Commit
β’
5725e99
1
Parent(s):
cfcb1ad
Training in progress, epoch 4
Browse files- {checkpoint-192 β checkpoint-480}/config.json +0 -0
- {checkpoint-192 β checkpoint-480}/optimizer.pt +2 -2
- {checkpoint-192 β checkpoint-480}/preprocessor_config.json +0 -0
- {checkpoint-192 β checkpoint-480}/pytorch_model.bin +1 -1
- {checkpoint-192 β checkpoint-480}/rng_state.pth +1 -1
- {checkpoint-192 β checkpoint-480}/scaler.pt +1 -1
- {checkpoint-192 β checkpoint-480}/scheduler.pt +1 -1
- {checkpoint-192 β checkpoint-480}/trainer_state.json +48 -3
- {checkpoint-192 β checkpoint-480}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-192 β checkpoint-480}/config.json
RENAMED
File without changes
|
{checkpoint-192 β checkpoint-480}/optimizer.pt
RENAMED
@@ -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 sha256:1b795539b78bf738fd54af53ed93604f1030808e674fef0cb6db817a6f9164b9
|
3 |
+
size 2490337809
|
{checkpoint-192 β checkpoint-480}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-192 β checkpoint-480}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:376983ae786038eae34616ce0e3b7a52a1f26bf9ad05a9e2fce0e200f7c041fa
|
3 |
size 1262063089
|
{checkpoint-192 β checkpoint-480}/rng_state.pth
RENAMED
@@ -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:c5f2e2ffcb1828049412b9c4ce2dd1433894da34deb1f2faa13084ce3eb624c6
|
3 |
size 14567
|
{checkpoint-192 β checkpoint-480}/scaler.pt
RENAMED
@@ -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 sha256:2461b163ff23e433395276a4f0dcf0a30de3489b02f5802e14476aa36b300549
|
3 |
size 559
|
{checkpoint-192 β checkpoint-480}/scheduler.pt
RENAMED
@@ -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:d5f7a180820bf6a92756a1401f564513c1deb0d9a15e14ad26cb4a2282a234c6
|
3 |
size 623
|
{checkpoint-192 β checkpoint-480}/trainer_state.json
RENAMED
@@ -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,
|
@@ -30,11 +30,56 @@
|
|
30 |
"eval_steps_per_second": 0.849,
|
31 |
"eval_wer": 1.0,
|
32 |
"step": 192
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"max_steps": 19200,
|
36 |
"num_train_epochs": 200,
|
37 |
-
"total_flos":
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.997402597402598,
|
5 |
+
"global_step": 480,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_steps_per_second": 0.849,
|
31 |
"eval_wer": 1.0,
|
32 |
"step": 192
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.08,
|
36 |
+
"learning_rate": 3.0781249999999994e-06,
|
37 |
+
"loss": 14.7046,
|
38 |
+
"step": 200
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_loss": 11.056963920593262,
|
43 |
+
"eval_runtime": 184.9586,
|
44 |
+
"eval_samples_per_second": 27.276,
|
45 |
+
"eval_steps_per_second": 0.854,
|
46 |
+
"eval_wer": 1.0,
|
47 |
+
"step": 288
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.12,
|
51 |
+
"learning_rate": 4.640624999999999e-06,
|
52 |
+
"loss": 11.6089,
|
53 |
+
"step": 300
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"eval_loss": 5.172672271728516,
|
58 |
+
"eval_runtime": 185.1159,
|
59 |
+
"eval_samples_per_second": 27.253,
|
60 |
+
"eval_steps_per_second": 0.854,
|
61 |
+
"eval_wer": 1.0,
|
62 |
+
"step": 384
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.17,
|
66 |
+
"learning_rate": 6.203124999999999e-06,
|
67 |
+
"loss": 5.9408,
|
68 |
+
"step": 400
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"eval_loss": 3.6944665908813477,
|
73 |
+
"eval_runtime": 186.0698,
|
74 |
+
"eval_samples_per_second": 27.113,
|
75 |
+
"eval_steps_per_second": 0.849,
|
76 |
+
"eval_wer": 1.0,
|
77 |
+
"step": 480
|
78 |
}
|
79 |
],
|
80 |
"max_steps": 19200,
|
81 |
"num_train_epochs": 200,
|
82 |
+
"total_flos": 7.455905805922749e+18,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
85 |
}
|
{checkpoint-192 β checkpoint-480}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:376983ae786038eae34616ce0e3b7a52a1f26bf9ad05a9e2fce0e200f7c041fa
|
3 |
size 1262063089
|