End of training

README.md

@@ -2,9 +2,12 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 library_name: peft
 model-index:
 - name: zephyr-7b-nca_pair-qlora-lr5e6-beta0.1
@@ -17,17 +20,17 @@ 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/1014579852qq-tsinghua-university/huggingface/runs/p6zmvlxg)
 # zephyr-7b-nca_pair-qlora-lr5e6-beta0.1
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3409
-- Rewards/chosen: 0.1433
-- Rewards/rejected: -0.3268
-- Rewards/accuracies: 0.7475
-- Rewards/margins: 0.4701
-- Logps/rejected: -257.3707
-- Logps/chosen: -270.7436
-- Logits/rejected: -2.2339
-- Logits/chosen: -2.3137
+- Loss: 1.3408
+- Rewards/chosen: 0.1419
+- Rewards/rejected: -0.3279
+- Rewards/accuracies: 0.7450
+- Rewards/margins: 0.4698
+- Logps/rejected: -257.3817
+- Logps/chosen: -270.7577
+- Logits/rejected: -2.2321
+- Logits/chosen: -2.3119
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9996728819103696,
+    "eval_logits/chosen": -2.3119311332702637,
+    "eval_logits/rejected": -2.2321126461029053,
+    "eval_logps/chosen": -270.7576904296875,
+    "eval_logps/rejected": -257.3817138671875,
+    "eval_loss": 1.3408429622650146,
+    "eval_rewards/accuracies": 0.7450000047683716,
+    "eval_rewards/chosen": 0.1418824940919876,
+    "eval_rewards/margins": 0.4697629511356354,
+    "eval_rewards/rejected": -0.32788047194480896,
+    "eval_runtime": 191.9401,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 10.42,
+    "eval_steps_per_second": 0.521,
     "total_flos": 0.0,
     "train_loss": 1.343712306771603,
     "train_runtime": 13958.9948,

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9996728819103696,
+    "eval_logits/chosen": -2.3119311332702637,
+    "eval_logits/rejected": -2.2321126461029053,
+    "eval_logps/chosen": -270.7576904296875,
+    "eval_logps/rejected": -257.3817138671875,
+    "eval_loss": 1.3408429622650146,
+    "eval_rewards/accuracies": 0.7450000047683716,
+    "eval_rewards/chosen": 0.1418824940919876,
+    "eval_rewards/margins": 0.4697629511356354,
+    "eval_rewards/rejected": -0.32788047194480896,
+    "eval_runtime": 191.9401,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 10.42,
+    "eval_steps_per_second": 0.521
+}