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:
+- silviasapora/low_quality_dpo7k
 model-index:
 - name: gemma-7b-borpo-low-quality
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-7b-borpo-low-quality
 
-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 silviasapora/low_quality_dpo7k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5380
 - Rewards/chosen: -0.0547

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 2.9865871833084947,
+    "eval_log_odds_chosen": 0.27211081981658936,
+    "eval_log_odds_ratio": -0.7039158344268799,
+    "eval_logits/chosen": 296.6807556152344,
+    "eval_logits/rejected": 267.234619140625,
+    "eval_logps/chosen": -1.0933129787445068,
+    "eval_logps/rejected": -1.2508149147033691,
+    "eval_loss": 1.5379581451416016,
+    "eval_nll_loss": 1.4702765941619873,
+    "eval_rewards/accuracies": 0.5467625856399536,
+    "eval_rewards/chosen": -0.054665643721818924,
+    "eval_rewards/margins": 0.007875093258917332,
+    "eval_rewards/rejected": -0.06254073977470398,
+    "eval_runtime": 112.3528,
+    "eval_samples": 553,
+    "eval_samples_per_second": 4.922,
+    "eval_steps_per_second": 1.237,
     "total_flos": 0.0,
     "train_loss": 1.4583633707431025,
     "train_runtime": 13840.413,

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": 2.9865871833084947,
+    "eval_log_odds_chosen": 0.27211081981658936,
+    "eval_log_odds_ratio": -0.7039158344268799,
+    "eval_logits/chosen": 296.6807556152344,
+    "eval_logits/rejected": 267.234619140625,
+    "eval_logps/chosen": -1.0933129787445068,
+    "eval_logps/rejected": -1.2508149147033691,
+    "eval_loss": 1.5379581451416016,
+    "eval_nll_loss": 1.4702765941619873,
+    "eval_rewards/accuracies": 0.5467625856399536,
+    "eval_rewards/chosen": -0.054665643721818924,
+    "eval_rewards/margins": 0.007875093258917332,
+    "eval_rewards/rejected": -0.06254073977470398,
+    "eval_runtime": 112.3528,
+    "eval_samples": 553,
+    "eval_samples_per_second": 4.922,
+    "eval_steps_per_second": 1.237
+}

runs/Sep20_22-31-39_65ecb96dba42/events.out.tfevents.1726885774.65ecb96dba42.240178.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290d291474cf79db25057754860f09bc43212a2cbcb8c0ae98abbed02d3dc879
+size 997