End of training
Browse files- README.md +5 -1
- config.json +34 -0
README.md
CHANGED
@@ -2,9 +2,13 @@
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
8 |
base_model: microsoft/phi-2
|
9 |
model-index:
|
10 |
- name: phi-2-gpo-ultrachat-lora
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# phi-2-gpo-ultrachat-lora
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.0001
|
22 |
- Rewards/chosen: -0.0000
|
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- generated_from_trainer
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
+
datasets:
|
11 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
12 |
base_model: microsoft/phi-2
|
13 |
model-index:
|
14 |
- name: phi-2-gpo-ultrachat-lora
|
|
|
20 |
|
21 |
# phi-2-gpo-ultrachat-lora
|
22 |
|
23 |
+
This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 0.0001
|
26 |
- Rewards/chosen: -0.0000
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-2",
|
3 |
+
"architectures": [
|
4 |
+
"PhiForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
9 |
+
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 50256,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 50256,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_size": 2560,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 10240,
|
18 |
+
"layer_norm_eps": 1e-05,
|
19 |
+
"max_position_embeddings": 2048,
|
20 |
+
"model_type": "phi",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"partial_rotary_factor": 0.4,
|
25 |
+
"qk_layernorm": false,
|
26 |
+
"resid_pdrop": 0.1,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "bfloat16",
|
31 |
+
"transformers_version": "4.36.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 51200
|
34 |
+
}
|