Alireza1044 commited on
Commit
3146e4a
1 Parent(s): 4463cd4
.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: wnli
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: GLUE WNLI
19
+ type: glue
20
+ args: wnli
21
+ metric:
22
+ name: Accuracy
23
+ type: accuracy
24
+ value: 0.5492957746478874
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
+ # wnli
31
+
32
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE WNLI dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.7013
35
+ - Accuracy: 0.5493
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: 2e-05
55
+ - train_batch_size: 64
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 4.9.1
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": 0.5492957746478874,
4
+ "eval_loss": 0.7012712359428406,
5
+ "eval_runtime": 0.3654,
6
+ "eval_samples": 71,
7
+ "eval_samples_per_second": 194.33,
8
+ "eval_steps_per_second": 24.633,
9
+ "train_loss": 0.7100192546844483,
10
+ "train_runtime": 28.5241,
11
+ "train_samples": 635,
12
+ "train_samples_per_second": 89.047,
13
+ "train_steps_per_second": 1.402
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": "wnli",
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": "4.9.1",
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": 0.5492957746478874,
4
+ "eval_loss": 0.7012712359428406,
5
+ "eval_runtime": 0.3654,
6
+ "eval_samples": 71,
7
+ "eval_samples_per_second": 194.33,
8
+ "eval_steps_per_second": 24.633
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0734a2959909d9ddc72371e925806c8fa82f83cada20db350790bc1989912318
3
+ size 46755537
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}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
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": 0.7100192546844483,
4
+ "train_runtime": 28.5241,
5
+ "train_samples": 635,
6
+ "train_samples_per_second": 89.047,
7
+ "train_steps_per_second": 1.402
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 40,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 4.0,
12
+ "step": 40,
13
+ "total_flos": 15175294617600.0,
14
+ "train_loss": 0.7100192546844483,
15
+ "train_runtime": 28.5241,
16
+ "train_samples_per_second": 89.047,
17
+ "train_steps_per_second": 1.402
18
+ }
19
+ ],
20
+ "max_steps": 40,
21
+ "num_train_epochs": 4,
22
+ "total_flos": 15175294617600.0,
23
+ "trial_name": null,
24
+ "trial_params": null
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a19671965c74699a433d77ebc26e46a1746b8ce7eb381919cad12e122024e0
3
+ size 2607