akshat-52 commited on
Commit
3008da3
1 Parent(s): f9cc404

End of training

Browse files
README.md CHANGED
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
49
 
50
  ### Framework versions
51
 
52
- - Transformers 4.34.0
53
- - Pytorch 2.0.1+cu118
54
- - Datasets 2.14.5
55
  - Tokenizers 0.14.1
 
49
 
50
  ### Framework versions
51
 
52
+ - Transformers 4.34.1
53
+ - Pytorch 2.1.0+cu118
54
+ - Datasets 2.14.6
55
  - Tokenizers 0.14.1
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "query_key_value",
20
- "dense_4h_to_h",
21
  "dense",
22
- "dense_h_to_4h"
 
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "dense",
20
+ "dense_h_to_4h",
21
+ "dense_4h_to_h",
22
+ "query_key_value"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0242a47e800ccc5ae2285aba15f70fc938b3aab43c6d373e19722c553c1ab055
3
- size 261189453
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ef0f0ca61c3d653ba6cdc2617a944dad7d735f6ee427b86571b298e17dcf3f
3
+ size 261189898
tokenizer_config.json CHANGED
@@ -118,5 +118,6 @@
118
  "attention_mask"
119
  ],
120
  "model_max_length": 2048,
 
121
  "tokenizer_class": "PreTrainedTokenizerFast"
122
  }
 
118
  "attention_mask"
119
  ],
120
  "model_max_length": 2048,
121
+ "pad_token": "<|endoftext|>",
122
  "tokenizer_class": "PreTrainedTokenizerFast"
123
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0675dde80c4eb85861e32829c0aafe2998411b8ec7cf96ac8e424168eedee1c5
3
- size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d139514e3f6109cf3cf00aca2413dc2c3b7b79feed48eb99e5fd83caa223dea1
3
+ size 4600