shenxq commited on
Commit
de0c06e
1 Parent(s): 29be7a4

End of training

Browse files
Files changed (2) hide show
  1. README.md +5 -1
  2. config.json +12 -0
README.md CHANGED
@@ -2,9 +2,13 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
 
5
  - trl
6
  - dpo
7
  - generated_from_trainer
 
 
8
  base_model: mistralai/Mistral-7B-v0.1
9
  model-index:
10
  - name: zephyr-7b-dpo-qlora
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # zephyr-7b-dpo-qlora
18
 
19
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6668
22
  - Rewards/chosen: -0.2672
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
  - trl
8
  - dpo
9
  - generated_from_trainer
10
+ datasets:
11
+ - snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
12
  base_model: mistralai/Mistral-7B-v0.1
13
  model-index:
14
  - name: zephyr-7b-dpo-qlora
 
20
 
21
  # zephyr-7b-dpo-qlora
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 snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset dataset.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 0.6668
26
  - Rewards/chosen: -0.2672
config.json CHANGED
@@ -15,6 +15,18 @@
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,
 
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bnb_4bit_compute_dtype": "float16",
20
+ "bnb_4bit_quant_type": "nf4",
21
+ "bnb_4bit_use_double_quant": false,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": null,
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": true,
27
+ "load_in_8bit": false,
28
+ "quant_method": "bitsandbytes"
29
+ },
30
  "rms_norm_eps": 1e-05,
31
  "rope_theta": 10000.0,
32
  "sliding_window": 4096,