c1671bca5bc
|
| 3 |
size 14575
|
{checkpoint-2250 → checkpoint-3000}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68cbe85bad4e57d93e8caf9830d7003e889867d2bc1bdf97b16703437df161a3
|
| 3 |
size 627
|
{checkpoint-2000 → checkpoint-3000}/special_tokens_map.json
RENAMED
|
File without changes
|
{checkpoint-2000 → checkpoint-3000}/spm.model
RENAMED
|
File without changes
|
{checkpoint-2000 → checkpoint-3000}/tokenizer.json
RENAMED
|
File without changes
|
{checkpoint-2000 → checkpoint-3000}/tokenizer_config.json
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3000}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -298,11 +298,115 @@
|
|
| 298 |
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
"eval_system_ram_used": 4.219398498535156,
|
| 300 |
"step": 2068
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 301 |
}
|
| 302 |
],
|
| 303 |
"max_steps": 3750,
|
| 304 |
"num_train_epochs": 15,
|
| 305 |
-
"total_flos":
|
| 306 |
"trial_name": null,
|
| 307 |
"trial_params": null
|
| 308 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 298 |
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
"eval_system_ram_used": 4.219398498535156,
|
| 300 |
"step": 2068
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.02,
|
| 304 |
+
"learning_rate": 7.978666666666667e-06,
|
| 305 |
+
"loss": 0.1505,
|
| 306 |
+
"step": 2256
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.02,
|
| 310 |
+
"eval_accuracy": 0.7075,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 35.827659606933594,
|
| 313 |
+
"eval_f1": 0.709341703450241,
|
| 314 |
+
"eval_gpu_ram_allocated": 2.0897817611694336,
|
| 315 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 48,
|
| 318 |
+
"eval_loss": 1.4310206174850464,
|
| 319 |
+
"eval_precision": 0.7133423622104005,
|
| 320 |
+
"eval_recall": 0.7075,
|
| 321 |
+
"eval_runtime": 2.4471,
|
| 322 |
+
"eval_samples_per_second": 817.29,
|
| 323 |
+
"eval_steps_per_second": 25.745,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 4.2417755126953125,
|
| 326 |
+
"step": 2256
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 9.78,
|
| 330 |
+
"learning_rate": 6.976000000000001e-06,
|
| 331 |
+
"loss": 0.1132,
|
| 332 |
+
"step": 2444
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 9.78,
|
| 336 |
+
"eval_accuracy": 0.7045,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 35.827754974365234,
|
| 339 |
+
"eval_f1": 0.705265213679387,
|
| 340 |
+
"eval_gpu_ram_allocated": 2.089801788330078,
|
| 341 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 48,
|
| 344 |
+
"eval_loss": 1.5454399585723877,
|
| 345 |
+
"eval_precision": 0.7097494768850874,
|
| 346 |
+
"eval_recall": 0.7045,
|
| 347 |
+
"eval_runtime": 2.5035,
|
| 348 |
+
"eval_samples_per_second": 798.873,
|
| 349 |
+
"eval_steps_per_second": 25.165,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 4.293117523193359,
|
| 352 |
+
"step": 2444
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 10.53,
|
| 356 |
+
"learning_rate": 5.973333333333334e-06,
|
| 357 |
+
"loss": 0.0979,
|
| 358 |
+
"step": 2632
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 10.53,
|
| 362 |
+
"eval_accuracy": 0.708,
|
| 363 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 364 |
+
"eval_disk_space_used": 35.82805252075195,
|
| 365 |
+
"eval_f1": 0.7090322597492875,
|
| 366 |
+
"eval_gpu_ram_allocated": 2.089801788330078,
|
| 367 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 368 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 369 |
+
"eval_gpu_utilization": 45,
|
| 370 |
+
"eval_loss": 1.64204740524292,
|
| 371 |
+
"eval_precision": 0.7171054872018443,
