Hugging Face's logo

TetorisAce
/
topic_classifier_model

TensorBoard
Safetensors
distilbert
Model card Files
xet
Metrics Community
TetorisAce commited on
Commit
c24dad4
·
verified ·
1 Parent(s): bb6fc60

Training in progress, epoch 1

Browse files
Files changed (16) hide show
  1. config.json +4 -4
  2. model.safetensors +1 -1
  3. run-m68fs73f/checkpoint-63/config.json +36 -0
  4. run-m68fs73f/checkpoint-63/model.safetensors +3 -0
  5. run-m68fs73f/checkpoint-63/optimizer.pt +3 -0
  6. run-m68fs73f/checkpoint-63/rng_state.pth +3 -0
  7. run-m68fs73f/checkpoint-63/scheduler.pt +3 -0
  8. run-m68fs73f/checkpoint-63/special_tokens_map.json +7 -0
  9. run-m68fs73f/checkpoint-63/tokenizer.json +0 -0
  10. run-m68fs73f/checkpoint-63/tokenizer_config.json +56 -0
  11. run-m68fs73f/checkpoint-63/trainer_state.json +85 -0
  12. run-m68fs73f/checkpoint-63/training_args.bin +3 -0
  13. run-m68fs73f/checkpoint-63/vocab.txt +0 -0
  14. runs/Sep19_05-59-44_ea3a691caa9c/events.out.tfevents.1758261605.ea3a691caa9c.512.0 +3 -0
  15. runs/Sep19_06-20-34_ea3a691caa9c/events.out.tfevents.1758263121.ea3a691caa9c.6934.0 +3 -0
  16. training_args.bin +2 -2
config.json CHANGED
@@ -9,10 +9,10 @@
9
  "dtype": "float32",
10
  "hidden_dim": 3072,
11
  "id2label": {
12
- "0": "world",
13
- "1": "sports",
14
- "2": "business",
15
- "3": "Sci/Tech"
16
  },
17
  "initializer_range": 0.02,
18
  "label2id": {
 
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": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b5e839625daae2ce798635c49774e10832a3207805ddb7e6c969acc7c524141
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a01f0da45b11a5f96ec450d8b2f7143b430f0a9ce2ec856ea71a259936e918
3
  size 267838720
run-m68fs73f/checkpoint-63/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-m68fs73f/checkpoint-63/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a01f0da45b11a5f96ec450d8b2f7143b430f0a9ce2ec856ea71a259936e918
3
+ size 267838720
run-m68fs73f/checkpoint-63/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15817182261093930ccb1b491d3ce81a0dd6f6cb1dfb72bbe6bea6234ab8a5ff
3
+ size 535737163
run-m68fs73f/checkpoint-63/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae98b50072e77a9276f8753b0b13057424a20aea8b6dd2435909cd965f52464c
3
+ size 14455
run-m68fs73f/checkpoint-63/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90104f3b14ac7913ed515e9161e6980792a0bf978f4a714fcdc9290ced30c4f
3
+ size 1465
run-m68fs73f/checkpoint-63/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-m68fs73f/checkpoint-63/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-m68fs73f/checkpoint-63/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-m68fs73f/checkpoint-63/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 63,
3
+ "best_metric": 1.1014227867126465,
4
+ "best_model_checkpoint": "topic_classifier_model/run-m68fs73f/checkpoint-63",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 63,
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": 0.83,
15
+ "eval_loss": 1.1014227867126465,
16
+ "eval_runtime": 197.2915,
17
+ "eval_samples_per_second": 5.069,
18
+ "eval_steps_per_second": 0.319,
19
+ "step": 63
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 63,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 1,
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": true
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 16,
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": 9.257214581169088e-06,
80
+ "metric": "eval/loss",
81
+ "num_train_epochs": 1,
82
+ "per_device_train_batch_size": 16,
83
+ "seed": 28
84
+ }
85
+ }
run-m68fs73f/checkpoint-63/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34232a23c78b6f6755534d991bb12a02754ce44599c5431c24d5ddf1e8870af0
3
+ size 5777
run-m68fs73f/checkpoint-63/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Sep19_05-59-44_ea3a691caa9c/events.out.tfevents.1758261605.ea3a691caa9c.512.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78415716323ea3f89ffb8feb70854f8920563e352689b2ce36cc2cf819a9f967
3
+ size 5068
runs/Sep19_06-20-34_ea3a691caa9c/events.out.tfevents.1758263121.ea3a691caa9c.6934.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27969f7f2bc987b7ad0bcda3377faa6348bd3a53f4f5a2b38c5c08400ee4174e
3
+ size 5731
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d0c9f4679fc04ba1d727cde62e8415422bbbaac261fe7c5c22c03f63c2e3403
3
- size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34232a23c78b6f6755534d991bb12a02754ce44599c5431c24d5ddf1e8870af0
3
+ size 5777