Hugging Face's logo

richardchiu
/
work1_AIA_LLM_B_132001

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
sft
text-generation-inference
8-bit precision
bitsandbytes
Model card Files
xet
 Metrics Community
richardchiu commited on
Commit
d3fd1ab
·
verified ·
1 Parent(s): 81be6c1

Training in progress, epoch 2

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-2138/config.json +25 -0
  3. run-2/checkpoint-2138/model.safetensors +3 -0
  4. run-2/checkpoint-2138/optimizer.pt +3 -0
  5. run-2/checkpoint-2138/rng_state.pth +3 -0
  6. run-2/checkpoint-2138/scheduler.pt +3 -0
  7. run-2/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-2/checkpoint-2138/tokenizer.json +0 -0
  9. run-2/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-2/checkpoint-2138/trainer_state.json +63 -0
  11. run-2/checkpoint-2138/training_args.bin +3 -0
  12. run-2/checkpoint-2138/vocab.txt +0 -0
  13. run-2/checkpoint-4276/config.json +25 -0
  14. run-2/checkpoint-4276/model.safetensors +3 -0
  15. run-2/checkpoint-4276/optimizer.pt +3 -0
  16. run-2/checkpoint-4276/rng_state.pth +3 -0
  17. run-2/checkpoint-4276/scheduler.pt +3 -0
  18. run-2/checkpoint-4276/special_tokens_map.json +7 -0
  19. run-2/checkpoint-4276/tokenizer.json +0 -0
  20. run-2/checkpoint-4276/tokenizer_config.json +55 -0
  21. run-2/checkpoint-4276/trainer_state.json +100 -0
  22. run-2/checkpoint-4276/training_args.bin +3 -0
  23. run-2/checkpoint-4276/vocab.txt +0 -0
  24. runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711160551.d179836e26c8.903.6 +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:e0264745ed8cb93a9ba05fa315c92190f24a1e5993186e5f31190e5f0632d679
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c6519ba5d4b580f2f52064b42edbf44871eadd24a17a02fe9f61d11184818f
3
  size 267832560
run-2/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f26a0f89839d24c479c73ee3eb1e3ce7fb81ca91ea3e5e2aa211bec368354b
3
+ size 267832560
run-2/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6992259579c6bb158a21fc76966c32b8c99aa3fdc7bab38f7f6b8ccd417c898f
3
+ size 535727290
run-2/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95071fb065ad15a3f4c8376ad08b23f3a428062300f26d47bc02e618d17bf8ba
3
+ size 14244
run-2/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cceb79aa4afbbda9fd9cb81c4610ef19c01d5c7083ae51135cd5145651a1128e
3
+ size 1064
run-2/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-2/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06558874629318973,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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
+ "grad_norm": 4.178102493286133,
14
+ "learning_rate": 1.1439160576989274e-06,
15
+ "loss": 0.6208,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.47,
20
+ "grad_norm": 4.493968963623047,
21
+ "learning_rate": 9.924441220926076e-07,
22
+ "loss": 0.5768,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7,
27
+ "grad_norm": 4.8737568855285645,
28
+ "learning_rate": 8.409721864862877e-07,
29
+ "loss": 0.5989,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.94,
34
+ "grad_norm": 4.4068603515625,
35
+ "learning_rate": 6.895002508799678e-07,
36
+ "loss": 0.5716,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 0.5632339715957642,
42
+ "eval_matthews_correlation": 0.06558874629318973,
43
+ "eval_runtime": 0.736,
44
+ "eval_samples_per_second": 1417.115,
45
+ "eval_steps_per_second": 89.674,
46
+ "step": 2138
47
+ }
48
+ ],
49
+ "logging_steps": 500,
50
+ "max_steps": 4276,
51
+ "num_input_tokens_seen": 0,
52
+ "num_train_epochs": 2,
53
+ "save_steps": 500,
54
+ "total_flos": 32461756981584.0,
55
+ "train_batch_size": 4,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 1.2953879933052473e-06,
59
+ "num_train_epochs": 2,
