mprzibilla
commited on
Commit
•
a92d590
1
Parent(s):
66a8126
Training in progress, step 51600
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -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 168299
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69901d3978cdc49be64d8289ae9b4b65ae004575bf6ffa4ee3f8aaacdefe07f4
|
3 |
size 168299
|
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:ccd2a550a5449309631a19568a860c83fc4f3f3d2edc21cfd0809d00ea366358
|
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 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46cee912bcd3dad37403fef0191a5201336569c4385c3c3061d4ac528c02858e
|
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:f95d84b7a8c587c8591653169178fb282e47d5ae37af3622a4b8b308464727aa
|
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 sha256:7202b843e5da3adb88e8bb8487c0ed1f5f3f91c3f959eb2659e64dc2e655714c
|
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,
|
@@ -118,11 +118,27 @@
|
|
118 |
"eval_steps_per_second": 3.363,
|
119 |
"eval_wer": 0.9952380952380953,
|
120 |
"step": 45150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
}
|
122 |
],
|
123 |
"max_steps": 64500,
|
124 |
"num_train_epochs": 250,
|
125 |
-
"total_flos": 4.
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
128 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 200.0,
|
5 |
+
"global_step": 51600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
118 |
"eval_steps_per_second": 3.363,
|
119 |
"eval_wer": 0.9952380952380953,
|
120 |
"step": 45150
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 200.0,
|
124 |
+
"learning_rate": 2.109016727866177e-05,
|
125 |
+
"loss": 2.2885,
|
126 |
+
"step": 51600
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 200.0,
|
130 |
+
"eval_cer": 0.8337662337662337,
|
131 |
+
"eval_loss": 2.2457661628723145,
|
132 |
+
"eval_runtime": 8.1248,
|
133 |
+
"eval_samples_per_second": 25.847,
|
134 |
+
"eval_steps_per_second": 3.323,
|
135 |
+
"eval_wer": 0.9952380952380953,
|
136 |
+
"step": 51600
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 64500,
|
140 |
"num_train_epochs": 250,
|
141 |
+
"total_flos": 4.958565694536252e+19,
|
142 |
"trial_name": null,
|
143 |
"trial_params": null
|
144 |
}
|
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:ccd2a550a5449309631a19568a860c83fc4f3f3d2edc21cfd0809d00ea366358
|
3 |
size 377643361
|