updating model
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:b7560291d8270abd8e9dac4f379bf356cbdcf33ba3f78f31544c3164d8dc6e5b
|
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:f2839c2df31170b508c6f63c4a49617b4233f4433e5dc6dc6fb64bcc0d9e7bc8
|
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 sha256:39b3fe03d5430951580b4725b29a0caf4365f4eab1805f3041e3568c8cb59518
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -48,11 +48,25 @@
|
|
48 |
"eval_samples_per_second": 4.457,
|
49 |
"eval_wer": 0.4606879606879607,
|
50 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
}
|
52 |
],
|
53 |
"max_steps": 29490,
|
54 |
"num_train_epochs": 30,
|
55 |
-
"total_flos":
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.627670396744659,
|
5 |
+
"global_step": 1600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
48 |
"eval_samples_per_second": 4.457,
|
49 |
"eval_wer": 0.4606879606879607,
|
50 |
"step": 1200
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.63,
|
54 |
+
"learning_rate": 0.0002886167644015177,
|
55 |
+
"loss": 0.3595,
|
56 |
+
"step": 1600
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.63,
|
60 |
+
"eval_loss": 0.4238700568675995,
|
61 |
+
"eval_runtime": 235.4681,
|
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": 8.886108415980257e+18,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
72 |
}
|