Serega6678 commited on
Commit
a090d8e
1 Parent(s): f0229f0

End of training

Browse files
Files changed (2) hide show
  1. README.md +4 -2
  2. config.json +26 -0
README.md CHANGED
@@ -2,12 +2,14 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: mistralai/Mistral-7B-v0.1
9
  datasets:
10
- - generator
11
  model-index:
12
  - name: M7Bv01_SFT_50pct_LORA_BF16_FA_2H100
13
  results: []
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # M7Bv01_SFT_50pct_LORA_BF16_FA_2H100
20
 
21
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.9493
24
 
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
  - trl
8
  - sft
9
  - generated_from_trainer
10
  base_model: mistralai/Mistral-7B-v0.1
11
  datasets:
12
+ - HuggingFaceH4/ultrachat_200k
13
  model-index:
14
  - name: M7Bv01_SFT_50pct_LORA_BF16_FA_2H100
15
  results: []
 
20
 
21
  # M7Bv01_SFT_50pct_LORA_BF16_FA_2H100
22
 
23
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 0.9493
26
 
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.36.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }