mprzibilla
commited on
Commit
•
ab0ed87
1
Parent(s):
aa77323
Training in progress, step 273280
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:f6fdb7313a080f0d99c0e0db4f99187d1ad399ba3a96327faab7900d616c1f6b
|
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 sha256:041b386a8a93cf2a228158d2188325a175566354f65f7d104e2fac92bc6facd3
|
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 sha256:2f0496954e296c9f34828c91a2b4d65ac1d890cc600bb3e79c432a6a54e09372
|
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:e86b6f955c7a97e917f73b4dc175612def9b7020402b31d3dcd5fd2907e88b26
|
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:b364117e25f676ab93bfeb5c200f757da39699e73bb8ac51131a2dc05a040f1e
|
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,
|
@@ -118,11 +118,27 @@
|
|
118 |
"eval_steps_per_second": 25.942,
|
119 |
"eval_wer": 1.0,
|
120 |
"step": 239120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
}
|
122 |
],
|
123 |
"max_steps": 341600,
|
124 |
"num_train_epochs": 100,
|
125 |
-
"total_flos": 2.
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
128 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 80.0,
|
5 |
+
"global_step": 273280,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
118 |
"eval_steps_per_second": 25.942,
|
119 |
"eval_wer": 1.0,
|
120 |
"step": 239120
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 80.0,
|
124 |
+
"learning_rate": 2.108776038456798e-05,
|
125 |
+
"loss": 2.6548,
|
126 |
+
"step": 273280
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 80.0,
|
130 |
+
"eval_cer": 0.9324675324675324,
|
131 |
+
"eval_loss": 3.1870908737182617,
|
132 |
+
"eval_runtime": 1.0301,
|
133 |
+
"eval_samples_per_second": 203.86,
|
134 |
+
"eval_steps_per_second": 26.211,
|
135 |
+
"eval_wer": 1.0,
|
136 |
+
"step": 273280
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 341600,
|
140 |
"num_train_epochs": 100,
|
141 |
+
"total_flos": 2.5966630914638784e+20,
|
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 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:041b386a8a93cf2a228158d2188325a175566354f65f7d104e2fac92bc6facd3
|
3 |
size 377644503
|