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
f5e5696
•
1 Parent(s): 4141c3e

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. model.safetensors +1 -1
  2. run-6/checkpoint-268/config.json +25 -0
  3. run-6/checkpoint-268/model.safetensors +3 -0
  4. run-6/checkpoint-268/optimizer.pt +3 -0
  5. run-6/checkpoint-268/rng_state.pth +3 -0
  6. run-6/checkpoint-268/scheduler.pt +3 -0
  7. run-6/checkpoint-268/special_tokens_map.json +7 -0
  8. run-6/checkpoint-268/tokenizer.json +0 -0
  9. run-6/checkpoint-268/tokenizer_config.json +55 -0
  10. run-6/checkpoint-268/trainer_state.json +44 -0
  11. run-6/checkpoint-268/training_args.bin +3 -0
  12. run-6/checkpoint-268/vocab.txt +0 -0
  13. run-9/checkpoint-535/config.json +25 -0
  14. run-9/checkpoint-535/model.safetensors +3 -0
  15. run-9/checkpoint-535/optimizer.pt +3 -0
  16. run-9/checkpoint-535/rng_state.pth +3 -0
  17. run-9/checkpoint-535/scheduler.pt +3 -0
  18. run-9/checkpoint-535/special_tokens_map.json +7 -0
  19. run-9/checkpoint-535/tokenizer.json +0 -0
  20. run-9/checkpoint-535/tokenizer_config.json +55 -0
  21. run-9/checkpoint-535/trainer_state.json +42 -0
  22. run-9/checkpoint-535/training_args.bin +3 -0
  23. run-9/checkpoint-535/vocab.txt +0 -0
  24. runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161324.d179836e26c8.903.11 +3 -0
  25. runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161347.d179836e26c8.903.12 +3 -0
  26. runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161368.d179836e26c8.903.13 +3 -0
  27. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dd71b8c0b74767d522e813d7e177828bb7110f60a2e3fcde82478f0ef95e3e7
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f00392d84c44d6d3cd0c5443b702d3535d0a27e53a0a2cadd477a7ec4f0074
3
  size 267832560
run-6/checkpoint-268/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-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362856a7002a57f4e8e57605df46178f6e6a9b7bc7efd3fd6be6b3af6bef993a
3
+ size 267832560
run-6/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec707156d29af4d6ec49599eff57c7bc6bb58b48040444cf3b980ce47795a304
3
+ size 535727290
run-6/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9be7e0d36dddb54eaecfb0b77dc53cd069e477606d40da682f3bc5bf96dd61b
3
+ size 14244
run-6/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc702685ff975e88821319a16725d981e8d023e673225165fcafc77a42ce051f
3
+ size 1064
run-6/checkpoint-268/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-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-268/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-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5072784045554821,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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
+ "epoch": 2.0,
22
+ "eval_loss": 0.477949857711792,
23
+ "eval_matthews_correlation": 0.5072784045554821,
24
+ "eval_runtime": 0.8197,
25
+ "eval_samples_per_second": 1272.339,
26
+ "eval_steps_per_second": 80.512,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 268,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 3.3864170205221844e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 16
43
+ }
44
+ }
run-6/checkpoint-268/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-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-535/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-9/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f00392d84c44d6d3cd0c5443b702d3535d0a27e53a0a2cadd477a7ec4f0074
3
+ size 267832560
run-9/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48696b6330d0ec344d82c4a7459bca12b8190fa4101ba8bc0ba3be0fc8cd9d5
3
+ size 535727290
run-9/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb80725ff87b7d55bd86275350739d6bc1a93d01a7a8b93ce343a51c5edfaac
3
+ size 14244
run-9/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e832bb4be74798c9a163c3fb31d8c829ebf2da103698d67fc3b2e0f9ad0e080f
3
+ size 1064
run-9/checkpoint-535/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-9/checkpoint-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-535/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-9/checkpoint-535/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.40200223868227586,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "grad_norm": 4.314386367797852,
14
+ "learning_rate": 4.053427295916824e-06,
15
+ "loss": 0.5354,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.49596595764160156,
21
+ "eval_matthews_correlation": 0.40200223868227586,
22
+ "eval_runtime": 0.7307,
23
+ "eval_samples_per_second": 1427.454,
24
+ "eval_steps_per_second": 90.328,
25
+ "step": 535
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 535,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 1,
32
+ "save_steps": 500,
33
+ "total_flos": 149984142325152.0,
34
+ "train_batch_size": 16,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 6.195953152330003e-05,
38
+ "num_train_epochs": 1,
39
+ "per_device_train_batch_size": 16,
40
+ "seed": 39
41
+ }
42
+ }
run-9/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7261a8e1cec36613132455fb3188f5779eee7514cb299f8b48245a0771e51fd
3
+ size 5048
run-9/checkpoint-535/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.1711161324.d179836e26c8.903.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276bb4d00dd615b30b11f74e06ae3ad85e3d4f7029c355172a4afa42e815549e
3
+ size 4942
runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161347.d179836e26c8.903.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14dcc758b3014a50929cf34de7a2fadea85f659d8948201cbbca7b57888eec03
3
+ size 4941
runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161368.d179836e26c8.903.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd15d43ff96ad3ea79225300f4f33989bab71e890133f19bfbfa2c59f8bdd262
3
+ size 5506
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb80389a7fc088e5844ba718e7e18b53f00364a3051c518916518ff469150fda
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7261a8e1cec36613132455fb3188f5779eee7514cb299f8b48245a0771e51fd
3
  size 5048