Alireza1044 commited on
Commit
e406771
1 Parent(s): f216a9c
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ model_index:
12
+ - name: sst2
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: GLUE SST2
19
+ type: glue
20
+ args: sst2
21
+ metric:
22
+ name: Accuracy
23
+ type: accuracy
24
+ value: 0.9231651376146789
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
+ # sst2
31
+
32
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE SST2 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.3808
35
+ - Accuracy: 0.9232
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: 1e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 4.0
61
+
62
+ ### Training results
63
+
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.9.0
69
+ - Pytorch 1.9.0+cu102
70
+ - Datasets 1.10.2
71
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9231651376146789,
4
+ "eval_loss": 0.3807859718799591,
5
+ "eval_runtime": 8.172,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 106.705,
8
+ "eval_steps_per_second": 13.338,
9
+ "train_loss": 0.14146648778485005,
10
+ "train_runtime": 6028.0345,
11
+ "train_samples": 67349,
12
+ "train_samples_per_second": 44.691,
13
+ "train_steps_per_second": 1.397
14
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "finetuning_task": "sst2",
13
+ "gap_size": 0,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_dropout_prob": 0,
16
+ "hidden_size": 768,
17
+ "initializer_range": 0.02,
18
+ "inner_group_num": 1,
19
+ "intermediate_size": 3072,
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "albert",
23
+ "net_structure_type": 0,
24
+ "num_attention_heads": 12,
25
+ "num_hidden_groups": 1,
26
+ "num_hidden_layers": 12,
27
+ "num_memory_blocks": 0,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.9.0",
33
+ "type_vocab_size": 2,
34
+ "vocab_size": 30000
35
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9231651376146789,
4
+ "eval_loss": 0.3807859718799591,
5
+ "eval_runtime": 8.172,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 106.705,
8
+ "eval_steps_per_second": 13.338
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c8d97db2205a5d6748479b105db67fe1c56466d78eb652d77005387f602900
3
+ size 46755537
runs/Jul26_12-21-38_578c7831d7ba/1627302117.7817998/events.out.tfevents.1627302117.578c7831d7ba.805.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21bbb4b3b6e2eb5f4709437218c693f53720cd8bef9c0f25829cff58af7e70b
3
+ size 4167
runs/Jul26_12-21-38_578c7831d7ba/events.out.tfevents.1627302117.578c7831d7ba.805.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1e2e5113865b3ab8b85247a4e1d39a44c0da049fcf348b15507337abade0fa
3
+ size 5982
runs/Jul26_12-21-38_578c7831d7ba/events.out.tfevents.1627308154.578c7831d7ba.805.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834d9f777746d25b9cfdaa49b6ed5c3afd8fc3c54f71aa3ac5e411386e6a46fe
3
+ size 363
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
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, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.14146648778485005,
4
+ "train_runtime": 6028.0345,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 44.691,
7
+ "train_steps_per_second": 1.397
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 8420,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.24,
12
+ "learning_rate": 9.406175771971498e-06,
13
+ "loss": 0.3692,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.48,
18
+ "learning_rate": 8.812351543942995e-06,
19
+ "loss": 0.2463,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.71,
24
+ "learning_rate": 8.21852731591449e-06,
25
+ "loss": 0.2089,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.95,
30
+ "learning_rate": 7.624703087885986e-06,
31
+ "loss": 0.1926,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.19,
36
+ "learning_rate": 7.030878859857483e-06,
37
+ "loss": 0.1504,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.43,
42
+ "learning_rate": 6.437054631828979e-06,
43
+ "loss": 0.1411,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.66,
48
+ "learning_rate": 5.843230403800475e-06,
49
+ "loss": 0.1425,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.9,
54
+ "learning_rate": 5.2494061757719716e-06,
55
+ "loss": 0.1351,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.14,
60
+ "learning_rate": 4.6555819477434686e-06,
61
+ "loss": 0.1067,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 2.38,
66
+ "learning_rate": 4.061757719714965e-06,
67
+ "loss": 0.1002,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.61,
72
+ "learning_rate": 3.467933491686461e-06,
73
+ "loss": 0.1048,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.85,
78
+ "learning_rate": 2.874109263657958e-06,
79
+ "loss": 0.1099,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 3.09,
84
+ "learning_rate": 2.280285035629454e-06,
85
+ "loss": 0.0836,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 3.33,
90
+ "learning_rate": 1.6864608076009503e-06,
91
+ "loss": 0.071,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 3.56,
96
+ "learning_rate": 1.0926365795724466e-06,
97
+ "loss": 0.0729,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 3.8,
102
+ "learning_rate": 4.988123515439431e-07,
103
+ "loss": 0.0837,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 4.0,
108
+ "step": 8420,
109
+ "total_flos": 1609513255434240.0,
110
+ "train_loss": 0.14146648778485005,
111
+ "train_runtime": 6028.0345,
112
+ "train_samples_per_second": 44.691,
113
+ "train_steps_per_second": 1.397
114
+ }
115
+ ],
116
+ "max_steps": 8420,
117
+ "num_train_epochs": 4,
118
+ "total_flos": 1609513255434240.0,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b388633199c3ec69f5d793e929089e5be4a7e02891c673ec492629445a5e1ba4
3
+ size 2607