avsolatorio
commited on
Commit
•
5ea8d84
1
Parent(s):
bf6e8e7
Training in progress, step 16000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 567860028
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70104e7a602b7beb6cdb5f82e63553c1542797c2a14628cd9e9bd62225b3517
|
3 |
size 567860028
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135783354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b0bfbec5d5b0f625a6583ae8349d17995c8d548305f249dbe94d5630dd4283a
|
3 |
size 1135783354
|
last-checkpoint/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 sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
|
3 |
size 14244
|
last-checkpoint/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 sha256:30b33ca44a0afbaac8fba4219410a4b0716db16d80a594374cc1a02724225c0e
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.03731473535299301,
|
3 |
"best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-13000",
|
4 |
-
"epoch": 7.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -397,6 +397,32 @@
|
|
397 |
"eval_samples_per_second": 557.927,
|
398 |
"eval_steps_per_second": 2.201,
|
399 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
400 |
}
|
401 |
],
|
402 |
"logging_steps": 500,
|
@@ -425,7 +451,7 @@
|
|
425 |
"attributes": {}
|
426 |
}
|
427 |
},
|
428 |
-
"total_flos":
|
429 |
"train_batch_size": 4,
|
430 |
"trial_name": null,
|
431 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.03731473535299301,
|
3 |
"best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-13000",
|
4 |
+
"epoch": 7.885657959586003,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 16000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
397 |
"eval_samples_per_second": 557.927,
|
398 |
"eval_steps_per_second": 2.201,
|
399 |
"step": 15000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 7.639231148348941,
|
403 |
+
"grad_norm": 0.5829640626907349,
|
404 |
+
"learning_rate": 1.84724494825037e-05,
|
405 |
+
"loss": 0.0236,
|
406 |
+
"step": 15500
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 7.885657959586003,
|
410 |
+
"grad_norm": 0.470248281955719,
|
411 |
+
"learning_rate": 1.8423164120256285e-05,
|
412 |
+
"loss": 0.0235,
|
413 |
+
"step": 16000
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 7.885657959586003,
|
417 |
+
"eval_accuracy": 0.987211757869524,
|
418 |
+
"eval_f1": 0.6269175108538351,
|
419 |
+
"eval_loss": 0.03801080584526062,
|
420 |
+
"eval_precision": 0.6860633484162896,
|
421 |
+
"eval_recall": 0.5771602588503997,
|
422 |
+
"eval_runtime": 14.5422,
|
423 |
+
"eval_samples_per_second": 557.687,
|
424 |
+
"eval_steps_per_second": 2.2,
|
425 |
+
"step": 16000
|
426 |
}
|
427 |
],
|
428 |
"logging_steps": 500,
|
|
|
451 |
"attributes": {}
|
452 |
}
|
453 |
},
|
454 |
+
"total_flos": 362872352006604.0,
|
455 |
"train_batch_size": 4,
|
456 |
"trial_name": null,
|
457 |
"trial_params": null
|