End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5622
 - Rewards/chosen: -17.0278

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 19.84,
+    "eval_logits/chosen": -1.7818838357925415,
+    "eval_logits/rejected": -1.7583956718444824,
+    "eval_logps/chosen": -1971.018798828125,
+    "eval_logps/rejected": -2233.02197265625,
+    "eval_loss": 1.56223726272583,
+    "eval_rewards/accuracies": 0.6499999761581421,
+    "eval_rewards/chosen": -17.027843475341797,
+    "eval_rewards/margins": 2.817903757095337,
+    "eval_rewards/rejected": -19.845748901367188,
+    "eval_runtime": 67.4863,
+    "eval_samples": 200,
+    "eval_samples_per_second": 2.964,
+    "eval_steps_per_second": 0.37,
     "total_flos": 0.0,
     "train_loss": 0.13093096087141606,
     "train_runtime": 15450.2645,

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 19.84,
+    "eval_logits/chosen": -1.7818838357925415,
+    "eval_logits/rejected": -1.7583956718444824,
+    "eval_logps/chosen": -1971.018798828125,
+    "eval_logps/rejected": -2233.02197265625,
+    "eval_loss": 1.56223726272583,
+    "eval_rewards/accuracies": 0.6499999761581421,
+    "eval_rewards/chosen": -17.027843475341797,
+    "eval_rewards/margins": 2.817903757095337,
+    "eval_rewards/rejected": -19.845748901367188,
+    "eval_runtime": 67.4863,
+    "eval_samples": 200,
+    "eval_samples_per_second": 2.964,
+    "eval_steps_per_second": 0.37
+}