mprzibilla
commited on
Commit
•
349aadc
1
Parent(s):
70787d0
Training in progress, step 341600
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 174303
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4b497bb3f3c0c9853bebae18a51bf68dc57d0f20ae309f60841f0ed6dc6eab5
|
3 |
size 174303
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0ecbff3f45369d5af5b3f2deb165d88052931289e1872b8c6e1af17d5401d70
|
3 |
size 377644503
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90f283e9c40c79afacb07203cb48ad9d45d0833c6db0364f0fd28ed8e8d8db1c
|
3 |
size 14567
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83e230a92ccfab5ad47042e41dbe9c833e1445b10d58da5b7bc8006c319679b8
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9020891b9cdd5ced8956f4798855d85e290e6aba56c61a9edb8bb49fa7736d8
|
3 |
size 623
|
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,
|
@@ -150,11 +150,27 @@
|
|
150 |
"eval_steps_per_second": 26.201,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 307440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 341600,
|
156 |
"num_train_epochs": 100,
|
157 |
-
"total_flos":
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
+
"global_step": 341600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_steps_per_second": 26.201,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 307440
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 100.0,
|
156 |
+
"learning_rate": 4.4373228152348083e-08,
|
157 |
+
"loss": 2.651,
|
158 |
+
"step": 341600
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 100.0,
|
162 |
+
"eval_cer": 0.9324675324675324,
|
163 |
+
"eval_loss": 3.189643144607544,
|
164 |
+
"eval_runtime": 1.0382,
|
165 |
+
"eval_samples_per_second": 202.281,
|
166 |
+
"eval_steps_per_second": 26.008,
|
167 |
+
"eval_wer": 1.0,
|
168 |
+
"step": 341600
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 341600,
|
172 |
"num_train_epochs": 100,
|
173 |
+
"total_flos": 3.24550895516716e+20,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0ecbff3f45369d5af5b3f2deb165d88052931289e1872b8c6e1af17d5401d70
|
3 |
size 377644503
|