Hugging Face's logo

almersawi
/
falcon-1b-hse

Text Generation
Transformers
Safetensors
falcon
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
almersawi commited on
Commit
738c44a
·
verified ·
1 Parent(s): 4f3ca46

Upload logs

Browse files
Files changed (1) hide show
  1. logs.log +156 -156
logs.log CHANGED
@@ -1,156 +1,156 @@
1
- 2024-06-11 19:24:05,913 - INFO: Calling run..
2
- 2024-06-11 19:24:05,913 - INFO: Problem Type: text_causal_classification_modeling
3
- 2024-06-11 19:24:05,913 - INFO: Global random seed: 849738
4
- 2024-06-11 19:24:05,913 - INFO: Preparing the data...
5
- 2024-06-11 19:24:05,913 - INFO: Setting up automatic validation split...
6
- 2024-06-11 19:24:05,955 - INFO: Preparing train and validation data
7
- 2024-06-11 19:24:05,955 - INFO: Loading train dataset...
8
- 2024-06-11 19:24:10,161 - INFO: Loading validation dataset...
9
- 2024-06-11 19:24:10,266 - INFO: Number of observations in train dataset: 9600
10
- 2024-06-11 19:24:10,267 - INFO: Number of observations in validation dataset: 2400
11
- 2024-06-11 19:24:10,464 - WARNING: EOS token id not matching between config and tokenizer. Overwriting with tokenizer id.
12
- 2024-06-11 19:24:10,465 - WARNING: PAD token id not matching between config and tokenizer. Overwriting with tokenizer id.
13
- 2024-06-11 19:24:10,469 - INFO: Using bfloat16 for backbone
14
- 2024-06-11 19:24:10,469 - INFO: Loading tiiuae/falcon-rw-1b. This may take a while.
15
- 2024-06-11 19:24:22,250 - INFO: Loaded tiiuae/falcon-rw-1b.
16
- 2024-06-11 19:24:22,253 - WARNING: EOS token id not matching between generation config and tokenizer. Overwriting with tokenizer id.
17
- 2024-06-11 19:24:22,253 - WARNING: PAD token id not matching between generation config and tokenizer. Overwriting with tokenizer id.
18
- 2024-06-11 19:24:22,253 - INFO: Lora module names: ['query_key_value', 'dense', 'dense_h_to_4h', 'dense_4h_to_h']
19
- 2024-06-11 19:24:22,374 - INFO: Enough space available for saving model weights.Required space: 2591.11MB, Available space: 995995.53MB.
20
- 2024-06-11 19:24:22,379 - INFO: Optimizer AdamW has been provided with parameters {'weight_decay': 0.0, 'eps': 1e-08, 'betas': (0.8999999762, 0.9990000129), 'lr': 0.0001}
21
- 2024-06-11 19:24:22,520 - WARNING: No order set for keys: ['answer_column_label', 'num_classes'].
22
- 2024-06-11 19:24:22,535 - WARNING: No order set for keys: ['answer_column_label', 'num_classes'].
23
- 2024-06-11 19:24:23,373 - INFO: started process: 0, can_track: True, tracking_mode: TrackingMode.DURING_EPOCH
24
- 2024-06-11 19:24:23,374 - INFO: Training Epoch: 1 / 1
25
- 2024-06-11 19:24:23,374 - INFO: train loss: 0%| | 0/600 [00:00<?, ?it/s]
26
- 2024-06-11 19:24:23,592 - INFO: Evaluation step: 600
27
- 2024-06-11 19:24:26,265 - INFO: train loss: 38.50: 1%|1 | 6/600 [00:02<04:46, 2.08it/s]
28
- 2024-06-11 19:24:28,665 - INFO: train loss: 37.30: 2%|2 | 12/600 [00:05<04:15, 2.31it/s]
29
- 2024-06-11 19:24:31,130 - INFO: train loss: 16.17: 3%|3 | 18/600 [00:07<04:06, 2.36it/s]
30
- 2024-06-11 19:24:33,555 - INFO: train loss: 5.66: 4%|4 | 24/600 [00:10<03:59, 2.41it/s]
31
- 2024-06-11 19:24:36,045 - INFO: train loss: 3.87: 5%|5 | 30/600 [00:12<03:56, 2.41it/s]
32
- 2024-06-11 19:24:38,714 - INFO: train loss: 2.41: 6%|6 | 36/600 [00:15<03:59, 2.35it/s]
33
- 2024-06-11 19:24:41,306 - INFO: train loss: 2.09: 7%|7 | 42/600 [00:17<03:58, 2.34it/s]
34
- 2024-06-11 19:24:43,832 - INFO: train loss: 2.23: 8%|8 | 48/600 [00:20<03:54, 2.35it/s]
35
- 2024-06-11 19:24:46,208 - INFO: train loss: 2.14: 9%|9 | 54/600 [00:22<03:47, 2.40it/s]
36
- 2024-06-11 19:24:48,667 - INFO: train loss: 2.26: 10%|# | 60/600 [00:25<03:43, 2.41it/s]
37
- 2024-06-11 19:24:51,185 - INFO: train loss: 1.91: 11%|#1 | 66/600 [00:27<03:42, 2.40it/s]
38
- 2024-06-11 19:24:53,545 - INFO: train loss: 1.73: 12%|#2 | 72/600 [00:30<03:35, 2.44it/s]
39
