Commit
β’
20f5c45
1
Parent(s):
5725e99
Training in progress, epoch 5
Browse files- {checkpoint-288 β checkpoint-576}/config.json +0 -0
- {checkpoint-288 β checkpoint-576}/optimizer.pt +1 -1
- {checkpoint-288 β checkpoint-576}/preprocessor_config.json +0 -0
- {checkpoint-288 β checkpoint-576}/pytorch_model.bin +1 -1
- {checkpoint-288 β checkpoint-576}/rng_state.pth +1 -1
- {checkpoint-288 β checkpoint-576}/scaler.pt +1 -1
- {checkpoint-288 β checkpoint-576}/scheduler.pt +1 -1
- {checkpoint-288 β checkpoint-576}/trainer_state.json +48 -3
- {checkpoint-288 β checkpoint-576}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-288 β checkpoint-576}/config.json
RENAMED
File without changes
|
{checkpoint-288 β checkpoint-576}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb1350ff6e9893acaf16619961010f4c79ea8a244d121ac1c7e394f0ec20fe3
|
3 |
size 2490337809
|
{checkpoint-288 β checkpoint-576}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-288 β checkpoint-576}/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 sha256:6a4eb5262362bc942997943e8cac7304bde0ff46a7d74568873dcc9435010d2b
|
3 |
size 1262063089
|
{checkpoint-288 β checkpoint-576}/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 sha256:7623b4c7baef3e7f83b53332857785fb33c5c12d7f39597ff07744e1bac86639
|
3 |
size 14567
|
{checkpoint-288 β checkpoint-576}/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 sha256:4a4bfd784255410181d8b7f330e21b3d72f67d7de17ce03ce3ddbfe13e1014a2
|
3 |
size 559
|
{checkpoint-288 β checkpoint-576}/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 sha256:02bf983fc7d4d4e99567cd4deb53f5271898d5335892a0fd4365a6bb08882199
|
3 |
size 623
|
{checkpoint-288 β checkpoint-576}/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,
|
@@ -45,11 +45,56 @@
|
|
45 |
"eval_steps_per_second": 0.854,
|
46 |
"eval_wer": 1.0,
|
47 |
"step": 288
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"max_steps": 19200,
|
51 |
"num_train_epochs": 200,
|
52 |
-
"total_flos":
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.997402597402598,
|
5 |
+
"global_step": 576,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
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 |
+
"epoch": 5.21,
|
81 |
+
"learning_rate": 7.765624999999999e-06,
|
82 |
+
"loss": 3.8196,
|
83 |
+
"step": 500
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"eval_loss": 3.3380837440490723,
|
88 |
+
"eval_runtime": 183.9322,
|
89 |
+
"eval_samples_per_second": 27.429,
|
90 |
+
"eval_steps_per_second": 0.859,
|
91 |
+
"eval_wer": 1.0,
|
92 |
+
"step": 576
|
93 |
}
|
94 |
],
|
95 |
"max_steps": 19200,
|
96 |
"num_train_epochs": 200,
|
97 |
+
"total_flos": 8.945907324105985e+18,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
{checkpoint-288 β checkpoint-576}/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 sha256:6a4eb5262362bc942997943e8cac7304bde0ff46a7d74568873dcc9435010d2b
|
3 |
size 1262063089
|