Training in progress, step 45000, 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 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a568e96942cd89d7314e0d976df15beb19a7b31b7a80ad573473c86d1302e93c
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 281574266
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:567de69fd0ba1c4c7a9a8ffc136ab6ca0803415a38b7fe06415d067f7858636e
|
| 3 |
size 281574266
|
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 sha256:1b8b7531b1fc5b902cb75ca7a9dbdcd9897897bf6bc1fc2723033a58a96c2172
|
| 3 |
size 14244
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5d546b2fffc3da93a4aa8da01e4de08986619d071e84b750436edd9eb12f37
|
| 3 |
size 988
|
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 sha256:3757dbe7156f5bc61a69d443c6dc83b53c9ebd7e6ededa1da92af126d09a6c57
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 28000,
|
| 3 |
"best_metric": 0.18110816386678455,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-28000",
|
| 5 |
-
"epoch": 26.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3505,12 +3505,70 @@
|
|
| 3505 |
"learning_rate": 2.3699922519484072e-07,
|
| 3506 |
"loss": 0.6662,
|
| 3507 |
"step": 44300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3508 |
}
|
| 3509 |
],
|
| 3510 |
"logging_steps": 100,
|
| 3511 |
-
"max_steps":
|
| 3512 |
"num_input_tokens_seen": 0,
|
| 3513 |
-
"num_train_epochs":
|
| 3514 |
"save_steps": 1000,
|
| 3515 |
"stateful_callbacks": {
|
| 3516 |
"TrainerControl": {
|
|
@@ -3519,12 +3577,12 @@
|
|
| 3519 |
"should_evaluate": false,
|
| 3520 |
"should_log": false,
|
| 3521 |
"should_save": true,
|
| 3522 |
-
"should_training_stop":
|
| 3523 |
},
|
| 3524 |
"attributes": {}
|
| 3525 |
}
|
| 3526 |
},
|
| 3527 |
-
"total_flos": 5.
|
| 3528 |
"train_batch_size": 8,
|
| 3529 |
"trial_name": null,
|
| 3530 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 28000,
|
| 3 |
"best_metric": 0.18110816386678455,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-28000",
|
| 5 |
+
"epoch": 26.362038664323375,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 45000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3505 |
"learning_rate": 2.3699922519484072e-07,
|
| 3506 |
"loss": 0.6662,
|
| 3507 |
"step": 44300
|
| 3508 |
+
},
|
| 3509 |
+
{
|
| 3510 |
+
"epoch": 26.010544815465728,
|
| 3511 |
+
"grad_norm": 5.860207557678223,
|
| 3512 |
+
"learning_rate": 1.3472687832774603e-05,
|
| 3513 |
+
"loss": 0.6097,
|
| 3514 |
+
"step": 44400
|
| 3515 |
+
},
|
| 3516 |
+
{
|
| 3517 |
+
"epoch": 26.06912712360867,
|
| 3518 |
+
"grad_norm": 5.674122333526611,
|
| 3519 |
+
"learning_rate": 1.3275488069414319e-05,
|
| 3520 |
+
"loss": 0.6638,
|
| 3521 |
+
"step": 44500
|
| 3522 |
+
},
|
| 3523 |
+
{
|
| 3524 |
+
"epoch": 26.12770943175161,
|
| 3525 |
+
"grad_norm": 7.24979829788208,
|
| 3526 |
+
"learning_rate": 1.3078288306054034e-05,
|
| 3527 |
+
"loss": 0.641,
|
| 3528 |
+
"step": 44600
|
| 3529 |
+
},
|
| 3530 |
+
{
|
| 3531 |
+
"epoch": 26.186291739894553,
|
| 3532 |
+
"grad_norm": 7.524514198303223,
|
| 3533 |
+
"learning_rate": 1.288108854269375e-05,
|
| 3534 |
+
"loss": 0.6722,
|
| 3535 |
+
"step": 44700
|
| 3536 |
+
},
|
| 3537 |
+
{
|
| 3538 |
+
"epoch": 26.24487404803749,
|
| 3539 |
+
"grad_norm": 5.542699337005615,
|
| 3540 |
+
"learning_rate": 1.2683888779333466e-05,
|
| 3541 |
+
"loss": 0.6386,
|
| 3542 |
+
"step": 44800
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 26.303456356180433,
|
| 3546 |
+
"grad_norm": 7.757282257080078,
|
| 3547 |
+
"learning_rate": 1.2486689015973181e-05,
|
| 3548 |
+
"loss": 0.6976,
|
| 3549 |
+
"step": 44900
|
| 3550 |
+
},
|
| 3551 |
+
{
|
| 3552 |
+
"epoch": 26.362038664323375,
|
| 3553 |
+
"grad_norm": 5.828668117523193,
|
| 3554 |
+
"learning_rate": 1.2289489252612897e-05,
|
| 3555 |
+
"loss": 0.6921,
|
| 3556 |
+
"step": 45000
|
| 3557 |
+
},
|
| 3558 |
+
{
|
| 3559 |
+
"epoch": 26.362038664323375,
|
| 3560 |
+
"eval_loss": 0.08329325169324875,
|
| 3561 |
+
"eval_runtime": 154.0108,
|
| 3562 |
+
"eval_samples_per_second": 3.247,
|
| 3563 |
+
"eval_steps_per_second": 0.409,
|
| 3564 |
+
"eval_wer": 0.18803418803418803,
|
| 3565 |
+
"step": 45000
|
| 3566 |
}
|
| 3567 |
],
|
| 3568 |
"logging_steps": 100,
|
| 3569 |
+
"max_steps": 51210,
|
| 3570 |
"num_input_tokens_seen": 0,
|
| 3571 |
+
"num_train_epochs": 30,
|
| 3572 |
"save_steps": 1000,
|
| 3573 |
"stateful_callbacks": {
|
| 3574 |
"TrainerControl": {
|
|
|
|
| 3577 |
"should_evaluate": false,
|
| 3578 |
"should_log": false,
|
| 3579 |
"should_save": true,
|
| 3580 |
+
"should_training_stop": false
|
| 3581 |
},
|
| 3582 |
"attributes": {}
|
| 3583 |
}
|
| 3584 |
},
|
| 3585 |
+
"total_flos": 5.853273724551168e+19,
|
| 3586 |
"train_batch_size": 8,
|
| 3587 |
"trial_name": null,
|
| 3588 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4c57ccff6bf7086a307311fd25098672bae7b0308bc8beda9e8aefc9f99378d
|
| 3 |
size 5496
|