- 2024-06-11 19:24:55,938 - INFO: train loss: 1.85: 13%|#3 | 78/600 [00:32<03:31, 2.46it/s]
40
- 2024-06-11 19:24:58,438 - INFO: train loss: 1.98: 14%|#4 | 84/600 [00:35<03:31, 2.44it/s]
41
- 2024-06-11 19:25:00,935 - INFO: train loss: 1.92: 15%|#5 | 90/600 [00:37<03:29, 2.43it/s]
42
- 2024-06-11 19:25:03,532 - INFO: train loss: 1.83: 16%|#6 | 96/600 [00:40<03:30, 2.39it/s]
43
- 2024-06-11 19:25:06,109 - INFO: train loss: 1.60: 17%|#7 | 102/600 [00:42<03:29, 2.37it/s]
44
- 2024-06-11 19:25:08,584 - INFO: train loss: 1.85: 18%|#8 | 108/600 [00:45<03:25, 2.39it/s]
45
- 2024-06-11 19:25:11,083 - INFO: train loss: 2.02: 19%|#9 | 114/600 [00:47<03:23, 2.39it/s]
46
- 2024-06-11 19:25:13,366 - INFO: train loss: 1.99: 20%|## | 120/600 [00:49<03:15, 2.46it/s]
47
- 2024-06-11 19:25:15,909 - INFO: train loss: 1.88: 21%|##1 | 126/600 [00:52<03:15, 2.43it/s]
48
- 2024-06-11 19:25:18,314 - INFO: train loss: 1.95: 22%|##2 | 132/600 [00:54<03:11, 2.45it/s]
49
- 2024-06-11 19:25:20,805 - INFO: train loss: 1.82: 23%|##3 | 138/600 [00:57<03:09, 2.44it/s]
50
- 2024-06-11 19:25:23,180 - INFO: train loss: 1.80: 24%|##4 | 144/600 [00:59<03:05, 2.46it/s]
51
- 2024-06-11 19:25:25,788 - INFO: train loss: 1.89: 25%|##5 | 150/600 [01:02<03:06, 2.41it/s]
52
- 2024-06-11 19:25:28,422 - INFO: train loss: 2.07: 26%|##6 | 156/600 [01:05<03:07, 2.37it/s]
53
- 2024-06-11 19:25:30,947 - INFO: train loss: 2.02: 27%|##7 | 162/600 [01:07<03:04, 2.37it/s]
54
- 2024-06-11 19:25:33,560 - INFO: train loss: 1.64: 28%|##8 | 168/600 [01:10<03:03, 2.35it/s]
55
- 2024-06-11 19:25:35,986 - INFO: train loss: 1.88: 29%|##9 | 174/600 [01:12<02:58, 2.38it/s]
56
- 2024-06-11 19:25:38,424 - INFO: train loss: 2.17: 30%|### | 180/600 [01:15<02:54, 2.41it/s]
57
- 2024-06-11 19:25:40,841 - INFO: train loss: 1.92: 31%|###1 | 186/600 [01:17<02:50, 2.43it/s]
58
- 2024-06-11 19:25:43,479 - INFO: train loss: 1.89: 32%|###2 | 192/600 [01:20<02:51, 2.38it/s]
59
- 2024-06-11 19:25:46,108 - INFO: train loss: 1.71: 33%|###3 | 198/600 [01:22<02:51, 2.35it/s]
60
- 2024-06-11 19:25:48,485 - INFO: train loss: 1.76: 34%|###4 | 204/600 [01:25<02:45, 2.40it/s]
61
- 2024-06-11 19:25:50,947 - INFO: train loss: 1.93: 35%|###5 | 210/600 [01:27<02:41, 2.41it/s]
62
- 2024-06-11 19:25:53,448 - INFO: train loss: 1.66: 36%|###6 | 216/600 [01:30<02:39, 2.41it/s]
63
- 2024-06-11 19:25:55,958 - INFO: train loss: 1.70: 37%|###7 | 222/600 [01:32<02:37, 2.40it/s]
64
- 2024-06-11 19:25:58,603 - INFO: train loss: 1.68: 38%|###8 | 228/600 [01:35<02:37, 2.36it/s]
65
- 2024-06-11 19:26:01,255 - INFO: train loss: 1.67: 39%|###9 | 234/600 [01:37<02:37, 2.33it/s]
66
- 2024-06-11 19:26:03,885 - INFO: train loss: 1.69: 40%|#### | 240/600 [01:40<02:35, 2.32it/s]
67
- 2024-06-11 19:26:06,564 - INFO: train loss: 1.78: 41%|####1 | 246/600 [01:43<02:34, 2.29it/s]
68
- 2024-06-11 19:26:09,095 - INFO: train loss: 1.72: 42%|####2 | 252/600 [01:45<02:30, 2.32it/s]
69
- 2024-06-11 19:26:11,385 - INFO: train loss: 1.62: 43%|####3 | 258/600 [01:48<02:22, 2.40it/s]
70
- 2024-06-11 19:26:13,870 - INFO: train loss: 1.52: 44%|####4 | 264/600 [01:50<02:19, 2.40it/s]
71
- 2024-06-11 19:26:16,372 - INFO: train loss: 1.69: 45%|####5 | 270/600 [01:52<02:17, 2.40it/s]
72
- 2024-06-11 19:26:18,692 - INFO: train loss: 1.82: 46%|####6 | 276/600 [01:55<02:12, 2.45it/s]
73
- 2024-06-11 19:26:21,147 - INFO: train loss: 1.96: 47%|####6 | 282/600 [01:57<02:09, 2.45it/s]
74
- 2024-06-11 19:26:23,681 - INFO: train loss: 1.83: 48%|####8 | 288/600 [02:00<02:08, 2.43it/s]
75
- 2024-06-11 19:26:34,896 - INFO: train loss: 1.63: 49%|####9 | 294/600 [02:11<04:19, 1.18it/s]
76
- 2024-06-11 19:26:37,499 - INFO: train loss: 1.47: 50%|##### | 300/600 [02:14<03:37, 1.38it/s]
77
- 2024-06-11 19:26:40,069 - INFO: train loss: 1.69: 51%|#####1 | 306/600 [02:16<03:06, 1.57it/s]
78
- 2024-06-11 19:26:42,587 - INFO: train loss: 1.60: 52%|#####2 | 312/600 [02:19<02:44, 1.75it/s]
79
