Training in progress, step 100, 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 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95e8623e69648757e151b5e805bcac5813b5473c0d336aea4255672fb322283c
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484132184
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63e468a7b0c0af5b5504d027de1d04f0d144bba75567ce12edc590856f487551
|
3 |
size 484132184
|
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 sha256:369414d4cbb989858782aec606db60d381f44fce3d07dbd801991c9110c71977
|
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:ddfd4bb2631a2c6f0d4acd6792ddcf5c82cbca9ca7f951a5fd4ee4d896760b7f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 75.35101404056162,
|
3 |
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-25",
|
4 |
-
"epoch": 0
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -55,6 +55,22 @@
|
|
55 |
"eval_steps_per_second": 0.068,
|
56 |
"eval_wer": 100.0,
|
57 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 25,
|
@@ -69,12 +85,12 @@
|
|
69 |
"should_evaluate": false,
|
70 |
"should_log": false,
|
71 |
"should_save": true,
|
72 |
-
"should_training_stop":
|
73 |
},
|
74 |
"attributes": {}
|
75 |
}
|
76 |
},
|
77 |
-
"total_flos":
|
78 |
"train_batch_size": 16,
|
79 |
"trial_name": null,
|
80 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 75.35101404056162,
|
3 |
"best_model_checkpoint": "../openai/whisper-small-finetuned/checkpoint-25",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
55 |
"eval_steps_per_second": 0.068,
|
56 |
"eval_wer": 100.0,
|
57 |
"step": 75
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.0,
|
61 |
+
"grad_norm": 12.699311256408691,
|
62 |
+
"learning_rate": 5e-06,
|
63 |
+
"loss": 2.2342,
|
64 |
+
"step": 100
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 1.0,
|
68 |
+
"eval_loss": 2.0581600666046143,
|
69 |
+
"eval_runtime": 470.8577,
|
70 |
+
"eval_samples_per_second": 1.062,
|
71 |
+
"eval_steps_per_second": 0.068,
|
72 |
+
"eval_wer": 100.0,
|
73 |
+
"step": 100
|
74 |
}
|
75 |
],
|
76 |
"logging_steps": 25,
|
|
|
85 |
"should_evaluate": false,
|
86 |
"should_log": false,
|
87 |
"should_save": true,
|
88 |
+
"should_training_stop": true
|
89 |
},
|
90 |
"attributes": {}
|
91 |
}
|
92 |
},
|
93 |
+
"total_flos": 4.61736640512e+17,
|
94 |
"train_batch_size": 16,
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|