End of training

README.md

@@ -2,10 +2,16 @@
 license: mit
 library_name: peft
 tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
 base_model: HuggingFaceH4/mistral-7b-sft-beta
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: mistral-sft-7b-dpo-qlora
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-sft-7b-dpo-qlora
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -122.9924
+- Logps/chosen: -86.4923
+- Logits/rejected: -3.0448
+- Logits/chosen: -2.9816
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.9815621376037598,
+    "eval_logits/rejected": -3.0448005199432373,
+    "eval_logps/chosen": -86.49230194091797,
+    "eval_logps/rejected": -122.99235534667969,
+    "eval_loss": 0.6931473016738892,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 12.7004,
+    "eval_samples": 20,
+    "eval_samples_per_second": 1.575,
+    "eval_steps_per_second": 0.157,
     "train_loss": 0.5198603868484497,
     "train_runtime": 25.1995,
     "train_samples": 20,

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.9815621376037598,
+    "eval_logits/rejected": -3.0448005199432373,
+    "eval_logps/chosen": -86.49230194091797,
+    "eval_logps/rejected": -122.99235534667969,
+    "eval_loss": 0.6931473016738892,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 12.7004,
+    "eval_samples": 20,
+    "eval_samples_per_second": 1.575,
+    "eval_steps_per_second": 0.157
+}