- 2024-06-11 19:26:44,978 - INFO: train loss: 1.44: 53%|#####3 | 318/600 [02:21<02:26, 1.93it/s]
80
- 2024-06-11 19:26:47,347 - INFO: train loss: 1.38: 54%|#####4 | 324/600 [02:23<02:13, 2.08it/s]
81
- 2024-06-11 19:26:49,772 - INFO: train loss: 1.22: 55%|#####5 | 330/600 [02:26<02:03, 2.18it/s]
82
- 2024-06-11 19:26:52,193 - INFO: train loss: 1.34: 56%|#####6 | 336/600 [02:28<01:56, 2.26it/s]
83
- 2024-06-11 19:26:54,866 - INFO: train loss: 1.70: 57%|#####6 | 342/600 [02:31<01:54, 2.26it/s]
84
- 2024-06-11 19:26:57,352 - INFO: train loss: 1.63: 58%|#####8 | 348/600 [02:33<01:49, 2.30it/s]
85
- 2024-06-11 19:26:59,884 - INFO: train loss: 1.51: 59%|#####8 | 354/600 [02:36<01:45, 2.32it/s]
86
- 2024-06-11 19:27:02,254 - INFO: train loss: 1.32: 60%|###### | 360/600 [02:38<01:40, 2.38it/s]
87
- 2024-06-11 19:27:04,630 - INFO: train loss: 1.43: 61%|######1 | 366/600 [02:41<01:36, 2.42it/s]
88
- 2024-06-11 19:27:06,991 - INFO: train loss: 1.48: 62%|######2 | 372/600 [02:43<01:32, 2.46it/s]
89
- 2024-06-11 19:27:09,474 - INFO: train loss: 1.45: 63%|######3 | 378/600 [02:46<01:30, 2.44it/s]
90
- 2024-06-11 19:27:11,952 - INFO: train loss: 1.31: 64%|######4 | 384/600 [02:48<01:28, 2.44it/s]
91
- 2024-06-11 19:27:14,439 - INFO: train loss: 1.36: 65%|######5 | 390/600 [02:51<01:26, 2.43it/s]
92
- 2024-06-11 19:27:16,955 - INFO: train loss: 1.27: 66%|######6 | 396/600 [02:53<01:24, 2.42it/s]
93
- 2024-06-11 19:27:19,389 - INFO: train loss: 1.36: 67%|######7 | 402/600 [02:56<01:21, 2.43it/s]
94
- 2024-06-11 19:27:21,801 - INFO: train loss: 1.63: 68%|######8 | 408/600 [02:58<01:18, 2.45it/s]
95
- 2024-06-11 19:27:24,365 - INFO: train loss: 1.45: 69%|######9 | 414/600 [03:00<01:17, 2.41it/s]
96
- 2024-06-11 19:27:26,983 - INFO: train loss: 1.14: 70%|####### | 420/600 [03:03<01:15, 2.38it/s]
97
- 2024-06-11 19:27:29,629 - INFO: train loss: 1.08: 71%|#######1 | 426/600 [03:06<01:14, 2.34it/s]
98
- 2024-06-11 19:27:31,995 - INFO: train loss: 1.22: 72%|#######2 | 432/600 [03:08<01:10, 2.40it/s]
99
- 2024-06-11 19:27:34,489 - INFO: train loss: 1.17: 73%|#######3 | 438/600 [03:11<01:07, 2.40it/s]
100
- 2024-06-11 19:27:36,917 - INFO: train loss: 1.21: 74%|#######4 | 444/600 [03:13<01:04, 2.42it/s]
101
- 2024-06-11 19:27:39,322 - INFO: train loss: 1.28: 75%|#######5 | 450/600 [03:15<01:01, 2.44it/s]
102
- 2024-06-11 19:27:41,904 - INFO: train loss: 1.20: 76%|#######6 | 456/600 [03:18<00:59, 2.41it/s]
103
- 2024-06-11 19:27:44,618 - INFO: train loss: 1.17: 77%|#######7 | 462/600 [03:21<00:58, 2.34it/s]
104
- 2024-06-11 19:27:47,008 - INFO: train loss: 1.16: 78%|#######8 | 468/600 [03:23<00:55, 2.39it/s]
105
- 2024-06-11 19:27:49,405 - INFO: train loss: 1.16: 79%|#######9 | 474/600 [03:26<00:51, 2.42it/s]
106
- 2024-06-11 19:27:51,760 - INFO: train loss: 1.09: 80%|######## | 480/600 [03:28<00:48, 2.46it/s]
107
- 2024-06-11 19:27:54,239 - INFO: train loss: 1.19: 81%|########1 | 486/600 [03:30<00:46, 2.45it/s]
108
- 2024-06-11 19:27:56,731 - INFO: train loss: 1.25: 82%|########2 | 492/600 [03:33<00:44, 2.44it/s]
109
- 2024-06-11 19:27:59,481 - INFO: train loss: 1.17: 83%|########2 | 498/600 [03:36<00:43, 2.35it/s]
110
- 2024-06-11 19:28:02,025 - INFO: train loss: 1.21: 84%|########4 | 504/600 [03:38<00:40, 2.35it/s]
111
- 2024-06-11 19:28:04,499 - INFO: train loss: 1.11: 85%|########5 | 510/600 [03:41<00:37, 2.38it/s]
112
- 2024-06-11 19:28:07,055 - INFO: train loss: 1.09: 86%|########6 | 516/600 [03:43<00:35, 2.37it/s]
113
- 2024-06-11 19:28:09,588 - INFO: train loss: 0.99: 87%|########7 | 522/600 [03:46<00:32, 2.37it/s]
114
- 2024-06-11 19:28:12,009 - INFO: train loss: 1.08: 88%|########8 | 528/600 [03:48<00:30, 2.40it/s]
115
- 2024-06-11 19:28:14,559 - INFO: train loss: 1.10: 89%|########9 | 534/600 [03:51<00:27, 2.39it/s]
116
- 2024-06-11 19:28:17,044 - INFO: train loss: 1.03: 90%|######### | 540/600 [03:53<00:25, 2.39it/s]
117
