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_new_mixed_train
 
-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_new_mixed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8523
+- Loss: 0.8102
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.17500683620453925,
+    "eval_loss": 0.8101749420166016,
+    "eval_runtime": 211.4442,
+    "eval_samples_per_second": 22.285,
+    "eval_steps_per_second": 0.7,
+    "total_flos": 2.8452078024759706e+17,
+    "train_loss": 0.4666908696293831,
+    "train_runtime": 10276.9259,
+    "train_samples_per_second": 68.32,
+    "train_steps_per_second": 0.267
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.17500683620453925,
+    "eval_loss": 0.8101749420166016,
+    "eval_runtime": 211.4442,
+    "eval_samples_per_second": 22.285,
+    "eval_steps_per_second": 0.7
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.17500683620453925,
+    "total_flos": 2.8452078024759706e+17,
+    "train_loss": 0.4666908696293831,
+    "train_runtime": 10276.9259,
+    "train_samples_per_second": 68.32,
+    "train_steps_per_second": 0.267
+}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": 0.8101749420166016,
+  "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-110",
+  "epoch": 0.17500683620453925,
+  "eval_steps": 10,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010937927262783703,
+      "grad_norm": 1.4765043258666992,
+      "learning_rate": 0.00029999015487222375,
+      "loss": 1.0078,
+      "step": 10
+    },
+    {
+      "epoch": 0.010937927262783703,
+      "eval_loss": 0.9153856635093689,
+      "eval_runtime": 211.8553,
+      "eval_samples_per_second": 22.242,
+      "eval_steps_per_second": 0.699,
+      "step": 10
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "grad_norm": 0.5130007266998291,
+      "learning_rate": 0.00029996062078124905,
+      "loss": 0.5077,
+      "step": 20
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "eval_loss": 0.8372363448143005,
+      "eval_runtime": 211.905,
+      "eval_samples_per_second": 22.236,
+      "eval_steps_per_second": 0.698,
+      "step": 20
+    },
+    {
+      "epoch": 0.03281378178835111,
+      "grad_norm": 0.6383033394813538,
+      "learning_rate": 0.0002999114016039678,
+      "loss": 0.4613,
+      "step": 30
+    },
+    {
+      "epoch": 0.03281378178835111,
+      "eval_loss": 0.8332751989364624,
+      "eval_runtime": 212.0634,
+      "eval_samples_per_second": 22.22,
+      "eval_steps_per_second": 0.698,
+      "step": 30
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "grad_norm": 0.4186599552631378,
+      "learning_rate": 0.00029984250380130117,
+      "loss": 0.4794,
+      "step": 40
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "eval_loss": 0.832076370716095,
+      "eval_runtime": 211.9021,
+      "eval_samples_per_second": 22.237,
+      "eval_steps_per_second": 0.698,
+      "step": 40
+    },
+    {
+      "epoch": 0.05468963631391851,
+      "grad_norm": 0.39893779158592224,
+      "learning_rate": 0.0002997539364173515,
+      "loss": 0.4624,
+      "step": 50
+    },
+    {
+      "epoch": 0.05468963631391851,
+      "eval_loss": 0.8181496858596802,
+      "eval_runtime": 211.7599,
+      "eval_samples_per_second": 22.252,
+      "eval_steps_per_second": 0.699,
+      "step": 50
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 0.3842828571796417,
+      "learning_rate": 0.00029964571107821494,
+      "loss": 0.4366,
+      "step": 60
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 0.8192259669303894,
+      "eval_runtime": 212.0659,
+      "eval_samples_per_second": 22.22,
+      "eval_steps_per_second": 0.698,
+      "step": 60
+    },
+    {
+      "epoch": 0.07656549083948591,
+      "grad_norm": 0.36217156052589417,
+      "learning_rate": 0.00029951784199045534,
+      "loss": 0.4323,
+      "step": 70
+    },
+    {
+      "epoch": 0.07656549083948591,
+      "eval_loss": 0.8174964189529419,
+      "eval_runtime": 211.9859,
+      "eval_samples_per_second": 22.228,
+      "eval_steps_per_second": 0.698,
+      "step": 70
