End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: stackexchange_softwareengineering
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_softwareengineering
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/stackexchange_softwareengineering dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9408
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9407615661621094,
+    "eval_runtime": 26.6788,
+    "eval_samples_per_second": 39.357,
+    "eval_steps_per_second": 0.637,
+    "total_flos": 195769978060800.0,
+    "train_loss": 0.9480493904178978,
+    "train_runtime": 4080.0307,
+    "train_samples_per_second": 14.655,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9407615661621094,
+    "eval_runtime": 26.6788,
+    "eval_samples_per_second": 39.357,
+    "eval_steps_per_second": 0.637
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 195769978060800.0,
+    "train_loss": 0.9480493904178978,
+    "train_runtime": 4080.0307,
+    "train_samples_per_second": 14.655,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,143 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 2.241857183981803,
+      "learning_rate": 5e-06,
+      "loss": 1.1489,
+      "step": 10
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 1.562618778630362,
+      "learning_rate": 5e-06,
+      "loss": 1.0695,
+      "step": 20
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.027479539676093,
+      "learning_rate": 5e-06,
+      "loss": 1.0175,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9853456020355225,
+      "eval_runtime": 27.3629,
+      "eval_samples_per_second": 38.373,
+      "eval_steps_per_second": 0.621,
+      "step": 39
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 1.063498495420315,
+      "learning_rate": 5e-06,
+      "loss": 0.987,
+      "step": 40
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.794959634337265,
+      "learning_rate": 5e-06,
+      "loss": 0.939,
+      "step": 50
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.6915704905232531,
+      "learning_rate": 5e-06,
+      "loss": 0.9251,
+      "step": 60
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 0.78023595699972,
+      "learning_rate": 5e-06,
+      "loss": 0.9218,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9502609372138977,
+      "eval_runtime": 27.6057,
+      "eval_samples_per_second": 38.036,
+      "eval_steps_per_second": 0.616,
+      "step": 78
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 1.3781300281497275,
+      "learning_rate": 5e-06,
+      "loss": 0.905,
+      "step": 80
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.9697446440582159,
+      "learning_rate": 5e-06,
+      "loss": 0.864,
+      "step": 90
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.9257218001278112,
+      "learning_rate": 5e-06,
+      "loss": 0.8584,
+      "step": 100
+    },
+    {
+      "epoch": 2.8205128205128203,
+      "grad_norm": 1.075804580838569,
+      "learning_rate": 5e-06,
+      "loss": 0.8555,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9407615661621094,
+      "eval_runtime": 25.9516,
+      "eval_samples_per_second": 40.46,
+      "eval_steps_per_second": 0.655,
+      "step": 117
+    },
+    {
+      "epoch": 3.0,
+      "step": 117,
+      "total_flos": 195769978060800.0,
+      "train_loss": 0.9480493904178978,
+      "train_runtime": 4080.0307,
+      "train_samples_per_second": 14.655,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 117,
+  "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": 195769978060800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}