Training in progress, step 300, 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 14176064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9afc7b7996d1814a8d9fbd07291c0a536d3f2db5cef79ff0777ed4d77cffbf1
|
| 3 |
size 14176064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c266665c364407530a02ca9d9e313c860ceeb09f8b815cfe5215b13a2c885dd
|
| 3 |
+
size 4832890
|
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 sha256:84e0125559175d398bcf91f5bcb5f6c0428a678050a518cd1ad89ebeda6cffd3
|
| 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 sha256:86677a97583577eb5bfc1e4543cd0cd44192bd23f86c793c174ef809d983ea68
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -39,6 +39,22 @@
|
|
| 39 |
"eval_steps_per_second": 0.029,
|
| 40 |
"eval_wer": 97.12450290608749,
|
| 41 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
],
|
| 44 |
"logging_steps": 100,
|
|
@@ -53,12 +69,12 @@
|
|
| 53 |
"should_evaluate": false,
|
| 54 |
"should_log": false,
|
| 55 |
"should_save": true,
|
| 56 |
-
"should_training_stop":
|
| 57 |
},
|
| 58 |
"attributes": {}
|
| 59 |
}
|
| 60 |
},
|
| 61 |
-
"total_flos":
|
| 62 |
"train_batch_size": 32,
|
| 63 |
"trial_name": null,
|
| 64 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 95.74793514836341,
|
| 3 |
+
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-300",
|
| 4 |
+
"epoch": 4.16,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 39 |
"eval_steps_per_second": 0.029,
|
| 40 |
"eval_wer": 97.12450290608749,
|
| 41 |
"step": 200
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 4.16,
|
| 45 |
+
"grad_norm": 1.6685636043548584,
|
| 46 |
+
"learning_rate": 7.142857142857143e-07,
|
| 47 |
+
"loss": 2.405,
|
| 48 |
+
"step": 300
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.16,
|
| 52 |
+
"eval_loss": 3.106688976287842,
|
| 53 |
+
"eval_runtime": 382.1833,
|
| 54 |
+
"eval_samples_per_second": 1.047,
|
| 55 |
+
"eval_steps_per_second": 0.034,
|
| 56 |
+
"eval_wer": 95.74793514836341,
|
| 57 |
+
"step": 300
|
| 58 |
}
|
| 59 |
],
|
| 60 |
"logging_steps": 100,
|
|
|
|
| 69 |
"should_evaluate": false,
|
| 70 |
"should_log": false,
|
| 71 |
"should_save": true,
|
| 72 |
+
"should_training_stop": true
|
| 73 |
},
|
| 74 |
"attributes": {}
|
| 75 |
}
|
| 76 |
},
|
| 77 |
+
"total_flos": 2.80054659022848e+18,
|
| 78 |
"train_batch_size": 32,
|
| 79 |
"trial_name": null,
|
| 80 |
"trial_params": null
|