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_codegolf
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_codegolf
 
-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_codegolf dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5672
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9925187032418954,
+    "eval_loss": 0.5672302842140198,
+    "eval_runtime": 54.2261,
+    "eval_samples_per_second": 24.896,
+    "eval_steps_per_second": 0.406,
+    "total_flos": 251046207160320.0,
+    "train_loss": 0.5811795616149902,
+    "train_runtime": 8937.3206,
+    "train_samples_per_second": 8.608,
+    "train_steps_per_second": 0.017
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9925187032418954,
+    "eval_loss": 0.5672302842140198,
+    "eval_runtime": 54.2261,
+    "eval_samples_per_second": 24.896,
+    "eval_steps_per_second": 0.406
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9925187032418954,
+    "total_flos": 251046207160320.0,
+    "train_loss": 0.5811795616149902,
+    "train_runtime": 8937.3206,
+    "train_samples_per_second": 8.608,
+    "train_steps_per_second": 0.017
+}

trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9925187032418954,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 4.623498128431036,
+      "learning_rate": 5e-06,
+      "loss": 0.8013,
+      "step": 10
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 2.1821805178609672,
+      "learning_rate": 5e-06,
+      "loss": 0.6798,
+      "step": 20
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 4.415531229785867,
+      "learning_rate": 5e-06,
+      "loss": 0.6411,
+      "step": 30
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 6.723453799394174,
+      "learning_rate": 5e-06,
+      "loss": 0.6274,
+      "step": 40
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 1.067405523386397,
+      "learning_rate": 5e-06,
+      "loss": 0.6123,
+      "step": 50
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "eval_loss": 0.6066042184829712,
+      "eval_runtime": 54.2342,
+      "eval_samples_per_second": 24.892,
+      "eval_steps_per_second": 0.406,
+      "step": 50
+    },
+    {
+      "epoch": 1.1970074812967582,
+      "grad_norm": 2.541034230738679,
+      "learning_rate": 5e-06,
+      "loss": 0.6278,
+      "step": 60
+    },
+    {
+      "epoch": 1.3965087281795512,
+      "grad_norm": 0.6825423418485694,
+      "learning_rate": 5e-06,
+      "loss": 0.5677,
+      "step": 70
+    },
+    {
+      "epoch": 1.5960099750623442,
+      "grad_norm": 0.8666541576639258,
+      "learning_rate": 5e-06,
+      "loss": 0.5516,
+      "step": 80
+    },
+    {
+      "epoch": 1.7955112219451372,
+      "grad_norm": 0.791365005319929,
+      "learning_rate": 5e-06,
+      "loss": 0.5397,
+      "step": 90
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "grad_norm": 1.287898310420275,
+      "learning_rate": 5e-06,
+      "loss": 0.5438,
+      "step": 100
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "eval_loss": 0.5740869641304016,
+      "eval_runtime": 54.4016,
+      "eval_samples_per_second": 24.815,
+      "eval_steps_per_second": 0.404,
+      "step": 100
+    },
+    {
+      "epoch": 2.1945137157107233,
+      "grad_norm": 0.9888282972521568,
+      "learning_rate": 5e-06,
+      "loss": 0.5407,
+      "step": 110
+    },
+    {
+      "epoch": 2.3940149625935163,
+      "grad_norm": 0.8567373783067653,
+      "learning_rate": 5e-06,
+      "loss": 0.4996,
+      "step": 120
+    },
+    {
+      "epoch": 2.5935162094763093,
+      "grad_norm": 0.6523956470492996,
+      "learning_rate": 5e-06,
+      "loss": 0.4972,
+      "step": 130
+    },
+    {
+      "epoch": 2.7930174563591024,
+      "grad_norm": 0.7098096207597672,
+      "learning_rate": 5e-06,
+      "loss": 0.4926,
+      "step": 140
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "grad_norm": 0.6470766076468314,
+      "learning_rate": 5e-06,
+      "loss": 0.4952,
+      "step": 150
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "eval_loss": 0.5672302842140198,
+      "eval_runtime": 53.8678,
+      "eval_samples_per_second": 25.061,
+      "eval_steps_per_second": 0.408,
+      "step": 150
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "step": 150,
+      "total_flos": 251046207160320.0,
+      "train_loss": 0.5811795616149902,
+      "train_runtime": 8937.3206,
+      "train_samples_per_second": 8.608,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 150,
+  "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": 251046207160320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}