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: stackoverflow_5000tasks_.5p
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackoverflow_5000tasks_.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_5000tasks_.5p dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6593
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.944649446494465,
+    "eval_loss": 0.6592532992362976,
+    "eval_runtime": 23.8705,
+    "eval_samples_per_second": 38.206,
+    "eval_steps_per_second": 0.628,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.6797776800213438,
+    "train_runtime": 3538.4497,
+    "train_samples_per_second": 14.688,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.944649446494465,
+    "eval_loss": 0.6592532992362976,
+    "eval_runtime": 23.8705,
+    "eval_samples_per_second": 38.206,
+    "eval_steps_per_second": 0.628
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.944649446494465,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.6797776800213438,
+    "train_runtime": 3538.4497,
+    "train_samples_per_second": 14.688,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.944649446494465,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2952029520295203,
+      "grad_norm": 1.6298737624752542,
+      "learning_rate": 5e-06,
+      "loss": 0.8625,
+      "step": 10
+    },
+    {
+      "epoch": 0.5904059040590406,
+      "grad_norm": 20.660169538112434,
+      "learning_rate": 5e-06,
+      "loss": 0.7619,
+      "step": 20
+    },
+    {
+      "epoch": 0.8856088560885609,
+      "grad_norm": 1.3237989114564421,
+      "learning_rate": 5e-06,
+      "loss": 0.7397,
+      "step": 30
+    },
+    {
+      "epoch": 0.974169741697417,
+      "eval_loss": 0.7080272436141968,
+      "eval_runtime": 24.4319,
+      "eval_samples_per_second": 37.328,
+      "eval_steps_per_second": 0.614,
+      "step": 33
+    },
+    {
+      "epoch": 1.1918819188191883,
+      "grad_norm": 0.9592222984425236,
+      "learning_rate": 5e-06,
+      "loss": 0.7258,
+      "step": 40
+    },
+    {
+      "epoch": 1.4870848708487086,
+      "grad_norm": 1.0765367176513723,
+      "learning_rate": 5e-06,
+      "loss": 0.6617,
+      "step": 50
+    },
+    {
+      "epoch": 1.7822878228782288,
+      "grad_norm": 0.721768200972634,
+      "learning_rate": 5e-06,
+      "loss": 0.6487,
+      "step": 60
+    },
+    {
+      "epoch": 1.988929889298893,
+      "eval_loss": 0.6627019643783569,
+      "eval_runtime": 24.583,
+      "eval_samples_per_second": 37.099,
+      "eval_steps_per_second": 0.61,
+      "step": 67
+    },
+    {
+      "epoch": 2.088560885608856,
+      "grad_norm": 1.06012468227033,
+      "learning_rate": 5e-06,
+      "loss": 0.6553,
+      "step": 70
+    },
+    {
+      "epoch": 2.3837638376383765,
+      "grad_norm": 1.2324694242836023,
+      "learning_rate": 5e-06,
+      "loss": 0.5828,
+      "step": 80
+    },
+    {
+      "epoch": 2.678966789667897,
+      "grad_norm": 1.6475802532792028,
+      "learning_rate": 5e-06,
+      "loss": 0.5757,
+      "step": 90
+    },
+    {
+      "epoch": 2.944649446494465,
+      "eval_loss": 0.6592532992362976,
+      "eval_runtime": 23.0446,
+      "eval_samples_per_second": 39.575,
+      "eval_steps_per_second": 0.651,
+      "step": 99
+    },
+    {
+      "epoch": 2.944649446494465,
+      "step": 99,
+      "total_flos": 165619307642880.0,
+      "train_loss": 0.6797776800213438,
+      "train_runtime": 3538.4497,
+      "train_samples_per_second": 14.688,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 99,
+  "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": 165619307642880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}