End of training

README.md

@@ -2,9 +2,10 @@
 license: gemma
 library_name: peft
 tags:
+- llama-factory
+- lora
 - trl
 - dpo
-- llama-factory
 - generated_from_trainer
 base_model: google/gemma-2b-it
 model-index:
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Gemma-2B-It-ORPO-SALT
 
-This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
+This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the dpo_mix_en and the bct_non_cot_dpo_1000 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.3294
 - Rewards/chosen: -0.1257

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 2.9969690846635686,
+    "eval_logits/chosen": -20.66438865661621,
+    "eval_logits/rejected": -20.695892333984375,
+    "eval_logps/chosen": -1.2573115825653076,
+    "eval_logps/rejected": -1.3996058702468872,
+    "eval_loss": 1.3293771743774414,
+    "eval_odds_ratio_loss": 0.7206552624702454,
+    "eval_rewards/accuracies": 0.5345454812049866,
+    "eval_rewards/chosen": -0.12573117017745972,
+    "eval_rewards/margins": 0.014229409396648407,
+    "eval_rewards/rejected": -0.13996057212352753,
+    "eval_runtime": 82.3315,
+    "eval_samples_per_second": 13.361,
+    "eval_sft_loss": 1.2573115825653076,
+    "eval_steps_per_second": 6.68,
+    "total_flos": 5.618252880760013e+17,
+    "train_loss": 1.3892074464594277,
+    "train_runtime": 8722.5011,
+    "train_samples_per_second": 3.404,
+    "train_steps_per_second": 0.213
+}

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.9969690846635686,
+    "eval_logits/chosen": -20.66438865661621,
+    "eval_logits/rejected": -20.695892333984375,
+    "eval_logps/chosen": -1.2573115825653076,
+    "eval_logps/rejected": -1.3996058702468872,
+    "eval_loss": 1.3293771743774414,
+    "eval_odds_ratio_loss": 0.7206552624702454,
+    "eval_rewards/accuracies": 0.5345454812049866,
+    "eval_rewards/chosen": -0.12573117017745972,
+    "eval_rewards/margins": 0.014229409396648407,
+    "eval_rewards/rejected": -0.13996057212352753,
+    "eval_runtime": 82.3315,
+    "eval_samples_per_second": 13.361,
+    "eval_sft_loss": 1.2573115825653076,
+    "eval_steps_per_second": 6.68
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9969690846635686,
+    "total_flos": 5.618252880760013e+17,
+    "train_loss": 1.3892074464594277,
+    "train_runtime": 8722.5011,
+    "train_samples_per_second": 3.404,
+    "train_steps_per_second": 0.213
+}