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
@@ -16,17 +19,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora-r16-20k
 
-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: 0.5370
-- Rewards/chosen: -0.7888
-- Rewards/rejected: -1.4748
-- Rewards/accuracies: 0.7063
-- Rewards/margins: 0.6860
-- Logps/rejected: -395.5133
-- Logps/chosen: -362.1219
-- Logits/rejected: -2.5135
-- Logits/chosen: -2.5568
+- Loss: 0.5367
+- Rewards/chosen: -0.7912
+- Rewards/rejected: -1.4787
+- Rewards/accuracies: 0.7103
+- Rewards/margins: 0.6874
+- Logps/rejected: -395.8989
+- Logps/chosen: -362.3625
+- Logits/rejected: -2.5102
+- Logits/chosen: -2.5539
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.553934335708618,
+    "eval_logits/rejected": -2.510233163833618,
+    "eval_logps/chosen": -362.36248779296875,
+    "eval_logps/rejected": -395.8988952636719,
+    "eval_loss": 0.5367478132247925,
+    "eval_rewards/accuracies": 0.7103174328804016,
+    "eval_rewards/chosen": -0.7912437319755554,
+    "eval_rewards/margins": 0.6874489188194275,
+    "eval_rewards/rejected": -1.4786925315856934,
+    "eval_runtime": 165.9175,
+    "eval_samples": 500,
+    "eval_samples_per_second": 3.014,
+    "eval_steps_per_second": 0.38,
     "total_flos": 0.0,
     "train_loss": 0.5874967678070069,
     "train_runtime": 15864.6959,

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": 1.0,
+    "eval_logits/chosen": -2.553934335708618,
+    "eval_logits/rejected": -2.510233163833618,
+    "eval_logps/chosen": -362.36248779296875,
+    "eval_logps/rejected": -395.8988952636719,
+    "eval_loss": 0.5367478132247925,
+    "eval_rewards/accuracies": 0.7103174328804016,
+    "eval_rewards/chosen": -0.7912437319755554,
+    "eval_rewards/margins": 0.6874489188194275,
+    "eval_rewards/rejected": -1.4786925315856934,
+    "eval_runtime": 165.9175,
+    "eval_samples": 500,
+    "eval_samples_per_second": 3.014,
+    "eval_steps_per_second": 0.38
+}