lnewbould commited on
Commit
21b3b0f
·
verified ·
1 Parent(s): 2dd8abe

Training in progress, step 21

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a70896cda70c39157466e77a386e43d614d7340d26d1719e4aa7130a3a66c35
3
  size 263187752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ed7fd3654d1517d69911b4aebd59663bcf1eb00b666ccd8f51289dea96ae92
3
  size 263187752
run-1/checkpoint-21/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
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
+ "id2label": {
12
+ "0": "business",
13
+ "1": "civil-law",
14
+ "2": "constitutional-law",
15
+ "3": "contract",
16
+ "4": "contract-law",
17
+ "5": "copyright",
18
+ "6": "criminal-law",
19
+ "7": "employment",
20
+ "8": "intellectual-property",
21
+ "9": "internet",
22
+ "10": "liability",
23
+ "11": "licensing",
24
+ "12": "privacy",
25
+ "13": "software",
26
+ "14": "tax-law",
27
+ "15": "trademark"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "label2id": {
31
+ "business": 0,
32
+ "civil-law": 1,
33
+ "constitutional-law": 2,
34
+ "contract": 3,
35
+ "contract-law": 4,
36
+ "copyright": 5,
37
+ "criminal-law": 6,
38
+ "employment": 7,
39
+ "intellectual-property": 8,
40
+ "internet": 9,
41
+ "liability": 10,
42
+ "licensing": 11,
43
+ "privacy": 12,
44
+ "software": 13,
45
+ "tax-law": 14,
46
+ "trademark": 15
47
+ },
48
+ "max_position_embeddings": 512,
49
+ "model_type": "distilbert",
50
+ "n_heads": 12,
51
+ "n_layers": 6,
52
+ "output_past": true,
53
+ "pad_token_id": 0,
54
+ "problem_type": "single_label_classification",
55
+ "qa_dropout": 0.1,
56
+ "seq_classif_dropout": 0.2,
57
+ "sinusoidal_pos_embds": false,
58
+ "tie_weights_": true,
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.47.1",
61
+ "vocab_size": 28996
62
+ }
run-1/checkpoint-21/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ed7fd3654d1517d69911b4aebd59663bcf1eb00b666ccd8f51289dea96ae92
3
+ size 263187752
run-1/checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a19c46bf730e8c8a85a69354525210bc9950676d556e1d6165d47c1bd33572
3
+ size 526434810
run-1/checkpoint-21/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498398c79f2840c046c9db2b90678aeeff8b99a5e51751efba232bb460710449
3
+ size 13990
run-1/checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbab0b0745c1d2508d0200df9d4c6099b9b1dca8bce8dd4c3bacc32401661290
3
+ size 1064
run-1/checkpoint-21/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-21/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-21/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-1/checkpoint-21/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 21,
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_accuracy": 0.32,
14
+ "eval_loss": 2.6822216510772705,
15
+ "eval_runtime": 14.9433,
16
+ "eval_samples_per_second": 3.346,
17
+ "eval_steps_per_second": 0.468,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.32,
23
+ "eval_loss": 2.655679702758789,
24
+ "eval_runtime": 15.5155,
25
+ "eval_samples_per_second": 3.223,
26
+ "eval_steps_per_second": 0.451,
27
+ "step": 14
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 21,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": true
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 1.2936496217408461e-05,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 8,
54
+ "weight_decay": 0.023847976964843053
55
+ }
56
+ }
run-1/checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e44bca4a59239e4a7200c30ef6b3e2b07a901f394fab524d0eccacbf6749a9e
3
+ size 5240
run-1/checkpoint-21/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1ed3819cb2fe27bc2256360d46825e1851f5dc0f656a064e111a2321bc7183d
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e44bca4a59239e4a7200c30ef6b3e2b07a901f394fab524d0eccacbf6749a9e
3
  size 5240