Hugging Face's logo

Lithicsoft
/
The-Lithicsoft-Research-AI-01

Text Generation
Transformers
PyTorch
English
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Community
4
AnthonyErosion commited on
Commit
b5249ce
•
1 Parent(s): 0f1d11e

Delete logs.log

Browse files
Files changed (1) hide show
  1. logs.log +0 -78
logs.log DELETED
@@ -1,78 +0,0 @@
1
- 2023-07-02 08:31:42,382 - INFO: Global random seed: 1
2
- 2023-07-02 08:31:42,383 - INFO: Preparing the data...
3
- 2023-07-02 08:31:42,383 - INFO: Setting up automatic validation split...
4
- 2023-07-02 08:31:42,525 - INFO: Preparing train and validation data
5
- 2023-07-02 08:31:42,525 - INFO: Loading train dataset...
6
- 2023-07-02 08:31:46,354 - INFO: Loading validation dataset...
7
- 2023-07-02 08:31:46,939 - INFO: Number of observations in train dataset: 8191
8
- 2023-07-02 08:31:46,939 - INFO: Number of observations in validation dataset: 83
9
- 2023-07-02 08:31:47,629 - INFO: dtype: torch.float16
10
- 2023-07-02 08:32:23,828 - INFO: Training Epoch: 1 / 1
11
- 2023-07-02 08:32:23,830 - INFO: train loss: 0%| | 0/2047 [00:00<?, ?it/s]
12
- 2023-07-02 08:32:58,328 - INFO: train loss: 2.20: 5%|4 | 102/2047 [00:34<10:57, 2.96it/s]
13
- 2023-07-02 08:33:13,136 - INFO: train loss: 2.20: 5%|4 | 102/2047 [00:49<10:57, 2.96it/s]
14
- 2023-07-02 08:33:31,440 - INFO: train loss: 2.21: 10%|9 | 204/2047 [01:07<10:08, 3.03it/s]
15
- 2023-07-02 08:33:43,149 - INFO: train loss: 2.21: 10%|9 | 204/2047 [01:19<10:08, 3.03it/s]
16
- 2023-07-02 08:34:02,703 - INFO: train loss: 2.17: 15%|#4 | 306/2047 [01:38<09:16, 3.13it/s]
17
- 2023-07-02 08:34:13,263 - INFO: train loss: 2.17: 15%|#4 | 306/2047 [01:49<09:16, 3.13it/s]
18
- 2023-07-02 08:34:37,490 - INFO: train loss: 1.91: 20%|#9 | 408/2047 [02:13<08:57, 3.05it/s]
19
- 2023-07-02 08:34:53,265 - INFO: train loss: 1.91: 20%|#9 | 408/2047 [02:29<08:57, 3.05it/s]
20
- 2023-07-02 08:35:11,253 - INFO: train loss: 2.29: 25%|##4 | 510/2047 [02:47<08:25, 3.04it/s]
21
- 2023-07-02 08:35:23,269 - INFO: train loss: 2.29: 25%|##4 | 510/2047 [02:59<08:25, 3.04it/s]
22
- 2023-07-02 08:35:45,891 - INFO: train loss: 2.05: 30%|##9 | 612/2047 [03:22<07:57, 3.01it/s]
23
- 2023-07-02 08:36:03,278 - INFO: train loss: 2.05: 30%|##9 | 612/2047 [03:39<07:57, 3.01it/s]
24
- 2023-07-02 08:36:19,511 - INFO: train loss: 2.22: 35%|###4 | 714/2047 [03:55<07:22, 3.02it/s]
25
- 2023-07-02 08:36:33,279 - INFO: train loss: 2.22: 35%|###4 | 714/2047 [04:09<07:22, 3.02it/s]
26
- 2023-07-02 08:36:54,000 - INFO: train loss: 2.03: 40%|###9 | 816/2047 [04:30<06:50, 3.00it/s]
27