- 2024-06-11 19:28:19,569 - INFO: train loss: 1.06: 91%|#########1| 546/600 [03:56<00:22, 2.39it/s]
118
- 2024-06-11 19:28:22,110 - INFO: train loss: 1.00: 92%|#########2| 552/600 [03:58<00:20, 2.38it/s]
119
- 2024-06-11 19:28:24,605 - INFO: train loss: 0.95: 93%|#########3| 558/600 [04:01<00:17, 2.39it/s]
120
- 2024-06-11 19:28:26,921 - INFO: train loss: 1.02: 94%|#########3| 564/600 [04:03<00:14, 2.45it/s]
121
- 2024-06-11 19:28:29,323 - INFO: train loss: 1.06: 95%|#########5| 570/600 [04:05<00:12, 2.46it/s]
122
- 2024-06-11 19:28:31,750 - INFO: train loss: 1.11: 96%|#########6| 576/600 [04:08<00:09, 2.46it/s]
123
- 2024-06-11 19:28:34,275 - INFO: train loss: 1.13: 97%|#########7| 582/600 [04:10<00:07, 2.44it/s]
124
- 2024-06-11 19:28:36,803 - INFO: train loss: 1.15: 98%|#########8| 588/600 [04:13<00:04, 2.42it/s]
125
- 2024-06-11 19:28:39,449 - INFO: train loss: 1.01: 99%|#########9| 594/600 [04:16<00:02, 2.37it/s]
126
- 2024-06-11 19:28:42,270 - INFO: train loss: 0.92: 100%|##########| 600/600 [04:18<00:00, 2.29it/s]
127
- 2024-06-11 19:28:42,270 - INFO: train loss: 0.92: 100%|##########| 600/600 [04:18<00:00, 2.32it/s]
128
- 2024-06-11 19:28:42,270 - INFO: Saving last model checkpoint to /app/output
129
- 2024-06-11 19:28:42,270 - INFO: Saving checkpoint..
130
- 2024-06-11 19:28:44,868 - INFO: Starting validation inference
131
- 2024-06-11 19:28:44,868 - INFO: validation progress: 0%| | 0/150 [00:00<?, ?it/s]
132
- 2024-06-11 19:28:45,811 - INFO: validation progress: 5%|4 | 7/150 [00:00<00:19, 7.42it/s]
133
- 2024-06-11 19:28:46,542 - INFO: validation progress: 9%|9 | 14/150 [00:01<00:15, 8.55it/s]
134
- 2024-06-11 19:28:47,310 - INFO: validation progress: 14%|#4 | 21/150 [00:02<00:14, 8.80it/s]
135
- 2024-06-11 19:28:48,099 - INFO: validation progress: 19%|#8 | 28/150 [00:03<00:13, 8.83it/s]
136
- 2024-06-11 19:28:48,870 - INFO: validation progress: 23%|##3 | 35/150 [00:04<00:12, 8.92it/s]
137
- 2024-06-11 19:28:49,672 - INFO: validation progress: 28%|##8 | 42/150 [00:04<00:12, 8.85it/s]
138
- 2024-06-11 19:28:50,424 - INFO: validation progress: 33%|###2 | 49/150 [00:05<00:11, 9.00it/s]
139
- 2024-06-11 19:28:51,218 - INFO: validation progress: 37%|###7 | 56/150 [00:06<00:10, 8.94it/s]
140
- 2024-06-11 19:28:51,997 - INFO: validation progress: 42%|####2 | 63/150 [00:07<00:09, 8.95it/s]
141
- 2024-06-11 19:28:52,814 - INFO: validation progress: 47%|####6 | 70/150 [00:07<00:09, 8.83it/s]
142
- 2024-06-11 19:28:53,629 - INFO: validation progress: 51%|#####1 | 77/150 [00:08<00:08, 8.76it/s]
143
- 2024-06-11 19:28:54,398 - INFO: validation progress: 56%|#####6 | 84/150 [00:09<00:07, 8.86it/s]
144
- 2024-06-11 19:28:55,216 - INFO: validation progress: 61%|###### | 91/150 [00:10<00:06, 8.76it/s]
145
- 2024-06-11 19:28:55,965 - INFO: validation progress: 65%|######5 | 98/150 [00:11<00:05, 8.93it/s]
146
- 2024-06-11 19:28:56,706 - INFO: validation progress: 70%|####### | 105/150 [00:11<00:04, 9.08it/s]
147
- 2024-06-11 19:28:57,509 - INFO: validation progress: 75%|#######4 | 112/150 [00:12<00:04, 8.97it/s]
148
- 2024-06-11 19:28:58,294 - INFO: validation progress: 79%|#######9 | 119/150 [00:13<00:03, 8.95it/s]
149
- 2024-06-11 19:28:59,089 - INFO: validation progress: 84%|########4 | 126/150 [00:14<00:02, 8.91it/s]
150
- 2024-06-11 19:28:59,901 - INFO: validation progress: 89%|########8 | 133/150 [00:15<00:01, 8.82it/s]
151
- 2024-06-11 19:29:00,664 - INFO: validation progress: 93%|#########3| 140/150 [00:15<00:01, 8.92it/s]
152
- 2024-06-11 19:29:01,481 - INFO: validation progress: 98%|#########8| 147/150 [00:16<00:00, 8.81it/s]
153
- 2024-06-11 19:29:01,816 - INFO: validation progress: 100%|##########| 150/150 [00:16<00:00, 8.85it/s]
154
- 2024-06-11 19:29:01,876 - INFO: Validation AUC: 0.54705
155
- 2024-06-11 19:29:01,876 - INFO: Mean validation loss: 0.99504
156
- 2024-06-11 19:29:02,796 - WARNING: No order set for keys: ['answer_column_label', 'num_classes'].
