End of training

README.md

@@ -1,8 +1,10 @@
 ---
-library_name: transformers
+library_name: peft
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B-Instruct
 tags:
+- llama-factory
+- lora
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct-reward-100
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the bct_non_cot_dpo_100 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3586
 - Accuracy: 0.9
@@ -58,7 +60,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.12.0
 - Transformers 4.46.1
 - Pytorch 2.5.1+cu124
 - Datasets 3.1.0
-- Tokenizers 0.20.3
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022db441f59a672ec102930e9d928f3c8f2bfdc022833f02fde00cadaf206414
+size 83945296

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.488888888888889,
+    "eval_accuracy": 0.9,
+    "eval_loss": 0.3585858941078186,
+    "eval_runtime": 0.8147,
+    "eval_samples_per_second": 12.275,
+    "eval_steps_per_second": 6.137,
+    "total_flos": 0.0,
+    "train_loss": 0.13070689755084458,
+    "train_runtime": 217.2241,
+    "train_samples_per_second": 4.143,
+    "train_steps_per_second": 0.23
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.488888888888889,
+    "eval_accuracy": 0.9,
+    "eval_loss": 0.3585858941078186,
+    "eval_runtime": 0.8147,
+    "eval_samples_per_second": 12.275,
+    "eval_steps_per_second": 6.137
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.488888888888889,
+    "total_flos": 0.0,
+    "train_loss": 0.13070689755084458,
+    "train_runtime": 217.2241,
+    "train_samples_per_second": 4.143,
+    "train_steps_per_second": 0.23
+}

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.488888888888889,
+  "eval_steps": 50,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 15.148612976074219,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 0.5463,
+      "step": 10
+    },
+    {
+      "epoch": 3.7555555555555555,
+      "grad_norm": 1.5098639726638794,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1026,
+      "step": 20
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 8.635929407319054e-05,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0046,
+      "step": 30
+    },
+    {
+      "epoch": 7.5777777777777775,
+      "grad_norm": 0.0007328893407247961,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 9.488888888888889,
+      "grad_norm": 1.457463440601714e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 9.488888888888889,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.3585858941078186,
+      "eval_runtime": 0.8163,
+      "eval_samples_per_second": 12.25,
+      "eval_steps_per_second": 6.125,
+      "step": 50
+    },
+    {
+      "epoch": 9.488888888888889,
+      "step": 50,
+      "total_flos": 0.0,
+      "train_loss": 0.13070689755084458,
+      "train_runtime": 217.2241,
+      "train_samples_per_second": 4.143,
+      "train_steps_per_second": 0.23
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

value_head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49866d6862428bcce2401fc799bc910f2d295056c24d5182b7fc6fc689678fa
+size 16588