- 2023-07-02 08:37:04,102 - INFO: train loss: 2.03: 40%|###9 | 816/2047 [04:40<06:50, 3.00it/s]
28
- 2023-07-02 08:37:28,685 - INFO: train loss: 1.97: 45%|####4 | 918/2047 [05:04<06:18, 2.98it/s]
29
- 2023-07-02 08:37:43,385 - INFO: train loss: 1.97: 45%|####4 | 918/2047 [05:19<06:18, 2.98it/s]
30
- 2023-07-02 08:38:02,398 - INFO: train loss: 2.28: 50%|####9 | 1020/2047 [05:38<05:43, 2.99it/s]
31
- 2023-07-02 08:38:13,392 - INFO: train loss: 2.28: 50%|####9 | 1020/2047 [05:49<05:43, 2.99it/s]
32
- 2023-07-02 08:38:36,462 - INFO: train loss: 2.12: 55%|#####4 | 1122/2047 [06:12<05:09, 2.99it/s]
33
- 2023-07-02 08:38:53,394 - INFO: train loss: 2.12: 55%|#####4 | 1122/2047 [06:29<05:09, 2.99it/s]
34
- 2023-07-02 08:39:11,806 - INFO: train loss: 2.11: 60%|#####9 | 1224/2047 [06:47<04:38, 2.96it/s]
35
- 2023-07-02 08:39:23,408 - INFO: train loss: 2.11: 60%|#####9 | 1224/2047 [06:59<04:38, 2.96it/s]
36
- 2023-07-02 08:39:45,526 - INFO: train loss: 2.01: 65%|######4 | 1326/2047 [07:21<04:02, 2.98it/s]
37
- 2023-07-02 08:40:03,469 - INFO: train loss: 2.01: 65%|######4 | 1326/2047 [07:39<04:02, 2.98it/s]
38
- 2023-07-02 08:40:20,009 - INFO: train loss: 2.03: 70%|######9 | 1428/2047 [07:56<03:28, 2.97it/s]
39
- 2023-07-02 08:40:33,477 - INFO: train loss: 2.03: 70%|######9 | 1428/2047 [08:09<03:28, 2.97it/s]
40
- 2023-07-02 08:40:55,078 - INFO: train loss: 2.09: 75%|#######4 | 1530/2047 [08:31<02:55, 2.95it/s]
41
- 2023-07-02 08:41:13,519 - INFO: train loss: 2.09: 75%|#######4 | 1530/2047 [08:49<02:55, 2.95it/s]
42
- 2023-07-02 08:41:28,157 - INFO: train loss: 2.01: 80%|#######9 | 1632/2047 [09:04<02:18, 2.99it/s]
43
- 2023-07-02 08:41:43,521 - INFO: train loss: 2.01: 80%|#######9 | 1632/2047 [09:19<02:18, 2.99it/s]
44
- 2023-07-02 08:42:02,484 - INFO: train loss: 2.11: 85%|########4 | 1734/2047 [09:38<01:44, 2.99it/s]
45
- 2023-07-02 08:42:13,547 - INFO: train loss: 2.11: 85%|########4 | 1734/2047 [09:49<01:44, 2.99it/s]
46
- 2023-07-02 08:42:37,840 - INFO: train loss: 2.09: 90%|########9 | 1836/2047 [10:14<01:11, 2.95it/s]
47
- 2023-07-02 08:42:53,549 - INFO: train loss: 2.09: 90%|########9 | 1836/2047 [10:29<01:11, 2.95it/s]
48
- 2023-07-02 08:43:12,322 - INFO: train loss: 2.05: 95%|#########4| 1938/2047 [10:48<00:36, 2.96it/s]
49
- 2023-07-02 08:43:23,589 - INFO: train loss: 2.05: 95%|#########4| 1938/2047 [10:59<00:36, 2.96it/s]
50
- 2023-07-02 08:43:46,455 - INFO: train loss: 1.99: 100%|#########9| 2040/2047 [11:22<00:02, 2.97it/s]
51
- 2023-07-02 08:43:48,754 - INFO: train loss: 1.94: 100%|##########| 2047/2047 [11:24<00:00, 2.99it/s]
52