 
1
+ 2024-06-11 20:31:50,507 - INFO: Calling run..
2
+ 2024-06-11 20:31:50,508 - INFO: Problem Type: text_causal_classification_modeling
3
+ 2024-06-11 20:31:50,508 - INFO: Global random seed: 622910
4
+ 2024-06-11 20:31:50,508 - INFO: Preparing the data...
5
+ 2024-06-11 20:31:50,508 - INFO: Setting up automatic validation split...
6
+ 2024-06-11 20:31:50,549 - INFO: Preparing train and validation data
7
+ 2024-06-11 20:31:50,549 - INFO: Loading train dataset...
8
+ 2024-06-11 20:31:51,325 - INFO: Loading validation dataset...
9
+ 2024-06-11 20:31:51,461 - INFO: Number of observations in train dataset: 9600
10
+ 2024-06-11 20:31:51,461 - INFO: Number of observations in validation dataset: 2400
11
+ 2024-06-11 20:31:51,625 - WARNING: EOS token id not matching between config and tokenizer. Overwriting with tokenizer id.
12
+ 2024-06-11 20:31:51,625 - WARNING: PAD token id not matching between config and tokenizer. Overwriting with tokenizer id.
13
+ 2024-06-11 20:31:51,632 - INFO: Using bfloat16 for backbone
14
+ 2024-06-11 20:31:51,632 - INFO: Loading tiiuae/falcon-rw-1b. This may take a while.
15
+ 2024-06-11 20:32:00,834 - INFO: Loaded tiiuae/falcon-rw-1b.
16
+ 2024-06-11 20:32:00,836 - WARNING: EOS token id not matching between generation config and tokenizer. Overwriting with tokenizer id.
17
+ 2024-06-11 20:32:00,837 - WARNING: PAD token id not matching between generation config and tokenizer. Overwriting with tokenizer id.
18
+ 2024-06-11 20:32:00,837 - INFO: Lora module names: ['query_key_value', 'dense', 'dense_h_to_4h', 'dense_4h_to_h']
19
+ 2024-06-11 20:32:00,955 - INFO: Enough space available for saving model weights.Required space: 2591.11MB, Available space: 994803.55MB.
20
+ 2024-06-11 20:32:00,959 - INFO: Optimizer AdamW has been provided with parameters {'eps': 1e-08, 'weight_decay': 0.0, 'betas': (0.8999999762, 0.9990000129), 'lr': 0.0001}
21
+ 2024-06-11 20:32:01,103 - WARNING: No order set for keys: ['answer_column_label', 'num_classes'].
22
+ 2024-06-11 20:32:01,123 - WARNING: No order set for keys: ['answer_column_label', 'num_classes'].
23
+ 2024-06-11 20:32:02,308 - INFO: started process: 0, can_track: True, tracking_mode: TrackingMode.DURING_EPOCH
24
+ 2024-06-11 20:32:02,309 - INFO: Training Epoch: 1 / 1
25
+ 2024-06-11 20:32:02,310 - INFO: train loss: 0%| | 0/600 [00:00<?, ?it/s]
26
+ 2024-06-11 20:32:02,471 - INFO: Evaluation step: 600
27
+ 2024-06-11 20:32:05,292 - INFO: train loss: 39.27: 1%|1 | 6/600 [00:02<04:55, 2.01it/s]
28
+ 2024-06-11 20:32:07,845 - INFO: train loss: 45.45: 2%|2 | 12/600 [00:05<04:27, 2.20it/s]
29
+ 2024-06-11 20:32:10,594 - INFO: train loss: 23.80: 3%|3 | 18/600 [00:08<04:25, 2.19it/s]
30
+ 2024-06-11 20:32:13,096 - INFO: train loss: 5.30: 4%|4 | 24/600 [00:10<04:13, 2.27it/s]
31
+ 2024-06-11 20:32:15,642 - INFO: train loss: 3.56: 5%|5 | 30/600 [00:13<04:07, 2.30it/s]
32
+ 2024-06-11 20:32:18,124 - INFO: train loss: 2.98: 6%|6 | 36/600 [00:15<04:01, 2.34it/s]
33
+ 2024-06-11 20:32:20,653 - INFO: train loss: 2.45: 7%|7 | 42/600 [00:18<03:57, 2.35it/s]
34
+ 2024-06-11 20:32:23,248 - INFO: train loss: 2.32: 8%|8 | 48/600 [00:20<03:56, 2.34it/s]
35
+ 2024-06-11 20:32:25,954 - INFO: train loss: 1.79: 9%|9 | 54/600 [00:23<03:57, 2.30it/s]
36
+ 2024-06-11 20:32:28,506 - INFO: train loss: 2.08: 10%|# | 60/600 [00:26<03:53, 2.31it/s]
37
+ 2024-06-11 20:32:30,955 - INFO: train loss: 2.14: 11%|#1 | 66/600 [00:28<03:46, 2.35it/s]
38
+ 2024-06-11 20:32:33,574 - INFO: train loss: 2.11: 12%|#2 | 72/600 [00:31<03:46, 2.33it/s]
39
+ 2024-06-11 20:32:36,245 - INFO: train loss: 2.02: 13%|#3 | 78/600 [00:33<03:46, 2.31it/s]
40
+ 2024-06-11 20:32:38,773 - INFO: train loss: 2.11: 14%|#4 | 84/600 [00:36<03:41, 2.33it/s]
41
+ 2024-06-11 20:32:41,236 - INFO: train loss: 2.08: 15%|#5 | 90/600 [00:38<03:36, 2.36it/s]
