Commit
·
5863a28
1
Parent(s):
643b34f
Training in progress, epoch 15
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 sha256:5ef623cff9158c13d281fc55391bdc75fcf9a86c59930440c3e55e9a29a0d542
|
| 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:bd9a96a7cb24f6975617fc85cc49ef657775451909cd74185aa64605223994c2
|
| 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 sha256:1c99e84843df118a46bb9233483e0f78a733ac99b2f66d0c3f2231bb6a3e1790
|
| 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 sha256:272f9f694f78429521717d1b2f41d4b0d908deeadca9901d4c6c96f39358d425
|
| 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 sha256:2cfcc7522938b227acd84748cbe48d5940798338cb3a4a147390a21c4f7abce3
|
| 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,
|
|
@@ -244,11 +244,28 @@
|
|
| 244 |
"eval_samples_per_second": 26.462,
|
| 245 |
"eval_steps_per_second": 3.402,
|
| 246 |
"step": 14070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
}
|
| 248 |
],
|
| 249 |
"max_steps": 15075,
|
| 250 |
"num_train_epochs": 15,
|
| 251 |
-
"total_flos": 1.
|
| 252 |
"trial_name": null,
|
| 253 |
"trial_params": null
|
| 254 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"global_step": 15075,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 244 |
"eval_samples_per_second": 26.462,
|
| 245 |
"eval_steps_per_second": 3.402,
|
| 246 |
"step": 14070
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.0,
|
| 250 |
+
"learning_rate": 6.284038542103058e-08,
|
| 251 |
+
"loss": 3.4606,
|
| 252 |
+
"step": 15075
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 15.0,
|
| 256 |
+
"eval_cer": 1.0,
|
| 257 |
+
"eval_loss": 3.349709987640381,
|
| 258 |
+
"eval_new_wer": 1.0,
|
| 259 |
+
"eval_old_wer": 1.0,
|
| 260 |
+
"eval_runtime": 7.971,
|
| 261 |
+
"eval_samples_per_second": 26.345,
|
| 262 |
+
"eval_steps_per_second": 3.387,
|
| 263 |
+
"step": 15075
|
| 264 |
}
|
| 265 |
],
|
| 266 |
"max_steps": 15075,
|
| 267 |
"num_train_epochs": 15,
|
| 268 |
+
"total_flos": 1.1047620112237375e+19,
|
| 269 |
"trial_name": null,
|
| 270 |
"trial_params": null
|
| 271 |
}
|
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:bd9a96a7cb24f6975617fc85cc49ef657775451909cd74185aa64605223994c2
|
| 3 |
size 377646433
|