amodaresi commited on
Commit
4dd37fb
1 Parent(s): 724c0b4

initial model upload

Browse files
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - sst2
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: '42'
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: SST2
19
+ type: glue
20
+ args: sst2
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9254587155963303
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # 42
31
+
32
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the SST2 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.3109
35
+ - Accuracy: 0.9255
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 3e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - distributed_type: not_parallel
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 5
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 2105 | 0.2167 | 0.9232 |
68
+ | 0.2049 | 2.0 | 4210 | 0.2375 | 0.9278 |
69
+ | 0.123 | 3.0 | 6315 | 0.2636 | 0.9243 |
70
+ | 0.0839 | 4.0 | 8420 | 0.2865 | 0.9243 |
71
+ | 0.058 | 5.0 | 10525 | 0.3109 | 0.9255 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.17.0
77
+ - Pytorch 1.10.0+cu113
78
+ - Datasets 2.7.1
79
+ - Tokenizers 0.11.6
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.11400984666692955,
4
+ "train_runtime": 1175.3679,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 286.502,
7
+ "train_steps_per_second": 8.955,
8
+ "validation_accuracy": 0.9254587155963303,
9
+ "validation_loss": 0.31086066365242004,
10
+ "validation_runtime": 1.4824,
11
+ "validation_samples": 872,
12
+ "validation_samples_per_second": 588.248,
13
+ "validation_steps_per_second": 18.889
14
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "sst2",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "negative",
15
+ "1": "positive"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "negative": 0,
21
+ "positive": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.17.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8f72f9faf75a8974600ed89fcfb19eeca26a537c5511166d2e26d4fe02781b
3
+ size 1340739309
run_arguments.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name_or_path": "bert-large-uncased",
3
+ "task_name": "sst2",
4
+ "output_dir": "./output/bert-large/sst2/0001/42/",
5
+ "learning_rate": 3e-05,
6
+ "num_train_epochs": 5,
7
+ "per_device_eval_batch_size": 32,
8
+ "per_device_train_batch_size": 32,
9
+ "weight_decay": 0.1,
10
+ "seed": 42,
11
+ "warmup_steps": 0,
12
+ "do_train": true,
13
+ "do_eval": true,
14
+ "do_predict": false,
15
+ "pad_to_max_length": false,
16
+ "max_seq_length": 128,
17
+ "report_to": [],
18
+ "save_strategy": "no",
19
+ "evaluation_strategy": "epoch",
20
+ "logging_steps": 2500,
21
+ "use_fast_tokenizer": true,
22
+ "group_by_length": true,
23
+ "save_training_dynamics": false,
24
+ "save_training_dynamics_after_epoch": false
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased", "tokenizer_class": "BertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.11400984666692955,
4
+ "train_runtime": 1175.3679,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 286.502,
7
+ "train_steps_per_second": 8.955
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 10525,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.9231651376146789,
13
+ "eval_loss": 0.21673926711082458,
14
+ "eval_runtime": 1.4821,
15
+ "eval_samples_per_second": 588.353,
16
+ "eval_steps_per_second": 18.892,
17
+ "step": 2105
18
+ },
19
+ {
20
+ "epoch": 1.19,
21
+ "learning_rate": 2.2874109263657958e-05,
22
+ "loss": 0.2049,
23
+ "step": 2500
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_accuracy": 0.9277522935779816,
28
+ "eval_loss": 0.23751771450042725,
29
+ "eval_runtime": 1.48,
30
+ "eval_samples_per_second": 589.207,
31
+ "eval_steps_per_second": 18.919,
32
+ "step": 4210
33
+ },
34
+ {
35
+ "epoch": 2.38,
36
+ "learning_rate": 1.5748218527315915e-05,
37
+ "loss": 0.123,
38
+ "step": 5000
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "eval_accuracy": 0.9243119266055045,
43
+ "eval_loss": 0.2635619044303894,
44
+ "eval_runtime": 1.4812,
45
+ "eval_samples_per_second": 588.699,
46
+ "eval_steps_per_second": 18.903,
47
+ "step": 6315
48
+ },
49
+ {
50
+ "epoch": 3.56,
51
+ "learning_rate": 8.622327790973872e-06,
52
+ "loss": 0.0839,
53
+ "step": 7500
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_accuracy": 0.9243119266055045,
58
+ "eval_loss": 0.28654733300209045,
59
+ "eval_runtime": 1.4787,
60
+ "eval_samples_per_second": 589.696,
61
+ "eval_steps_per_second": 18.935,
62
+ "step": 8420
63
+ },
64
+ {
65
+ "epoch": 4.75,
66
+ "learning_rate": 1.496437054631829e-06,
67
+ "loss": 0.058,
68
+ "step": 10000
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy": 0.9254587155963303,
73
+ "eval_loss": 0.31086066365242004,
74
+ "eval_runtime": 1.4857,
75
+ "eval_samples_per_second": 586.933,
76
+ "eval_steps_per_second": 18.846,
77
+ "step": 10525
78
+ },
79
+ {
80
+ "epoch": 5.0,
81
+ "step": 10525,
82
+ "total_flos": 8559638497356828.0,
83
+ "train_loss": 0.11400984666692955,
84
+ "train_runtime": 1175.3679,
85
+ "train_samples_per_second": 286.502,
86
+ "train_steps_per_second": 8.955
87
+ }
88
+ ],
89
+ "max_steps": 10525,
90
+ "num_train_epochs": 5,
91
+ "total_flos": 8559638497356828.0,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8541b1339e53d1240efed18ebe6a2b59474d8e9e899771c348cb0008415d92ef
3
+ size 3119
validation_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "validation_accuracy": 0.9254587155963303,
4
+ "validation_loss": 0.31086066365242004,
5
+ "validation_runtime": 1.4824,
6
+ "validation_samples": 872,
7
+ "validation_samples_per_second": 588.248,
8
+ "validation_steps_per_second": 18.889
9
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff