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-v5
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-7b-borpo-low-quality-v5
 
-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: 2.0035
 - Rewards/chosen: -0.6455

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 2.9865871833084947,
+    "eval_log_odds_chosen": 0.33574143052101135,
+    "eval_log_odds_ratio": -0.6769095063209534,
+    "eval_logits/chosen": 292.74676513671875,
+    "eval_logits/rejected": 259.2041320800781,
+    "eval_logps/chosen": -1.2910676002502441,
+    "eval_logps/rejected": -1.5239651203155518,
+    "eval_loss": 2.003471851348877,
+    "eval_nll_loss": 1.6439613103866577,
+    "eval_rewards/accuracies": 0.6115108132362366,
+    "eval_rewards/chosen": -0.6455338001251221,
+    "eval_rewards/margins": 0.1164487823843956,
+    "eval_rewards/rejected": -0.7619825601577759,
+    "eval_runtime": 378.1416,
+    "eval_samples": 553,
+    "eval_samples_per_second": 1.462,
+    "eval_steps_per_second": 0.368,
     "total_flos": 0.0,
     "train_loss": 1.6206341998543805,
     "train_runtime": 33576.7022,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 2.9865871833084947,
+    "eval_log_odds_chosen": 0.33574143052101135,
+    "eval_log_odds_ratio": -0.6769095063209534,
+    "eval_logits/chosen": 292.74676513671875,
+    "eval_logits/rejected": 259.2041320800781,
+    "eval_logps/chosen": -1.2910676002502441,
+    "eval_logps/rejected": -1.5239651203155518,
+    "eval_loss": 2.003471851348877,
+    "eval_nll_loss": 1.6439613103866577,
+    "eval_rewards/accuracies": 0.6115108132362366,
+    "eval_rewards/chosen": -0.6455338001251221,
+    "eval_rewards/margins": 0.1164487823843956,
+    "eval_rewards/rejected": -0.7619825601577759,
+    "eval_runtime": 378.1416,
+    "eval_samples": 553,
+    "eval_samples_per_second": 1.462,
+    "eval_steps_per_second": 0.368
+}

runs/Sep29_15-57-26_zizgpu06.cpu.stats.ox.ac.uk/events.out.tfevents.1727656261.zizgpu06.cpu.stats.ox.ac.uk.1840392.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bafd71ae5a060fc9467c5a9234dd178912153e26e08dd5c492001b1cf270483
+size 997