End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: deepseek-ai/deepseek-math-7b-base
+datasets:
+- zfz1/my_preference_gsm8k_deepseek
 library_name: peft
 license: other
 tags:
+- alignment-handbook
 - trl
 - orpo
 - generated_from_trainer
@@ -17,7 +20,20 @@ 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/thuzfz1/huggingface/runs/zs68qfsi)
 # deepseek-8b-orpo-lora
 
-This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on an unknown dataset.
+This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on the zfz1/my_preference_gsm8k_deepseek dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1456
+- Rewards/chosen: -0.0726
+- Rewards/rejected: -0.0757
+- Rewards/accuracies: 0.5647
+- Rewards/margins: 0.0031
+- Logps/rejected: -0.7569
+- Logps/chosen: -0.7262
+- Logits/rejected: 30.3288
+- Logits/chosen: 30.4427
+- Nll Loss: 1.0719
+- Log Odds Ratio: -0.6909
+- Log Odds Chosen: 0.0553
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.9936102236421727,
+    "eval_log_odds_chosen": 0.05526316165924072,
+    "eval_log_odds_ratio": -0.6908599138259888,
+    "eval_logits/chosen": 30.44268798828125,
+    "eval_logits/rejected": 30.32880210876465,
+    "eval_logps/chosen": -0.7262152433395386,
+    "eval_logps/rejected": -0.7568790316581726,
+    "eval_loss": 1.1456295251846313,
+    "eval_nll_loss": 1.071852684020996,
+    "eval_rewards/accuracies": 0.5647059082984924,
+    "eval_rewards/chosen": -0.07262152433395386,
+    "eval_rewards/margins": 0.0030663711950182915,
+    "eval_rewards/rejected": -0.07568789273500443,
+    "eval_runtime": 247.9026,
+    "eval_samples": 5398,
+    "eval_samples_per_second": 21.775,
+    "eval_steps_per_second": 0.343,
     "total_flos": 0.0,
     "train_loss": 1.3676127867820935,
     "train_runtime": 5524.9246,

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-math-7b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 102400
+}

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 1.9936102236421727,
+    "eval_log_odds_chosen": 0.05526316165924072,
+    "eval_log_odds_ratio": -0.6908599138259888,
+    "eval_logits/chosen": 30.44268798828125,
+    "eval_logits/rejected": 30.32880210876465,
+    "eval_logps/chosen": -0.7262152433395386,
+    "eval_logps/rejected": -0.7568790316581726,
+    "eval_loss": 1.1456295251846313,
+    "eval_nll_loss": 1.071852684020996,
+    "eval_rewards/accuracies": 0.5647059082984924,
+    "eval_rewards/chosen": -0.07262152433395386,
+    "eval_rewards/margins": 0.0030663711950182915,
+    "eval_rewards/rejected": -0.07568789273500443,
+    "eval_runtime": 247.9026,
+    "eval_samples": 5398,
+    "eval_samples_per_second": 21.775,
+    "eval_steps_per_second": 0.343
+}

runs/Jul15_00-31-06_allegro-adams/events.out.tfevents.1721034884.allegro-adams.981573.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e3e42cdc1f7ea818293b9e9e14b4747b631016f5eece9e9794686da41b1730
+size 997