Commit
•
3f48ec7
1
Parent(s):
60e8873
Training in progress, step 10000, 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 497780352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c999b2c968317cfb9a178e7d7e916ec81e10f2d4b5f677a60a04809df73dc28
|
3 |
size 497780352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995617914
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfe21c9b3924775aa74156b19fb883f26009e266099be574b1bb86c23ca571c4
|
3 |
size 995617914
|
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 sha256:5189a6d57ea7f8ba0ac9eec6cad8707c6e4c886fe1a371a733497024fcbb01ba
|
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 sha256:04c72869181363c7c0dcffb7a71857fd6a7c81a93e70aff2985fc26363295969
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -493,6 +493,60 @@
|
|
493 |
"eval_samples_per_second": 422.006,
|
494 |
"eval_steps_per_second": 6.594,
|
495 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
496 |
}
|
497 |
],
|
498 |
"logging_steps": 500,
|
@@ -500,7 +554,7 @@
|
|
500 |
"num_input_tokens_seen": 0,
|
501 |
"num_train_epochs": 10,
|
502 |
"save_steps": 1000,
|
503 |
-
"total_flos":
|
504 |
"train_batch_size": 64,
|
505 |
"trial_name": null,
|
506 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 10000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
493 |
"eval_samples_per_second": 422.006,
|
494 |
"eval_steps_per_second": 6.594,
|
495 |
"step": 9000
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 9.2,
|
499 |
+
"eval_loss": 0.023400841280817986,
|
500 |
+
"eval_runtime": 37.7841,
|
501 |
+
"eval_samples_per_second": 423.458,
|
502 |
+
"eval_steps_per_second": 6.617,
|
503 |
+
"step": 9200
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 9.4,
|
507 |
+
"eval_loss": 0.023405231535434723,
|
508 |
+
"eval_runtime": 37.8666,
|
509 |
+
"eval_samples_per_second": 422.536,
|
510 |
+
"eval_steps_per_second": 6.602,
|
511 |
+
"step": 9400
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 9.5,
|
515 |
+
"grad_norm": 0.16063953936100006,
|
516 |
+
"learning_rate": 3.077914851215585e-07,
|
517 |
+
"loss": 0.0241,
|
518 |
+
"step": 9500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 9.6,
|
522 |
+
"eval_loss": 0.023399699479341507,
|
523 |
+
"eval_runtime": 37.8663,
|
524 |
+
"eval_samples_per_second": 422.539,
|
525 |
+
"eval_steps_per_second": 6.602,
|
526 |
+
"step": 9600
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 9.8,
|
530 |
+
"eval_loss": 0.023402543738484383,
|
531 |
+
"eval_runtime": 37.6977,
|
532 |
+
"eval_samples_per_second": 424.429,
|
533 |
+
"eval_steps_per_second": 6.632,
|
534 |
+
"step": 9800
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 10.0,
|
538 |
+
"grad_norm": 0.11751583963632584,
|
539 |
+
"learning_rate": 0.0,
|
540 |
+
"loss": 0.024,
|
541 |
+
"step": 10000
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 10.0,
|
545 |
+
"eval_loss": 0.023403601720929146,
|
546 |
+
"eval_runtime": 37.692,
|
547 |
+
"eval_samples_per_second": 424.493,
|
548 |
+
"eval_steps_per_second": 6.633,
|
549 |
+
"step": 10000
|
550 |
}
|
551 |
],
|
552 |
"logging_steps": 500,
|
|
|
554 |
"num_input_tokens_seen": 0,
|
555 |
"num_train_epochs": 10,
|
556 |
"save_steps": 1000,
|
557 |
+
"total_flos": 4.180672512e+16,
|
558 |
"train_batch_size": 64,
|
559 |
"trial_name": null,
|
560 |
"trial_params": null
|