RodrigoSalazar-U
commited on
Commit
•
021f49d
1
Parent(s):
95444c4
Training in progress, step 7500, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4785762744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5868ba587c3a824bc63fc899fdaeb6194618d48e020066ab2d114a4922121e1
|
3 |
size 4785762744
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3497859804
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a7d4f1caf511e7340b15cbbb3b6dc53b6d076d036358b828129c1ff3e45f7d3
|
3 |
size 3497859804
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14308
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56ada7a9076e894e38e63b2e547d8bfe564d09412403a53a9fd4f37e79358b8d
|
3 |
size 14308
|
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 sha256:16a4fdf7915d781b2a36593733c87afb8e5ce6e3d04384acc5dc1d5c1959abad
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -497,6 +497,41 @@
|
|
497 |
"learning_rate": 1.4887421946651437e-05,
|
498 |
"loss": 0.1058,
|
499 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 100,
|
@@ -516,7 +551,7 @@
|
|
516 |
"attributes": {}
|
517 |
}
|
518 |
},
|
519 |
-
"total_flos": 3.
|
520 |
"train_batch_size": 16,
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.140215291195142,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
497 |
"learning_rate": 1.4887421946651437e-05,
|
498 |
"loss": 0.1058,
|
499 |
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 3.919403808998068,
|
503 |
+
"grad_norm": 0.451486200094223,
|
504 |
+
"learning_rate": 1.354154177409932e-05,
|
505 |
+
"loss": 0.1057,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 3.9746066795473363,
|
510 |
+
"grad_norm": 0.4829927384853363,
|
511 |
+
"learning_rate": 1.224984117967648e-05,
|
512 |
+
"loss": 0.1034,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 4.029809550096605,
|
517 |
+
"grad_norm": 0.29708752036094666,
|
518 |
+
"learning_rate": 1.1014239712279945e-05,
|
519 |
+
"loss": 0.0977,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 4.0850124206458736,
|
524 |
+
"grad_norm": 0.4131404459476471,
|
525 |
+
"learning_rate": 9.83657355395079e-06,
|
526 |
+
"loss": 0.09,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 4.140215291195142,
|
531 |
+
"grad_norm": 0.3377688229084015,
|
532 |
+
"learning_rate": 8.718592791191299e-06,
|
533 |
+
"loss": 0.0907,
|
534 |
+
"step": 7500
|
535 |
}
|
536 |
],
|
537 |
"logging_steps": 100,
|
|
|
551 |
"attributes": {}
|
552 |
}
|
553 |
},
|
554 |
+
"total_flos": 3.9786029952435487e+18,
|
555 |
"train_batch_size": 16,
|
556 |
"trial_name": null,
|
557 |
"trial_params": null
|