End of training

README.md

@@ -3,9 +3,15 @@ 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
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan-4e-07-0.45-cosine-1.0
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-4e-07-0.45-cosine-1.0
 
-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.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 0.6494
-- Rewards/chosen: 0.7541
-- Rewards/rejected: 0.2411
-- Rewards/accuracies: 0.3552
-- Rewards/margins: 0.5130
-- Logps/rejected: -80.5926
-- Logps/chosen: -72.8155
-- Logits/rejected: -2.5245
-- Logits/chosen: -2.5411
+- Loss: 0.6450
+- Rewards/chosen: 0.6594
+- Rewards/rejected: 0.1472
+- Rewards/accuracies: 0.3532
+- Rewards/margins: 0.5122
+- Logps/rejected: -80.8012
+- Logps/chosen: -73.0258
+- Logits/rejected: -2.5362
+- Logits/chosen: -2.5527
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.5527360439300537,
+    "eval_logits/rejected": -2.5362329483032227,
+    "eval_logps/chosen": -73.02584075927734,
+    "eval_logps/rejected": -80.80119323730469,
+    "eval_loss": 0.6450211405754089,
+    "eval_rewards/accuracies": 0.3531745970249176,
+    "eval_rewards/chosen": 0.6594291925430298,
+    "eval_rewards/margins": 0.5122048258781433,
+    "eval_rewards/rejected": 0.14722436666488647,
+    "eval_runtime": 113.9424,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.553,
+    "eval_steps_per_second": 0.553,
     "total_flos": 0.0,
     "train_loss": 0.6522094729885407,
     "train_runtime": 3372.3295,

config.json

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

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.5527360439300537,
+    "eval_logits/rejected": -2.5362329483032227,
+    "eval_logps/chosen": -73.02584075927734,
+    "eval_logps/rejected": -80.80119323730469,
+    "eval_loss": 0.6450211405754089,
+    "eval_rewards/accuracies": 0.3531745970249176,
+    "eval_rewards/chosen": 0.6594291925430298,
+    "eval_rewards/margins": 0.5122048258781433,
+    "eval_rewards/rejected": 0.14722436666488647,
+    "eval_runtime": 113.9424,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.553,
+    "eval_steps_per_second": 0.553
+}

runs/Sep27_19-52-54_qa-a100-005.crc.nd.edu/events.out.tfevents.1727485089.qa-a100-005.crc.nd.edu.4162250.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb295e6e17d20924dd1fa9a9acae3939bebeea6c9c56cceefe15af60284ad35d
+size 828