- 2023-07-02 08:43:48,757 - INFO: Starting validation inference
53
- 2023-07-02 08:43:48,758 - INFO: validation progress: 0%| | 0/21 [00:00<?, ?it/s]
54
- 2023-07-02 08:43:58,281 - INFO: validation progress: 5%|4 | 1/21 [00:09<03:10, 9.52s/it]
55
- 2023-07-02 08:44:05,283 - INFO: validation progress: 10%|9 | 2/21 [00:16<02:32, 8.04s/it]
56
- 2023-07-02 08:44:13,957 - INFO: validation progress: 14%|#4 | 3/21 [00:25<02:29, 8.33s/it]
57
- 2023-07-02 08:44:22,667 - INFO: validation progress: 19%|#9 | 4/21 [00:33<02:24, 8.48s/it]
58
- 2023-07-02 08:44:29,029 - INFO: validation progress: 24%|##3 | 5/21 [00:40<02:03, 7.72s/it]
59
- 2023-07-02 08:44:38,612 - INFO: validation progress: 29%|##8 | 6/21 [00:49<02:05, 8.35s/it]
60
- 2023-07-02 08:44:46,886 - INFO: validation progress: 33%|###3 | 7/21 [00:58<01:56, 8.33s/it]
61
- 2023-07-02 08:44:53,537 - INFO: validation progress: 38%|###8 | 8/21 [01:04<01:41, 7.79s/it]
62
- 2023-07-02 08:45:02,729 - INFO: validation progress: 43%|####2 | 9/21 [01:13<01:38, 8.23s/it]
63
- 2023-07-02 08:45:11,418 - INFO: validation progress: 48%|####7 | 10/21 [01:22<01:32, 8.37s/it]
64
- 2023-07-02 08:45:18,299 - INFO: validation progress: 52%|#####2 | 11/21 [01:29<01:19, 7.92s/it]
65
- 2023-07-02 08:45:27,541 - INFO: validation progress: 57%|#####7 | 12/21 [01:38<01:14, 8.32s/it]
66
- 2023-07-02 08:45:35,645 - INFO: validation progress: 62%|######1 | 13/21 [01:46<01:06, 8.25s/it]
67
- 2023-07-02 08:45:53,202 - INFO: validation progress: 67%|######6 | 14/21 [02:04<01:17, 11.06s/it]
68
- 2023-07-02 08:46:00,073 - INFO: validation progress: 71%|#######1 | 15/21 [02:11<00:58, 9.80s/it]
69
- 2023-07-02 08:46:07,159 - INFO: validation progress: 76%|#######6 | 16/21 [02:18<00:44, 8.98s/it]
70
- 2023-07-02 08:46:16,822 - INFO: validation progress: 81%|######## | 17/21 [02:28<00:36, 9.19s/it]
71
- 2023-07-02 08:46:23,565 - INFO: validation progress: 86%|########5 | 18/21 [02:34<00:25, 8.45s/it]
72
- 2023-07-02 08:46:30,419 - INFO: validation progress: 90%|######### | 19/21 [02:41<00:15, 7.97s/it]
73
- 2023-07-02 08:46:40,555 - INFO: validation progress: 95%|#########5| 20/21 [02:51<00:08, 8.62s/it]
74
- 2023-07-02 08:46:47,216 - INFO: validation progress: 100%|##########| 21/21 [02:58<00:00, 8.03s/it]
75
- 2023-07-02 08:46:47,219 - INFO: validation progress: 100%|##########| 21/21 [02:58<00:00, 8.50s/it]
76
- 2023-07-02 08:46:47,440 - INFO: Mean validation loss: 2.12888
77
- 2023-07-02 08:46:47,488 - INFO: Validation BLEU: 3.14715
78
- 2023-07-02 08:46:47,694 - INFO: Saving last model checkpoint: val_loss 2.1289, val_BLEU 3.1471 to output/demo_oasst-data/