Commit
•
248315d
1
Parent(s):
ab3e230
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- nohup.out +23 -0
- train_results.json +8 -0
- trainer_state.json +115 -0
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 49.98,
|
3 |
+
"eval_loss": 2.8934524059295654,
|
4 |
+
"eval_runtime": 13.0771,
|
5 |
+
"eval_samples": 341,
|
6 |
+
"eval_samples_per_second": 26.076,
|
7 |
+
"eval_steps_per_second": 3.288,
|
8 |
+
"eval_wer": 0.9874538745387453,
|
9 |
+
"train_loss": 5.6772947265625,
|
10 |
+
"train_runtime": 2084.0288,
|
11 |
+
"train_samples": 810,
|
12 |
+
"train_samples_per_second": 19.434,
|
13 |
+
"train_steps_per_second": 0.6
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 49.98,
|
3 |
+
"eval_loss": 2.8934524059295654,
|
4 |
+
"eval_runtime": 13.0771,
|
5 |
+
"eval_samples": 341,
|
6 |
+
"eval_samples_per_second": 26.076,
|
7 |
+
"eval_steps_per_second": 3.288,
|
8 |
+
"eval_wer": 0.9874538745387453
|
9 |
+
}
|
nohup.out
CHANGED
@@ -635,3 +635,26 @@ Configuration saved in ./preprocessor_config.json
|
|
635 |
|
636 |
Dropping the following result as it does not have all the necessary fields:
|
637 |
{'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'ur'}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
638 |
0%| | 0/43 [00:00<?, ?it/s]
|
639 |
5%|▍ | 2/43 [00:00<00:04, 9.60it/s]
|
640 |
7%|▋ | 3/43 [00:00<00:06, 5.79it/s]
|
641 |
9%|▉ | 4/43 [00:00<00:08, 4.35it/s]
|
642 |
12%|█▏ | 5/43 [00:01<00:09, 4.11it/s]
|
643 |
14%|█▍ | 6/43 [00:01<00:09, 3.90it/s]
|
644 |
16%|█▋ | 7/43 [00:01<00:09, 3.85it/s]
|
645 |
19%|█▊ | 8/43 [00:01<00:09, 3.80it/s]
|
646 |
21%|██ | 9/43 [00:02<00:09, 3.52it/s]
|
647 |
23%|██▎ | 10/43 [00:02<00:08, 3.78it/s]
|
648 |
26%|██▌ | 11/43 [00:02<00:08, 3.78it/s]
|
649 |
28%|██▊ | 12/43 [00:02<00:08, 3.83it/s]
|
650 |
30%|███ | 13/43 [00:03<00:07, 3.85it/s]
|
651 |
33%|███▎ | 14/43 [00:03<00:08, 3.31it/s]
|
652 |
35%|███▍ | 15/43 [00:04<00:09, 2.96it/s]
|
653 |
37%|███▋ | 16/43 [00:04<00:08, 3.02it/s]
|
654 |
40%|███▉ | 17/43 [00:04<00:08, 3.10it/s]
|
655 |
42%|████▏ | 18/43 [00:05<00:08, 3.02it/s]
|
656 |
44%|████▍ | 19/43 [00:05<00:08, 2.83it/s]
|
657 |
47%|████▋ | 20/43 [00:05<00:08, 2.56it/s]
|
658 |
49%|████▉ | 21/43 [00:06<00:08, 2.64it/s]
|
659 |
51%|█████ | 22/43 [00:06<00:07, 2.69it/s]
|
660 |
53%|█████▎ | 23/43 [00:06<00:07, 2.81it/s]
|
661 |
56%|█████▌ | 24/43 [00:07<00:06, 3.08it/s]
|
662 |
58%|█████▊ | 25/43 [00:07<00:05, 3.22it/s]
|
663 |
60%|██████ | 26/43 [00:07<00:05, 3.28it/s]
|
664 |
63%|██████▎ | 27/43 [00:07<00:04, 3.67it/s]
|
665 |
65%|██████▌ | 28/43 [00:08<00:04, 3.66it/s]
|
666 |
67%|██████▋ | 29/43 [00:08<00:03, 3.71it/s]
|
667 |
70%|██████▉ | 30/43 [00:08<00:03, 3.81it/s]
|
668 |
72%|███████▏ | 31/43 [00:08<00:03, 3.77it/s]
|
669 |
74%|███████▍ | 32/43 [00:09<00:02, 3.81it/s]
|
670 |
77%|███████▋ | 33/43 [00:09<00:02, 3.53it/s]
|
671 |
79%|███████▉ | 34/43 [00:09<00:02, 3.49it/s]
|
672 |
81%|████████▏ | 35/43 [00:10<00:02, 3.47it/s]
|
673 |
84%|████████▎ | 36/43 [00:10<00:02, 3.38it/s]
|
674 |
86%|████████▌ | 37/43 [00:10<00:01, 3.53it/s]
|
675 |
88%|████████▊ | 38/43 [00:11<00:01, 3.27it/s]
|
676 |
91%|█████████ | 39/43 [00:11<00:01, 3.34it/s]
|
677 |
93%|█████████▎| 40/43 [00:11<00:00, 3.17it/s]
