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-0.0-0.0-cosine-2
   results: []
@@ -23,17 +17,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.0-cosine-2
 
-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: 4.5795
-- Rewards/chosen: -16.1471
-- Rewards/rejected: -25.8390
-- Rewards/accuracies: 0.3075
-- Rewards/margins: 9.6918
-- Logps/rejected: -601.5961
-- Logps/chosen: -399.7386
-- Logits/rejected: 4.1594
-- Logits/chosen: 3.9982
+- Logits/chosen: 2.2227
+- Logits/rejected: 2.3998
+- Logps/chosen: -231.4086
+- Logps/rejected: -327.2254
+- Loss: 0.6710
+- Rewards/accuracies: 0.3155
+- Rewards/chosen: -0.1518
+- Rewards/margins: 0.0862
+- Rewards/rejected: -0.2380
 
 ## Model description
 
@@ -52,7 +46,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.454537113325051e-07
+- learning_rate: 8.19247218325348e-07
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42

all_results.json

@@ -15,8 +15,8 @@
     "eval_steps_per_second": 0.55,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0151,
+    "train_runtime": 0.1474,
     "train_samples": 6113,
-    "train_samples_per_second": 807844.742,
-    "train_steps_per_second": 12686.585
+    "train_samples_per_second": 82937.448,
+    "train_steps_per_second": 1302.469
 }

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_08-23-57_qa-a100-005.crc.nd.edu/events.out.tfevents.1727526487.qa-a100-005.crc.nd.edu.128253.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794adc09cc67db4e706a29c5423133e2bd723ac702d66d9e24309bbdfbb03191
+size 6808

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 2.0,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0151,
+    "train_runtime": 0.1474,
     "train_samples": 6113,
-    "train_samples_per_second": 807844.742,
-    "train_steps_per_second": 12686.585
+    "train_samples_per_second": 82937.448,
+    "train_steps_per_second": 1302.469
 }

trainer_state.json

@@ -329,9 +329,9 @@
       "step": 192,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0151,
-      "train_samples_per_second": 807844.742,
-      "train_steps_per_second": 12686.585
+      "train_runtime": 0.1474,
+      "train_samples_per_second": 82937.448,
+      "train_steps_per_second": 1302.469
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e72b12738e7223504a07d5d00dad20ac1780fd7771a882714ca5d69e9ccd7ee
+oid sha256:47f4747ecc1a43dc104d8c92b54ff27690d6500810e68ed5cfcf56d8c9aa612f
 size 7672