Hugging Face's logo

ung30
/
sst2-BART-base

Safetensors
bart
Model card Files
xet
Community
ung30 commited on
Commit
4e6f93d
·
verified ·
1 Parent(s): ad3d509

Upload 9 files

Browse files
Files changed (9) hide show
  1. config.json +73 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. trainer_state.json +108 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartForSequenceClassification"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.1,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 768,
14
+ "decoder_attention_heads": 12,
15
+ "decoder_ffn_dim": 3072,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "early_stopping": true,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 2,
26
+ "forced_bos_token_id": 0,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "max_position_embeddings": 1024,
40
+ "model_type": "bart",
41
+ "no_repeat_ngram_size": 3,
42
+ "normalize_before": false,
43
+ "normalize_embedding": true,
44
+ "num_beams": 4,
45
+ "num_hidden_layers": 6,
46
+ "pad_token_id": 1,
47
+ "problem_type": "single_label_classification",
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.52.3",
71
+ "use_cache": true,
72
+ "vocab_size": 50265
73
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64101be3637a0ba7ce706df87649a31fc8a6e5478f6321fdf076fa94bd33667e
3
+ size 560080392
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "BartTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 21000,
3
+ "best_metric": 0.919884471379488,
4
+ "best_model_checkpoint": "./saved_best/sst2_BART-20000/full_text/checkpoint-21000",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 21000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 0.40724968910217285,
15
+ "learning_rate": 1.3334285714285714e-05,
16
+ "loss": 2.167,
17
+ "step": 7000
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.9023333333333333,
22
+ "eval_f1_macro": 0.9016989529876082,
23
+ "eval_f1_weighted": 0.9025202254683811,
24
+ "eval_loss": 1.5102022886276245,
25
+ "eval_runtime": 400.0393,
26
+ "eval_samples_per_second": 14.999,
27
+ "eval_steps_per_second": 7.499,
28
+ "step": 7000
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.08096525818109512,
33
+ "learning_rate": 6.667619047619049e-06,
34
+ "loss": 1.3183,
35
+ "step": 14000
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.916,
40
+ "eval_f1_macro": 0.9155205698472799,
41
+ "eval_f1_weighted": 0.9161824380227166,
42
+ "eval_loss": 1.3292620182037354,
43
+ "eval_runtime": 400.5613,
44
+ "eval_samples_per_second": 14.979,
45
+ "eval_steps_per_second": 7.489,
46
+ "step": 14000
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "grad_norm": 0.19997699558734894,
51
+ "learning_rate": 9.523809523809524e-10,
52
+ "loss": 0.8244,
53
+ "step": 21000
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "eval_accuracy": 0.921,
58
+ "eval_f1_macro": 0.919884471379488,
59
+ "eval_f1_weighted": 0.9208676491467189,
60
+ "eval_loss": 1.2811408042907715,
61
+ "eval_runtime": 399.4772,
62
+ "eval_samples_per_second": 15.02,
63
+ "eval_steps_per_second": 7.51,
64
+ "step": 21000
65
+ },
66
+ {
67
+ "epoch": 3.0,
68
+ "step": 21000,
69
+ "total_flos": 1559792198160000.0,
70
+ "train_loss": 1.4365767531622025,
71
+ "train_runtime": 5688.3135,
72
+ "train_samples_per_second": 7.384,
73
+ "train_steps_per_second": 3.692
74
+ },
75
+ {
76
+ "epoch": 3.0,
77
+ "eval_accuracy": 0.921,
78
+ "eval_f1_macro": 0.919884471379488,
79
+ "eval_f1_weighted": 0.9208676491467189,
80
+ "eval_loss": 1.2811408042907715,
81
+ "eval_runtime": 399.7755,
82
+ "eval_samples_per_second": 15.008,
83
+ "eval_steps_per_second": 7.504,
84
+ "step": 21000
85
+ }
86
+ ],
87
+ "logging_steps": 10,
88
+ "max_steps": 21000,
89
+ "num_input_tokens_seen": 0,
90
+ "num_train_epochs": 3,
91
+ "save_steps": 500,
92
+ "stateful_callbacks": {
93
+ "TrainerControl": {
94
+ "args": {
95
+ "should_epoch_stop": false,
96
+ "should_evaluate": false,
97
+ "should_log": false,
98
+ "should_save": true,
99
+ "should_training_stop": true
100
+ },
101
+ "attributes": {}
102
+ }
103
+ },
104
+ "total_flos": 1559792198160000.0,
105
+ "train_batch_size": 2,
106
+ "trial_name": null,
107
+ "trial_params": null
108
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119ad46c4bf865b4d20a1afa13617f0a08ef6796bc91c6fe5342585191a3b559
3
+ size 5649
vocab.json ADDED
The diff for this file is too large to render. See raw diff