hushell commited on
Commit
e94cea6
1 Parent(s): abecc5b

End of training

Browse files
Files changed (2) hide show
  1. README.md +6 -2
  2. config.json +1 -1
README.md CHANGED
@@ -1,11 +1,15 @@
1
  ---
2
  base_model: ondevicellm/tinyllama_mole_v1
3
  tags:
 
 
 
 
4
  - trl
5
  - sft
6
  - generated_from_trainer
7
  datasets:
8
- - generator
9
  model-index:
10
  - name: tinyllama_mole_sft_routeraux_ultrachat_ep3
11
  results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # tinyllama_mole_sft_routeraux_ultrachat_ep3
18
 
19
- This model is a fine-tuned version of [ondevicellm/tinyllama_mole_v1](https://huggingface.co/ondevicellm/tinyllama_mole_v1) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 1.2128
22
 
 
1
  ---
2
  base_model: ondevicellm/tinyllama_mole_v1
3
  tags:
4
+ - alignment-handbook
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
  - trl
9
  - sft
10
  - generated_from_trainer
11
  datasets:
12
+ - HuggingFaceH4/ultrachat_200k
13
  model-index:
14
  - name: tinyllama_mole_sft_routeraux_ultrachat_ep3
15
  results: []
 
20
 
21
  # tinyllama_mole_sft_routeraux_ultrachat_ep3
22
 
23
+ This model is a fine-tuned version of [ondevicellm/tinyllama_mole_v1](https://huggingface.co/ondevicellm/tinyllama_mole_v1) on the HuggingFaceH4/ultrachat_200k dataset.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 1.2128
26
 
config.json CHANGED
@@ -36,6 +36,6 @@
36
  "torch_dtype": "bfloat16",
37
  "transformers_version": "4.37.0",
38
  "trust_remote_code": true,
39
- "use_cache": false,
40
  "vocab_size": 32000
41
  }
 
36
  "torch_dtype": "bfloat16",
37
  "transformers_version": "4.37.0",
38
  "trust_remote_code": true,
39
+ "use_cache": true,
40
  "vocab_size": 32000
41
  }