End of training

README.md

@@ -2,9 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
 - trl
 - orpo
 - generated_from_trainer
+- trl
+- orpo
+- generated_from_trainer
+datasets:
+- vipinkatara/dataset_complete_final
 model-index:
 - name: Mistral-7B-v0.1-orpo-final1
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-7B-v0.1-orpo-final1
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the vipinkatara/dataset_complete_final dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 - Rewards/chosen: nan

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_log_odds_chosen": NaN,
+    "eval_log_odds_ratio": NaN,
+    "eval_logits/chosen": NaN,
+    "eval_logits/rejected": NaN,
+    "eval_logps/chosen": NaN,
+    "eval_logps/rejected": NaN,
+    "eval_loss": NaN,
+    "eval_nll_loss": NaN,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": NaN,
+    "eval_rewards/margins": NaN,
+    "eval_rewards/rejected": NaN,
+    "eval_runtime": 306.8444,
+    "eval_samples": 17893,
+    "eval_samples_per_second": 58.313,
+    "eval_steps_per_second": 1.825,
     "total_flos": 0.0,
     "train_loss": 0.04676872755621073,
     "train_runtime": 74758.4678,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 1.0,
+    "eval_log_odds_chosen": NaN,
+    "eval_log_odds_ratio": NaN,
+    "eval_logits/chosen": NaN,
+    "eval_logits/rejected": NaN,
+    "eval_logps/chosen": NaN,
+    "eval_logps/rejected": NaN,
+    "eval_loss": NaN,
+    "eval_nll_loss": NaN,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": NaN,
+    "eval_rewards/margins": NaN,
+    "eval_rewards/rejected": NaN,
+    "eval_runtime": 306.8444,
+    "eval_samples": 17893,
+    "eval_samples_per_second": 58.313,
+    "eval_steps_per_second": 1.825
+}

runs/May06_10-31-03_2bd66e41e5c24228a6d21c69169aa93f000000/events.out.tfevents.1715067059.2bd66e41e5c24228a6d21c69169aa93f000000.346.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec8f2a499dadcf88234ab3fc83ba5c7ff21ee490be05909c6e9b2165990450e
+size 997