andyfriedrich-amd commited on
Commit
1976c0b
1 Parent(s): 5987ca2

End of training

Browse files
Files changed (5) hide show
  1. README.md +8 -8
  2. config.json +2 -1
  3. generation_config.json +1 -1
  4. pytorch_model.bin +2 -2
  5. training_args.bin +2 -2
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.1270
21
- - Bleu: 0.1514
22
- - Gen Len: 19.0
23
 
24
  ## Model description
25
 
@@ -50,13 +50,13 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
53
- | No log | 1.0 | 8 | 2.2852 | 0.1544 | 19.0 |
54
- | No log | 2.0 | 16 | 2.1270 | 0.1514 | 19.0 |
55
 
56
 
57
  ### Framework versions
58
 
59
- - Transformers 4.31.0
60
- - Pytorch 2.0.0a0+git70f6d0c
61
- - Datasets 2.14.0
62
  - Tokenizers 0.13.3
 
17
 
18
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.1911
21
+ - Bleu: 0.1208
22
+ - Gen Len: 18.9504
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
53
+ | No log | 1.0 | 8 | 2.3434 | 0.1222 | 18.9504 |
54
+ | No log | 2.0 | 16 | 2.1911 | 0.1208 | 18.9504 |
55
 
56
 
57
  ### Framework versions
58
 
59
+ - Transformers 4.32.0
60
+ - Pytorch 2.1.0a0+git794e397
61
+ - Datasets 2.14.4
62
  - Tokenizers 0.13.3
config.json CHANGED
@@ -3,6 +3,7 @@
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
6
  "d_ff": 2048,
7
  "d_kv": 64,
8
  "d_model": 512,
@@ -54,7 +55,7 @@
54
  }
55
  },
56
  "torch_dtype": "float32",
57
- "transformers_version": "4.31.0",
58
  "use_cache": true,
59
  "vocab_size": 32128
60
  }
 
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
+ "classifier_dropout": 0.0,
7
  "d_ff": 2048,
8
  "d_kv": 64,
9
  "d_model": 512,
 
55
  }
56
  },
57
  "torch_dtype": "float32",
58
+ "transformers_version": "4.32.0",
59
  "use_cache": true,
60
  "vocab_size": 32128
61
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
5
- "transformers_version": "4.31.0"
6
  }
 
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
5
+ "transformers_version": "4.32.0"
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b605c8c0b2a967b15633d65b80a060e44c862550b2e016193390696b062ba092
3
- size 242071641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e4583b4bd952e7f488dbe49d7f2731ebb2d58a66e99d549ff2abf9233667b4
3
+ size 242071838
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c170dd0d3dfb4bcfe7e4d394d1cdc059c8263f17c8cec937f8e33e660606f77
3
- size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df2faf3a2e2848a20c008bc528b31cfd02062b8ea00f7711c06b9f21f06c069
3
+ size 4416