End of training
Browse files- README.md +5 -1
- 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
|
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,
|