marinone94 commited on
Commit
4591caf
β€’
1 Parent(s): a0cfb9d

Training in progress, step 80

Browse files
{checkpoint-20 β†’ checkpoint-80}/config.json RENAMED
File without changes
{checkpoint-20 β†’ checkpoint-80}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:075df4bf25f6d34069d73115a8c7331da68aa4a7dd3f23353e295886bc03506a
3
  size 2490337361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b638480e632c1a7b61ada4cfb4e085fc6687b2cc7006a885f1727d7d5a41f17
3
  size 2490337361
{checkpoint-20 β†’ checkpoint-80}/preprocessor_config.json RENAMED
File without changes
{checkpoint-20 β†’ checkpoint-80}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b6100773ca3a4687e69ef744a414602f964603f13c71a09f8727f73dd051f1
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d243142fcbd07def1347c28af05f32d03aa37c7536de513cc8503d261cf6d773
3
  size 1262063089
{checkpoint-20 β†’ checkpoint-80}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73e968b5fb75f3d028c5b87fc29d361b46586d839eb1fc406be3e77c69542778
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26c7900baa445f707767794b45729eeb213e1b2dc71ded73ca14c4c4a7d25a4
3
  size 14567
{checkpoint-20 β†’ checkpoint-80}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d1040cd70f91f849688103143e8c9d631ff10c4acee0b2f4d6ff9e27727776
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2409ebedbf30ba97120ef308e1ac839369eea668dd8be70d109b5b98fe71857f
3
  size 559
{checkpoint-20 β†’ checkpoint-80}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bee97b3839fd1b431d21567a2339671d799c163d5402ee322afd861513750b5
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:721652adf9b5a54ee9b9baf3dac2052ee6350d8d896360a6439d75c8bb179b00
3
  size 623
{checkpoint-20 β†’ checkpoint-80}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.26490066225165565,
5
- "global_step": 20,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -27,11 +27,74 @@
27
  "eval_steps_per_second": 0.762,
28
  "eval_wer": 1.0,
29
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  }
31
  ],
32
  "max_steps": 750,
33
  "num_train_epochs": 10,
34
- "total_flos": 4.155165485184e+17,
35
  "trial_name": null,
36
  "trial_params": null
37
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0662251655629138,
5
+ "global_step": 80,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
27
  "eval_steps_per_second": 0.762,
28
  "eval_wer": 1.0,
29
  "step": 20
30
+ },
31
+ {
32
+ "epoch": 0.4,
33
+ "learning_rate": 7.36734693877551e-05,
34
+ "loss": 8.0091,
35
+ "step": 30
36
+ },
37
+ {
38
+ "epoch": 0.53,
39
+ "learning_rate": 7.265306122448979e-05,
40
+ "loss": 7.6332,
41
+ "step": 40
42
+ },
43
+ {
44
+ "epoch": 0.53,
45
+ "eval_loss": 4.783994197845459,
46
+ "eval_runtime": 4.9818,
47
+ "eval_samples_per_second": 19.672,
48
+ "eval_steps_per_second": 0.803,
49
+ "eval_wer": 1.0,
50
+ "step": 40
51
+ },
52
+ {
53
+ "epoch": 0.66,
54
+ "learning_rate": 7.163265306122449e-05,
55
+ "loss": 3.8261,
56
+ "step": 50
57
+ },
58
+ {
59
+ "epoch": 0.79,
60
+ "learning_rate": 7.061224489795918e-05,
61
+ "loss": 3.8717,
62
+ "step": 60
63
+ },
64
+ {
65
+ "epoch": 0.79,
66
+ "eval_loss": 3.6783852577209473,
67
+ "eval_runtime": 4.9141,
68
+ "eval_samples_per_second": 19.943,
69
+ "eval_steps_per_second": 0.814,
70
+ "eval_wer": 1.0,
71
+ "step": 60
72
+ },
73
+ {
74
+ "epoch": 0.93,
75
+ "learning_rate": 6.959183673469387e-05,
76
+ "loss": 3.7607,
77
+ "step": 70
78
+ },
79
+ {
80
+ "epoch": 1.07,
81
+ "learning_rate": 6.857142857142857e-05,
82
+ "loss": 3.638,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 1.07,
87
+ "eval_loss": 3.4979612827301025,
88
+ "eval_runtime": 5.0758,
89
+ "eval_samples_per_second": 19.307,
90
+ "eval_steps_per_second": 0.788,
91
+ "eval_wer": 1.0,
92
+ "step": 80
93
  }
94
  ],
95
  "max_steps": 750,
96
  "num_train_epochs": 10,
97
+ "total_flos": 1.61703171100896e+18,
98
  "trial_name": null,
99
  "trial_params": null
100
  }
{checkpoint-20 β†’ checkpoint-80}/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:ed09bae03da69e6e7d54c45ff801a7cd8e65f5bb600585b021024798e5fafa4a
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d243142fcbd07def1347c28af05f32d03aa37c7536de513cc8503d261cf6d773
3
  size 1262063089