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-0.0-0.4-polynomial-2
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.4-polynomial-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 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: 0.7712
-- Rewards/chosen: 0.7556
-- Rewards/rejected: 0.1333
-- Rewards/accuracies: 0.3313
-- Rewards/margins: 0.6223
-- Logps/rejected: -80.8200
-- Logps/chosen: -72.7430
-- Logits/rejected: -2.5200
-- Logits/chosen: -2.5356
+- Loss: 0.8224
+- Rewards/chosen: -0.8205
+- Rewards/rejected: -1.9403
+- Rewards/accuracies: 0.3433
+- Rewards/margins: 1.1198
+- Logps/rejected: -85.6178
+- Logps/chosen: -76.3898
+- Logits/rejected: -2.4242
+- Logits/chosen: -2.4424
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 2.0,
+    "eval_logits/chosen": -2.4423749446868896,
+    "eval_logits/rejected": -2.424229860305786,
+    "eval_logps/chosen": -76.38975524902344,
+    "eval_logps/rejected": -85.61776733398438,
+    "eval_loss": 0.8224331140518188,
+    "eval_rewards/accuracies": 0.3432539701461792,
+    "eval_rewards/chosen": -0.8205374479293823,
+    "eval_rewards/margins": 1.119767189025879,
+    "eval_rewards/rejected": -1.9403046369552612,
+    "eval_runtime": 113.8823,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.562,
+    "eval_steps_per_second": 0.553,
     "total_flos": 0.0,
     "train_loss": 0.5438582648833593,
     "train_runtime": 2038.8345,

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": 2.0,
+    "eval_logits/chosen": -2.4423749446868896,
+    "eval_logits/rejected": -2.424229860305786,
+    "eval_logps/chosen": -76.38975524902344,
+    "eval_logps/rejected": -85.61776733398438,
+    "eval_loss": 0.8224331140518188,
+    "eval_rewards/accuracies": 0.3432539701461792,
+    "eval_rewards/chosen": -0.8205374479293823,
+    "eval_rewards/margins": 1.119767189025879,
+    "eval_rewards/rejected": -1.9403046369552612,
+    "eval_runtime": 113.8823,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.562,
+    "eval_steps_per_second": 0.553
+}

runs/Sep24_11-01-55_qa-a100-004.crc.nd.edu/events.out.tfevents.1727192564.qa-a100-004.crc.nd.edu.1820830.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb8b37d54bedf7bc562c4cc0001b266a581d958626ba9fa23c6713fa60b02b5
+size 828