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:
@@ -14,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama3_AAID_mixed_train_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 AAID_mixed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8574
+- Loss: 0.8216
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.17500683620453925,
+    "eval_loss": 0.8215847015380859,
+    "eval_runtime": 2752.7727,
+    "eval_samples_per_second": 17.117,
+    "eval_steps_per_second": 2.14,
+    "total_flos": 2.8452078024759706e+17,
+    "train_loss": 0.46669088304042816,
+    "train_runtime": 28921.018,
+    "train_samples_per_second": 24.277,
+    "train_steps_per_second": 0.095
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.17500683620453925,
+    "eval_loss": 0.8215847015380859,
+    "eval_runtime": 2752.7727,
+    "eval_samples_per_second": 17.117,
+    "eval_steps_per_second": 2.14
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.17500683620453925,
+    "total_flos": 2.8452078024759706e+17,
+    "train_loss": 0.46669088304042816,
+    "train_runtime": 28921.018,
+    "train_samples_per_second": 24.277,
+    "train_steps_per_second": 0.095
+}

trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_metric": 0.8215847015380859,
+  "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-60",
+  "epoch": 0.17500683620453925,
+  "eval_steps": 20,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021875854525567406,
+      "grad_norm": 0.5130007266998291,
+      "learning_rate": 0.00029996062078124905,
+      "loss": 0.7577,
+      "step": 20
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "eval_loss": 0.83742755651474,
+      "eval_runtime": 2755.0602,
+      "eval_samples_per_second": 17.103,
+      "eval_steps_per_second": 2.138,
+      "step": 20
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "grad_norm": 0.4186599552631378,
+      "learning_rate": 0.00029984250380130117,
+      "loss": 0.4704,
+      "step": 40
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "eval_loss": 0.8378908038139343,
+      "eval_runtime": 2753.9472,
+      "eval_samples_per_second": 17.11,
+      "eval_steps_per_second": 2.139,
+      "step": 40
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 0.3842828571796417,
+      "learning_rate": 0.00029964571107821494,
+      "loss": 0.4495,
+      "step": 60
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 0.8215847015380859,
+      "eval_runtime": 2752.3483,
+      "eval_samples_per_second": 17.12,
+      "eval_steps_per_second": 2.14,
+      "step": 60
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "grad_norm": 0.3985615074634552,
+      "learning_rate": 0.0002993703459392396,
+      "loss": 0.4326,
+      "step": 80
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "eval_loss": 0.8271545767784119,
+      "eval_runtime": 2752.2053,
+      "eval_samples_per_second": 17.121,
+      "eval_steps_per_second": 2.14,
+      "step": 80
+    },
+    {
+      "epoch": 0.10937927262783702,
+      "grad_norm": 0.4009046256542206,
+      "learning_rate": 0.0002990165529665622,
+      "loss": 0.421,
+      "step": 100
+    },
+    {
+      "epoch": 0.10937927262783702,
+      "eval_loss": 0.8493741154670715,
+      "eval_runtime": 2752.6266,
+      "eval_samples_per_second": 17.118,
+      "eval_steps_per_second": 2.14,
+      "step": 100
+    },
+    {
+      "epoch": 0.13125512715340443,
+      "grad_norm": 0.37745875120162964,
+      "learning_rate": 0.00029858451792139453,
+      "loss": 0.406,
+      "step": 120
+    },
+    {
+      "epoch": 0.13125512715340443,
+      "eval_loss": 0.8483362793922424,
+      "eval_runtime": 2752.0772,
+      "eval_samples_per_second": 17.122,
+      "eval_steps_per_second": 2.14,
+      "step": 120
+    },
+    {
+      "epoch": 0.15313098167897182,
+      "grad_norm": 0.32064810395240784,
+      "learning_rate": 0.0002980744676464371,
+      "loss": 0.3974,
+      "step": 140
+    },
+    {
+      "epoch": 0.15313098167897182,
+      "eval_loss": 0.8315320014953613,
+      "eval_runtime": 2754.4395,
+      "eval_samples_per_second": 17.107,
+      "eval_steps_per_second": 2.138,
+      "step": 140
+    },
+    {
+      "epoch": 0.17500683620453925,
+      "grad_norm": 0.351032018661499,
+      "learning_rate": 0.00029748666994677467,
+      "loss": 0.3989,
+      "step": 160
+    },
+    {
+      "epoch": 0.17500683620453925,
+      "eval_loss": 0.8574348092079163,
+      "eval_runtime": 2752.7532,
+      "eval_samples_per_second": 17.117,
+      "eval_steps_per_second": 2.14,
+      "step": 160
+    },
+    {
+      "epoch": 0.17500683620453925,
+      "step": 160,
+      "total_flos": 2.8452078024759706e+17,
+      "train_loss": 0.46669088304042816,
+      "train_runtime": 28921.018,
+      "train_samples_per_second": 24.277,
+      "train_steps_per_second": 0.095
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2742,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8452078024759706e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}