mprzibilla
commited on
Commit
•
96136fc
1
Parent(s):
6950c3a
Training in progress, epoch 9
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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c02091ac6b92226695a59577ab7d4dcb9cd98977e07434d7fa01e3945bc7df3
|
3 |
size 721661957
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09c61da1490c623ed4c01c66304040f3e326c2c1ff57ea40ea62eb04deab3d3a
|
3 |
size 377646433
|
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 sha256:9984e3cbd8716939c7fdea32bd39972cea55b1ab6285ee007229d989a1230b1c
|
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 sha256:3e7730cfcb24b34ccf70f77b07c8d0d2b73e258077d413002a5407dd82e57b83
|
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 sha256:130febd259da8024c5a724e8fe97e74d600f3893f62eaf38860a523a0936e692
|
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,
|
@@ -142,11 +142,28 @@
|
|
142 |
"eval_samples_per_second": 26.751,
|
143 |
"eval_steps_per_second": 3.439,
|
144 |
"step": 2528
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
}
|
146 |
],
|
147 |
"max_steps": 4740,
|
148 |
"num_train_epochs": 15,
|
149 |
-
"total_flos":
|
150 |
"trial_name": null,
|
151 |
"trial_params": null
|
152 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 2844,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
142 |
"eval_samples_per_second": 26.751,
|
143 |
"eval_steps_per_second": 3.439,
|
144 |
"step": 2528
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.2282922496113704e-05,
|
149 |
+
"loss": 3.2856,
|
150 |
+
"step": 2844
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_cer": 1.0,
|
155 |
+
"eval_loss": 3.2858822345733643,
|
156 |
+
"eval_new_wer": 1.0,
|
157 |
+
"eval_old_wer": 1.0,
|
158 |
+
"eval_runtime": 5.3674,
|
159 |
+
"eval_samples_per_second": 26.083,
|
160 |
+
"eval_steps_per_second": 3.354,
|
161 |
+
"step": 2844
|
162 |
}
|
163 |
],
|
164 |
"max_steps": 4740,
|
165 |
"num_train_epochs": 15,
|
166 |
+
"total_flos": 2.104156079215534e+18,
|
167 |
"trial_name": null,
|
168 |
"trial_params": null
|
169 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09c61da1490c623ed4c01c66304040f3e326c2c1ff57ea40ea62eb04deab3d3a
|
3 |
size 377646433
|