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
9b19e98
·
1 Parent(s): 72788ee

Training in progress, epoch 2

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-268/config.json +25 -0
  3. run-1/checkpoint-268/model.safetensors +3 -0
  4. run-1/checkpoint-268/optimizer.pt +3 -0
  5. run-1/checkpoint-268/rng_state.pth +3 -0
  6. run-1/checkpoint-268/scheduler.pt +3 -0
  7. run-1/checkpoint-268/special_tokens_map.json +7 -0
  8. run-1/checkpoint-268/tokenizer.json +0 -0
  9. run-1/checkpoint-268/tokenizer_config.json +55 -0
  10. run-1/checkpoint-268/trainer_state.json +44 -0
  11. run-1/checkpoint-268/training_args.bin +3 -0
  12. run-1/checkpoint-268/vocab.txt +0 -0
  13. run-1/checkpoint-402/config.json +25 -0
  14. run-1/checkpoint-402/model.safetensors +3 -0
  15. run-1/checkpoint-402/optimizer.pt +3 -0
  16. run-1/checkpoint-402/rng_state.pth +3 -0
  17. run-1/checkpoint-402/scheduler.pt +3 -0
  18. run-1/checkpoint-402/special_tokens_map.json +7 -0
  19. run-1/checkpoint-402/tokenizer.json +0 -0
  20. run-1/checkpoint-402/tokenizer_config.json +55 -0
  21. run-1/checkpoint-402/trainer_state.json +53 -0
  22. run-1/checkpoint-402/training_args.bin +3 -0
  23. run-1/checkpoint-402/vocab.txt +0 -0
  24. run-2/checkpoint-2138/config.json +25 -0
  25. run-2/checkpoint-2138/model.safetensors +3 -0
  26. run-2/checkpoint-2138/optimizer.pt +3 -0
  27. run-2/checkpoint-2138/rng_state.pth +3 -0
  28. run-2/checkpoint-2138/scheduler.pt +3 -0
  29. run-2/checkpoint-2138/special_tokens_map.json +7 -0
  30. run-2/checkpoint-2138/tokenizer.json +0 -0
  31. run-2/checkpoint-2138/tokenizer_config.json +55 -0
  32. run-2/checkpoint-2138/trainer_state.json +59 -0
  33. run-2/checkpoint-2138/training_args.bin +3 -0
  34. run-2/checkpoint-2138/vocab.txt +0 -0
  35. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298679.04248f4b0c3a.492.3 +2 -2
  36. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298770.04248f4b0c3a.492.4 +3 -0
  37. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ff9f6968410a06a7e54fed912c3823c6e302e93856d594b0391906d3fcc1aae
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb37994c8d195c3403ae005a1dbdf662d7da0433fc507c766712b75a4a073113
3
  size 267832560
run-1/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35e7bcb0042a1532ebe6084ae646b96a1fbd07553aee9b1879124316e6df876
3
+ size 267832560
run-1/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99728e78ca7fc311d488644c60bb050bc05cd8bea5c9d108fe7406d7b4c21627
3
+ size 535727290
run-1/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a387a70985a9d5ddb23665a6eba8dcab8fe97931f627799da68ebbabc1450185
3
+ size 14244
run-1/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4536bda8851b0928bb454e014a3f5ae1fe099e60bfffc09ea2573727cfded89
3
+ size 1064
run-1/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-1/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5147088719382571,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.47572973370552063,
14
+ "eval_matthews_correlation": 0.44075455043157863,
15
+ "eval_runtime": 0.7472,
16
+ "eval_samples_per_second": 1395.808,
17
+ "eval_steps_per_second": 88.325,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4667774438858032,
23
+ "eval_matthews_correlation": 0.5147088719382571,
24
+ "eval_runtime": 1.8072,
25
+ "eval_samples_per_second": 577.142,
26
+ "eval_steps_per_second": 36.521,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 402,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 6.238111577485738e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 5
43
+ }
44
+ }
run-1/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e50c6849763306314de124bc4b6d43aafce6a6fe2ad2c143497ab357b26a273
3
+ size 4792
run-1/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-402/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-1/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fe24e77dd0840e339eeea7b6354b6970852d52916c9a002a2342b1e0d69ac5
3
+ size 267832560
run-1/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0ba2b4cbc756864bb2c9dd44d828b6028e8181dc3b22ed6be564cf17ac73fa
3
+ size 535727290