|
678 |
95%|█████████▌| 41/43 [00:12<00:00, 3.28it/s]
|
679 |
98%|█████████▊| 42/43 [00:12<00:00, 3.18it/s]
|
|
|
|
|
|
|
|
|
|
635 |
|
636 |
Dropping the following result as it does not have all the necessary fields:
|
637 |
{'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'ur'}}
|
638 |
+
To https://huggingface.co/HarrisDePerceptron/xls-r-300m-ur
|
639 |
+
4e1557d..ab3e230 main -> main
|
640 |
+
|
641 |
+
02/02/2022 18:41:43 - WARNING - huggingface_hub.repository - To https://huggingface.co/HarrisDePerceptron/xls-r-300m-ur
|
642 |
+
4e1557d..ab3e230 main -> main
|
643 |
+
|
644 |
+
***** train metrics *****
|
645 |
+
epoch = 49.98
|
646 |
+
train_loss = 5.6773
|
647 |
+
train_runtime = 0:34:44.02
|
648 |
+
train_samples = 810
|
649 |
+
train_samples_per_second = 19.434
|
650 |
+
train_steps_per_second = 0.6
|
651 |
+
02/02/2022 18:41:45 - INFO - __main__ - *** Evaluate ***
|
652 |
+
The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
|
653 |
+
***** Running Evaluation *****
|
654 |
+
Num examples = 341
|
655 |
+
Batch size = 8
|
656 |
+
|
657 |
0%| | 0/43 [00:00<?, ?it/s]
|
658 |
5%|▍ | 2/43 [00:00<00:04, 9.60it/s]
|
659 |
7%|▋ | 3/43 [00:00<00:06, 5.79it/s]
|
660 |
9%|▉ | 4/43 [00:00<00:08, 4.35it/s]
|
661 |
12%|█▏ | 5/43 [00:01<00:09, 4.11it/s]
|
662 |
14%|█▍ | 6/43 [00:01<00:09, 3.90it/s]
|
663 |
16%|█▋ | 7/43 [00:01<00:09, 3.85it/s]
|
664 |
19%|█▊ | 8/43 [00:01<00:09, 3.80it/s]
|
665 |
21%|██ | 9/43 [00:02<00:09, 3.52it/s]
|
666 |
23%|██▎ | 10/43 [00:02<00:08, 3.78it/s]
|
667 |
26%|██▌ | 11/43 [00:02<00:08, 3.78it/s]
|
668 |
28%|██▊ | 12/43 [00:02<00:08, 3.83it/s]
|
669 |
30%|███ | 13/43 [00:03<00:07, 3.85it/s]
|
670 |
33%|███▎ | 14/43 [00:03<00:08, 3.31it/s]
|
671 |
35%|███▍ | 15/43 [00:04<00:09, 2.96it/s]
|
672 |
37%|███▋ | 16/43 [00:04<00:08, 3.02it/s]
|
673 |
40%|███▉ | 17/43 [00:04<00:08, 3.10it/s]
|
674 |
42%|████▏ | 18/43 [00:05<00:08, 3.02it/s]
|
675 |
44%|████▍ | 19/43 [00:05<00:08, 2.83it/s]
|
676 |
47%|████▋ | 20/43 [00:05<00:08, 2.56it/s]
|
677 |
49%|████▉ | 21/43 [00:06<00:08, 2.64it/s]
|
678 |
51%|█████ | 22/43 [00:06<00:07, 2.69it/s]
|
679 |
53%|█████▎ | 23/43 [00:06<00:07, 2.81it/s]
|
680 |
56%|█████▌ | 24/43 [00:07<00:06, 3.08it/s]
|
681 |
58%|█████▊ | 25/43 [00:07<00:05, 3.22it/s]
|
682 |
60%|██████ | 26/43 [00:07<00:05, 3.28it/s]
|
683 |
63%|██████▎ | 27/43 [00:07<00:04, 3.67it/s]
|
684 |
65%|██████▌ | 28/43 [00:08<00:04, 3.66it/s]
|
685 |
67%|██████▋ | 29/43 [00:08<00:03, 3.71it/s]
|
686 |
70%|██████▉ | 30/43 [00:08<00:03, 3.81it/s]
|
687 |
72%|███████▏ | 31/43 [00:08<00:03, 3.77it/s]
|
688 |
74%|███████▍ | 32/43 [00:09<00:02, 3.81it/s]
|
689 |
77%|███████▋ | 33/43 [00:09<00:02, 3.53it/s]
|
690 |
79%|███████▉ | 34/43 [00:09<00:02, 3.49it/s]
|
691 |
81%|████████▏ | 35/43 [00:10<00:02, 3.47it/s]
|
692 |
84%|████████▎ | 36/43 [00:10<00:02, 3.38it/s]
|
693 |
86%|████████▌ | 37/43 [00:10<00:01, 3.53it/s]
|
694 |
88%|████████▊ | 38/43 [00:11<00:01, 3.27it/s]
|
695 |
91%|█████████ | 39/43 [00:11<00:01, 3.34it/s]
|
696 |
93%|█████████▎| 40/43 [00:11<00:00, 3.17it/s]
|
697 |
95%|█████████▌| 41/43 [00:12<00:00, 3.28it/s]
|
698 |
98%|█████████▊| 42/43 [00:12<00:00, 3.18it/s]
|
699 |
+
Saving model checkpoint to ./
|