42
+ 2024-06-11 20:32:43,828 - INFO: train loss: 2.40: 16%|#6 | 96/600 [00:41<03:34, 2.35it/s]
43
+ 2024-06-11 20:32:46,344 - INFO: train loss: 2.27: 17%|#7 | 102/600 [00:44<03:31, 2.36it/s]
44
+ 2024-06-11 20:32:49,065 - INFO: train loss: 1.77: 18%|#8 | 108/600 [00:46<03:33, 2.31it/s]
45
+ 2024-06-11 20:32:51,821 - INFO: train loss: 1.81: 19%|#9 | 114/600 [00:49<03:34, 2.27it/s]
46
+ 2024-06-11 20:32:54,414 - INFO: train loss: 1.95: 20%|## | 120/600 [00:52<03:30, 2.28it/s]
47
+ 2024-06-11 20:32:56,900 - INFO: train loss: 1.84: 21%|##1 | 126/600 [00:54<03:24, 2.32it/s]
48
+ 2024-06-11 20:32:59,366 - INFO: train loss: 1.90: 22%|##2 | 132/600 [00:57<03:18, 2.35it/s]
49
+ 2024-06-11 20:33:01,981 - INFO: train loss: 1.97: 23%|##3 | 138/600 [00:59<03:17, 2.33it/s]
50
+ 2024-06-11 20:33:04,669 - INFO: train loss: 1.92: 24%|##4 | 144/600 [01:02<03:18, 2.30it/s]
51
+ 2024-06-11 20:33:07,232 - INFO: train loss: 1.85: 25%|##5 | 150/600 [01:04<03:14, 2.31it/s]
52
+ 2024-06-11 20:33:09,831 - INFO: train loss: 1.88: 26%|##6 | 156/600 [01:07<03:11, 2.31it/s]
53
+ 2024-06-11 20:33:12,242 - INFO: train loss: 1.87: 27%|##7 | 162/600 [01:09<03:05, 2.36it/s]
54
+ 2024-06-11 20:33:14,922 - INFO: train loss: 1.68: 28%|##8 | 168/600 [01:12<03:05, 2.32it/s]
55
+ 2024-06-11 20:33:17,402 - INFO: train loss: 1.62: 29%|##9 | 174/600 [01:15<03:01, 2.35it/s]
56
+ 2024-06-11 20:33:19,889 - INFO: train loss: 1.43: 30%|### | 180/600 [01:17<02:57, 2.37it/s]
57
+ 2024-06-11 20:33:22,285 - INFO: train loss: 1.60: 31%|###1 | 186/600 [01:19<02:51, 2.41it/s]
58
+ 2024-06-11 20:33:24,740 - INFO: train loss: 1.81: 32%|###2 | 192/600 [01:22<02:48, 2.42it/s]
59
+ 2024-06-11 20:33:27,301 - INFO: train loss: 1.81: 33%|###3 | 198/600 [01:24<02:47, 2.40it/s]
60
+ 2024-06-11 20:33:29,915 - INFO: train loss: 1.65: 34%|###4 | 204/600 [01:27<02:47, 2.36it/s]
61
+ 2024-06-11 20:33:32,554 - INFO: train loss: 1.65: 35%|###5 | 210/600 [01:30<02:46, 2.34it/s]
62
+ 2024-06-11 20:33:34,994 - INFO: train loss: 1.72: 36%|###6 | 216/600 [01:32<02:41, 2.37it/s]
63
+ 2024-06-11 20:33:37,565 - INFO: train loss: 1.57: 37%|###7 | 222/600 [01:35<02:40, 2.36it/s]
64
+ 2024-06-11 20:33:40,073 - INFO: train loss: 1.62: 38%|###8 | 228/600 [01:37<02:36, 2.37it/s]
65
+ 2024-06-11 20:33:42,706 - INFO: train loss: 1.45: 39%|###9 | 234/600 [01:40<02:36, 2.34it/s]
66
+ 2024-06-11 20:33:45,222 - INFO: train loss: 1.37: 40%|#### | 240/600 [01:42<02:32, 2.35it/s]
67
+ 2024-06-11 20:33:47,835 - INFO: train loss: 1.46: 41%|####1 | 246/600 [01:45<02:31, 2.34it/s]
68
+ 2024-06-11 20:33:50,306 - INFO: train loss: 1.42: 42%|####2 | 252/600 [01:47<02:27, 2.36it/s]
69
+ 2024-06-11 20:33:52,851 - INFO: train loss: 1.46: 43%|####3 | 258/600 [01:50<02:24, 2.36it/s]
70
+ 2024-06-11 20:33:55,260 - INFO: train loss: 1.64: 44%|####4 | 264/600 [01:52<02:20, 2.40it/s]
71
+ 2024-06-11 20:33:57,686 - INFO: train loss: 1.86: 45%|####5 | 270/600 [01:55<02:16, 2.42it/s]
72
+ 2024-06-11 20:34:00,497 - INFO: train loss: 1.53: 46%|####6 | 276/600 [01:58<02:19, 2.33it/s]
73
+ 2024-06-11 20:34:02,806 - INFO: train loss: 1.37: 47%|####6 | 282/600 [02:00<02:12, 2.40it/s]
74
+ 2024-06-11 20:34:05,233 - INFO: train loss: 1.35: 48%|####8 | 288/600 [02:02<02:08, 2.42it/s]
75
+ 2024-06-11 20:34:07,591 - INFO: train loss: 1.42: 49%|####9 | 294/600 [02:05<02:04, 2.46it/s]
76
+ 2024-06-11 20:34:10,121 - INFO: train loss: 1.36: 50%|##### | 300/600 [02:07<02:03, 2.43it/s]
77
+ 2024-06-11 20:34:12,788 - INFO: train loss: 1.24: 51%|#####1 | 306/600 [02:10<02:03, 2.37it/s]
78
+ 2024-06-11 20:34:15,105 - INFO: train loss: 1.01: 52%|#####2 | 312/600 [02:12<01:58, 2.43it/s]
79
+ 2024-06-11 20:34:17,567 - INFO: train loss: 1.19: 53%|#####3 | 318/600 [02:15<01:55, 2.44it/s]
80
+ 2024-06-11 20:34:19,920 - INFO: train loss: 1.22: 54%|#####4 | 324/600 [02:17<01:51, 2.47it/s]
