Hugging Face's logo

halu1003
/
LLMClassWork1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
halu1003 commited on
Commit
661d80c
·
1 Parent(s): 23b15c9

Training in progress, epoch 2

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-2138/config.json +25 -0
  3. run-3/checkpoint-2138/model.safetensors +3 -0
  4. run-3/checkpoint-2138/optimizer.pt +3 -0
  5. run-3/checkpoint-2138/rng_state.pth +3 -0
  6. run-3/checkpoint-2138/scheduler.pt +3 -0
  7. run-3/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-3/checkpoint-2138/tokenizer.json +0 -0
  9. run-3/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-3/checkpoint-2138/trainer_state.json +59 -0
  11. run-3/checkpoint-2138/training_args.bin +3 -0
  12. run-3/checkpoint-2138/vocab.txt +0 -0
  13. run-3/checkpoint-4276/config.json +25 -0
  14. run-3/checkpoint-4276/model.safetensors +3 -0
  15. run-3/checkpoint-4276/optimizer.pt +3 -0
  16. run-3/checkpoint-4276/rng_state.pth +3 -0
  17. run-3/checkpoint-4276/scheduler.pt +3 -0
  18. run-3/checkpoint-4276/special_tokens_map.json +7 -0
  19. run-3/checkpoint-4276/tokenizer.json +0 -0
  20. run-3/checkpoint-4276/tokenizer_config.json +55 -0
  21. run-3/checkpoint-4276/trainer_state.json +92 -0
  22. run-3/checkpoint-4276/training_args.bin +3 -0
  23. run-3/checkpoint-4276/vocab.txt +0 -0
  24. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299284.04248f4b0c3a.492.5 +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 sha256:2e2137cd6dae0095fd7ade4b342667694adb6462949382ea7db824bc80b8cd04
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9533b2071acf8adc45b12085153135a595570e6ebc96380b9e145f579c506ff7
3
  size 267832560
run-3/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-3/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e667461e203241292a12c60839c4805043954b6710f44763f1556c63504944
3
+ size 267832560
run-3/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507a3f10130561cb8dfcb3a7c27a863ff237d98ae2e8b748a484012787e2450a
3
+ size 535727290
run-3/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7420204ce756934358b74169b5e7ac1f0b50022ac6b5031ceea68686e63995f4
3
+ size 14244
run-3/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa9c0ef0f24bc8e7403ea75db53bc7945d21cdc70c113feb396ba84b420354c
3
+ size 1064
run-3/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-3/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2787671229651657,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2138",
4
+ "epoch": 1.0,
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": 0.23,
13
+ "learning_rate": 1.8134386732635114e-06,
14
+ "loss": 0.6097,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.6601212338601031e-06,
20
+ "loss": 0.5883,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.506803794456695e-06,
26
+ "loss": 0.562,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.3534863550532868e-06,
32
+ "loss": 0.5302,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5693901181221008,
38
+ "eval_matthews_correlation": 0.2787671229651657,
39
+ "eval_runtime": 0.716,
40
+ "eval_samples_per_second": 1456.694,
41
+ "eval_steps_per_second": 92.178,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 6414,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 3,
49
+ "save_steps": 500,
50
+ "total_flos": 32610782805072.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.9667561126669194e-06,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 1
58
+ }
59
+ }
run-3/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91e4836dde5a11432215e79bbc165d4ffa71f41124bd5e3404c89fe5fe37126
3
+ size 4792
run-3/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-4276/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-3/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9533b2071acf8adc45b12085153135a595570e6ebc96380b9e145f579c506ff7
3
+ size 267832560
run-3/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c33f12ce52eb20cc55973a22b7df72f1764d7ff045dbd1532126972699ffb8d
3
+ size 535727290
run-3/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e606f3059ebf03f51d93cd2c74f738c7986405265dea3dc627097bbebab1f9ba
3
+ size 14244
run-3/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492f1d3b964a5dc1385381d1e3d9cbf52ab1a44259d26483a3ccbb979c7d7ab4
3
+ size 1064
run-3/checkpoint-4276/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-3/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-4276/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-3/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4068953869702192,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 1.8134386732635114e-06,
14
+ "loss": 0.6097,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 1.6601212338601031e-06,
20
+ "loss": 0.5883,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 1.506803794456695e-06,
26
+ "loss": 0.562,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 1.3534863550532868e-06,
32
+ "loss": 0.5302,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5693901181221008,
38
+ "eval_matthews_correlation": 0.2787671229651657,
39
+ "eval_runtime": 0.716,
40
+ "eval_samples_per_second": 1456.694,
41
+ "eval_steps_per_second": 92.178,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 1.2001689156498788e-06,
47
+ "loss": 0.5141,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 1.0468514762464705e-06,
53
+ "loss": 0.5067,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 8.935340368430625e-07,
59
+ "loss": 0.4926,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 7.402165974396544e-07,
65
+ "loss": 0.501,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.5920860171318054,
71
+ "eval_matthews_correlation": 0.4068953869702192,
72
+ "eval_runtime": 0.7393,
73
+ "eval_samples_per_second": 1410.839,
74
+ "eval_steps_per_second": 89.276,
75
+ "step": 4276
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 6414,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 3,
82
+ "save_steps": 500,
83
+ "total_flos": 65084182429116.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 1.9667561126669194e-06,
88
+ "num_train_epochs": 3,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 1
91
+ }
92
+ }
run-3/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91e4836dde5a11432215e79bbc165d4ffa71f41124bd5e3404c89fe5fe37126
3
+ size 4792
run-3/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299284.04248f4b0c3a.492.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3530fccc718c2aaeb2a5a5b3a3ee7014f61c517e0b1fcc7f55eb211617a86a61
3
+ size 6747
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4cd2fef8507de0b6ec4fc6f0e972dd20ee83952ed9d6116f7f100b26d2a1eca
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91e4836dde5a11432215e79bbc165d4ffa71f41124bd5e3404c89fe5fe37126
3
  size 4792