Malek1410 commited on
Commit
b2fd76f
·
verified ·
1 Parent(s): 3fdda91

End of training

Browse files
Files changed (4) hide show
  1. README.md +48 -0
  2. config.json +43 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: albert-base-v2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: albert_project_test_trainer
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # albert_project_test_trainer
15
+
16
+ This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 3.0
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.35.2
46
+ - Pytorch 2.1.0+cu121
47
+ - Datasets 2.16.1
48
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "LABEL_0",
18
+ "1": "LABEL_1",
19
+ "2": "LABEL_2"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "inner_group_num": 1,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "albert",
32
+ "net_structure_type": 0,
33
+ "num_attention_heads": 12,
34
+ "num_hidden_groups": 1,
35
+ "num_hidden_layers": 12,
36
+ "num_memory_blocks": 0,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.35.2",
41
+ "type_vocab_size": 2,
42
+ "vocab_size": 30000
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb460050c64e3cee1152ea58072091636f5bf32b36c043c33d4fc7b255695629
3
+ size 46746988
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457fdf3df362b2ad08602d202537845bc56f90a4aa0a1cb2d94a3d2381577919
3
+ size 4600