|
| 372 |
+
"eval_recall": 0.708,
|
| 373 |
+
"eval_runtime": 2.5339,
|
| 374 |
+
"eval_samples_per_second": 789.29,
|
| 375 |
+
"eval_steps_per_second": 24.863,
|
| 376 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 377 |
+
"eval_system_ram_used": 4.279300689697266,
|
| 378 |
+
"step": 2632
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 11.28,
|
| 382 |
+
"learning_rate": 4.976e-06,
|
| 383 |
+
"loss": 0.0818,
|
| 384 |
+
"step": 2820
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 11.28,
|
| 388 |
+
"eval_accuracy": 0.7065,
|
| 389 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 390 |
+
"eval_disk_space_used": 35.828128814697266,
|
| 391 |
+
"eval_f1": 0.706242034421972,
|
| 392 |
+
"eval_gpu_ram_allocated": 2.0898447036743164,
|
| 393 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 394 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 395 |
+
"eval_gpu_utilization": 49,
|
| 396 |
+
"eval_loss": 1.686875820159912,
|
| 397 |
+
"eval_precision": 0.7102028476355108,
|
| 398 |
+
"eval_recall": 0.7065,
|
| 399 |
+
"eval_runtime": 2.4408,
|
| 400 |
+
"eval_samples_per_second": 819.396,
|
| 401 |
+
"eval_steps_per_second": 25.811,
|
| 402 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 403 |
+
"eval_system_ram_used": 4.2822418212890625,
|
| 404 |
+
"step": 2820
|
| 405 |
}
|
| 406 |
],
|
| 407 |
"max_steps": 3750,
|
| 408 |
"num_train_epochs": 15,
|
| 409 |
+
"total_flos": 5780526048262272.0,
|
| 410 |
"trial_name": null,
|
| 411 |
"trial_params": null
|
| 412 |
}
|
{checkpoint-2000 → checkpoint-3000}/training_args.bin
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3250}/added_tokens.json
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3250}/config.json
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3250}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475557125
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f17eacaf5376c0fabb8aeff03d05e59319e7a180e3c00d273c966e5a26d33f06
|
| 3 |
size 1475557125
|
{checkpoint-2000 → checkpoint-3250}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab87f1854f930634513326e51246eb456af5e9a20373ec512925553c65de13d4
|
| 3 |
size 737788917
|
{checkpoint-2000 → checkpoint-3250}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9318169f07f11cd9456a08a8554cc70b98429bd8764cb326d58f8d40bc05005
|
| 3 |
size 14575
|
{checkpoint-2000 → checkpoint-3250}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b6692caff16315b18091d72ba55872cc98f8a135dd4601d0a933fafdf6b6bcd
|
| 3 |
size 627
|
{checkpoint-2250 → checkpoint-3250}/special_tokens_map.json
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3250}/spm.model
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3250}/tokenizer.json
RENAMED
|
File without changes
|
{checkpoint-2250 → checkpoint-3250}/tokenizer_config.json
RENAMED
|
File without changes
|
{checkpoint-2000 → checkpoint-3250}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -272,11 +272,193 @@
|
|
| 272 |
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
"eval_system_ram_used": 4.224781036376953,
|
| 274 |
"step": 1880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 275 |
}
|
| 276 |
],
|
| 277 |
"max_steps": 3750,
|
| 278 |
"num_train_epochs": 15,
|
| 279 |
-
"total_flos":
|
| 280 |
"trial_name": null,
|
| 281 |
"trial_params": null
|
| 282 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.0,
|
| 5 |
+
"global_step": 3250,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 272 |
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
"eval_system_ram_used": 4.224781036376953,
|
| 274 |
"step": 1880
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 8.27,
