End of training

README.md

@@ -2,9 +2,15 @@
 license: other
 base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
 model-index:
 - name: zephyr-7b-gemma-dpo
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/kirill-fedyanin/huggingface/runs/uj2to373)
 # zephyr-7b-gemma-dpo
 
-This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4608
-- Rewards/chosen: -4.1286
-- Rewards/rejected: -5.8457
+- Loss: 0.4658
+- Rewards/chosen: -4.1134
+- Rewards/rejected: -5.8777
 - Rewards/accuracies: 0.7292
-- Rewards/margins: 1.7171
-- Logps/rejected: -478.9854
-- Logps/chosen: -446.2400
-- Logits/rejected: 85.7808
-- Logits/chosen: 91.4893
+- Rewards/margins: 1.7644
+- Logps/rejected: -479.6258
+- Logps/chosen: -445.9359
+- Logits/rejected: 85.7594
+- Logits/chosen: 91.4868
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.971563981042654,
+    "eval_logits/chosen": 91.48676300048828,
+    "eval_logits/rejected": 85.7594223022461,
+    "eval_logps/chosen": -445.9359436035156,
+    "eval_logps/rejected": -479.6258239746094,
+    "eval_loss": 0.465834379196167,
+    "eval_rewards/accuracies": 0.7291666865348816,
+    "eval_rewards/chosen": -4.113387584686279,
+    "eval_rewards/margins": 1.7643555402755737,
+    "eval_rewards/rejected": -5.877742767333984,
+    "eval_runtime": 131.0653,
+    "eval_samples": 750,
+    "eval_samples_per_second": 5.722,
+    "eval_steps_per_second": 0.183,
     "total_flos": 0.0,
     "train_loss": 0.38906457561713,
     "train_runtime": 3484.4936,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.971563981042654,
+    "eval_logits/chosen": 91.48676300048828,
+    "eval_logits/rejected": 85.7594223022461,
+    "eval_logps/chosen": -445.9359436035156,
+    "eval_logps/rejected": -479.6258239746094,
+    "eval_loss": 0.465834379196167,
+    "eval_rewards/accuracies": 0.7291666865348816,
+    "eval_rewards/chosen": -4.113387584686279,
+    "eval_rewards/margins": 1.7643555402755737,
+    "eval_rewards/rejected": -5.877742767333984,
+    "eval_runtime": 131.0653,
+    "eval_samples": 750,
+    "eval_samples_per_second": 5.722,
+    "eval_steps_per_second": 0.183
+}

runs/May14_19-58-02_t01pdscgpu05/events.out.tfevents.1715706965.t01pdscgpu05.1564816.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578b19dbc8e6a36372fdfe0d4e15b3205c910642221501d507277fd108dfd6be
+size 815