700 |
+
Configuration saved in ./config.json
|
701 |
+
Model weights saved in ./pytorch_model.bin
|
702 |
+
Configuration saved in ./preprocessor_config.json
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 49.98,
|
3 |
+
"train_loss": 5.6772947265625,
|
4 |
+
"train_runtime": 2084.0288,
|
5 |
+
"train_samples": 810,
|
6 |
+
"train_samples_per_second": 19.434,
|
7 |
+
"train_steps_per_second": 0.6
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 49.98039215686274,
|
5 |
+
"global_step": 1250,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 3.98,
|
12 |
+
"learning_rate": 3.675e-06,
|
13 |
+
"loss": 20.0794,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 7.98,
|
18 |
+
"learning_rate": 7.425e-06,
|
19 |
+
"loss": 10.5776,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 11.98,
|
24 |
+
"learning_rate": 1.1174999999999999e-05,
|
25 |
+
"loss": 6.6033,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 15.98,
|
30 |
+
"learning_rate": 1.4925e-05,
|
31 |
+
"loss": 5.3857,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 19.98,
|
36 |
+
"learning_rate": 1.8675e-05,
|
37 |
+
"loss": 4.4431,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 19.98,
|
42 |
+
"eval_loss": 4.144110202789307,
|
43 |
+
"eval_runtime": 12.9526,
|
44 |
+
"eval_samples_per_second": 26.327,
|
45 |
+
"eval_steps_per_second": 3.32,
|
46 |
+
"eval_wer": 1.0,
|
47 |
+
"step": 500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 23.98,
|
51 |
+
"learning_rate": 2.2424999999999996e-05,
|
52 |
+
"loss": 3.7383,
|
53 |
+
"step": 600
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 27.98,
|
57 |
+
"learning_rate": 2.6174999999999996e-05,
|
58 |
+
"loss": 3.361,
|
59 |
+
"step": 700
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 31.98,
|
63 |
+
"learning_rate": 2.9925e-05,
|
64 |
+
"loss": 3.2219,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 35.98,
|
69 |
+
"learning_rate": 3.3675e-05,
|
70 |
+
"loss": 3.104,
|
71 |
+
"step": 900
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 39.98,
|
75 |
+
"learning_rate": 3.7424999999999995e-05,
|
76 |
+
"loss": 3.0399,
|
77 |
+
"step": 1000
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 39.98,
|
81 |
+
"eval_loss": 2.9768528938293457,
|
82 |
+
"eval_runtime": 12.8843,
|
83 |
+
"eval_samples_per_second": 26.466,
|
84 |
+
"eval_steps_per_second": 3.337,
|
85 |
+
"eval_wer": 0.9988929889298893,
|
86 |
+
"step": 1000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 43.98,
|
90 |
+
"learning_rate": 4.1175e-05,
|
91 |
+
"loss": 2.9893,
|
92 |
+
"step": 1100
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 47.98,
|
96 |
+
"learning_rate": 4.4924999999999994e-05,
|
97 |
+
"loss": 2.953,
|
98 |
+
"step": 1200
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 49.98,
|
102 |
+
"step": 1250,
|
103 |
+
"total_flos": 4.919672600088422e+18,
|
104 |
+
"train_loss": 5.6772947265625,
|
105 |
+
"train_runtime": 2084.0288,
|
106 |
+
"train_samples_per_second": 19.434,
|
107 |
+
"train_steps_per_second": 0.6
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 1250,
|
111 |
+
"num_train_epochs": 50,
|
112 |
+
"total_flos": 4.919672600088422e+18,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|