marinone94
commited on
Commit
β’
6043014
1
Parent(s):
20f5c45
Training in progress, epoch 6
Browse files- {checkpoint-384 β checkpoint-672}/config.json +0 -0
- {checkpoint-384 β checkpoint-672}/optimizer.pt +1 -1
- {checkpoint-384 β checkpoint-672}/preprocessor_config.json +0 -0
- {checkpoint-384 β checkpoint-672}/pytorch_model.bin +1 -1
- {checkpoint-384 β checkpoint-672}/rng_state.pth +1 -1
- {checkpoint-384 β checkpoint-672}/scaler.pt +1 -1
- {checkpoint-384 β checkpoint-672}/scheduler.pt +1 -1
- {checkpoint-384 β checkpoint-672}/trainer_state.json +48 -3
- {checkpoint-384 β checkpoint-672}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-384 β checkpoint-672}/config.json
RENAMED
File without changes
|
{checkpoint-384 β checkpoint-672}/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 sha256:5bfba90dfb145308edc9cc54791241d132cd937db592ef07d6e7026b82f83748
|
3 |
size 2490337809
|
{checkpoint-384 β checkpoint-672}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-384 β checkpoint-672}/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 sha256:6cda6c609d26894118f60831d66a918be45540d348cdd4e71e2cfd6c4296b3de
|
3 |
size 1262063089
|
{checkpoint-384 β checkpoint-672}/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:ebfa122200e74335f79d2f8a43ce26c726efd4c21ffe6331de97989b229b381e
|
3 |
size 14567
|
{checkpoint-384 β checkpoint-672}/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 sha256:03f55b5a17595526cb1157c4710c777fc0eafef249129dba3a1e2632c2bb5762
|
3 |
size 559
|
{checkpoint-384 β checkpoint-672}/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 sha256:1bb60131ff9244ecc96d9d9ae122e339002db12489062cce1759d60df5d23b66
|
3 |
size 623
|
{checkpoint-384 β checkpoint-672}/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,
|
@@ -60,11 +60,56 @@
|
|
60 |
"eval_steps_per_second": 0.854,
|
61 |
"eval_wer": 1.0,
|
62 |
"step": 384
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 19200,
|
66 |
"num_train_epochs": 200,
|
67 |
-
"total_flos":
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.997402597402598,
|
5 |
+
"global_step": 672,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
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 |
+
"epoch": 6.25,
|
96 |
+
"learning_rate": 9.328125e-06,
|
97 |
+
"loss": 3.3535,
|
98 |
+
"step": 600
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 3.2117931842803955,
|
103 |
+
"eval_runtime": 186.1,
|
104 |
+
"eval_samples_per_second": 27.109,
|
105 |
+
"eval_steps_per_second": 0.849,
|
106 |
+
"eval_wer": 1.0,
|
107 |
+
"step": 672
|
108 |
}
|
109 |
],
|
110 |
"max_steps": 19200,
|
111 |
"num_train_epochs": 200,
|
112 |
+
"total_flos": 1.0436571367071685e+19,
|
113 |
"trial_name": null,
|
114 |
"trial_params": null
|
115 |
}
|
{checkpoint-384 β checkpoint-672}/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 sha256:6cda6c609d26894118f60831d66a918be45540d348cdd4e71e2cfd6c4296b3de
|
3 |
size 1262063089
|