nazemi commited on
Commit
7243078
·
1 Parent(s): e2f7e5c

End of training

Browse files
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0745
19
 
20
  ## Model description
21
 
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 6.6008 | 1.0 | 55 | 3.7359 |
50
- | 0.9015 | 2.0 | 110 | 0.4882 |
51
- | 0.5158 | 3.0 | 165 | 0.2454 |
52
- | 0.6051 | 4.0 | 220 | 0.1737 |
53
- | 1.0759 | 5.0 | 275 | 0.1356 |
54
- | 0.0473 | 6.0 | 330 | 0.1097 |
55
- | 0.0412 | 7.0 | 385 | 0.0928 |
56
- | 0.5505 | 8.0 | 440 | 0.0827 |
57
- | 0.0438 | 9.0 | 495 | 0.0764 |
58
- | 0.0687 | 10.0 | 550 | 0.0745 |
59
 
60
 
61
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0203
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 1.1179 | 1.0 | 109 | 0.6176 |
50
+ | 0.09 | 2.0 | 218 | 0.1340 |
51
+ | 0.0982 | 3.0 | 327 | 0.0781 |
52
+ | 0.0015 | 4.0 | 436 | 0.0522 |
53
+ | 0.3695 | 5.0 | 545 | 0.0406 |
54
+ | 0.0051 | 6.0 | 654 | 0.0310 |
55
+ | 0.0294 | 7.0 | 763 | 0.0251 |
56
+ | 0.0027 | 8.0 | 872 | 0.0228 |
57
+ | 0.015 | 9.0 | 981 | 0.0209 |
58
+ | 0.0303 | 10.0 | 1090 | 0.0203 |
59
 
60
 
61
  ### Framework versions
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57faa7d020c04c840a4d14245ce47dc32f1d9c51da4a94fa927edf972d88c254
3
+ size 2950734544
runs/Jan16_13-37-12_192168021136.tpgi.com.au/events.out.tfevents.1705383434.192168021136.tpgi.com.au.1725.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b45ee47559d8bf2b7f9dee117b3fbae22784d6f73f2234640600b9a79e118d
3
+ size 179083
special_tokens_map.json CHANGED
@@ -101,25 +101,7 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": {
105
- "content": "</s>",
106
- "lstrip": false,
107
- "normalized": false,
108
- "rstrip": false,
109
- "single_word": false
110
- },
111
- "pad_token": {
112
- "content": "<pad>",
113
- "lstrip": false,
114
- "normalized": false,
115
- "rstrip": false,
116
- "single_word": false
117
- },
118
- "unk_token": {
119
- "content": "<unk>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false
124
- }
125
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -930,10 +930,8 @@
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
933
- "legacy": true,
934
  "model_max_length": 512,
935
  "pad_token": "<pad>",
936
- "sp_model_kwargs": {},
937
  "tokenizer_class": "T5Tokenizer",
938
  "unk_token": "<unk>"
939
  }
 
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
  "extra_ids": 100,
 
933
  "model_max_length": 512,
934
  "pad_token": "<pad>",
 
935
  "tokenizer_class": "T5Tokenizer",
936
  "unk_token": "<unk>"
937
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a465a03cc88f2d53db9e8a6e393e05ada784636e34368f3533fdaa7670f6ee14
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18f399c5074d52fb1d1ed088bd6cb6707284192259a03502e115b045bad7e85
3
  size 4792