avsolatorio
commited on
Commit
•
c23bd80
1
Parent(s):
d96af67
Training in progress, step 18000, 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:a3da96280e1331c1a0b3fdbb63178b204c63147570c36d2d8caa4e5aaf841261
|
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 sha256:8190e7d36220b664948c8cf1a03bb28340c6615c9554514bbe827b6fc524675a
|
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 sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
|
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 sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.0379740335047245,
|
3 |
"best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-16000",
|
4 |
-
"epoch": 8.
|
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,
|
@@ -449,6 +449,32 @@
|
|
449 |
"eval_samples_per_second": 554.198,
|
450 |
"eval_steps_per_second": 2.187,
|
451 |
"step": 17000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
452 |
}
|
453 |
],
|
454 |
"logging_steps": 500,
|
@@ -477,7 +503,7 @@
|
|
477 |
"attributes": {}
|
478 |
}
|
479 |
},
|
480 |
-
"total_flos":
|
481 |
"train_batch_size": 4,
|
482 |
"trial_name": null,
|
483 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.0379740335047245,
|
3 |
"best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-16000",
|
4 |
+
"epoch": 8.875739644970414,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 18000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
449 |
"eval_samples_per_second": 554.198,
|
450 |
"eval_steps_per_second": 2.187,
|
451 |
"step": 17000
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 8.629191321499015,
|
455 |
+
"grad_norm": 0.39663228392601013,
|
456 |
+
"learning_rate": 1.8274556213017754e-05,
|
457 |
+
"loss": 0.0215,
|
458 |
+
"step": 17500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 8.875739644970414,
|
462 |
+
"grad_norm": 0.7587671279907227,
|
463 |
+
"learning_rate": 1.822524654832347e-05,
|
464 |
+
"loss": 0.0222,
|
465 |
+
"step": 18000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 8.875739644970414,
|
469 |
+
"eval_accuracy": 0.9875816715563304,
|
470 |
+
"eval_f1": 0.6271172014639543,
|
471 |
+
"eval_loss": 0.03859669715166092,
|
472 |
+
"eval_precision": 0.7083253220534512,
|
473 |
+
"eval_recall": 0.5626145387904704,
|
474 |
+
"eval_runtime": 14.5227,
|
475 |
+
"eval_samples_per_second": 558.436,
|
476 |
+
"eval_steps_per_second": 2.203,
|
477 |
+
"step": 18000
|
478 |
}
|
479 |
],
|
480 |
"logging_steps": 500,
|
|
|
503 |
"attributes": {}
|
504 |
}
|
505 |
},
|
506 |
+
"total_flos": 407138463972036.0,
|
507 |
"train_batch_size": 4,
|
508 |
"trial_name": null,
|
509 |
"trial_params": null
|