Hugging Face's logo

LarryTW
/
llm_NLP

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
LarryTW commited on
Commit
a70024b
·
1 Parent(s): fdc6bb2

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-2138/config.json +25 -0
  3. run-8/checkpoint-2138/model.safetensors +3 -0
  4. run-8/checkpoint-2138/optimizer.pt +3 -0
  5. run-8/checkpoint-2138/rng_state.pth +3 -0
  6. run-8/checkpoint-2138/scheduler.pt +3 -0
  7. run-8/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-8/checkpoint-2138/tokenizer.json +0 -0
  9. run-8/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-8/checkpoint-2138/trainer_state.json +68 -0
  11. run-8/checkpoint-2138/training_args.bin +3 -0
  12. run-8/checkpoint-2138/vocab.txt +0 -0
  13. run-8/checkpoint-3207/config.json +25 -0
  14. run-8/checkpoint-3207/model.safetensors +3 -0
  15. run-8/checkpoint-3207/optimizer.pt +3 -0
  16. run-8/checkpoint-3207/rng_state.pth +3 -0
  17. run-8/checkpoint-3207/scheduler.pt +3 -0
  18. run-8/checkpoint-3207/special_tokens_map.json +7 -0
  19. run-8/checkpoint-3207/tokenizer.json +0 -0
  20. run-8/checkpoint-3207/tokenizer_config.json +55 -0
  21. run-8/checkpoint-3207/trainer_state.json +89 -0
  22. run-8/checkpoint-3207/training_args.bin +3 -0
  23. run-8/checkpoint-3207/vocab.txt +0 -0
  24. runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703297055.cab255cafe95.13310.10 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:299a3a1778d979da450436f982d9a07300714da5b0bec5bfa4de2499e232bb89
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c18f088ad3484b7949435a2e6c71218b17eabd3f720c94f95032724bf7933e2
3
  size 267832560
run-8/checkpoint-2138/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bf10d8bbc832a7555e04c14699694f0eb4aaab287f8f16b137bd0d6a92b1bc
3
+ size 267832560
run-8/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011b78bb34e05a058b330639d0834bd1a727c804981a7aaf0f662a6cfbadbc4b
3
+ size 535727290
run-8/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9c8e5e8fb49e95050d2aa2f256ba0f70fdaf95fbc4a0b2f1e5cc7df7855730
3
+ size 14308
run-8/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb75f16d8375e5da362a56b686880a3be0f41f90318b9020967f4281a9ca35e
3
+ size 1064
run-8/checkpoint-2138/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-8/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-2138/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-8/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.48138791213884463,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-2138",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "learning_rate": 7.540690617488091e-06,
14
+ "loss": 0.558,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 6.542188152248672e-06,
20
+ "loss": 0.5143,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.49273109436035156,
26
+ "eval_matthews_correlation": 0.43591443951045983,
27
+ "eval_runtime": 0.7692,
28
+ "eval_samples_per_second": 1355.973,
29
+ "eval_steps_per_second": 85.805,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 5.543685687009253e-06,
35
+ "loss": 0.408,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 4.545183221769834e-06,
41
+ "loss": 0.3963,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.4984338581562042,
47
+ "eval_matthews_correlation": 0.48138791213884463,
48
+ "eval_runtime": 0.837,
49
+ "eval_samples_per_second": 1246.126,
50
+ "eval_steps_per_second": 78.854,
51
+ "step": 2138
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 4276,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 4,
58
+ "save_steps": 500,
59
+ "total_flos": 75521423306424.0,
60
+ "train_batch_size": 8,
61
+ "trial_name": null,
62
+ "trial_params": {
63
+ "learning_rate": 8.53919308272751e-06,
64
+ "num_train_epochs": 4,
65
+ "per_device_train_batch_size": 8,
66
+ "seed": 13
67
+ }
68
+ }
run-8/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03af6426126617078e5cb8b57bf2b46d6a95fbaa7edb84b6fba2f994f10481f9
3
+ size 4792
run-8/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-3207/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c18f088ad3484b7949435a2e6c71218b17eabd3f720c94f95032724bf7933e2
3
+ size 267832560
run-8/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada975b571c230729c845077e8545026f019e475784d07afb21bba2d0410f313
3
+ size 535727290
run-8/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6875c2f2045c8bbc18e9462ab46e15bfe1bbb6525b2daaa7ff1879eb7e7caa
3
+ size 14308
run-8/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882db2f339d6a730c7167ee53f1418405f7206e0268a351e7291077e953dece0
3
+ size 1064
run-8/checkpoint-3207/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-8/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-3207/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-8/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.49799539554804517,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-3207",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "learning_rate": 7.540690617488091e-06,
14
+ "loss": 0.558,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 6.542188152248672e-06,
20
+ "loss": 0.5143,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.49273109436035156,
26
+ "eval_matthews_correlation": 0.43591443951045983,
27
+ "eval_runtime": 0.7692,
28
+ "eval_samples_per_second": 1355.973,
29
+ "eval_steps_per_second": 85.805,
30
+ "step": 1069
31
+ },
32
+ {
33
+ "epoch": 1.4,
34
+ "learning_rate": 5.543685687009253e-06,
35
+ "loss": 0.408,
36
+ "step": 1500
37
+ },
38
+ {
39
+ "epoch": 1.87,
40
+ "learning_rate": 4.545183221769834e-06,
41
+ "loss": 0.3963,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 2.0,
46
+ "eval_loss": 0.4984338581562042,
47
+ "eval_matthews_correlation": 0.48138791213884463,
48
+ "eval_runtime": 0.837,
49
+ "eval_samples_per_second": 1246.126,
50
+ "eval_steps_per_second": 78.854,
51
+ "step": 2138
52
+ },
53
+ {
54
+ "epoch": 2.34,
55
+ "learning_rate": 3.5466807565304158e-06,
56
+ "loss": 0.3146,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 2.81,
61
+ "learning_rate": 2.5481782912909966e-06,
62
+ "loss": 0.3216,
63
+ "step": 3000
64
+ },
65
+ {
66
+ "epoch": 3.0,
67
+ "eval_loss": 0.6548400521278381,
68
+ "eval_matthews_correlation": 0.49799539554804517,
69
+ "eval_runtime": 0.7558,
70
+ "eval_samples_per_second": 1380.007,
71
+ "eval_steps_per_second": 87.325,
72
+ "step": 3207
73
+ }
74
+ ],
75
+ "logging_steps": 500,
76
+ "max_steps": 4276,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 4,
79
+ "save_steps": 500,
80
+ "total_flos": 112955364794592.0,
81
+ "train_batch_size": 8,
82
+ "trial_name": null,
83
+ "trial_params": {
84
+ "learning_rate": 8.53919308272751e-06,
85
+ "num_train_epochs": 4,
86
+ "per_device_train_batch_size": 8,
87
+ "seed": 13
88
+ }
89
+ }
run-8/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03af6426126617078e5cb8b57bf2b46d6a95fbaa7edb84b6fba2f994f10481f9
3
+ size 4792
run-8/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703297055.cab255cafe95.13310.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32dd318ffd7cddf79a7c814d2e9357d7e0c14cf5faac95511658842a695aa10f
3
- size 5797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b8307bf5f453df015037dd9568969948e33ad03e8ddea2ef6a80c1b78f5ab2
3
+ size 7292