Hugging Face's logo

TetorisAce
/
topic_classifier_model

TensorBoard
Safetensors
distilbert
Model card Files
xet
Metrics Community
TetorisAce commited on
Commit
f397f67
·
verified ·
1 Parent(s): ab59740

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-9816kcc3/checkpoint-250/config.json +36 -0
  3. run-9816kcc3/checkpoint-250/model.safetensors +3 -0
  4. run-9816kcc3/checkpoint-250/optimizer.pt +3 -0
  5. run-9816kcc3/checkpoint-250/rng_state.pth +3 -0
  6. run-9816kcc3/checkpoint-250/scheduler.pt +3 -0
  7. run-9816kcc3/checkpoint-250/special_tokens_map.json +7 -0
  8. run-9816kcc3/checkpoint-250/tokenizer.json +0 -0
  9. run-9816kcc3/checkpoint-250/tokenizer_config.json +56 -0
  10. run-9816kcc3/checkpoint-250/trainer_state.json +85 -0
  11. run-9816kcc3/checkpoint-250/training_args.bin +3 -0
  12. run-9816kcc3/checkpoint-250/vocab.txt +0 -0
  13. run-rjh1814l/checkpoint-64/config.json +36 -0
  14. run-rjh1814l/checkpoint-64/model.safetensors +3 -0
  15. run-rjh1814l/checkpoint-64/optimizer.pt +3 -0
  16. run-rjh1814l/checkpoint-64/rng_state.pth +3 -0
  17. run-rjh1814l/checkpoint-64/scheduler.pt +3 -0
  18. run-rjh1814l/checkpoint-64/special_tokens_map.json +7 -0
  19. run-rjh1814l/checkpoint-64/tokenizer.json +0 -0
  20. run-rjh1814l/checkpoint-64/tokenizer_config.json +56 -0
  21. run-rjh1814l/checkpoint-64/trainer_state.json +94 -0
  22. run-rjh1814l/checkpoint-64/training_args.bin +3 -0
  23. run-rjh1814l/checkpoint-64/vocab.txt +0 -0
  24. runs/Sep19_08-00-22_8a8f19444048/events.out.tfevents.1758273022.8a8f19444048.1681.7 +3 -0
  25. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19b08e2051b5ac65dbd33521576118ce2adb39603059ad0ef467135b36d32be0
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503898bb4f7bb12354efafb4d17d0b3a026feab26cf41e45595c46c050e0c6f7
3
  size 267838720
run-9816kcc3/checkpoint-250/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "transformers_version": "4.56.1",
35
+ "vocab_size": 30522
36
+ }
run-9816kcc3/checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503898bb4f7bb12354efafb4d17d0b3a026feab26cf41e45595c46c050e0c6f7
3
+ size 267838720
run-9816kcc3/checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871d704613ea5a6f94aa397876bbe7a693aa8bc2168b092503ee3dcfc73b4b42
3
+ size 535741515
run-9816kcc3/checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a3239957270b8c89b662dfd6e819cc7c0fc743421ae0d7ebc63ad02c5e208fd
3
+ size 14645
run-9816kcc3/checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c2fa550b05776370e7fda1b8f3cd948adc3438eb8e8bc4490909701b5da2e0
3
+ size 1465
run-9816kcc3/checkpoint-250/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-9816kcc3/checkpoint-250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9816kcc3/checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-9816kcc3/checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 250,
3
+ "best_metric": 0.3948093354701996,
4
+ "best_model_checkpoint": "topic_classifier_model/run-9816kcc3/checkpoint-250",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 250,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.879,
15
+ "eval_loss": 0.3948093354701996,
16
+ "eval_runtime": 2.6827,
17
+ "eval_samples_per_second": 372.763,
18
+ "eval_steps_per_second": 23.484,
19
+ "step": 250
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 1500,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 6,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 4,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "_wandb": {
44
+ "cli_version": "0.21.3",
45
+ "m": [],
46
+ "python_version": "3.12.11",
47
+ "t": {
48
+ "1": [
49
+ 1,
50
+ 2,
51
+ 3,
52
+ 5,
53
+ 11,
54
+ 12,
55
+ 41,
56
+ 49,
57
+ 51,
58
+ 53,
59
+ 71,
60
+ 98,
61
+ 100,
62
+ 105
63
+ ],
64
+ "12": "0.21.3",
65
+ "13": "linux-x86_64",
66
+ "3": [
67
+ 14
68
+ ],
69
+ "4": "3.12.11",
70
