zlfkrmnz commited on
Commit
8d7a6b4
·
verified ·
1 Parent(s): 5f8064a

Upload model files

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "Negative",
12
+ "1": "Notr",
13
+ "2": "Positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "Negative": 0,
19
+ "Notr": 1,
20
+ "Positive": 2
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.55.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 32000
35
+ }
label_mappings.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label2id": {
3
+ "Negative": 0,
4
+ "Notr": 1,
5
+ "Positive": 2
6
+ },
7
+ "id2label": {
8
+ "0": "Negative",
9
+ "1": "Notr",
10
+ "2": "Positive"
11
+ }
12
+ }
metrics.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 0.12734396755695343,
3
+ "eval_accuracy": 0.973818033289084,
4
+ "eval_precision": 0.9596881517623093,
5
+ "eval_recall": 0.948582581730769,
6
+ "eval_f1": 0.9539490963490337,
7
+ "eval_runtime": 54.0919,
8
+ "eval_samples_per_second": 905.219,
9
+ "eval_steps_per_second": 28.304,
10
+ "epoch": 3.0
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1643007f2633b6d45410fd5a26cacc5273ace5d1c82cd11dd72b906dc88843
3
+ size 442502140
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_len": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ede9b3ae96da85edabdf874b00b8522ff3d89c94032491b8045b494c532bbb
3
+ size 5280
training_args.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "./outputs",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": true,
6
+ "do_predict": false,
7
+ "eval_strategy": "epoch",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 16,
10
+ "per_device_eval_batch_size": 32,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 1,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 2e-05,
18
+ "weight_decay": 0.01,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.999,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 3,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "linear",
26
+ "lr_scheduler_kwargs": {},
27
+ "warmup_ratio": 0.0,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "./outputs/runs/Aug14_13-11-07_6d0676c186de",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": false,
35
+ "logging_steps": 50,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "epoch",
38
+ "save_steps": 500,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": null,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": false,
52
+ "fp16": true,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": [],
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": null,
65
+ "dataloader_num_workers": 0,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": null,
69
+ "disable_tqdm": false,
70
+ "remove_unused_columns": false,
71
+ "label_names": null,
72
+ "load_best_model_at_end": true,
73
+ "metric_for_best_model": "f1",
74
+ "greater_is_better": true,
75
+ "ignore_data_skip": false,
76
+ "fsdp": [],
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": {
79
+ "min_num_params": 0,
80
+ "xla": false,
81
+ "xla_fsdp_v2": false,
82
+ "xla_fsdp_grad_ckpt": false
83
+ },
84
+ "fsdp_transformer_layer_cls_to_wrap": null,
85
+ "accelerator_config": {
86
+ "split_batches": false,
87
+ "dispatch_batches": null,
88
+ "even_batches": true,
89
+ "use_seedable_sampler": true,
90
+ "non_blocking": false,
91
+ "gradient_accumulation_kwargs": null
92
+ },
93
+ "deepspeed": null,
94
+ "label_smoothing_factor": 0.0,
95
+ "optim": "adamw_torch",
96
+ "optim_args": null,
97
+ "adafactor": false,
98
+ "group_by_length": false,
99
+ "length_column_name": "length",
100
+ "report_to": [],
101
+ "ddp_find_unused_parameters": null,
102
+ "ddp_bucket_cap_mb": null,
103
+ "ddp_broadcast_buffers": null,
104
+ "dataloader_pin_memory": true,
105
+ "dataloader_persistent_workers": false,
106
+ "skip_memory_metrics": true,
107
+ "use_legacy_prediction_loop": false,
108
+ "push_to_hub": false,
109
+ "resume_from_checkpoint": null,
110
+ "hub_model_id": null,
111
+ "hub_strategy": "every_save",
112
+ "hub_token": "<HUB_TOKEN>",
113
+ "hub_private_repo": null,
114
+ "hub_always_push": false,
115
+ "hub_revision": null,
116
+ "gradient_checkpointing": false,
117
+ "gradient_checkpointing_kwargs": null,
118
+ "include_inputs_for_metrics": false,
119
+ "include_for_metrics": [],
120
+ "eval_do_concat_batches": true,
121
+ "fp16_backend": "auto",
122
+ "push_to_hub_model_id": null,
123
+ "push_to_hub_organization": null,
124
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
125
+ "mp_parameters": "",
126
+ "auto_find_batch_size": false,
127
+ "full_determinism": false,
128
+ "torchdynamo": null,
129
+ "ray_scope": "last",
130
+ "ddp_timeout": 1800,
131
+ "torch_compile": false,
132
+ "torch_compile_backend": null,
133
+ "torch_compile_mode": null,
134
+ "include_tokens_per_second": false,
135
+ "include_num_input_tokens_seen": false,
136
+ "neftune_noise_alpha": null,
137
+ "optim_target_modules": null,
138
+ "batch_eval_metrics": false,
139
+ "eval_on_start": false,
140
+ "use_liger_kernel": false,
141
+ "liger_kernel_config": null,
142
+ "eval_use_gather_object": false,
143
+ "average_tokens_across_devices": false
144
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff