Hugging Face's logo

TetorisAce
/
topic_classifier_model

TensorBoard
Safetensors
distilbert
Model card Files
xet
Metrics Community
TetorisAce commited on
Commit
3029fee
·
verified ·
1 Parent(s): 44ec689

Training in progress, epoch 1

Browse files
Files changed (16) hide show
  1. config.json +4 -4
  2. model.safetensors +1 -1
  3. run-8ogzfam8/checkpoint-250/config.json +36 -0
  4. run-8ogzfam8/checkpoint-250/model.safetensors +3 -0
  5. run-8ogzfam8/checkpoint-250/optimizer.pt +3 -0
  6. run-8ogzfam8/checkpoint-250/rng_state.pth +3 -0
  7. run-8ogzfam8/checkpoint-250/scheduler.pt +3 -0
  8. run-8ogzfam8/checkpoint-250/special_tokens_map.json +7 -0
  9. run-8ogzfam8/checkpoint-250/tokenizer.json +0 -0
  10. run-8ogzfam8/checkpoint-250/tokenizer_config.json +56 -0
  11. run-8ogzfam8/checkpoint-250/trainer_state.json +94 -0
  12. run-8ogzfam8/checkpoint-250/training_args.bin +3 -0
  13. run-8ogzfam8/checkpoint-250/vocab.txt +0 -0
  14. runs/Sep19_08-00-22_8a8f19444048/events.out.tfevents.1758274249.8a8f19444048.1681.10 +3 -0
  15. runs/Sep19_09-34-05_8a8f19444048/events.out.tfevents.1758274507.8a8f19444048.1681.11 +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": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
15
- "3": "LABEL_3"
16
  },
17
  "initializer_range": 0.02,
18
  "label2id": {
 
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": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536eba2c997f23d7f1f444aca3b050dc6e8bac16da9485f788d7042b6383507d
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35eed8c359d50f8b7de5fda756d40252d204df3e20b6c5f5d65d8870c556fe21
3
  size 267838720
run-8ogzfam8/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-8ogzfam8/checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd5f94556399d5695870305f39c04a9e6fd8a4643e3f00560322d25b0ae7c5c
3
+ size 267838720
run-8ogzfam8/checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49ba06cbfb7b73aadcc8af71478bcdfe4009f0c1767204a052c3efc12267ea8
3
+ size 535741515
run-8ogzfam8/checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8fc583b3b446dc18748ecd9f5d7c6bb9678a40c0bcb6416ae318dc6bbea03f
3
+ size 14645
run-8ogzfam8/checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:170c6513457fd547d32056f5288f331e47bfbc2e4db8b1fd1b77a88a08660154
3
+ size 1465
run-8ogzfam8/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-8ogzfam8/checkpoint-250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8ogzfam8/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-8ogzfam8/checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 250,
3
+ "best_metric": 0.3955004811286926,
4
+ "best_model_checkpoint": "topic_classifier_model/run-8ogzfam8/checkpoint-250",
5
+ "epoch": 2.0,
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": 0.871,
15
+ "eval_loss": 0.42684227228164673,
16
+ "eval_runtime": 2.6757,
17
+ "eval_samples_per_second": 373.729,
18
+ "eval_steps_per_second": 23.545,
19
+ "step": 125
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.884,
24
+ "eval_loss": 0.3955004811286926,
25
+ "eval_runtime": 2.8827,
26
+ "eval_samples_per_second": 346.899,
27
+ "eval_steps_per_second": 21.855,
28
+ "step": 250
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 250,
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": 8,
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": 3.346839943657667e-05,
89
+ "metric": "eval/loss",
90
+ "num_train_epochs": 2,
91
+ "per_device_train_batch_size": 8,
92
+ "seed": 11
93
+ }
94
+ }
run-8ogzfam8/checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaecd1888fa501407db3d399b7bb3a72fc50b8bd9383dd5e59f00c74c28896d
3
+ size 5777
run-8ogzfam8/checkpoint-250/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.1758274249.8a8f19444048.1681.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52187c27be7a194d4ecfacb18152976b53acbf43e28a304ab9f6fcb39a6d5a2c
3
+ size 5383
runs/Sep19_09-34-05_8a8f19444048/events.out.tfevents.1758274507.8a8f19444048.1681.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c1dfd5455b2c0460256a8c9a1cbac4338fd6a8010d090962552c0469581f96
3
+ size 7035
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eaecd1888fa501407db3d399b7bb3a72fc50b8bd9383dd5e59f00c74c28896d
3
- size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23f0a0d06750e2404668a35e52bd6320029e2f6d3ec745bcdd0956e0639934e
3
+ size 5841