more training
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- scheduler.pt +1 -1
- trainer_state.json +17 -3
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490339591
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ec0667d993c3f120c1d8a82b4485dc0f1e1f05f231fae102da6dcf82e9d1f4
|
3 |
size 2490339591
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262065048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4fcc26137a3ca289aeb72befc5b018e20b28e0e43aa434fa2a2467b52372e02
|
3 |
size 1262065048
|
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:bea1393d7c8716a158a855861ef15a9d29632d763274abd05c73238c435e73b6
|
3 |
size 623
|
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,
|
@@ -62,11 +62,25 @@
|
|
62 |
"eval_samples_per_second": 7.946,
|
63 |
"eval_wer": 0.4348894348894349,
|
64 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
}
|
66 |
],
|
67 |
"max_steps": 29490,
|
68 |
"num_train_epochs": 30,
|
69 |
-
"total_flos":
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
72 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.034587995930824,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
62 |
"eval_samples_per_second": 7.946,
|
63 |
"eval_wer": 0.4348894348894349,
|
64 |
"step": 1600
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 2.03,
|
68 |
+
"learning_rate": 0.0002844774060020697,
|
69 |
+
"loss": 0.3181,
|
70 |
+
"step": 2000
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 2.03,
|
74 |
+
"eval_loss": 0.4156078100204468,
|
75 |
+
"eval_runtime": 234.1423,
|
76 |
+
"eval_samples_per_second": 7.991,
|
77 |
+
"eval_wer": 0.42106879606879605,
|
78 |
+
"step": 2000
|
79 |
}
|
80 |
],
|
81 |
"max_steps": 29490,
|
82 |
"num_train_epochs": 30,
|
83 |
+
"total_flos": 1.1113863503200174e+19,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|
86 |
}
|