shradha01 commited on
Commit
1a78802
·
verified ·
1 Parent(s): cba4f4e

Model save

Browse files
Files changed (5) hide show
  1. README.md +53 -0
  2. config.json +45 -0
  3. generation_config.json +12 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: code-completion
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # code-completion
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
+
16
+ ## Model description
17
+
18
+ More information needed
19
+
20
+ ## Intended uses & limitations
21
+
22
+ More information needed
23
+
24
+ ## Training and evaluation data
25
+
26
+ More information needed
27
+
28
+ ## Training procedure
29
+
30
+ ### Training hyperparameters
31
+
32
+ The following hyperparameters were used during training:
33
+ - learning_rate: 5e-05
34
+ - train_batch_size: 48
35
+ - eval_batch_size: 96
36
+ - seed: 42
37
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
38
+ - lr_scheduler_type: linear
39
+ - lr_scheduler_warmup_steps: 1000
40
+ - num_epochs: 1
41
+ - mixed_precision_training: Native AMP
42
+ - label_smoothing_factor: 0.1
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.36.2
51
+ - Pytorch 2.4.1
52
+ - Datasets 2.16.1
53
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "BartForClassificationAndGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "classifier_dropout": 0.0,
10
+ "d_model": 768,
11
+ "decoder_attention_heads": 12,
12
+ "decoder_ffn_dim": 3072,
13
+ "decoder_layerdrop": 0.0,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 1,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 12,
18
+ "encoder_ffn_dim": 3072,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_layers": 12,
21
+ "eos_token_id": 2,
22
+ "forced_eos_token_id": 2,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "max_length": 100,
34
+ "max_position_embeddings": 512,
35
+ "min_length": 1,
36
+ "model_type": "bart",
37
+ "num_beams": 5,
38
+ "num_hidden_layers": 12,
39
+ "pad_token_id": 0,
40
+ "scale_embedding": false,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.36.2",
43
+ "use_cache": true,
44
+ "vocab_size": 2831
45
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "max_length": 100,
8
+ "min_length": 1,
9
+ "num_beams": 5,
10
+ "pad_token_id": 0,
11
+ "transformers_version": "4.36.2"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278e25b971081dacdb9ee09516f98123cb9dff4c635f328ab0d82a4eeaa8cb68
3
+ size 808209620
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0aead5f0657461b5cab840a52adfc7d78d8d64c85f013b2dd6f96d5cbbaecc0
3
+ size 4984