Training in progress, step 177, 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 121155320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d96bf1960b150602e5e76b3faa6ec34c3d4128539a376971f5bfe284307e68
|
3 |
size 121155320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61896852
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57013b5e51a30dae40b7285217c759a1d05db1a242ab0edceebd0444817d72b8
|
3 |
size 61896852
|
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:fa65732a2e2e4637165a27bb72afa324ebe26d80426fca5be7655f29ac48d281
|
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 sha256:3920ee4a294e40209fd09294d2bc1408892fffa1eb0ce50b11d8a2f2e706c9ae
|
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": 15,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -488,6 +488,34 @@
|
|
488 |
"eval_samples_per_second": 89.194,
|
489 |
"eval_steps_per_second": 22.524,
|
490 |
"step": 165
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
491 |
}
|
492 |
],
|
493 |
"logging_steps": 3,
|
@@ -502,12 +530,12 @@
|
|
502 |
"should_evaluate": false,
|
503 |
"should_log": false,
|
504 |
"should_save": true,
|
505 |
-
"should_training_stop":
|
506 |
},
|
507 |
"attributes": {}
|
508 |
}
|
509 |
},
|
510 |
-
"total_flos":
|
511 |
"train_batch_size": 4,
|
512 |
"trial_name": null,
|
513 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0127659574468084,
|
5 |
"eval_steps": 15,
|
6 |
+
"global_step": 177,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
488 |
"eval_samples_per_second": 89.194,
|
489 |
"eval_steps_per_second": 22.524,
|
490 |
"step": 165
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 2.8595744680851065,
|
494 |
+
"grad_norm": 5.334619998931885,
|
495 |
+
"learning_rate": 7.149145929922607e-07,
|
496 |
+
"loss": 0.332,
|
497 |
+
"step": 168
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 2.9106382978723406,
|
501 |
+
"grad_norm": 4.500619888305664,
|
502 |
+
"learning_rate": 3.1816191188415166e-07,
|
503 |
+
"loss": 0.3051,
|
504 |
+
"step": 171
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.9617021276595743,
|
508 |
+
"grad_norm": 3.653864860534668,
|
509 |
+
"learning_rate": 7.960384569353219e-08,
|
510 |
+
"loss": 0.2497,
|
511 |
+
"step": 174
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 3.0127659574468084,
|
515 |
+
"grad_norm": 3.714113235473633,
|
516 |
+
"learning_rate": 0.0,
|
517 |
+
"loss": 0.2474,
|
518 |
+
"step": 177
|
519 |
}
|
520 |
],
|
521 |
"logging_steps": 3,
|
|
|
530 |
"should_evaluate": false,
|
531 |
"should_log": false,
|
532 |
"should_save": true,
|
533 |
+
"should_training_stop": true
|
534 |
},
|
535 |
"attributes": {}
|
536 |
}
|
537 |
},
|
538 |
+
"total_flos": 5889895783464960.0,
|
539 |
"train_batch_size": 4,
|
540 |
"trial_name": null,
|
541 |
"trial_params": null
|