run-1/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f35dd237e371b6c0bbc9d6320379a900c883423b43835ff0337cf152f5f897
3
+ size 14244
run-1/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ac101175951dcc13d763f327e177d2b4f57cc41759edb38d83cbf69dc30d2c
3
+ size 1064
run-1/checkpoint-402/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-1/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-402/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-1/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5147088719382571,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.47572973370552063,
14
+ "eval_matthews_correlation": 0.44075455043157863,
15
+ "eval_runtime": 0.7472,
16
+ "eval_samples_per_second": 1395.808,
17
+ "eval_steps_per_second": 88.325,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4667774438858032,
23
+ "eval_matthews_correlation": 0.5147088719382571,
24
+ "eval_runtime": 1.8072,
25
+ "eval_samples_per_second": 577.142,
26
+ "eval_steps_per_second": 36.521,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.570951521396637,
32
+ "eval_matthews_correlation": 0.5075813582663956,
33
+ "eval_runtime": 1.1406,
34
+ "eval_samples_per_second": 914.446,
35
+ "eval_steps_per_second": 57.865,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 402,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 6.238111577485738e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 5
52
+ }
53
+ }
run-1/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e50c6849763306314de124bc4b6d43aafce6a6fe2ad2c143497ab357b26a273
3
+ size 4792
run-1/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "4.36.2",
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 sha256:85846c16c98e80ebef8a22052010fcba95456f90a765a3e1a4ee1397f0d779d1
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 sha256:40490a0b2bf74f13f68e8dce5ac9c5c53bca94a8373be87e8bf92db051c564b0
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 sha256:5008a6b97f7f941a202ea9000ec91099bbc523c9bc2122970f9599146b56306f
3
+ size 14308
run-2/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f42eabfc9dabf0fa93654ddfb3fe7fc336d66e42f676ec070126162c886a9a5
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.16979966395795365,
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
+ "learning_rate": 5.6188127124741755e-05,
14
+ "loss": 0.6368,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 5.269904819250494e-05,
20
+ "loss": 0.6054,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 4.920996926026812e-05,
26
+ "loss": 0.6131,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 4.57208903280313e-05,
32
+ "loss": 0.5971,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.6043549180030823,
38
+ "eval_matthews_correlation": 0.16979966395795365,
39
+ "eval_runtime": 0.8177,
40
+ "eval_samples_per_second": 1275.601,
41
+ "eval_steps_per_second": 80.719,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 8552,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 32693574929232.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 5.967720605697858e-05,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 37
58
+ }
59
+ }
run-2/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cd2fef8507de0b6ec4fc6f0e972dd20ee83952ed9d6116f7f100b26d2a1eca
3
+ size 4792
run-2/checkpoint-2138/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.1703298679.04248f4b0c3a.492.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f4989fa55602dcc148981a83338cd8ba489725cc15a33dbc66b50cdc9c9c1d9
3
- size 5020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3157d7c809f10cf10ccae23dec8f84b2981be5687d2d179cf9845e3d7aba7d07
3
+ size 5709
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298770.04248f4b0c3a.492.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b9ac68f93d6f2a706e457e18bb618aa30393fc441f2d4b5c13b2e9b9058cc9
3
+ size 6590
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e50c6849763306314de124bc4b6d43aafce6a6fe2ad2c143497ab357b26a273
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cd2fef8507de0b6ec4fc6f0e972dd20ee83952ed9d6116f7f100b26d2a1eca
3
  size 4792