Hugging Face's logo

ssarathi
/
Text_Summarizer_Using_Transformers

Summarization
Safetensors
English
bart
nlp
transformer
text-generation
huggingface
Model card Files
xet
Community
ssarathi commited on
Commit
90ca2a3
·
verified ·
1 Parent(s): 6ad0f66

Added more epochs and Fine tuned

Browse files
Files changed (10) hide show
  1. config.json +73 -73
  2. generation_config.json +13 -15
  3. model.safetensors +1 -1
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -15
  8. tokenizer_config.json +58 -58
  9. trainer_state.json +104 -0
  10. training_args.bin +2 -2
config.json CHANGED
@@ -1,73 +1,73 @@
1
- {
2
- "activation_dropout": 0.1,
3
- "activation_function": "gelu",
4
- "add_bias_logits": false,
5
- "add_final_layer_norm": false,
6
- "architectures": [
7
- "BartForConditionalGeneration"
8
- ],
9
- "attention_dropout": 0.1,
10
- "bos_token_id": 0,
11
- "classif_dropout": 0.1,
12
- "classifier_dropout": 0.0,
13
- "d_model": 768,
14
- "decoder_attention_heads": 12,
15
- "decoder_ffn_dim": 3072,
16
- "decoder_layerdrop": 0.0,
17
- "decoder_layers": 6,
18
- "decoder_start_token_id": 2,
19
- "dropout": 0.1,
20
- "dtype": "float32",
21
- "early_stopping": null,
22
- "encoder_attention_heads": 12,
23
- "encoder_ffn_dim": 3072,
24
- "encoder_layerdrop": 0.0,
25
- "encoder_layers": 6,
26
- "eos_token_id": 2,
27
- "forced_eos_token_id": 2,
28
- "gradient_checkpointing": false,
29
- "id2label": {
30
- "0": "LABEL_0",
31
- "1": "LABEL_1",
32
- "2": "LABEL_2"
33
- },
34
- "init_std": 0.02,
35
- "is_encoder_decoder": true,
36
- "label2id": {
37
- "LABEL_0": 0,
38
- "LABEL_1": 1,
39
- "LABEL_2": 2
40
- },
41
- "max_position_embeddings": 1024,
42
- "model_type": "bart",
43
- "no_repeat_ngram_size": null,
44
- "normalize_before": false,
45
- "normalize_embedding": true,
46
- "num_beams": null,
47
- "num_hidden_layers": 6,
48
- "pad_token_id": 1,
49
- "scale_embedding": false,
50
- "task_specific_params": {
51
- "summarization": {
52
- "length_penalty": 1.0,
53
- "max_length": 128,
54
- "min_length": 12,
55
- "num_beams": 4
56
- },
57
- "summarization_cnn": {
58
- "length_penalty": 2.0,
59
- "max_length": 142,
60
- "min_length": 56,
61
- "num_beams": 4
62
- },
63
- "summarization_xsum": {
64
- "length_penalty": 1.0,
65
- "max_length": 62,
66
- "min_length": 11,
67
- "num_beams": 6
68
- }
69
- },
70
- "transformers_version": "4.56.0",
71
- "use_cache": true,
72
- "vocab_size": 50265
73
- }
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.1,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 768,
14
+ "decoder_attention_heads": 12,
15
+ "decoder_ffn_dim": 3072,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "early_stopping": null,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "no_repeat_ngram_size": null,
43
+ "normalize_before": false,
44
+ "normalize_embedding": true,
45
+ "num_beams": null,
46
+ "num_hidden_layers": 6,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.55.0",
71
+ "use_cache": true,
72
+ "vocab_size": 50265
73
+ }
generation_config.json CHANGED
@@ -1,15 +1,13 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "early_stopping": true,
6
- "eos_token_id": [
7
- 2
8
- ],
9
- "forced_bos_token_id": 0,
10
- "forced_eos_token_id": 2,
11
- "no_repeat_ngram_size": 3,
12
- "num_beams": 4,
13
- "pad_token_id": 1,
14
- "transformers_version": "4.56.0"
15
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.55.0"
13
+ }
 
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c67a303b31bbb39951554a70da82e7cfeffde5d9d6a4bb97c4260f8174b64cbe
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb08e1ef8dba7bee759f51e32bbf2a12e9fbe524d586955f192445ace53c0f7
3
  size 557912620
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99da1ce44649f1eb0fd04ec0dba39f3c4348237cd3af5080a55d605a7c3e60d0
3
+ size 1115579898
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c43bd4c5dc0d7d9a99e8a433d7514b6f495573b87e2daced0c6fb8c5332c2b
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93028d1fb94e1d4aa43e7b4d10fa63f40cb9a8f9bb360d602aed68e9178eabed
3
+ size 1064
special_tokens_map.json CHANGED
@@ -1,15 +1,15 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
- }
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json CHANGED
@@ -1,58 +1,58 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 1000000000000000019884624838656,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "BartTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": "<unk>"
58
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "BartTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 3.3184640407562256,
15
+ "learning_rate": 1.8004000000000002e-05,
16
+ "loss": 1.903,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "grad_norm": 3.314566135406494,
22
+ "learning_rate": 1.6004e-05,
23
+ "loss": 0.8126,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 3.0,
28
+ "grad_norm": 3.398888111114502,
29
+ "learning_rate": 1.4004000000000002e-05,
30
+ "loss": 0.7188,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 4.0,
35
+ "grad_norm": 3.308872699737549,
36
+ "learning_rate": 1.2004e-05,
37
+ "loss": 0.6496,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 5.0,
42
+ "grad_norm": 2.8485875129699707,
43
+ "learning_rate": 1.0004000000000001e-05,
44
+ "loss": 0.5958,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 6.0,
49
+ "grad_norm": 2.999493360519409,
50
+ "learning_rate": 8.004e-06,
51
+ "loss": 0.5524,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 7.0,
56
+ "grad_norm": 3.292451858520508,
57
+ "learning_rate": 6.004000000000001e-06,
58
+ "loss": 0.5184,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 8.0,
63
+ "grad_norm": 3.01755952835083,
64
+ "learning_rate": 4.004e-06,
65
+ "loss": 0.4901,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 9.0,
70
+ "grad_norm": 2.8285794258117676,
71
+ "learning_rate": 2.004e-06,
72
+ "loss": 0.4722,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 10.0,
77
+ "grad_norm": 2.7315330505371094,
78
+ "learning_rate": 4e-09,
79
+ "loss": 0.4564,
80
+ "step": 5000
81
+ }
82
+ ],
83
+ "logging_steps": 500,
84
+ "max_steps": 5000,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 10,
87
+ "save_steps": 500,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": true
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 6097364582400000.0,
101
+ "train_batch_size": 4,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17241749972ebf18573b3b07abf054aee55a9fa7a6d0823ff15207458eb19d62
3
- size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c6bc94880cac7c848a4ab4deefbbf50efe1e4120fee68963b664f296e43c9b
3
+ size 5496