Training in progress, step 22720, 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 151061672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cae76b04802b8f9b4fe64c3135bc74911f7b45c2dc3c6d910d606238be3672f4
|
3 |
size 151061672
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 297616186
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:954a72a87d8e27f24312c7c1708c089e72b49ac1b9a9fab05848592e1c8aa5df
|
3 |
size 297616186
|
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:fa0bc08a41e3445c13a31b1d0b2b3104bb282ffb43dacbb30e59d82a20f83c72
|
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:a6350b3a3c9208c2dd86b60aba9eb59060a84444d927f994a8243e2f7d9bcb3c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 13.300085415920426,
|
3 |
"best_model_checkpoint": "./Whisper_tiny_fine_tune_Quran/checkpoint-22000",
|
4 |
-
"epoch": 7.
|
5 |
"eval_steps": 400,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -3703,6 +3703,48 @@
|
|
3703 |
"eval_steps_per_second": 0.218,
|
3704 |
"eval_wer": 13.344171052269033,
|
3705 |
"step": 22400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3706 |
}
|
3707 |
],
|
3708 |
"logging_steps": 50,
|
@@ -3717,12 +3759,12 @@
|
|
3717 |
"should_evaluate": false,
|
3718 |
"should_log": false,
|
3719 |
"should_save": true,
|
3720 |
-
"should_training_stop":
|
3721 |
},
|
3722 |
"attributes": {}
|
3723 |
}
|
3724 |
},
|
3725 |
-
"total_flos": 3.
|
3726 |
"train_batch_size": 16,
|
3727 |
"trial_name": null,
|
3728 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 13.300085415920426,
|
3 |
"best_model_checkpoint": "./Whisper_tiny_fine_tune_Quran/checkpoint-22000",
|
4 |
+
"epoch": 7.999911979579262,
|
5 |
"eval_steps": 400,
|
6 |
+
"global_step": 22720,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
3703 |
"eval_steps_per_second": 0.218,
|
3704 |
"eval_wer": 13.344171052269033,
|
3705 |
"step": 22400
|
3706 |
+
},
|
3707 |
+
{
|
3708 |
+
"epoch": 7.904849925182642,
|
3709 |
+
"grad_norm": 16952.939453125,
|
3710 |
+
"learning_rate": 3.6427253854814934e-08,
|
3711 |
+
"loss": 0.0014,
|
3712 |
+
"step": 22450
|
3713 |
+
},
|
3714 |
+
{
|
3715 |
+
"epoch": 7.922454009330164,
|
3716 |
+
"grad_norm": 2679.947021484375,
|
3717 |
+
"learning_rate": 2.4185885400596075e-08,
|
3718 |
+
"loss": 0.0012,
|
3719 |
+
"step": 22500
|
3720 |
+
},
|
3721 |
+
{
|
3722 |
+
"epoch": 7.9400580934776865,
|
3723 |
+
"grad_norm": 25717.123046875,
|
3724 |
+
"learning_rate": 1.4442041196538469e-08,
|
3725 |
+
"loss": 0.0015,
|
3726 |
+
"step": 22550
|
3727 |
+
},
|
3728 |
+
{
|
3729 |
+
"epoch": 7.957662177625209,
|
3730 |
+
"grad_norm": 1721.3587646484375,
|
3731 |
+
"learning_rate": 7.196208187926213e-09,
|
3732 |
+
"loss": 0.0014,
|
3733 |
+
"step": 22600
|
3734 |
+
},
|
3735 |
+
{
|
3736 |
+
"epoch": 7.975266261772731,
|
3737 |
+
"grad_norm": 41844.98046875,
|
3738 |
+
"learning_rate": 2.4487484827917516e-09,
|
3739 |
+
"loss": 0.0016,
|
3740 |
+
"step": 22650
|
3741 |
+
},
|
3742 |
+
{
|
3743 |
+
"epoch": 7.992870345920253,
|
3744 |
+
"grad_norm": 48478.3515625,
|
3745 |
+
"learning_rate": 1.998993338192534e-10,
|
3746 |
+
"loss": 0.0014,
|
3747 |
+
"step": 22700
|
3748 |
}
|
3749 |
],
|
3750 |
"logging_steps": 50,
|
|
|
3759 |
"should_evaluate": false,
|
3760 |
"should_log": false,
|
3761 |
"should_save": true,
|
3762 |
+
"should_training_stop": true
|
3763 |
},
|
3764 |
"attributes": {}
|
3765 |
}
|
3766 |
},
|
3767 |
+
"total_flos": 3.57978284752896e+19,
|
3768 |
"train_batch_size": 16,
|
3769 |
"trial_name": null,
|
3770 |
"trial_params": null
|