End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: gemma
 base_model: google/gemma-7b
 tags:
+- alignment-handbook
 - trl
 - orpo
 - generated_from_trainer
+- trl
+- orpo
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
 model-index:
 - name: gemma-7b-borpo
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-7b-borpo
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the argilla/dpo-mix-7k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5984
 - Rewards/chosen: -0.0575

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 2.9904761904761905,
+    "eval_log_odds_chosen": 0.367882639169693,
+    "eval_log_odds_ratio": -0.6760825514793396,
+    "eval_logits/chosen": 299.86248779296875,
+    "eval_logits/rejected": 270.96282958984375,
+    "eval_logps/chosen": -1.1505995988845825,
+    "eval_logps/rejected": -1.3976730108261108,
+    "eval_loss": 1.59840989112854,
+    "eval_nll_loss": 1.5312451124191284,
+    "eval_rewards/accuracies": 0.5899280309677124,
+    "eval_rewards/chosen": -0.057529982179403305,
+    "eval_rewards/margins": 0.012353661470115185,
+    "eval_rewards/rejected": -0.06988365203142166,
+    "eval_runtime": 112.534,
+    "eval_samples": 553,
+    "eval_samples_per_second": 4.914,
+    "eval_steps_per_second": 1.235,
     "total_flos": 0.0,
     "train_loss": 1.4937715783493788,
     "train_runtime": 12592.9879,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 2.9904761904761905,
+    "eval_log_odds_chosen": 0.367882639169693,
+    "eval_log_odds_ratio": -0.6760825514793396,
+    "eval_logits/chosen": 299.86248779296875,
+    "eval_logits/rejected": 270.96282958984375,
+    "eval_logps/chosen": -1.1505995988845825,
+    "eval_logps/rejected": -1.3976730108261108,
+    "eval_loss": 1.59840989112854,
+    "eval_nll_loss": 1.5312451124191284,
+    "eval_rewards/accuracies": 0.5899280309677124,
+    "eval_rewards/chosen": -0.057529982179403305,
+    "eval_rewards/margins": 0.012353661470115185,
+    "eval_rewards/rejected": -0.06988365203142166,
+    "eval_runtime": 112.534,
+    "eval_samples": 553,
+    "eval_samples_per_second": 4.914,
+    "eval_steps_per_second": 1.235
+}

runs/Sep21_12-42-46_65ecb96dba42/events.out.tfevents.1726935580.65ecb96dba42.271982.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e873b78441df4ce70f690fac903eb759244348172ee08ecb7598b67f45fc71
+size 997