End of training

README.md

@@ -4,6 +4,7 @@ library_name: peft
 license: llama3.1
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: Llama-3.1-8B-Instruct-SFT
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct-SFT
 
-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_sft_1000 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1108
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.986666666666667,
+    "eval_loss": 0.11075915396213531,
+    "eval_runtime": 3.2515,
+    "eval_samples_per_second": 30.755,
+    "eval_steps_per_second": 15.378,
+    "total_flos": 1.4701145828622336e+16,
+    "train_loss": 0.5345617514990625,
+    "train_runtime": 365.3436,
+    "train_samples_per_second": 7.39,
+    "train_steps_per_second": 0.46
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.986666666666667,
+    "eval_loss": 0.11075915396213531,
+    "eval_runtime": 3.2515,
+    "eval_samples_per_second": 30.755,
+    "eval_steps_per_second": 15.378
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.986666666666667,
+    "total_flos": 1.4701145828622336e+16,
+    "train_loss": 0.5345617514990625,
+    "train_runtime": 365.3436,
+    "train_samples_per_second": 7.39,
+    "train_steps_per_second": 0.46
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.986666666666667,
+  "eval_steps": 500,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 5.874284267425537,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 1.6312,
+      "step": 10
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 4.8905839920043945,
+      "learning_rate": 4.997836020254328e-06,
+      "loss": 1.6062,
+      "step": 20
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 4.010315418243408,
+      "learning_rate": 4.922489359292928e-06,
+      "loss": 1.3296,
+      "step": 30
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 4.480731964111328,
+      "learning_rate": 4.7426609101991605e-06,
+      "loss": 1.0087,
+      "step": 40
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.9216177463531494,
+      "learning_rate": 4.466106660773884e-06,
+      "loss": 0.794,
+      "step": 50
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.1213908195495605,
+      "learning_rate": 4.104754375481665e-06,
+      "loss": 0.6263,
+      "step": 60
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 2.6194798946380615,
+      "learning_rate": 3.674189151845515e-06,
+      "loss": 0.4176,
+      "step": 70
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 2.223825693130493,
+      "learning_rate": 3.1929812363354766e-06,
+      "loss": 0.3157,
+      "step": 80
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.024078369140625,
+      "learning_rate": 2.68188509100236e-06,
+      "loss": 0.2453,
+      "step": 90
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.36781644821167,
+      "learning_rate": 2.1629442550539283e-06,
+      "loss": 0.1523,
+      "step": 100
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.575614094734192,
+      "learning_rate": 1.6585406086279847e-06,
+      "loss": 0.1674,
+      "step": 110
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 2.0267510414123535,
+      "learning_rate": 1.1904290439459974e-06,
+      "loss": 0.1176,
+      "step": 120
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.4237582683563232,
+      "learning_rate": 7.787991784095e-07,
+      "loss": 0.1299,
+      "step": 130
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.752246618270874,
+      "learning_rate": 4.414045778845144e-07,
+      "loss": 0.1384,
+      "step": 140
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.4376964569091797,
+      "learning_rate": 1.927970467097573e-07,
+      "loss": 0.1232,
+      "step": 150
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.431710124015808,
+      "learning_rate": 4.369900944435734e-08,
+      "loss": 0.1002,
+      "step": 160
+    },
+    {
+      "epoch": 2.986666666666667,
+      "step": 168,
+      "total_flos": 1.4701145828622336e+16,
+      "train_loss": 0.5345617514990625,
+      "train_runtime": 365.3436,
+      "train_samples_per_second": 7.39,
+      "train_steps_per_second": 0.46
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4701145828622336e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}