Hugging Face's logo

pietrolesci
/
bert-tiny_mnli_cdc7ea0d50

TensorBoard
Model card Files
xet
Metrics Community
pietrolesci commited on
Commit
629193a
·
verified ·
1 Parent(s): 8053734

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +44 -0
  2. hparams.yaml +60 -0
  3. tb_logs/version_0/events.out.tfevents.1709573676.dev-gpu-pl487.42005.0 +3 -0
  4. tensorboard_logs.parquet +3 -0
  5. train.log +139 -0
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Run info
2
+ - complete_hash: cdc7e895a985daa842292b6780da0d50
3
+ - short_hash: cdc7ea0d50
4
+
5
+ ### Configuration```yaml
6
+ data:
7
+ batch_size: 32
8
+ data_seed: 42
9
+ drop_last: false
10
+ eval_batch_size: 128
11
+ max_length: 512
12
+ multiprocessing_context: null
13
+ num_workers: 8
14
+ persistent_workers: false
15
+ pin_memory: true
16
+ replacement: false
17
+ shuffle: true
18
+ dataset: mnli
19
+ estimator:
20
+ accelerator: gpu
21
+ convert_to_bettertransformer: false
22
+ deterministic: true
23
+ precision: bf16-true
24
+ tf32_mode: high
25
+ fit:
26
+ enable_progress_bar: true
27
+ limit_train_batches: null
28
+ limit_validation_batches: null
29
+ log_interval: 100
30
+ max_epochs: 20
31
+ optimizer_kwargs:
32
+ init_kwargs:
33
+ fused: true
34
+ lr: 3.0e-05
35
+ name: adamw
36
+ scheduler_kwargs:
37
+ name: constant_schedule_with_warmup
38
+ num_warmup_steps: 2000
39
+ model:
40
+ name: bert-tiny
41
+ revision: null
42
+ seed: 42
43
+ seed: 42
44
+ ```
hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ estimator:
2
+ accelerator: gpu
3
+ precision: bf16-true
4
+ deterministic: true
5
+ tf32_mode: high
6
+ convert_to_bettertransformer: false
7
+ callbacks:
8
+ timer:
9
+ _target_: energizer.active_learning.callbacks.Timer
10
+ lr_monitor:
11
+ _target_: energizer.callbacks.lr_monitor.LearningRateMonitor
12
+ model_checkpoint:
13
+ _target_: energizer.callbacks.model_checkpoint.ModelCheckpoint
14
+ dirpath: .checkpoints
15
+ stage: train
16
+ frequency: 1:epoch
17
+ loggers:
18
+ tensorboard:
19
+ _target_: energizer.loggers.TensorBoardLogger
20
+ root_dir: ./
21
+ name: tb_logs
22
+ version: null
23
+ data:
24
+ batch_size: 32
25
+ eval_batch_size: 128
26
+ shuffle: true
27
+ replacement: false
28
+ data_seed: 42
29
+ drop_last: false
30
+ num_workers: 8
31
+ pin_memory: true
32
+ persistent_workers: false
33
+ multiprocessing_context: null
34
+ max_length: 512
35
+ fit:
36
+ max_epochs: 20
37
+ optimizer_kwargs:
38
+ name: adamw
39
+ lr: 3.0e-05
40
+ init_kwargs:
41
+ fused: true
42
+ scheduler_kwargs:
43
+ name: constant_schedule_with_warmup
44
+ num_warmup_steps: 2000
45
+ log_interval: 100
46
+ enable_progress_bar: true
47
+ limit_train_batches: null
48
+ limit_validation_batches: null
49
+ model:
50
+ name: bert-tiny
51
+ revision: null
52
+ seed: 42
53
+ log_interval: 100
54
+ enable_progress_bar: true
55
+ limit_batches: null
56
+ seed: 42
57
+ experiment_group: training
58
+ run_name: bert-tiny_2024-03-04T17-34-08
59
+ data_path: /home/pl487/coreset-project/data/processed
60
+ dataset: mnli
tb_logs/version_0/events.out.tfevents.1709573676.dev-gpu-pl487.42005.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063115d5e55766e4effd3903de1c8533a552d2d5d4e97c650d2b5f1c65203424
3
+ size 404506
tensorboard_logs.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863f97419d0825eef7df6ec77877f6b024e95237f8b2435f432c2ef0ed65e80c
3
+ size 40157
train.log ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-03-04 17:34:08,795][hydra][INFO] -
2
+ estimator:
3
+ accelerator: gpu
