End of training

README.md

@@ -1,9 +1,15 @@
 ---
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- ChenWu98/skills_red_herring_chat
 base_model: merged_ckpts/skills_metaphor_chat-lora
 model-index:
 - name: skills_metaphor_chat-then-skills_red_herring_chat-lora
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # skills_metaphor_chat-then-skills_red_herring_chat-lora
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [merged_ckpts/skills_metaphor_chat-lora](https://huggingface.co/merged_ckpts/skills_metaphor_chat-lora) on the ChenWu98/skills_red_herring_chat dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2440
 

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "merged_ckpts/skills_metaphor_chat-lora",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}