60
+ "per_device_train_batch_size": 4,
61
+ "seed": 39
62
+ }
63
+ }
run-2/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aeeb2d1e31d4b18883a91a955a533ec57f95112ef6d2da3d527674942708b70
3
+ size 5048
run-2/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c6519ba5d4b580f2f52064b42edbf44871eadd24a17a02fe9f61d11184818f
3
+ size 267832560
run-2/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6528826ba4914f8ef439e5ee605dbaf2bfba961678d693da6720035e7bc1fb05
3
+ size 535727290
run-2/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4e1213f15b10af0d16191bbee6d106c5cda897e7d786fbdf4727cb132b2232
3
+ size 14244
run-2/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3715de86b8baccf76e9a6ffab228d3493b16d3a0b559fea810a290c2f997f9af
3
+ size 1064
run-2/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-2/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2045620264226157,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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
+ "grad_norm": 4.178102493286133,
14
+ "learning_rate": 1.1439160576989274e-06,
15
+ "loss": 0.6208,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.47,
20
+ "grad_norm": 4.493968963623047,
21
+ "learning_rate": 9.924441220926076e-07,
22
+ "loss": 0.5768,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.7,
27
+ "grad_norm": 4.8737568855285645,
28
+ "learning_rate": 8.409721864862877e-07,
29
+ "loss": 0.5989,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.94,
34
+ "grad_norm": 4.4068603515625,
35
+ "learning_rate": 6.895002508799678e-07,
36
+ "loss": 0.5716,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_loss": 0.5632339715957642,
42
+ "eval_matthews_correlation": 0.06558874629318973,
43
+ "eval_runtime": 0.736,
44
+ "eval_samples_per_second": 1417.115,
45
+ "eval_steps_per_second": 89.674,
46
+ "step": 2138
47
+ },
48
+ {
49
+ "epoch": 1.17,
50
+ "grad_norm": 6.09544038772583,
51
+ "learning_rate": 5.380283152736481e-07,
52
+ "loss": 0.5432,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.4,
57
+ "grad_norm": 25.411874771118164,
58
+ "learning_rate": 3.865563796673282e-07,
59
+ "loss": 0.5308,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 1.64,
64
+ "grad_norm": 18.580930709838867,
65
+ "learning_rate": 2.3508444406100838e-07,
66
+ "loss": 0.5388,
67
+ "step": 3500
68
+ },
69
+ {
70
+ "epoch": 1.87,
71
+ "grad_norm": 6.283896446228027,
72
+ "learning_rate": 8.361250845468855e-08,
73
+ "loss": 0.5153,
74
+ "step": 4000
75
+ },
76
+ {
77
+ "epoch": 2.0,
78
+ "eval_loss": 0.5738433003425598,
79
+ "eval_matthews_correlation": 0.2045620264226157,
80
+ "eval_runtime": 0.7468,
81
+ "eval_samples_per_second": 1396.66,
82
+ "eval_steps_per_second": 88.379,
83
+ "step": 4276
84
+ }
85
+ ],
86
+ "logging_steps": 500,
87
+ "max_steps": 4276,
88
+ "num_input_tokens_seen": 0,
89
+ "num_train_epochs": 2,
90
+ "save_steps": 500,
91
+ "total_flos": 65128941921240.0,
92
+ "train_batch_size": 4,
93
+ "trial_name": null,
94
+ "trial_params": {
95
+ "learning_rate": 1.2953879933052473e-06,
96
+ "num_train_epochs": 2,
97
+ "per_device_train_batch_size": 4,
98
+ "seed": 39
99
+ }
100
+ }
run-2/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aeeb2d1e31d4b18883a91a955a533ec57f95112ef6d2da3d527674942708b70
3
+ size 5048
run-2/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711160551.d179836e26c8.903.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b3e27df10563fa8f5223c1cf131f092ddcd52b22e79c1aaf676c7a8612fa30
3
+ size 7318
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc31c849e6487c8907123e1d6a6f0f93bddeccd5c1dc35d3d931b06422622412
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aeeb2d1e31d4b18883a91a955a533ec57f95112ef6d2da3d527674942708b70
3
  size 5048