End of training

README.md

@@ -3,6 +3,7 @@ base_model: mistralai/Mistral-7B-v0.1
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,17 +17,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4932
-- Rewards/chosen: -1.7916
-- Rewards/rejected: -2.7322
-- Rewards/accuracies: 0.7262
-- Rewards/margins: 0.9407
-- Logps/rejected: -535.5854
-- Logps/chosen: -446.6503
-- Logits/rejected: 0.9353
-- Logits/chosen: 0.5257
+- Loss: 0.4930
+- Rewards/chosen: -1.7956
+- Rewards/rejected: -2.7390
+- Rewards/accuracies: 0.7242
+- Rewards/margins: 0.9434
+- Logps/rejected: -536.2667
+- Logps/chosen: -447.0530
+- Logits/rejected: 0.9396
+- Logits/chosen: 0.5316
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 0.5316108465194702,
+    "eval_logits/rejected": 0.9396071434020996,
+    "eval_logps/chosen": -447.05303955078125,
+    "eval_logps/rejected": -536.2667236328125,
+    "eval_loss": 0.49303239583969116,
+    "eval_rewards/accuracies": 0.7242063283920288,
+    "eval_rewards/chosen": -1.7955820560455322,
+    "eval_rewards/margins": 0.9434418678283691,
+    "eval_rewards/rejected": -2.7390236854553223,
+    "eval_runtime": 363.1163,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.508,
+    "eval_steps_per_second": 0.173,
     "train_loss": 0.5264237219126436,
     "train_runtime": 29801.8239,
     "train_samples": 61135,

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 0.5316108465194702,
+    "eval_logits/rejected": 0.9396071434020996,
+    "eval_logps/chosen": -447.05303955078125,
+    "eval_logps/rejected": -536.2667236328125,
+    "eval_loss": 0.49303239583969116,
+    "eval_rewards/accuracies": 0.7242063283920288,
+    "eval_rewards/chosen": -1.7955820560455322,
+    "eval_rewards/margins": 0.9434418678283691,
+    "eval_rewards/rejected": -2.7390236854553223,
+    "eval_runtime": 363.1163,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.508,
+    "eval_steps_per_second": 0.173
+}