mprzibilla
commited on
Commit
·
d49144d
1
Parent(s):
85d157a
Training in progress, epoch 8
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 sha256:4eb118859ccd2b17b7c4ddc77d35f3fe0ef85393a1eeeb72c87b218498a749f7
|
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:abc34843e0965196a4479f17cf08bf8a88225eec6c573845d80ec4df06d5bcf4
|
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 sha256:769917d52eee0e3ec39baab8d23748c7392a020826ef8ddf1250670f1fa7a2d1
|
3 |
+
size 14575
|
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 sha256:9d06a48b6590730359e992b5a9274a6f0aa5a3415a51fce3457d99a6fd60c656
|
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 sha256:2bb234e8aff204ba837868e8af06d316f481bb10dedb985a07200d97b524462f
|
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,
|
@@ -125,11 +125,28 @@
|
|
125 |
"eval_samples_per_second": 28.038,
|
126 |
"eval_steps_per_second": 3.605,
|
127 |
"step": 2254
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
}
|
129 |
],
|
130 |
"max_steps": 4830,
|
131 |
"num_train_epochs": 15,
|
132 |
-
"total_flos": 1.
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|
135 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 2576,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
125 |
"eval_samples_per_second": 28.038,
|
126 |
"eval_steps_per_second": 3.605,
|
127 |
"step": 2254
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.9269993462628025e-05,
|
132 |
+
"loss": 3.3976,
|
133 |
+
"step": 2576
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_cer": 1.0,
|
138 |
+
"eval_loss": 3.305764675140381,
|
139 |
+
"eval_new_wer": 1.0,
|
140 |
+
"eval_old_wer": 1.0,
|
141 |
+
"eval_runtime": 7.4908,
|
142 |
+
"eval_samples_per_second": 28.034,
|
143 |
+
"eval_steps_per_second": 3.604,
|
144 |
+
"step": 2576
|
145 |
}
|
146 |
],
|
147 |
"max_steps": 4830,
|
148 |
"num_train_epochs": 15,
|
149 |
+
"total_flos": 1.912160410310016e+18,
|
150 |
"trial_name": null,
|
151 |
"trial_params": null
|
152 |
}
|
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:abc34843e0965196a4479f17cf08bf8a88225eec6c573845d80ec4df06d5bcf4
|
3 |
size 377643361
|