End of training

README.md

@@ -2,6 +2,7 @@
 library_name: peft
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B
 model-index:
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # LLama3_deneme
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the emollms_ei_oc_mixed dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1256
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.4979253112033195,
+    "eval_loss": 0.12561871111392975,
+    "eval_runtime": 54.7022,
+    "eval_samples_per_second": 15.667,
+    "eval_steps_per_second": 1.974,
+    "total_flos": 2.42755307569152e+16,
+    "train_loss": 0.2621128797531128,
+    "train_runtime": 650.0908,
+    "train_samples_per_second": 5.929,
+    "train_steps_per_second": 0.023
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.4979253112033195,
+    "eval_loss": 0.12561871111392975,
+    "eval_runtime": 54.7022,
+    "eval_samples_per_second": 15.667,
+    "eval_steps_per_second": 1.974
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.4979253112033195,
+    "total_flos": 2.42755307569152e+16,
+    "train_loss": 0.2621128797531128,
+    "train_runtime": 650.0908,
+    "train_samples_per_second": 5.929,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.12561871111392975,
+  "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-10",
+  "epoch": 0.4979253112033195,
+  "eval_steps": 10,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33195020746887965,
+      "grad_norm": 0.14592523872852325,
+      "learning_rate": 7.500000000000002e-05,
+      "loss": 0.3294,
+      "step": 10
+    },
+    {
+      "epoch": 0.33195020746887965,
+      "eval_loss": 0.12561871111392975,
+      "eval_runtime": 54.6753,
+      "eval_samples_per_second": 15.674,
+      "eval_steps_per_second": 1.975,
+      "step": 10
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "step": 15,
+      "total_flos": 2.42755307569152e+16,
+      "train_loss": 0.2621128797531128,
+      "train_runtime": 650.0908,
+      "train_samples_per_second": 5.929,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.42755307569152e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}