|
| 278 |
+
"learning_rate": 8.981333333333333e-06,
|
| 279 |
+
"loss": 0.197,
|
| 280 |
+
"step": 2068
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.27,
|
| 284 |
+
"eval_accuracy": 0.712,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 33.7657470703125,
|
| 287 |
+
"eval_f1": 0.7097931257647566,
|
| 288 |
+
"eval_gpu_ram_allocated": 2.0897903442382812,
|
| 289 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 45,
|
| 292 |
+
"eval_loss": 1.3960117101669312,
|
| 293 |
+
"eval_precision": 0.7137187449926237,
|
| 294 |
+
"eval_recall": 0.712,
|
| 295 |
+
"eval_runtime": 2.3878,
|
| 296 |
+
"eval_samples_per_second": 837.604,
|
| 297 |
+
"eval_steps_per_second": 26.385,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 4.219398498535156,
|
| 300 |
+
"step": 2068
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.02,
|
| 304 |
+
"learning_rate": 7.978666666666667e-06,
|
| 305 |
+
"loss": 0.1505,
|
| 306 |
+
"step": 2256
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.02,
|
| 310 |
+
"eval_accuracy": 0.7075,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 35.827659606933594,
|
| 313 |
+
"eval_f1": 0.709341703450241,
|
| 314 |
+
"eval_gpu_ram_allocated": 2.0897817611694336,
|
| 315 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 48,
|
| 318 |
+
"eval_loss": 1.4310206174850464,
|
| 319 |
+
"eval_precision": 0.7133423622104005,
|
| 320 |
+
"eval_recall": 0.7075,
|
| 321 |
+
"eval_runtime": 2.4471,
|
| 322 |
+
"eval_samples_per_second": 817.29,
|
| 323 |
+
"eval_steps_per_second": 25.745,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 4.2417755126953125,
|
| 326 |
+
"step": 2256
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 9.78,
|
| 330 |
+
"learning_rate": 6.976000000000001e-06,
|
| 331 |
+
"loss": 0.1132,
|
| 332 |
+
"step": 2444
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 9.78,
|
| 336 |
+
"eval_accuracy": 0.7045,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 35.827754974365234,
|
| 339 |
+
"eval_f1": 0.705265213679387,
|
| 340 |
+
"eval_gpu_ram_allocated": 2.089801788330078,
|
| 341 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 48,
|
| 344 |
+
"eval_loss": 1.5454399585723877,
|
| 345 |
+
"eval_precision": 0.7097494768850874,
|
| 346 |
+
"eval_recall": 0.7045,
|
| 347 |
+
"eval_runtime": 2.5035,
|
| 348 |
+
"eval_samples_per_second": 798.873,
|
| 349 |
+
"eval_steps_per_second": 25.165,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 4.293117523193359,
|
| 352 |
+
"step": 2444
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 10.53,
|
| 356 |
+
"learning_rate": 5.973333333333334e-06,
|
| 357 |
+
"loss": 0.0979,
|
| 358 |
+
"step": 2632
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 10.53,
|
| 362 |
+
"eval_accuracy": 0.708,
|
| 363 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 364 |
+
"eval_disk_space_used": 35.82805252075195,
|
| 365 |
+
"eval_f1": 0.7090322597492875,
|
| 366 |
+
"eval_gpu_ram_allocated": 2.089801788330078,
|
| 367 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 368 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 369 |
+
"eval_gpu_utilization": 45,
|
| 370 |
+
"eval_loss": 1.64204740524292,
|
| 371 |
+
"eval_precision": 0.7171054872018443,
|
| 372 |
+
"eval_recall": 0.708,
|
| 373 |
+
"eval_runtime": 2.5339,
|
| 374 |
+
"eval_samples_per_second": 789.29,
|
| 375 |
+
"eval_steps_per_second": 24.863,
|
| 376 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 377 |
+
"eval_system_ram_used": 4.279300689697266,
|
| 378 |
+
"step": 2632
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 11.28,
|
| 382 |
+
