End of training

README.md

@@ -2,10 +2,15 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-Instruct-v0.2
+datasets:
+- nthakur/multilingual-truthy-v0.1-dpo-pairs
+- nthakur/multilingual-orca-dpo-pairs
+- nthakur/multilingual-mistral-neg-orca-dpo-pairs
 model-index:
 - name: mistral-7b-instruct-v0.2-dpo-multilingual-mix-1st-apr-final
   results: []
@@ -16,7 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-instruct-v0.2-dpo-multilingual-mix-1st-apr-final
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the nthakur/multilingual-truthy-v0.1-dpo-pairs, the nthakur/multilingual-orca-dpo-pairs and the nthakur/multilingual-mistral-neg-orca-dpo-pairs datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.0524
+- Rewards/chosen: -0.1806
+- Rewards/rejected: -11.0616
+- Rewards/accuracies: 0.9918
+- Rewards/margins: 10.8811
+- Logps/rejected: -1280.7075
+- Logps/chosen: -363.8373
+- Logits/rejected: -0.2239
+- Logits/chosen: -0.5036
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.5036042332649231,
+    "eval_logits/rejected": -0.22393426299095154,
+    "eval_logps/chosen": -363.8373107910156,
+    "eval_logps/rejected": -1280.70751953125,
+    "eval_loss": 0.05244915559887886,
+    "eval_rewards/accuracies": 0.9918341636657715,
+    "eval_rewards/chosen": -0.18055257201194763,
+    "eval_rewards/margins": 10.881051063537598,
+    "eval_rewards/rejected": -11.061604499816895,
+    "eval_runtime": 1903.9644,
+    "eval_samples": 3174,
+    "eval_samples_per_second": 1.667,
+    "eval_steps_per_second": 0.105,
     "train_loss": 0.150745850255092,
     "train_runtime": 48820.8334,
     "train_samples": 38447,

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.5036042332649231,
+    "eval_logits/rejected": -0.22393426299095154,
+    "eval_logps/chosen": -363.8373107910156,
+    "eval_logps/rejected": -1280.70751953125,
+    "eval_loss": 0.05244915559887886,
+    "eval_rewards/accuracies": 0.9918341636657715,
+    "eval_rewards/chosen": -0.18055257201194763,
+    "eval_rewards/margins": 10.881051063537598,
+    "eval_rewards/rejected": -11.061604499816895,
+    "eval_runtime": 1903.9644,
+    "eval_samples": 3174,
+    "eval_samples_per_second": 1.667,
+    "eval_steps_per_second": 0.105
+}