Model save

README.md

@@ -3,16 +3,10 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
-- alignment-handbook
-- trl
-- dpo
-- generated_from_trainer
 - trl
 - dpo
 - alignment-handbook
 - generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan
   results: []
@@ -23,17 +17,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5960
-- Rewards/chosen: -0.6252
-- Rewards/rejected: -1.0907
-- Rewards/accuracies: 0.3690
-- Rewards/margins: 0.4655
-- Logps/rejected: -190.1945
-- Logps/chosen: -137.0085
-- Logits/rejected: 0.9319
-- Logits/chosen: 0.4522
+- Logits/chosen: 0.4326
+- Logits/rejected: 0.9106
+- Logps/chosen: -136.2882
+- Logps/rejected: -189.5506
+- Loss: 0.5958
+- Rewards/accuracies: 0.3710
+- Rewards/chosen: -0.6180
+- Rewards/margins: 0.4663
+- Rewards/rejected: -1.0842
 
 ## Model description
 

all_results.json

@@ -15,8 +15,8 @@
     "eval_steps_per_second": 0.55,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0268,
-    "train_samples": 18340,
-    "train_samples_per_second": 685440.279,
-    "train_steps_per_second": 10726.356
+    "train_runtime": 0.0165,
+    "train_samples": 6113,
+    "train_samples_per_second": 369998.418,
+    "train_steps_per_second": 5810.543
 }

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

runs/Sep28_03-46-54_qa-a100-005.crc.nd.edu/events.out.tfevents.1727509796.qa-a100-005.crc.nd.edu.84817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839bfb5dad32914cbdf849c609e075bcc6fdf04826f38afae89d36f8f7dbc5be
+size 6547

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 0.9994767137624281,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0268,
-    "train_samples": 18340,
-    "train_samples_per_second": 685440.279,
-    "train_steps_per_second": 10726.356
+    "train_runtime": 0.0165,
+    "train_samples": 6113,
+    "train_samples_per_second": 369998.418,
+    "train_steps_per_second": 5810.543
 }

trainer_state.json

@@ -1597,13 +1597,13 @@
       "step": 955,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0268,
-      "train_samples_per_second": 685440.279,
-      "train_steps_per_second": 10726.356
+      "train_runtime": 0.0165,
+      "train_samples_per_second": 369998.418,
+      "train_steps_per_second": 5810.543
     }
   ],
   "logging_steps": 10,
-  "max_steps": 287,
+  "max_steps": 96,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0f835252b36fd36cd8edf822ccf745170faee0971ede50f0f053d29e698185
+oid sha256:8ade03fb878ac7c60053df63e47d29e251159bd45be422b248832744b06632c0
 size 7544