RTHGV commited on
Commit
a420e59
·
verified ·
1 Parent(s): b01aeaa

End of training

Browse files
Files changed (5) hide show
  1. README.md +5 -7
  2. config.json +61 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,9 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/flan-t5-small
4
  tags:
5
  - generated_from_trainer
6
- library_name: peft
7
  model-index:
8
  - name: indian-constitution-qa
9
  results: []
@@ -14,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # indian-constitution-qa
16
 
17
- This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the Dhiraj223/IndianConstitutionData dataset.
18
 
19
  ## Model description
20
 
@@ -33,13 +32,13 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 1e-05
37
  - train_batch_size: 32
38
  - eval_batch_size: 32
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 8
43
 
44
  ### Training results
45
 
@@ -47,8 +46,7 @@ The following hyperparameters were used during training:
47
 
48
  ### Framework versions
49
 
50
- - PEFT 0.7.1
51
  - Transformers 4.36.2
52
  - Pytorch 2.5.1+cu121
53
  - Datasets 2.15.0
54
- - Tokenizers 0.15.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: t5-small
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: indian-constitution-qa
8
  results: []
 
13
 
14
  # indian-constitution-qa
15
 
16
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the Dhiraj223/IndianConstitutionData dataset.
17
 
18
  ## Model description
19
 
 
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
+ - learning_rate: 0.001
36
  - train_batch_size: 32
37
  - eval_batch_size: 32
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 10
42
 
43
  ### Training results
44
 
 
46
 
47
  ### Framework versions
48
 
 
49
  - Transformers 4.36.2
50
  - Pytorch 2.5.1+cu121
51
  - Datasets 2.15.0
52
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.36.2",
59
+ "use_cache": false,
60
+ "vocab_size": 32128
61
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae9cff9190c431964879861324639a8c26186fc07c1cd1976bbfd62bef76a95
3
+ size 242041896
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c101e3c4223da2a18d639ab84aebb09086d318f2ad8e71e4d5af8f92e37e9231
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5695a58371290a31ff02b079af50492e6518200f0d57b1029e4e9bb72e68fb54
3
  size 4856