marinone94
commited on
Commit
β’
cfcb1ad
1
Parent(s):
15e5a98
Training in progress, epoch 3
Browse files- {checkpoint-96 β checkpoint-384}/config.json +0 -0
- {checkpoint-96 β checkpoint-384}/optimizer.pt +2 -2
- {checkpoint-96 β checkpoint-384}/preprocessor_config.json +0 -0
- {checkpoint-96 β checkpoint-384}/pytorch_model.bin +1 -1
- {checkpoint-96 β checkpoint-384}/rng_state.pth +2 -2
- {checkpoint-96 β checkpoint-384}/scaler.pt +1 -1
- {checkpoint-96 β checkpoint-384}/scheduler.pt +1 -1
- {checkpoint-96 β checkpoint-384}/trainer_state.json +48 -3
- {checkpoint-96 β checkpoint-384}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-96 β checkpoint-384}/config.json
RENAMED
File without changes
|
{checkpoint-96 β checkpoint-384}/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:bccdf1951285bc8f144e548c876fbba29c6232b75d96f576898dd120c4e52c32
|
3 |
+
size 2490337809
|
{checkpoint-96 β checkpoint-384}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-96 β checkpoint-384}/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 sha256:39cd4931c86a20e934a7a6a159fcff1ae2afc563726fc1d6f8d1d4b9ddf31f04
|
3 |
size 1262063089
|
{checkpoint-96 β checkpoint-384}/rng_state.pth
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 sha256:326defae442174688b8a39c89a59d4cd08f602e59d0f8c786318fe121dc96f13
|
3 |
+
size 14567
|
{checkpoint-96 β checkpoint-384}/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:f500d0462151884dfc3fb596f7314ea368243375fee037876ece3f34632a4556
|
3 |
size 559
|
{checkpoint-96 β checkpoint-384}/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 sha256:3339333fbf9f04b9505e1075b6ae46b18caeefdc727f16807fe4be87e1daff43
|
3 |
size 623
|
{checkpoint-96 β checkpoint-384}/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,
|
@@ -15,11 +15,56 @@
|
|
15 |
"eval_steps_per_second": 0.839,
|
16 |
"eval_wer": 1.0021133629565406,
|
17 |
"step": 96
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
"max_steps": 19200,
|
21 |
"num_train_epochs": 200,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.9974025974025973,
|
5 |
+
"global_step": 384,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
15 |
"eval_steps_per_second": 0.839,
|
16 |
"eval_wer": 1.0021133629565406,
|
17 |
"step": 96
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.04,
|
21 |
+
"learning_rate": 1.5156249999999998e-06,
|
22 |
+
"loss": 15.219,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_loss": 17.49703025817871,
|
28 |
+
"eval_runtime": 186.0672,
|
29 |
+
"eval_samples_per_second": 27.114,
|
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 |
"max_steps": 19200,
|
66 |
"num_train_epochs": 200,
|
67 |
+
"total_flos": 5.964637507404861e+18,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
{checkpoint-96 β checkpoint-384}/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 sha256:39cd4931c86a20e934a7a6a159fcff1ae2afc563726fc1d6f8d1d4b9ddf31f04
|
3 |
size 1262063089
|