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "grad_norm": 0.3985615074634552,
+      "learning_rate": 0.0002993703459392396,
+      "loss": 0.433,
+      "step": 80
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "eval_loss": 0.8255279064178467,
+      "eval_runtime": 212.0217,
+      "eval_samples_per_second": 22.224,
+      "eval_steps_per_second": 0.698,
+      "step": 80
+    },
+    {
+      "epoch": 0.09844134536505332,
+      "grad_norm": 0.38471728563308716,
+      "learning_rate": 0.00029920324228613376,
+      "loss": 0.4401,
+      "step": 90
+    },
+    {
+      "epoch": 0.09844134536505332,
+      "eval_loss": 0.8293283581733704,
+      "eval_runtime": 212.0935,
+      "eval_samples_per_second": 22.217,
+      "eval_steps_per_second": 0.698,
+      "step": 90
+    },
+    {
+      "epoch": 0.10937927262783702,
+      "grad_norm": 0.4009046256542206,
+      "learning_rate": 0.0002990165529665622,
+      "loss": 0.4019,
+      "step": 100
+    },
+    {
+      "epoch": 0.10937927262783702,
+      "eval_loss": 0.8467400074005127,
+      "eval_runtime": 211.8895,
+      "eval_samples_per_second": 22.238,
+      "eval_steps_per_second": 0.698,
+      "step": 100
+    },
+    {
+      "epoch": 0.12031719989062073,
+      "grad_norm": 0.3922439515590668,
+      "learning_rate": 0.0002988103024869277,
+      "loss": 0.4112,
+      "step": 110
+    },
+    {
+      "epoch": 0.12031719989062073,
+      "eval_loss": 0.8101749420166016,
+      "eval_runtime": 211.8892,
+      "eval_samples_per_second": 22.238,
+      "eval_steps_per_second": 0.698,
+      "step": 110
+    },
+    {
+      "epoch": 0.13125512715340443,
+      "grad_norm": 0.37745875120162964,
+      "learning_rate": 0.00029858451792139453,
+      "loss": 0.4009,
+      "step": 120
+    },
+    {
+      "epoch": 0.13125512715340443,
+      "eval_loss": 0.8458078503608704,
+      "eval_runtime": 211.8294,
+      "eval_samples_per_second": 22.244,
+      "eval_steps_per_second": 0.699,
+      "step": 120
+    },
+    {
+      "epoch": 0.14219305441618812,
+      "grad_norm": 0.3471999764442444,
+      "learning_rate": 0.0002983392289083346,
+      "loss": 0.4023,
+      "step": 130
+    },
+    {
+      "epoch": 0.14219305441618812,
+      "eval_loss": 0.8429893255233765,
+      "eval_runtime": 211.9578,
+      "eval_samples_per_second": 22.231,
+      "eval_steps_per_second": 0.698,
+      "step": 130
+    },
+    {
+      "epoch": 0.15313098167897182,
+      "grad_norm": 0.32064810395240784,
+      "learning_rate": 0.0002980744676464371,
+      "loss": 0.3924,
+      "step": 140
+    },
+    {
+      "epoch": 0.15313098167897182,
+      "eval_loss": 0.8300093412399292,
+      "eval_runtime": 211.8193,
+      "eval_samples_per_second": 22.245,
+      "eval_steps_per_second": 0.699,
+      "step": 140
+    },
+    {
+      "epoch": 0.16406890894175555,
+      "grad_norm": 0.31663310527801514,
+      "learning_rate": 0.0002977902688904813,
+      "loss": 0.4079,
+      "step": 150
+    },
+    {
+      "epoch": 0.16406890894175555,
+      "eval_loss": 0.8369516134262085,
+      "eval_runtime": 211.9219,
+      "eval_samples_per_second": 22.235,
+      "eval_steps_per_second": 0.698,
+      "step": 150
+    },
+    {
+      "epoch": 0.17500683620453925,
+      "grad_norm": 0.351032018661499,
+      "learning_rate": 0.00029748666994677467,
+      "loss": 0.3898,
+      "step": 160
+    },
+    {
+      "epoch": 0.17500683620453925,
+      "eval_loss": 0.8523072004318237,
+      "eval_runtime": 211.5677,
+      "eval_samples_per_second": 22.272,
+      "eval_steps_per_second": 0.7,
+      "step": 160
+    },
+    {
+      "epoch": 0.17500683620453925,
+      "step": 160,
+      "total_flos": 2.8452078024759706e+17,
+      "train_loss": 0.4666908696293831,
+      "train_runtime": 10276.9259,
+      "train_samples_per_second": 68.32,
+      "train_steps_per_second": 0.267
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2742,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "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
+}