81
+ 2024-06-11 20:34:22,339 - INFO: train loss: 1.26: 55%|#####5 | 330/600 [02:20<01:49, 2.47it/s]
82
+ 2024-06-11 20:34:24,935 - INFO: train loss: 1.11: 56%|#####6 | 336/600 [02:22<01:49, 2.42it/s]
83
+ 2024-06-11 20:34:27,728 - INFO: train loss: 1.11: 57%|#####6 | 342/600 [02:25<01:50, 2.33it/s]
84
+ 2024-06-11 20:34:30,159 - INFO: train loss: 1.08: 58%|#####8 | 348/600 [02:27<01:46, 2.37it/s]
85
+ 2024-06-11 20:34:32,641 - INFO: train loss: 0.94: 59%|#####8 | 354/600 [02:30<01:43, 2.39it/s]
86
+ 2024-06-11 20:34:35,057 - INFO: train loss: 1.11: 60%|###### | 360/600 [02:32<01:39, 2.41it/s]
87
+ 2024-06-11 20:34:37,412 - INFO: train loss: 1.18: 61%|######1 | 366/600 [02:35<01:35, 2.45it/s]
88
+ 2024-06-11 20:34:39,890 - INFO: train loss: 1.03: 62%|######2 | 372/600 [02:37<01:33, 2.44it/s]
89
+ 2024-06-11 20:34:42,275 - INFO: train loss: 1.00: 63%|######3 | 378/600 [02:39<01:30, 2.46it/s]
90
+ 2024-06-11 20:34:44,903 - INFO: train loss: 1.02: 64%|######4 | 384/600 [02:42<01:29, 2.41it/s]
91
+ 2024-06-11 20:34:47,349 - INFO: train loss: 0.91: 65%|######5 | 390/600 [02:45<01:26, 2.42it/s]
92
+ 2024-06-11 20:34:49,839 - INFO: train loss: 0.72: 66%|######6 | 396/600 [02:47<01:24, 2.42it/s]
93
+ 2024-06-11 20:34:52,489 - INFO: train loss: 0.81: 67%|######7 | 402/600 [02:50<01:23, 2.37it/s]
94
+ 2024-06-11 20:34:55,035 - INFO: train loss: 0.77: 68%|######8 | 408/600 [02:52<01:21, 2.37it/s]
95
+ 2024-06-11 20:34:57,554 - INFO: train loss: 0.80: 69%|######9 | 414/600 [02:55<01:18, 2.37it/s]
96
+ 2024-06-11 20:35:00,243 - INFO: train loss: 0.62: 70%|####### | 420/600 [02:57<01:17, 2.33it/s]
97
+ 2024-06-11 20:35:02,714 - INFO: train loss: 0.72: 71%|#######1 | 426/600 [03:00<01:13, 2.36it/s]
98
+ 2024-06-11 20:35:05,239 - INFO: train loss: 0.80: 72%|#######2 | 432/600 [03:02<01:11, 2.36it/s]
99
+ 2024-06-11 20:35:07,446 - INFO: train loss: 0.65: 73%|#######3 | 438/600 [03:05<01:05, 2.46it/s]
100
+ 2024-06-11 20:35:09,916 - INFO: train loss: 0.51: 74%|#######4 | 444/600 [03:07<01:03, 2.45it/s]
101
+ 2024-06-11 20:35:12,415 - INFO: train loss: 0.43: 75%|#######5 | 450/600 [03:10<01:01, 2.43it/s]
102
+ 2024-06-11 20:35:14,980 - INFO: train loss: 0.50: 76%|#######6 | 456/600 [03:12<00:59, 2.41it/s]
103
+ 2024-06-11 20:35:17,754 - INFO: train loss: 0.56: 77%|#######7 | 462/600 [03:15<00:59, 2.33it/s]
104
+ 2024-06-11 20:35:20,220 - INFO: train loss: 0.67: 78%|#######8 | 468/600 [03:17<00:55, 2.36it/s]
105
+ 2024-06-11 20:35:22,599 - INFO: train loss: 0.53: 79%|#######9 | 474/600 [03:20<00:52, 2.40it/s]
106
+ 2024-06-11 20:35:25,068 - INFO: train loss: 0.56: 80%|######## | 480/600 [03:22<00:49, 2.41it/s]
107
+ 2024-06-11 20:35:27,661 - INFO: train loss: 0.68: 81%|########1 | 486/600 [03:25<00:47, 2.38it/s]
108
+ 2024-06-11 20:35:30,067 - INFO: train loss: 0.70: 82%|########2 | 492/600 [03:27<00:44, 2.41it/s]
109
+ 2024-06-11 20:35:32,686 - INFO: train loss: 0.49: 83%|########2 | 498/600 [03:30<00:42, 2.38it/s]
110
+ 2024-06-11 20:35:35,154 - INFO: train loss: 0.51: 84%|########4 | 504/600 [03:32<00:40, 2.39it/s]
111
+ 2024-06-11 20:35:37,517 - INFO: train loss: 0.53: 85%|########5 | 510/600 [03:35<00:36, 2.43it/s]
112
+ 2024-06-11 20:35:39,862 - INFO: train loss: 0.48: 86%|########6 | 516/600 [03:37<00:34, 2.47it/s]
113
+ 2024-06-11 20:35:42,367 - INFO: train loss: 0.56: 87%|########7 | 522/600 [03:40<00:31, 2.45it/s]
114
+ 2024-06-11 20:35:44,941 - INFO: train loss: 0.65: 88%|########8 | 528/600 [03:42<00:29, 2.41it/s]
115
+ 2024-06-11 20:35:47,450 - INFO: train loss: 0.62: 89%|########9 | 534/600 [03:45<00:27, 2.41it/s]
116
+ 2024-06-11 20:35:50,018 - INFO: train loss: 0.73: 90%|######### | 540/600 [03:47<00:25, 2.38it/s]
117
+ 2024-06-11 20:35:52,437 - INFO: train loss: 0.63: 91%|#########1| 546/600 [03:50<00:22, 2.41it/s]
118