4
+ precision: bf16-true
5
+ deterministic: true
6
+ tf32_mode: high
7
+ convert_to_bettertransformer: false
8
+ callbacks:
9
+ timer:
10
+ _target_: energizer.active_learning.callbacks.Timer
11
+ lr_monitor:
12
+ _target_: energizer.callbacks.lr_monitor.LearningRateMonitor
13
+ model_checkpoint:
14
+ _target_: energizer.callbacks.model_checkpoint.ModelCheckpoint
15
+ dirpath: .checkpoints
16
+ stage: train
17
+ frequency: 1:epoch
18
+ loggers:
19
+ tensorboard:
20
+ _target_: energizer.loggers.TensorBoardLogger
21
+ root_dir: ./
22
+ name: tb_logs
23
+ version: null
24
+ data:
25
+ batch_size: 32
26
+ eval_batch_size: 128
27
+ shuffle: true
28
+ replacement: false
29
+ data_seed: 42
30
+ drop_last: false
31
+ num_workers: 8
32
+ pin_memory: true
33
+ persistent_workers: false
34
+ multiprocessing_context: null
35
+ max_length: 512
36
+ fit:
37
+ max_epochs: 20
38
+ optimizer_kwargs:
39
+ name: adamw
40
+ lr: 3.0e-05
41
+ init_kwargs:
42
+ fused: true
43
+ scheduler_kwargs:
44
+ name: constant_schedule_with_warmup
45
+ num_warmup_steps: 2000
46
+ log_interval: 100
47
+ enable_progress_bar: true
48
+ limit_train_batches: null
49
+ limit_validation_batches: null
50
+ model:
51
+ name: bert-tiny
52
+ revision: null
53
+ seed: 42
54
+ log_interval: 100
55
+ enable_progress_bar: true
56
+ limit_batches: null
57
+ seed: 42
58
+ experiment_group: training
59
+ run_name: bert-tiny_2024-03-04T17-34-08
60
+ data_path: /home/pl487/coreset-project/data/processed
61
+ dataset: mnli
62
+
63
+ ======================================================================
64
+ [2024-03-04 17:34:08,796][hydra][INFO] - Seed enabled: 42
65
+ [2024-03-04 17:34:09,910][hydra][INFO] - Label distribution:
66
+ {<RunningStage.TRAIN: 'train'>: {'0-(entailment)': 130899, '1-(neutral)': 130900, '2-(contradiction)': 130903}}
67
+ [2024-03-04 17:34:21,700][hydra][INFO] - Loggers: [<energizer.loggers.tensorboard.TensorBoardLogger object at 0x7f79509062f0>]
68
+ [2024-03-04 17:34:21,700][hydra][INFO] - Callbacks: [<energizer.active_learning.callbacks.Timer object at 0x7f792e9ecfd0>, <energizer.callbacks.lr_monitor.LearningRateMonitor object at 0x7f792e9ed030>, <energizer.callbacks.model_checkpoint.ModelCheckpoint object at 0x7f792e9ed540>]
69
+ [2024-03-04 17:34:21,702][hydra][INFO] - Model summary:
70
+ Total num params: 4.4M
71
+ Of which trainable: 4.4M
72
+ With a memory footprint of 0.01GB
73
+ Total memory allocated 0.03GB
74
+ [2024-03-04 17:34:21,702][hydra][INFO] - Dataloading params:
75
+ SequenceClassificationDataloaderArgs(batch_size=32, eval_batch_size=128, num_workers=8, pin_memory=True, drop_last=False, persistent_workers=False, shuffle=True, replacement=False, data_seed=42, multiprocessing_context=None, max_length=512)
76
+ [2024-03-04 17:34:21,737][hydra][INFO] - Batch:
77
+ {<InputKeys.INPUT_IDS: 'input_ids'>: tensor([[ 101, 2092, 7910, 2008, 1005, 1055, 2785, 1997, 5793, 1045,
78
+ 2812, 2027, 1005, 2128, 2130, 4755, 2009, 2000, 2000, 2073,
79
+ 2085, 7910, 2008, 2027, 4748, 16874, 5562, 2006, 2694, 2017,
80
+ 2113, 2065, 2115, 2065, 2017, 7910, 2017, 2113, 2031, 2589,
81
+ 2023, 2030, 2065, 2017, 2342, 2023, 7910, 7910, 2057, 1005,
82
+ 2222, 9790, 2005, 2017, 1998, 2017, 2123, 1005, 1056, 2031,
83
+ 2000, 3477, 2149, 4983, 2017, 2021, 2059, 2054, 2027, 2123,
84
+ 1005, 1056, 2425, 2017, 2003, 2008, 2065, 2017, 2065, 2027,
85
+ 2663, 2017, 2507, 2068, 2012, 2560, 1037, 2353, 1997, 1996,
86
+ 1997, 1996, 2518, 2008, 2027, 2663, 2061, 1045, 2123, 1005,
87
