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: llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks__5p
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks__5p
 
-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/stackoverflow_25000tasks_.5p dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6489
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.998165137614679,
+    "eval_loss": 0.6488585472106934,
+    "eval_runtime": 106.065,
+    "eval_samples_per_second": 8.655,
+    "eval_steps_per_second": 0.273,
+    "total_flos": 170853799034880.0,
+    "train_loss": 0.1902820573133581,
+    "train_runtime": 5607.5857,
+    "train_samples_per_second": 9.324,
+    "train_steps_per_second": 0.018
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.998165137614679,
+    "eval_loss": 0.6488585472106934,
+    "eval_runtime": 106.065,
+    "eval_samples_per_second": 8.655,
+    "eval_steps_per_second": 0.273
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.998165137614679,
+    "total_flos": 170853799034880.0,
+    "train_loss": 0.1902820573133581,
+    "train_runtime": 5607.5857,
+    "train_samples_per_second": 9.324,
+    "train_steps_per_second": 0.018
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.998165137614679,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 4.42750711816544,
+      "learning_rate": 5e-06,
+      "loss": 0.8622,
+      "step": 10
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 4.510468980568199,
+      "learning_rate": 5e-06,
+      "loss": 0.7615,
+      "step": 20
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 2.554603378964487,
+      "learning_rate": 5e-06,
+      "loss": 0.7229,
+      "step": 30
+    },
+    {
+      "epoch": 0.998165137614679,
+      "eval_loss": 0.6932151913642883,
+      "eval_runtime": 109.2878,
+      "eval_samples_per_second": 8.4,
+      "eval_steps_per_second": 0.265,
+      "step": 34
+    },
+    {
+      "epoch": 1.1743119266055047,
+      "grad_norm": 0.7647134442337394,
+      "learning_rate": 5e-06,
+      "loss": 0.684,
+      "step": 40
+    },
+    {
+      "epoch": 1.4678899082568808,
+      "grad_norm": 1.5853789970798486,
+      "learning_rate": 5e-06,
+      "loss": 0.6549,
+      "step": 50
+    },
+    {
+      "epoch": 1.761467889908257,
+      "grad_norm": 1.358127609429742,
+      "learning_rate": 5e-06,
+      "loss": 0.6412,
+      "step": 60
+    },
+    {
+      "epoch": 1.996330275229358,
+      "eval_loss": 0.6560695171356201,
+      "eval_runtime": 106.8155,
+      "eval_samples_per_second": 8.594,
+      "eval_steps_per_second": 0.271,
+      "step": 68
+    },
+    {
+      "epoch": 2.0587155963302752,
+      "grad_norm": 1.4446871291974328,
+      "learning_rate": 5e-06,
+      "loss": 0.5857,
+      "step": 70
+    },
+    {
+      "epoch": 2.3522935779816514,
+      "grad_norm": 1.245102669617799,
+      "learning_rate": 5e-06,
+      "loss": 0.5754,
+      "step": 80
+    },
+    {
+      "epoch": 2.6458715596330276,
+      "grad_norm": 1.3673500463540726,
+      "learning_rate": 5e-06,
+      "loss": 0.5682,
+      "step": 90
+    },
+    {
+      "epoch": 2.9394495412844037,
+      "grad_norm": 1.468126930185911,
+      "learning_rate": 5e-06,
+      "loss": 0.5675,
+      "step": 100
+    },
+    {
+      "epoch": 2.998165137614679,
+      "eval_loss": 0.6488585472106934,
+      "eval_runtime": 116.3522,
+      "eval_samples_per_second": 7.89,
+      "eval_steps_per_second": 0.249,
+      "step": 102
+    },
+    {
+      "epoch": 2.998165137614679,
+      "step": 102,
+      "total_flos": 170853799034880.0,
+      "train_loss": 0.1902820573133581,
+      "train_runtime": 5607.5857,
+      "train_samples_per_second": 9.324,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 102,
+  "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": 170853799034880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}