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_philosophy
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_philosophy
 
-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_philosophy dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9768
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9767674207687378,
+    "eval_runtime": 21.8868,
+    "eval_samples_per_second": 40.572,
+    "eval_steps_per_second": 0.64,
+    "total_flos": 165619307642880.0,
+    "train_loss": 1.0098309083418413,
+    "train_runtime": 3598.1862,
+    "train_samples_per_second": 14.067,
+    "train_steps_per_second": 0.028
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9767674207687378,
+    "eval_runtime": 21.8868,
+    "eval_samples_per_second": 40.572,
+    "eval_steps_per_second": 0.64
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 165619307642880.0,
+    "train_loss": 1.0098309083418413,
+    "train_runtime": 3598.1862,
+    "train_samples_per_second": 14.067,
+    "train_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 2.719936948474264,
+      "learning_rate": 5e-06,
+      "loss": 1.2221,
+      "step": 10
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 5.345162990072681,
+      "learning_rate": 5e-06,
+      "loss": 1.1135,
+      "step": 20
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.4460836035673772,
+      "learning_rate": 5e-06,
+      "loss": 1.0698,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0388543605804443,
+      "eval_runtime": 23.0434,
+      "eval_samples_per_second": 38.536,
+      "eval_steps_per_second": 0.608,
+      "step": 33
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 1.2962091959425812,
+      "learning_rate": 5e-06,
+      "loss": 1.0194,
+      "step": 40
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 1.2630058026908848,
+      "learning_rate": 5e-06,
+      "loss": 0.992,
+      "step": 50
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.5551526308760681,
+      "learning_rate": 5e-06,
+      "loss": 0.9788,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9927644729614258,
+      "eval_runtime": 23.304,
+      "eval_samples_per_second": 38.105,
+      "eval_steps_per_second": 0.601,
+      "step": 66
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 1.7037341451158614,
+      "learning_rate": 5e-06,
+      "loss": 0.9522,
+      "step": 70
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 1.5855990656505108,
+      "learning_rate": 5e-06,
+      "loss": 0.9176,
+      "step": 80
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.7761267872894142,
+      "learning_rate": 5e-06,
+      "loss": 0.9123,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9767674207687378,
+      "eval_runtime": 22.4983,
+      "eval_samples_per_second": 39.47,
+      "eval_steps_per_second": 0.622,
+      "step": 99
+    },
+    {
+      "epoch": 3.0,
+      "step": 99,
+      "total_flos": 165619307642880.0,
+      "train_loss": 1.0098309083418413,
+      "train_runtime": 3598.1862,
+      "train_samples_per_second": 14.067,
+      "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
+}