End of training

README.md

@@ -2,9 +2,10 @@
 license: apache-2.0
 library_name: peft
 tags:
+- llama-factory
+- lora
 - trl
 - dpo
-- llama-factory
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-Instruct-v0.3
 model-index:
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-7B-Instruct-v0.3-ORPO-SALT-HALF
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the dpo_mix_en and the bct_non_cot_dpo_500 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.8506
 - Rewards/chosen: -0.0787

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 2.9974597798475866,
+    "eval_logits/chosen": -3.130527973175049,
+    "eval_logits/rejected": -3.1507296562194824,
+    "eval_logps/chosen": -0.7867480516433716,
+    "eval_logps/rejected": -0.9955620169639587,
+    "eval_loss": 0.8505691885948181,
+    "eval_odds_ratio_loss": 0.638211727142334,
+    "eval_rewards/accuracies": 0.5723809599876404,
+    "eval_rewards/chosen": -0.0786748081445694,
+    "eval_rewards/margins": 0.020881392061710358,
+    "eval_rewards/rejected": -0.09955620020627975,
+    "eval_runtime": 194.0793,
+    "eval_samples_per_second": 5.41,
+    "eval_sft_loss": 0.7867480516433716,
+    "eval_steps_per_second": 2.705,
+    "total_flos": 2.0399855839629804e+18,
+    "train_loss": 0.8663494454938813,
+    "train_runtime": 17638.0542,
+    "train_samples_per_second": 1.607,
+    "train_steps_per_second": 0.1
+}

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.9974597798475866,
+    "eval_logits/chosen": -3.130527973175049,
+    "eval_logits/rejected": -3.1507296562194824,
+    "eval_logps/chosen": -0.7867480516433716,
+    "eval_logps/rejected": -0.9955620169639587,
+    "eval_loss": 0.8505691885948181,
+    "eval_odds_ratio_loss": 0.638211727142334,
+    "eval_rewards/accuracies": 0.5723809599876404,
+    "eval_rewards/chosen": -0.0786748081445694,
+    "eval_rewards/margins": 0.020881392061710358,
+    "eval_rewards/rejected": -0.09955620020627975,
+    "eval_runtime": 194.0793,
+    "eval_samples_per_second": 5.41,
+    "eval_sft_loss": 0.7867480516433716,
+    "eval_steps_per_second": 2.705
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9974597798475866,
+    "total_flos": 2.0399855839629804e+18,
+    "train_loss": 0.8663494454938813,
+    "train_runtime": 17638.0542,
+    "train_samples_per_second": 1.607,
+    "train_steps_per_second": 0.1
+}