End of training

README.md

@@ -2,9 +2,17 @@
 license: llama2
 base_model: elichen3051/llama2-7b-sft-chat-no-template
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
+- HuggingFaceH4/orca_dpo_pairs
+- HuggingFaceH4/cai-conversation-harmless
 model-index:
 - name: Llama2-7b-sft-chat-custom-template-dpo
   results: []
@@ -16,17 +24,17 @@ 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/eli3051/huggingface/runs/6n0utdab)
 # Llama2-7b-sft-chat-custom-template-dpo
 
-This model is a fine-tuned version of [elichen3051/llama2-7b-sft-chat-no-template](https://huggingface.co/elichen3051/llama2-7b-sft-chat-no-template) on the None dataset.
+This model is a fine-tuned version of [elichen3051/llama2-7b-sft-chat-no-template](https://huggingface.co/elichen3051/llama2-7b-sft-chat-no-template) on the HuggingFaceH4/ultrafeedback_binarized, the HuggingFaceH4/orca_dpo_pairs and the HuggingFaceH4/cai-conversation-harmless datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.4718
-- Rewards/chosen: -1.6795
-- Rewards/rejected: -3.1900
-- Rewards/accuracies: 0.6420
-- Rewards/margins: 1.5105
-- Logps/rejected: -518.9514
-- Logps/chosen: -379.1832
-- Logits/rejected: -2.6434
-- Logits/chosen: -2.6374
+- Loss: 0.4717
+- Rewards/chosen: -1.6807
+- Rewards/rejected: -3.1957
+- Rewards/accuracies: 0.6345
+- Rewards/margins: 1.5150
+- Logps/rejected: -519.5196
+- Logps/chosen: -379.2986
+- Logits/rejected: -2.7275
+- Logits/chosen: -2.7213
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.9940933254577673,
+    "eval_logits/chosen": -2.721290349960327,
+    "eval_logits/rejected": -2.727541208267212,
+    "eval_logps/chosen": -379.29864501953125,
+    "eval_logps/rejected": -519.5195922851562,
+    "eval_loss": 0.4716758131980896,
+    "eval_rewards/accuracies": 0.6344696879386902,
+    "eval_rewards/chosen": -1.6806795597076416,
+    "eval_rewards/margins": 1.5150176286697388,
+    "eval_rewards/rejected": -3.19569730758667,
+    "eval_runtime": 226.304,
+    "eval_samples": 3656,
+    "eval_samples_per_second": 16.155,
+    "eval_steps_per_second": 0.292,
     "total_flos": 0.0,
     "train_loss": 0.5345145690638872,
     "train_runtime": 33183.7631,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32002
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.9940933254577673,
+    "eval_logits/chosen": -2.721290349960327,
+    "eval_logits/rejected": -2.727541208267212,
+    "eval_logps/chosen": -379.29864501953125,
+    "eval_logps/rejected": -519.5195922851562,
+    "eval_loss": 0.4716758131980896,
+    "eval_rewards/accuracies": 0.6344696879386902,
+    "eval_rewards/chosen": -1.6806795597076416,
+    "eval_rewards/margins": 1.5150176286697388,
+    "eval_rewards/rejected": -3.19569730758667,
+    "eval_runtime": 226.304,
+    "eval_samples": 3656,
+    "eval_samples_per_second": 16.155,
+    "eval_steps_per_second": 0.292
+}

runs/Jun11_14-12-33_9e8ca53f2036/events.out.tfevents.1718149241.9e8ca53f2036.10634.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d767c85b3ad1b31e3dd8c1893f7bfd9690d1fc2f7a40f8a13080b963bc20d1
+size 828