Training in progress, epoch 1

README.md

@@ -2,7 +2,10 @@
 license: mit
 base_model: HuggingFaceH4/mistral-7b-sft-beta
 tags:
+- alignment-handbook
 - generated_from_trainer
+datasets:
+- Anthropic/hh-rlhf
 model-index:
 - name: zephyr-7b-dpo-lora
   results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the Anthropic/hh-rlhf dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7922
 - Rewards/chosen: -6.3032

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "v_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213b0f6f8e85b2818b033e447a504cd4547cace514f1e7d4088fb8b661b1e852
+oid sha256:198041c9f2f3cfff0260eeb97df84c0b7c987704bbc445b9717adff9cb2a5743
 size 109086672

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ee00fede12c044e84a0c3b8f7f79fb304de3238d63211269f7479f86d71ae7
+oid sha256:a567abdf9183c4e61e9d3def199b460676cfa0d856a80e25f3c953319fc8e5d3
 size 5688