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_10000tasks_.25p
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackoverflow_10000tasks_.25p
 
-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_10000tasks_.25p dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5873
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.955223880597015,
+    "eval_loss": 0.5872882008552551,
+    "eval_runtime": 23.8853,
+    "eval_samples_per_second": 37.722,
+    "eval_steps_per_second": 0.628,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.5984680050551289,
+    "train_runtime": 3523.3561,
+    "train_samples_per_second": 14.569,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.955223880597015,
+    "eval_loss": 0.5872882008552551,
+    "eval_runtime": 23.8853,
+    "eval_samples_per_second": 37.722,
+    "eval_steps_per_second": 0.628
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.955223880597015,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.5984680050551289,
+    "train_runtime": 3523.3561,
+    "train_samples_per_second": 14.569,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.955223880597015,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 1.7684459850293275,
+      "learning_rate": 5e-06,
+      "loss": 0.8004,
+      "step": 10
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 5.291389940035488,
+      "learning_rate": 5e-06,
+      "loss": 0.6944,
+      "step": 20
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 1.725289856003478,
+      "learning_rate": 5e-06,
+      "loss": 0.6489,
+      "step": 30
+    },
+    {
+      "epoch": 0.9850746268656716,
+      "eval_loss": 0.6296907663345337,
+      "eval_runtime": 24.3832,
+      "eval_samples_per_second": 36.952,
+      "eval_steps_per_second": 0.615,
+      "step": 33
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 1.4095957956739007,
+      "learning_rate": 5e-06,
+      "loss": 0.6397,
+      "step": 40
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 0.8576531250052165,
+      "learning_rate": 5e-06,
+      "loss": 0.5745,
+      "step": 50
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 1.4305503586564623,
+      "learning_rate": 5e-06,
+      "loss": 0.565,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5920219421386719,
+      "eval_runtime": 24.4827,
+      "eval_samples_per_second": 36.802,
+      "eval_steps_per_second": 0.613,
+      "step": 67
+    },
+    {
+      "epoch": 2.08955223880597,
+      "grad_norm": 1.785396129175589,
+      "learning_rate": 5e-06,
+      "loss": 0.5686,
+      "step": 70
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 0.9984119235329142,
+      "learning_rate": 5e-06,
+      "loss": 0.5017,
+      "step": 80
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 1.0333775054380918,
+      "learning_rate": 5e-06,
+      "loss": 0.4948,
+      "step": 90
+    },
+    {
+      "epoch": 2.955223880597015,
+      "eval_loss": 0.5872882008552551,
+      "eval_runtime": 24.1525,
+      "eval_samples_per_second": 37.305,
+      "eval_steps_per_second": 0.621,
+      "step": 99
+    },
+    {
+      "epoch": 2.955223880597015,
+      "step": 99,
+      "total_flos": 165619307642880.0,
+      "train_loss": 0.5984680050551289,
+      "train_runtime": 3523.3561,
+      "train_samples_per_second": 14.569,
+      "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
+}