Chung-Fan commited on
Commit
be6661b
1 Parent(s): 91be14f

Training done for primera-pubmed-20k

Browse files
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [allenai/PRIMERA](https://huggingface.co/allenai/PRIMERA) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.1417
18
 
19
  ## Model description
20
 
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:----:|:---------------:|
51
- | 1.3016 | 0.75 | 500 | 1.1417 |
52
 
53
 
54
  ### Framework versions
55
 
56
- - Transformers 4.38.2
57
  - Pytorch 2.2.1+cu121
58
- - Datasets 2.18.0
59
- - Tokenizers 0.15.2
 
14
 
15
  This model is a fine-tuned version of [allenai/PRIMERA](https://huggingface.co/allenai/PRIMERA) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.9689
18
 
19
  ## Model description
20
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:----:|:---------------:|
51
+ | 1.0637 | 0.7477 | 500 | 0.9689 |
52
 
53
 
54
  ### Framework versions
55
 
56
+ - Transformers 4.40.0
57
  - Pytorch 2.2.1+cu121
58
+ - Datasets 2.19.0
59
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -92,7 +92,7 @@
92
  }
93
  },
94
  "torch_dtype": "float32",
95
- "transformers_version": "4.38.2",
96
  "use_cache": true,
97
  "vocab_size": 50266
98
  }
 
92
  }
93
  },
94
  "torch_dtype": "float32",
95
+ "transformers_version": "4.40.0",
96
  "use_cache": true,
97
  "vocab_size": 50266
98
  }
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "eos_token_id": 2,
6
  "no_repeat_ngram_size": 3,
7
  "pad_token_id": 1,
8
- "transformers_version": "4.38.2"
9
  }
 
5
  "eos_token_id": 2,
6
  "no_repeat_ngram_size": 3,
7
  "pad_token_id": 1,
8
+ "transformers_version": "4.40.0"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e4df0f07166f816749935f598ad3b2f5822775612ca2e98487c7bc5313086f8
3
  size 1789150784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ab5273654bb32614e98c297bf5f748919f5ed2dff758794086031b714eb0e2
3
  size 1789150784
tokenizer.json CHANGED
@@ -106,6 +106,7 @@
106
  "end_of_word_suffix": "",
107
  "fuse_unk": false,
108
  "byte_fallback": false,
 
109
  "vocab": {
110
  "<s>": 0,
111
  "<pad>": 1,
 
106
  "end_of_word_suffix": "",
107
  "fuse_unk": false,
108
  "byte_fallback": false,
109
+ "ignore_merges": false,
110
  "vocab": {
111
  "<s>": 0,
112
  "<pad>": 1,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb7524c013e5b90c6ef09028289d13d3913a5d5a4805869c92c7380d38c7203d
3
- size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5e02689f5be21a0f53908ddbb6cb67102b281f3ff0f8a9a4665f83bb5a0451
3
+ size 4984