+ 1056, 2113, 2009, 2003, 7910, 2009, 1005, 1055, 2893, 2000,
88
+ 2022, 2062, 2449, 2085, 2738, 2084, 7910, 2941, 7910, 7149,
89
+ 2007, 1996, 4126, 2084, 2007, 7910, 8529, 1996, 7910, 7750,
90
+ 2027, 1996, 1996, 9559, 2024, 2074, 1999, 2009, 2005, 1996,
91
+ 2769, 1045, 1005, 1049, 1045, 1005, 1049, 6427, 1045, 2113,
92
+ 1045, 1045, 5993, 2007, 2017, 1045, 2228, 2017, 1005, 2128,
93
+ 2613, 2017, 1005, 2128, 2200, 2157, 2008, 1996, 8801, 2323,
94
+ 1045, 2228, 2027, 2323, 2031, 2019, 5020, 3815, 1997, 2017,
95
+ 2113, 2672, 2027, 2064, 2031, 1037, 2261, 2021, 1045, 2228,
96
+ 2087, 1997, 2068, 2323, 2022, 2025, 7910, 9559, 1999, 1996,
97
+ 2755, 1998, 2008, 1005, 1055, 2126, 2126, 2027, 1005, 2310,
98
+ 5407, 2046, 4331, 2009, 1005, 1055, 2138, 1997, 1996, 1996,
99
+ 2375, 2477, 2017, 2113, 1996, 15932, 1998, 2673, 2021, 7910,
100
+ 2021, 2053, 1045, 2113, 2057, 2009, 8529, 2057, 1005, 2128,
101
+ 1999, 5374, 1998, 7910, 2057, 2031, 1996, 2168, 2518, 2058,
102
+ 24375, 4667, 1998, 1998, 7910, 2027, 2024, 5599, 2068, 2041,
103
+ 1045, 2812, 2074, 1996, 3180, 7173, 6251, 2518, 2027, 2292,
104
+ 2068, 2041, 2138, 1997, 2027, 2123, 1005, 1056, 2031, 2151,
105
+ 2173, 2000, 2562, 2000, 2404, 2068, 2061, 8307, 2008, 2071,
106
+ 2017, 2113, 7910, 4983, 7910, 2042, 1037, 2350, 10048, 2021,
107
+ 7910, 7910, 2130, 1996, 14255, 14141, 2135, 2210, 4933, 1045,
108
+ 2812, 1996, 1996, 4364, 2008, 12386, 2651, 1999, 2637, 2003,
109
+ 1996, 6778, 1998, 9444, 2008, 2089, 2022, 3251, 2009, 1005,
110
+ 1055, 1037, 13742, 2030, 5850, 2030, 3649, 2842, 8529, 2027,
111
+ 2024, 1996, 3924, 2008, 2024, 2183, 2000, 3477, 1998, 2027,
112
+ 2024, 1996, 2028, 2008, 2024, 2183, 2000, 9015, 1998, 1996,
113
+ 2060, 2711, 2017, 2113, 2065, 2027, 3477, 2065, 2027, 2065,
114
+ 2027, 7910, 6545, 2068, 7910, 1998, 7910, 2059, 1996, 2017,
115
+ 2113, 2051, 1996, 2375, 3138, 2058, 7910, 2431, 1996, 2051,
116
+ 7910, 2027, 2593, 2292, 2068, 2175, 2030, 2027, 2131, 2125,
117
+ 2007, 1037, 1037, 6251, 2138, 2027, 1005, 2310, 2018, 1037,
118
+ 5160, 2008, 2017, 2113, 5683, 2008, 2008, 2027, 4694, 1005,
119
+ 1056, 2035, 2362, 2043, 2027, 2106, 2009, 102, 1045, 2228,
120
+ 2008, 2045, 2323, 2022, 2019, 5020, 6630, 1997, 15406, 1999,
121
+ 2256, 8801, 1012, 102]]), <InputKeys.ATT_MASK: 'attention_mask'>: tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
122
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
123
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
124
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
125
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
126
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
127
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
128
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
129
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
130
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
131
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
132
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
133
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
134
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
135
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
136
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
137
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
138
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
139
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]), <InputKeys.LABELS: 'labels'>: tensor([0]), <InputKeys.ON_CPU: 'on_cpu'>: {<SpecialKeys.ID: 'uid'>: [221950]}}