Commit
•
f4d8b96
1
Parent(s):
a4f31c8
Training in progress, epoch 8
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 +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 sha256:911e783859de200ee856ea020a337ed6fd58158d927fdad27f58cc95e41518ce
|
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 sha256:89b80b139cef01fd9b602dfac9c0896df7559dc96671d6411b235eb86f2fddb0
|
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 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ced15c725d859bed0b1f98b9eae921565b887986994c804e9dc9b99fe8c78868
|
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 sha256:971f2667e86066fc978a1099a9710d51e2e0613e9915add47dd7faa5f1d0e4b5
|
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 sha256:9b12d0b9a3a875a2aec9f9a0359d12814fa93fd9cd4ce92d62912b530c291996
|
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,
|
@@ -125,11 +125,28 @@
|
|
125 |
"eval_samples_per_second": 24.749,
|
126 |
"eval_steps_per_second": 3.182,
|
127 |
"step": 29890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
}
|
129 |
],
|
130 |
"max_steps": 64050,
|
131 |
"num_train_epochs": 15,
|
132 |
-
"total_flos": 2.
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|
135 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 34160,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
125 |
"eval_samples_per_second": 24.749,
|
126 |
"eval_steps_per_second": 3.182,
|
127 |
"step": 29890
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.915198527478307e-05,
|
132 |
+
"loss": 0.1926,
|
133 |
+
"step": 34160
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_cer": 0.12727272727272726,
|
138 |
+
"eval_loss": 1.098648190498352,
|
139 |
+
"eval_new_wer": 0.14761904761904762,
|
140 |
+
"eval_old_wer": 0.23809523809523808,
|
141 |
+
"eval_runtime": 8.5184,
|
142 |
+
"eval_samples_per_second": 24.653,
|
143 |
+
"eval_steps_per_second": 3.17,
|
144 |
+
"step": 34160
|
145 |
}
|
146 |
],
|
147 |
"max_steps": 64050,
|
148 |
"num_train_epochs": 15,
|
149 |
+
"total_flos": 2.588128854040959e+19,
|
150 |
"trial_name": null,
|
151 |
"trial_params": null
|
152 |
}
|
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 sha256:89b80b139cef01fd9b602dfac9c0896df7559dc96671d6411b235eb86f2fddb0
|
3 |
size 377646433
|