Hugging Face's logo

richardchiu
/
work1_AIA_LLM_B_132001

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
sft
text-generation-inference
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Metrics Community
richardchiu commited on
Commit
4141c3e
•
1 Parent(s): 71ef7a7

Training in progress, epoch 1

Browse files
Files changed (25) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-1340/config.json +25 -0
  3. run-5/checkpoint-1340/model.safetensors +3 -0
  4. run-5/checkpoint-1340/optimizer.pt +3 -0
  5. run-5/checkpoint-1340/rng_state.pth +3 -0
  6. run-5/checkpoint-1340/scheduler.pt +3 -0
  7. run-5/checkpoint-1340/special_tokens_map.json +7 -0
  8. run-5/checkpoint-1340/tokenizer.json +0 -0
  9. run-5/checkpoint-1340/tokenizer_config.json +55 -0
  10. run-5/checkpoint-1340/trainer_state.json +85 -0
  11. run-5/checkpoint-1340/training_args.bin +3 -0
  12. run-5/checkpoint-1340/vocab.txt +0 -0
  13. run-6/checkpoint-134/config.json +25 -0
  14. run-6/checkpoint-134/model.safetensors +3 -0
  15. run-6/checkpoint-134/optimizer.pt +3 -0
  16. run-6/checkpoint-134/rng_state.pth +3 -0
  17. run-6/checkpoint-134/scheduler.pt +3 -0
  18. run-6/checkpoint-134/special_tokens_map.json +7 -0
  19. run-6/checkpoint-134/tokenizer.json +0 -0
  20. run-6/checkpoint-134/tokenizer_config.json +55 -0
  21. run-6/checkpoint-134/trainer_state.json +35 -0
  22. run-6/checkpoint-134/training_args.bin +3 -0
  23. run-6/checkpoint-134/vocab.txt +0 -0
  24. runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161215.d179836e26c8.903.10 +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:a0ec1375d7819609f06105f3870abc2a54172d9a7099016fc1da269afa7a977a
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd71b8c0b74767d522e813d7e177828bb7110f60a2e3fcde82478f0ef95e3e7
3
  size 267832560
run-5/checkpoint-1340/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-5/checkpoint-1340/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6924014bf59ea78b5fb2877725379b58387c390575cf05d8b2214c1e897a754
3
+ size 267832560
run-5/checkpoint-1340/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc05456e26f1c50f13a49163aca978e2cf38efaf56e2405384b7983ecfd60962
3
+ size 535727290
run-5/checkpoint-1340/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4588875a5fbed58e929a85f3d56b0d55e9bcd483ab055f6f849f6d129245a124
3
+ size 14244
run-5/checkpoint-1340/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbadd4653547d16ad332105d7db088fc9b2f85e5e30b0e89a4123fc4c3f335e4
3
+ size 1064
run-5/checkpoint-1340/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-5/checkpoint-1340/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1340/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-5/checkpoint-1340/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5115958993985192,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1340",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1340,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.46541309356689453,
14
+ "eval_matthews_correlation": 0.4611631351812362,
15
+ "eval_runtime": 0.7349,
16
+ "eval_samples_per_second": 1419.226,
17
+ "eval_steps_per_second": 89.807,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 5.322132587432861,
23
+ "learning_rate": 2.8926577590888014e-05,
24
+ "loss": 0.415,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.5235322117805481,
30
+ "eval_matthews_correlation": 0.48584699342231225,
31
+ "eval_runtime": 0.8286,
32
+ "eval_samples_per_second": 1258.804,
33
+ "eval_steps_per_second": 79.656,
34
+ "step": 536
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.6811769604682922,
39
+ "eval_matthews_correlation": 0.4886634303966225,
40
+ "eval_runtime": 1.1682,
41
+ "eval_samples_per_second": 892.827,
42
+ "eval_steps_per_second": 56.497,
43
+ "step": 804
44
+ },
45
+ {
46
+ "epoch": 3.73,
47
+ "grad_norm": 5.797658920288086,
48
+ "learning_rate": 1.1708376643930863e-05,
49
+ "loss": 0.1523,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_loss": 0.8018879294395447,
55
+ "eval_matthews_correlation": 0.5029119946692125,
56
+ "eval_runtime": 0.7895,
57
+ "eval_samples_per_second": 1321.02,
58
+ "eval_steps_per_second": 83.593,
59
+ "step": 1072
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_loss": 0.930472731590271,
64
+ "eval_matthews_correlation": 0.5115958993985192,
65
+ "eval_runtime": 1.1184,
66
+ "eval_samples_per_second": 932.607,
67
+ "eval_steps_per_second": 59.014,
68
+ "step": 1340
69
+ }
70
+ ],
71
+ "logging_steps": 500,
72
+ "max_steps": 1340,
73
+ "num_input_tokens_seen": 0,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "total_flos": 191380204405152.0,
77
+ "train_batch_size": 32,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "learning_rate": 4.6144778537845165e-05,
81
+ "num_train_epochs": 5,
82
+ "per_device_train_batch_size": 32,
83
+ "seed": 3
84
+ }
85
+ }
run-5/checkpoint-1340/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb396c880ed21cbe5386566eb59cb1266f1baa96469ad33b08f5bdf8bfd36bd0
3
+ size 5048
run-5/checkpoint-1340/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-134/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-6/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd71b8c0b74767d522e813d7e177828bb7110f60a2e3fcde82478f0ef95e3e7
3
+ size 267832560
run-6/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348bf351569cfd040213112990135d920b3099006c58db7e1ebe193809c3c266
3
+ size 535727290
run-6/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67de1495d89bad1bf433ea074faeed5cad69203839c69144ec9b9dd8e5891ce0
3
+ size 14244
run-6/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c228f60e941e071784831a9788fb9a8d1c897654908ed7aa836107b8a9f698d6
3
+ size 1064
run-6/checkpoint-134/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-6/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-134/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-6/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4751366513569292,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.4657443165779114,
14
+ "eval_matthews_correlation": 0.4751366513569292,
15
+ "eval_runtime": 0.7348,
16
+ "eval_samples_per_second": 1419.5,
17
+ "eval_steps_per_second": 89.825,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 268,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 3.3864170205221844e-05,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 16
34
+ }
35
+ }
run-6/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb80389a7fc088e5844ba718e7e18b53f00364a3051c518916518ff469150fda
3
+ size 5048
run-6/checkpoint-134/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.1711161215.d179836e26c8.903.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b906996a25d9d0d72a59bbe4c225d5224638780e7c13e7c1a50bcc07d050e5
3
+ size 5631
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb396c880ed21cbe5386566eb59cb1266f1baa96469ad33b08f5bdf8bfd36bd0
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb80389a7fc088e5844ba718e7e18b53f00364a3051c518916518ff469150fda
3
  size 5048