Commit
·
5e32c4a
1
Parent(s):
b73c4c5
Training in progress, epoch 7
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +20 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 721655813
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba01e089a7d0d111ffa2cf87cec428e79a57063bceec5834b7988aa4f6f19b11
|
3 |
size 721655813
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7927f57dd3bae4345457eed7a7f96392f72a62357ecafb122ebfb78e388e8d21
|
3 |
size 377643361
|
last-checkpoint/rng_state.pth
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 sha256:2d01e9887d2d1bfecc2b155015432c6c15dd0c65df771f3404cee5e99400ce23
|
3 |
+
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5f1d2b61e9d2c061cad6a41bad8a6f6ed9332684d248478138394a5c02eddae
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c7dbb7374ee87d07ded3f16ea79561b7e1a248cafd7c371017dd77677398a2a
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -108,11 +108,28 @@
|
|
108 |
"eval_samples_per_second": 24.513,
|
109 |
"eval_steps_per_second": 3.152,
|
110 |
"step": 1932
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
}
|
112 |
],
|
113 |
"max_steps": 4830,
|
114 |
"num_train_epochs": 15,
|
115 |
-
"total_flos": 1.
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.0,
|
5 |
+
"global_step": 2254,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
108 |
"eval_samples_per_second": 24.513,
|
109 |
"eval_steps_per_second": 3.152,
|
110 |
"step": 1932
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 5.628677271736762e-05,
|
115 |
+
"loss": 1.204,
|
116 |
+
"step": 2254
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_cer": 0.7177489177489178,
|
121 |
+
"eval_loss": 3.089792013168335,
|
122 |
+
"eval_new_wer": 0.5666666666666667,
|
123 |
+
"eval_old_wer": 1.0,
|
124 |
+
"eval_runtime": 8.7621,
|
125 |
+
"eval_samples_per_second": 23.967,
|
126 |
+
"eval_steps_per_second": 3.081,
|
127 |
+
"step": 2254
|
128 |
}
|
129 |
],
|
130 |
"max_steps": 4830,
|
131 |
"num_train_epochs": 15,
|
132 |
+
"total_flos": 1.673618996832096e+18,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|
135 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7927f57dd3bae4345457eed7a7f96392f72a62357ecafb122ebfb78e388e8d21
|
3 |
size 377643361
|