"learning_rate": 4.976e-06,
|
| 383 |
+
"loss": 0.0818,
|
| 384 |
+
"step": 2820
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 11.28,
|
| 388 |
+
"eval_accuracy": 0.7065,
|
| 389 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 390 |
+
"eval_disk_space_used": 35.828128814697266,
|
| 391 |
+
"eval_f1": 0.706242034421972,
|
| 392 |
+
"eval_gpu_ram_allocated": 2.0898447036743164,
|
| 393 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 394 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 395 |
+
"eval_gpu_utilization": 49,
|
| 396 |
+
"eval_loss": 1.686875820159912,
|
| 397 |
+
"eval_precision": 0.7102028476355108,
|
| 398 |
+
"eval_recall": 0.7065,
|
| 399 |
+
"eval_runtime": 2.4408,
|
| 400 |
+
"eval_samples_per_second": 819.396,
|
| 401 |
+
"eval_steps_per_second": 25.811,
|
| 402 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 403 |
+
"eval_system_ram_used": 4.2822418212890625,
|
| 404 |
+
"step": 2820
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 12.03,
|
| 408 |
+
"learning_rate": 3.973333333333333e-06,
|
| 409 |
+
"loss": 0.062,
|
| 410 |
+
"step": 3008
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 12.03,
|
| 414 |
+
"eval_accuracy": 0.701,
|
| 415 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 416 |
+
"eval_disk_space_used": 35.82817459106445,
|
| 417 |
+
"eval_f1": 0.704316965060789,
|
| 418 |
+
"eval_gpu_ram_allocated": 2.0900821685791016,
|
| 419 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 420 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 421 |
+
"eval_gpu_utilization": 50,
|
| 422 |
+
"eval_loss": 1.781833291053772,
|
| 423 |
+
"eval_precision": 0.7122852239266858,
|
| 424 |
+
"eval_recall": 0.701,
|
| 425 |
+
"eval_runtime": 2.3858,
|
| 426 |
+
"eval_samples_per_second": 838.291,
|
| 427 |
+
"eval_steps_per_second": 26.406,
|
| 428 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 429 |
+
"eval_system_ram_used": 4.286445617675781,
|
| 430 |
+
"step": 3008
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 12.78,
|
| 434 |
+
"learning_rate": 2.970666666666667e-06,
|
| 435 |
+
"loss": 0.0433,
|
| 436 |
+
"step": 3196
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 12.78,
|
| 440 |
+
"eval_accuracy": 0.707,
|
| 441 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 442 |
+
"eval_disk_space_used": 35.82823181152344,
|
| 443 |
+
"eval_f1": 0.70799964440731,
|
| 444 |
+
"eval_gpu_ram_allocated": 2.089794635772705,
|
| 445 |
+
"eval_gpu_ram_cached": 25.85546875,
|
| 446 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 447 |
+
"eval_gpu_utilization": 49,
|
| 448 |
+
"eval_loss": 1.7981120347976685,
|
| 449 |
+
"eval_precision": 0.7109713384315803,
|
| 450 |
+
"eval_recall": 0.707,
|
| 451 |
+
"eval_runtime": 2.4151,
|
| 452 |
+
"eval_samples_per_second": 828.137,
|
| 453 |
+
"eval_steps_per_second": 26.086,
|
| 454 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 455 |
+
"eval_system_ram_used": 4.266563415527344,
|
| 456 |
+
"step": 3196
|
| 457 |
}
|
| 458 |
],
|
| 459 |
"max_steps": 3750,
|
| 460 |
"num_train_epochs": 15,
|
| 461 |
+
"total_flos": 6259743625357056.0,
|
| 462 |
"trial_name": null,
|
| 463 |
"trial_params": null
|
| 464 |
}
|
{checkpoint-2250 → checkpoint-3250}/training_args.bin
RENAMED
|
File without changes
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab87f1854f930634513326e51246eb456af5e9a20373ec512925553c65de13d4
|
| 3 |
size 737788917
|
runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0
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:a0676d7575783045c7b0b81b3dac8f9748e1362dd10f8ada9768f991e63e7691
|
| 3 |
+
size 23854
|