End of training

README.md

@@ -2,10 +2,13 @@
 license: mit
 library_name: peft
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - dpo
-- generated_from_trainer
 base_model: microsoft/phi-2
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: phi-2-gpo-renew2-b0.001-vllm-i1
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-2-gpo-renew2-b0.001-vllm-i1
 
-This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+This model is a fine-tuned version of [DUAL-GPO/phi-2-gpo-renew2-b0.001-i0](https://huggingface.co/DUAL-GPO/phi-2-gpo-renew2-b0.001-i0) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0674
 - Rewards/chosen: 0.2141

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}