+ "5": "0.21.3",
71
+ "6": "4.56.1",
72
+ "8": [
73
+ 1,
74
+ 12
75
+ ]
76
+ }
77
+ },
78
+ "assignments": {},
79
+ "learning_rate": 1.1240103243940362e-05,
80
+ "metric": "eval/loss",
81
+ "num_train_epochs": 6,
82
+ "per_device_train_batch_size": 4,
83
+ "seed": 2
84
+ }
85
+ }
run-9816kcc3/checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348c9a7783dc1814fcc5d9bc464e430840421ea1ee3a083be1b16c81dc13b1c1
3
+ size 5777
run-9816kcc3/checkpoint-250/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-rjh1814l/checkpoint-64/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "dtype": "float32",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "transformers_version": "4.56.1",
35
+ "vocab_size": 30522
36
+ }
run-rjh1814l/checkpoint-64/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771b640d05f95ba9838b33b88df301659a44930951691a390ebd6209516fd451
3
+ size 267838720
run-rjh1814l/checkpoint-64/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f1459f04bfe90f16931f3f0245078203d569e45420a0c06b257a39d8506afd2
3
+ size 535741515
run-rjh1814l/checkpoint-64/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bde8652d7d2a43794be38c31e0f909ca003a57ae84e7600753082b7650e86b
3
+ size 14645
run-rjh1814l/checkpoint-64/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d93a9102b977dfbf15005ba6565937cf8e57f02a0f5373cd943a8c10c328312
3
+ size 1465
run-rjh1814l/checkpoint-64/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-rjh1814l/checkpoint-64/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-rjh1814l/checkpoint-64/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-rjh1814l/checkpoint-64/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 64,
3
+ "best_metric": 0.3751676678657532,
4
+ "best_model_checkpoint": "topic_classifier_model/run-rjh1814l/checkpoint-64",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 64,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.867,
15
+ "eval_loss": 0.43408745527267456,
16
+ "eval_runtime": 2.7363,
17
+ "eval_samples_per_second": 365.457,
18
+ "eval_steps_per_second": 23.024,
19
+ "step": 32
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.883,
24
+ "eval_loss": 0.3751676678657532,
25
+ "eval_runtime": 2.7274,
26
+ "eval_samples_per_second": 366.649,
27
+ "eval_steps_per_second": 23.099,
28
+ "step": 64
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 64,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": true
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 32,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "_wandb": {
53
+ "cli_version": "0.21.3",
54
+ "m": [],
55
+ "python_version": "3.12.11",
56
+ "t": {
57
+ "1": [
58
+ 1,
59
+ 2,
60
+ 3,
61
+ 5,
62
+ 11,
63
+ 12,
64
+ 41,
65
+ 49,
66
+ 51,
67
+ 53,
68
+ 71,
69
+ 98,
70
+ 100,
71
+ 105
72
+ ],
73
+ "12": "0.21.3",
74
+ "13": "linux-x86_64",
75
+ "3": [
76
+ 14
77
+ ],
78
+ "4": "3.12.11",
79
+ "5": "0.21.3",
80
+ "6": "4.56.1",
81
+ "8": [
82
+ 1,
83
+ 12
84
+ ]
85
+ }
86
+ },
87
+ "assignments": {},
88
+ "learning_rate": 7.094843693018797e-05,
89
+ "metric": "eval/loss",
90
+ "num_train_epochs": 2,
91
+ "per_device_train_batch_size": 32,
92
+ "seed": 40
93
+ }
94
+ }
run-rjh1814l/checkpoint-64/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ef255ef21ff4e8ea3b6d7f8cb93247e99a2abac4abd80f57607a782116fa88
3
+ size 5777
run-rjh1814l/checkpoint-64/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Sep19_08-00-22_8a8f19444048/events.out.tfevents.1758273022.8a8f19444048.1681.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5f99f0d1512bfae6a10a4d18ec4b1601b8d9db70bcf4ca937c9a47d3d4d030
3
+ size 7990
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48ef255ef21ff4e8ea3b6d7f8cb93247e99a2abac4abd80f57607a782116fa88
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348c9a7783dc1814fcc5d9bc464e430840421ea1ee3a083be1b16c81dc13b1c1
3
  size 5777