+ 2024-06-11 20:35:54,985 - INFO: train loss: 0.55: 92%|#########2| 552/600 [03:52<00:20, 2.39it/s]
119
+ 2024-06-11 20:35:57,432 - INFO: train loss: 0.59: 93%|#########3| 558/600 [03:55<00:17, 2.41it/s]
120
+ 2024-06-11 20:35:59,896 - INFO: train loss: 0.54: 94%|#########3| 564/600 [03:57<00:14, 2.42it/s]
121
+ 2024-06-11 20:36:02,380 - INFO: train loss: 0.60: 95%|#########5| 570/600 [04:00<00:12, 2.42it/s]
122
+ 2024-06-11 20:36:04,784 - INFO: train loss: 0.64: 96%|#########6| 576/600 [04:02<00:09, 2.44it/s]
123
+ 2024-06-11 20:36:07,386 - INFO: train loss: 0.68: 97%|#########7| 582/600 [04:05<00:07, 2.40it/s]
124
+ 2024-06-11 20:36:09,709 - INFO: train loss: 0.64: 98%|#########8| 588/600 [04:07<00:04, 2.45it/s]
125
+ 2024-06-11 20:36:12,267 - INFO: train loss: 0.56: 99%|#########9| 594/600 [04:09<00:02, 2.42it/s]
126
+ 2024-06-11 20:36:14,683 - INFO: train loss: 0.51: 100%|##########| 600/600 [04:12<00:00, 2.44it/s]
127
+ 2024-06-11 20:36:14,683 - INFO: train loss: 0.51: 100%|##########| 600/600 [04:12<00:00, 2.38it/s]
128
+ 2024-06-11 20:36:14,683 - INFO: Saving last model checkpoint to /app/output
129
+ 2024-06-11 20:36:14,683 - INFO: Saving checkpoint..
130
+ 2024-06-11 20:36:17,205 - INFO: Starting validation inference
131
+ 2024-06-11 20:36:17,205 - INFO: validation progress: 0%| | 0/150 [00:00<?, ?it/s]
132
+ 2024-06-11 20:36:18,147 - INFO: validation progress: 5%|4 | 7/150 [00:00<00:19, 7.43it/s]
133
+ 2024-06-11 20:36:18,877 - INFO: validation progress: 9%|9 | 14/150 [00:01<00:15, 8.57it/s]
134
+ 2024-06-11 20:36:19,646 - INFO: validation progress: 14%|#4 | 21/150 [00:02<00:14, 8.80it/s]
135
+ 2024-06-11 20:36:20,434 - INFO: validation progress: 19%|#8 | 28/150 [00:03<00:13, 8.83it/s]
136
+ 2024-06-11 20:36:21,206 - INFO: validation progress: 23%|##3 | 35/150 [00:04<00:12, 8.92it/s]
137
+ 2024-06-11 20:36:22,012 - INFO: validation progress: 28%|##8 | 42/150 [00:04<00:12, 8.84it/s]
138
+ 2024-06-11 20:36:22,764 - INFO: validation progress: 33%|###2 | 49/150 [00:05<00:11, 8.98it/s]
139
+ 2024-06-11 20:36:23,541 - INFO: validation progress: 37%|###7 | 56/150 [00:06<00:10, 8.99it/s]
140
+ 2024-06-11 20:36:24,317 - INFO: validation progress: 42%|####2 | 63/150 [00:07<00:09, 9.00it/s]
141
+ 2024-06-11 20:36:25,136 - INFO: validation progress: 47%|####6 | 70/150 [00:07<00:09, 8.86it/s]
142
+ 2024-06-11 20:36:25,949 - INFO: validation progress: 51%|#####1 | 77/150 [00:08<00:08, 8.78it/s]
143
+ 2024-06-11 20:36:26,719 - INFO: validation progress: 56%|#####6 | 84/150 [00:09<00:07, 8.87it/s]
144
+ 2024-06-11 20:36:27,539 - INFO: validation progress: 61%|###### | 91/150 [00:10<00:06, 8.77it/s]
145
+ 2024-06-11 20:36:28,286 - INFO: validation progress: 65%|######5 | 98/150 [00:11<00:05, 8.94it/s]
146
+ 2024-06-11 20:36:29,026 - INFO: validation progress: 70%|####### | 105/150 [00:11<00:04, 9.09it/s]
147
+ 2024-06-11 20:36:29,827 - INFO: validation progress: 75%|#######4 | 112/150 [00:12<00:04, 8.98it/s]
148
+ 2024-06-11 20:36:30,617 - INFO: validation progress: 79%|#######9 | 119/150 [00:13<00:03, 8.95it/s]
149
+ 2024-06-11 20:36:31,410 - INFO: validation progress: 84%|########4 | 126/150 [00:14<00:02, 8.91it/s]
150
+ 2024-06-11 20:36:32,219 - INFO: validation progress: 89%|########8 | 133/150 [00:15<00:01, 8.83it/s]
151
+ 2024-06-11 20:36:32,983 - INFO: validation progress: 93%|#########3| 140/150 [00:15<00:01, 8.93it/s]
152
+ 2024-06-11 20:36:33,778 - INFO: validation progress: 98%|#########8| 147/150 [00:16<00:00, 8.89it/s]
153
+ 2024-06-11 20:36:34,114 - INFO: validation progress: 100%|##########| 150/150 [00:16<00:00, 8.87it/s]
154
+ 2024-06-11 20:36:34,172 - INFO: Validation AUC: 0.75388
155
+ 2024-06-11 20:36:34,173 - INFO: Mean validation loss: 0.51912
156
+ 2024-06-11 20:36:35,118 - WARNING: No order set for keys: ['answer_column_label', 'num_classes'].