Hugging Face's logo

sumanthk
/
PEFT_expo

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sumanthk commited on
Commit
810685a
•
1 Parent(s): 59c5bce

End of training

Browse files
Files changed (10) hide show
  1. README.md +7 -6
  2. config.json +1 -1
  3. generation_config.json +2 -2
  4. model.safetensors +1 -1
  5. runs/Oct23_15-05-54_3e476168aed7/events.out.tfevents.1729695958.3e476168aed7.1366.0 +3 -0
  6. training_args.bin +2 -2
  7. tuned_model_1/config.json +1 -1
  8. tuned_model_1/generation_config.json +2 -2
  9. tuned_model_1/model.safetensors +1 -1
  10. tuned_model_1/training_args.bin +2 -2
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  license: mit
3
  base_model: facebook/bart-large-cnn
4
  tags:
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the samsum dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3199
21
 
22
  ## Model description
23
 
@@ -48,13 +49,13 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 0.2573 | 1.0 | 37 | 0.3059 |
52
- | 0.2092 | 2.0 | 74 | 0.3199 |
53
 
54
 
55
  ### Framework versions
56
 
57
- - Transformers 4.41.0
58
- - Pytorch 2.3.0+cu121
59
- - Datasets 2.19.1
60
  - Tokenizers 0.19.1
 
1
  ---
2
+ library_name: transformers
3
  license: mit
4
  base_model: facebook/bart-large-cnn
5
  tags:
 
18
 
19
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the samsum dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2688
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.9239 | 1.0 | 19 | 0.2793 |
53
+ | 0.1915 | 2.0 | 38 | 0.2688 |
54
 
55
 
56
  ### Framework versions
57
 
58
+ - Transformers 4.44.2
59
+ - Pytorch 2.4.1+cu121
60
+ - Datasets 3.0.2
61
  - Tokenizers 0.19.1
config.json CHANGED
@@ -64,7 +64,7 @@
64
  }
65
  },
66
  "torch_dtype": "float32",
67
- "transformers_version": "4.41.0",
68
  "use_cache": true,
69
  "vocab_size": 50264
70
  }
 
64
  }
65
  },
66
  "torch_dtype": "float32",
67
+ "transformers_version": "4.44.2",
68
  "use_cache": true,
69
  "vocab_size": 50264
70
  }
generation_config.json CHANGED
@@ -1,7 +1,7 @@
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,
@@ -12,5 +12,5 @@
12
  "no_repeat_ngram_size": 3,
13
  "num_beams": 4,
14
  "pad_token_id": 1,
15
- "transformers_version": "4.41.0"
16
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
  "early_stopping": true,
6
  "eos_token_id": 2,
7
  "forced_bos_token_id": 0,
 
12
  "no_repeat_ngram_size": 3,
13
  "num_beams": 4,
14
  "pad_token_id": 1,
15
+ "transformers_version": "4.44.2"
16
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7e829339a1f6d0ded8deb26dbfa21c191e07eabdf907d2b0c5dc9cff46f8fe8
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11406ac0b6fff22f84dd2a5b57ab7a07f445ec5b5b8e01d197d68da036ac873a
3
  size 1625422896
runs/Oct23_15-05-54_3e476168aed7/events.out.tfevents.1729695958.3e476168aed7.1366.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef68d7358ddbe51d566b28e36bf42e66d813d39e80ce238c41d01ac32f7874c
3
+ size 7448
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e404c0886111bfd46bc8b3454bbf433f5a96d6b811ac9b41c4c0cd84cf5029fc
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743bcc51c80aad3029bdeed7b0c34f8f6aa1b0785ca3e6e791ae486d8c4173a8
3
+ size 5240
tuned_model_1/config.json CHANGED
@@ -64,7 +64,7 @@
64
  }
65
  },
66
  "torch_dtype": "float32",
67
- "transformers_version": "4.41.0",
68
  "use_cache": true,
69
  "vocab_size": 50264
70
  }
 
64
  }
65
  },
66
  "torch_dtype": "float32",
67
+ "transformers_version": "4.44.2",
68
  "use_cache": true,
69
  "vocab_size": 50264
70
  }
tuned_model_1/generation_config.json CHANGED
@@ -1,7 +1,7 @@
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,
@@ -12,5 +12,5 @@
12
  "no_repeat_ngram_size": 3,
13
  "num_beams": 4,
14
  "pad_token_id": 1,
15
- "transformers_version": "4.41.0"
16
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
  "early_stopping": true,
6
  "eos_token_id": 2,
7
  "forced_bos_token_id": 0,
 
12
  "no_repeat_ngram_size": 3,
13
  "num_beams": 4,
14
  "pad_token_id": 1,
15
+ "transformers_version": "4.44.2"
16
  }
tuned_model_1/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7e829339a1f6d0ded8deb26dbfa21c191e07eabdf907d2b0c5dc9cff46f8fe8
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11406ac0b6fff22f84dd2a5b57ab7a07f445ec5b5b8e01d197d68da036ac873a
3
  size 1625422896
tuned_model_1/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e404c0886111bfd46bc8b3454bbf433f5a96d6b811ac9b41c4c0cd84cf5029fc
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743bcc51c80aad3029bdeed7b0c34f8f6aa1b0785ca3e6e791ae486d8c4173a8
3
+ size 5240