End of training

README.md

@@ -2,6 +2,7 @@
 library_name: peft
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 base_model: meta-llama/Llama-2-7b-hf
 model-index:
@@ -14,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama2_AAID_structured_train
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the AAID_structured dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5326
+- Loss: 0.4973
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.08750341810226962,
+    "eval_loss": 0.4972783327102661,
+    "eval_runtime": 2237.7507,
+    "eval_samples_per_second": 21.057,
+    "eval_steps_per_second": 0.658,
+    "total_flos": 1.5705059263040717e+17,
+    "train_loss": 0.46784958243370056,
+    "train_runtime": 21860.8593,
+    "train_samples_per_second": 32.118,
+    "train_steps_per_second": 0.125
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.08750341810226962,
+    "eval_loss": 0.4972783327102661,
+    "eval_runtime": 2237.7507,
+    "eval_samples_per_second": 21.057,
+    "eval_steps_per_second": 0.658
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.08750341810226962,
+    "total_flos": 1.5705059263040717e+17,
+    "train_loss": 0.46784958243370056,
+    "train_runtime": 21860.8593,
+    "train_samples_per_second": 32.118,
+    "train_steps_per_second": 0.125
+}

trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_metric": 0.4972783327102661,
+  "best_model_checkpoint": "saves/Llama2-7B/lora/train_1/checkpoint-30",
+  "epoch": 0.08750341810226962,
+  "eval_steps": 10,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010937927262783703,
+      "grad_norm": 0.6052247285842896,
+      "learning_rate": 0.00029999015487222375,
+      "loss": 1.1654,
+      "step": 10
+    },
+    {
+      "epoch": 0.010937927262783703,
+      "eval_loss": 0.5498645901679993,
+      "eval_runtime": 2237.1123,
+      "eval_samples_per_second": 21.063,
+      "eval_steps_per_second": 0.658,
+      "step": 10
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "grad_norm": 0.5759575366973877,
+      "learning_rate": 0.00029996062078124905,
+      "loss": 0.4462,
+      "step": 20
+    },
+    {
+      "epoch": 0.021875854525567406,
+      "eval_loss": 0.5069721937179565,
+      "eval_runtime": 2237.2387,
+      "eval_samples_per_second": 21.062,
+      "eval_steps_per_second": 0.658,
+      "step": 20
+    },
+    {
+      "epoch": 0.03281378178835111,
+      "grad_norm": 0.3752610981464386,
+      "learning_rate": 0.0002999114016039678,
+      "loss": 0.3949,
+      "step": 30
+    },
+    {
+      "epoch": 0.03281378178835111,
+      "eval_loss": 0.4972783327102661,
+      "eval_runtime": 2238.0311,
+      "eval_samples_per_second": 21.054,
+      "eval_steps_per_second": 0.658,
+      "step": 30
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "grad_norm": 0.3636493980884552,
+      "learning_rate": 0.00029984250380130117,
+      "loss": 0.3903,
+      "step": 40
+    },
+    {
+      "epoch": 0.04375170905113481,
+      "eval_loss": 0.5445077419281006,
+      "eval_runtime": 2236.7311,
+      "eval_samples_per_second": 21.066,
+      "eval_steps_per_second": 0.659,
+      "step": 40
+    },
+    {
+      "epoch": 0.05468963631391851,
+      "grad_norm": 0.2787908911705017,
+      "learning_rate": 0.0002997539364173515,
+      "loss": 0.3617,
+      "step": 50
+    },
+    {
+      "epoch": 0.05468963631391851,
+      "eval_loss": 0.5150302052497864,
+      "eval_runtime": 2236.8051,
+      "eval_samples_per_second": 21.066,
+      "eval_steps_per_second": 0.659,
+      "step": 50
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 0.2524549961090088,
+      "learning_rate": 0.00029964571107821494,
+      "loss": 0.3346,
+      "step": 60
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 0.5358502268791199,
+      "eval_runtime": 2236.589,
+      "eval_samples_per_second": 21.068,
+      "eval_steps_per_second": 0.659,
+      "step": 60
+    },
+    {
+      "epoch": 0.07656549083948591,
+      "grad_norm": 0.2973044812679291,
+      "learning_rate": 0.00029951784199045534,
+      "loss": 0.3284,
+      "step": 70
+    },
+    {
+      "epoch": 0.07656549083948591,
+      "eval_loss": 0.5421467423439026,
+      "eval_runtime": 2236.0929,
+      "eval_samples_per_second": 21.072,
+      "eval_steps_per_second": 0.659,
+      "step": 70
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "grad_norm": 0.3223881721496582,
+      "learning_rate": 0.0002993703459392396,
+      "loss": 0.3215,
+      "step": 80
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "eval_loss": 0.5325918793678284,
+      "eval_runtime": 2234.6934,
+      "eval_samples_per_second": 21.086,
+      "eval_steps_per_second": 0.659,
+      "step": 80
+    },
+    {
+      "epoch": 0.08750341810226962,
+      "step": 80,
+      "total_flos": 1.5705059263040717e+17,
+      "train_loss": 0.46784958243370056,
+      "train_runtime": 21860.8593,
+      "train_samples_per_second": 32.118,
+      "train_steps_per_second": 0.125
+    }
+  ],
+  "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": 1.5705059263040717e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}