Training in progress, step 51210, 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 sha256:37c60fec1d61a715abc34621b50732bb6b292b703f3afc3223e3e83424c74ab7
|
| 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 sha256:4b66491803298bd494de49c07185852ace2b4947178790cf4fa9c4e8672a271e
|
| 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 sha256:81b07648b78bb7a2992c7dd8ed36fd94978c5a54d9b9e494eed5b57a0c11e7e7
|
| 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 sha256:8ece15461d3df986ea66e8c68a5924ba82a155ca2f8c576aeb5dbb460a0585e0
|
| 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 sha256:3798d28e55ce039da2d5ff96e3dde65a999d6fa0cc557856baaa4f2f9f004976
|
| 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":
|
| 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,
|
|
@@ -4037,6 +4037,20 @@
|
|
| 4037 |
"eval_steps_per_second": 0.434,
|
| 4038 |
"eval_wer": 0.18980253463012084,
|
| 4039 |
"step": 51000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4040 |
}
|
| 4041 |
],
|
| 4042 |
"logging_steps": 100,
|
|
@@ -4051,12 +4065,12 @@
|
|
| 4051 |
"should_evaluate": false,
|
| 4052 |
"should_log": false,
|
| 4053 |
"should_save": true,
|
| 4054 |
-
"should_training_stop":
|
| 4055 |
},
|
| 4056 |
"attributes": {}
|
| 4057 |
}
|
| 4058 |
},
|
| 4059 |
-
"total_flos": 6.
|
| 4060 |
"train_batch_size": 8,
|
| 4061 |
"trial_name": null,
|
| 4062 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 28000,
|
| 3 |
"best_metric": 0.18110816386678455,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-28000",
|
| 5 |
+
"epoch": 30.0,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 51210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4037 |
"eval_steps_per_second": 0.434,
|
| 4038 |
"eval_wer": 0.18980253463012084,
|
| 4039 |
"step": 51000
|
| 4040 |
+
},
|
| 4041 |
+
{
|
| 4042 |
+
"epoch": 29.935559461042764,
|
| 4043 |
+
"grad_norm": 4.774900436401367,
|
| 4044 |
+
"learning_rate": 2.6424768290278054e-07,
|
| 4045 |
+
"loss": 0.6359,
|
| 4046 |
+
"step": 51100
|
| 4047 |
+
},
|
| 4048 |
+
{
|
| 4049 |
+
"epoch": 29.994141769185706,
|
| 4050 |
+
"grad_norm": 4.431262493133545,
|
| 4051 |
+
"learning_rate": 6.704791954249655e-08,
|
| 4052 |
+
"loss": 0.6618,
|
| 4053 |
+
"step": 51200
|
| 4054 |
}
|
| 4055 |
],
|
| 4056 |
"logging_steps": 100,
|
|
|
|
| 4065 |
"should_evaluate": false,
|
| 4066 |
"should_log": false,
|
| 4067 |
"should_save": true,
|
| 4068 |
+
"should_training_stop": true
|
| 4069 |
},
|
| 4070 |
"attributes": {}
|
| 4071 |
}
|
| 4072 |
},
|
| 4073 |
+
"total_flos": 6.6610187993088e+19,
|
| 4074 |
"train_batch_size": 8,
|
| 4075 |
"trial_name": null,
|
| 4076 |
"trial_params": null
|