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: top_1_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # top_1_ranking_stackexchange
 
-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/top_1_ranking_stackexchange dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5613
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9925187032418954,
+    "eval_loss": 0.5612708926200867,
+    "eval_runtime": 55.4018,
+    "eval_samples_per_second": 24.331,
+    "eval_steps_per_second": 0.397,
+    "total_flos": 251046207160320.0,
+    "train_loss": 0.5803195349375407,
+    "train_runtime": 9079.4053,
+    "train_samples_per_second": 8.46,
+    "train_steps_per_second": 0.017
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9925187032418954,
+    "eval_loss": 0.5612708926200867,
+    "eval_runtime": 55.4018,
+    "eval_samples_per_second": 24.331,
+    "eval_steps_per_second": 0.397
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9925187032418954,
+    "total_flos": 251046207160320.0,
+    "train_loss": 0.5803195349375407,
+    "train_runtime": 9079.4053,
+    "train_samples_per_second": 8.46,
+    "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": 59.38634222354722,
+      "learning_rate": 5e-06,
+      "loss": 0.812,
+      "step": 10
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 2.1960032800772877,
+      "learning_rate": 5e-06,
+      "loss": 0.6885,
+      "step": 20
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 7.000153159965406,
+      "learning_rate": 5e-06,
+      "loss": 0.6424,
+      "step": 30
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 7.945600307179786,
+      "learning_rate": 5e-06,
+      "loss": 0.6225,
+      "step": 40
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 1.4092966622843572,
+      "learning_rate": 5e-06,
+      "loss": 0.6165,
+      "step": 50
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "eval_loss": 0.6011843085289001,
+      "eval_runtime": 55.5185,
+      "eval_samples_per_second": 24.28,
+      "eval_steps_per_second": 0.396,
+      "step": 50
+    },
+    {
+      "epoch": 1.1970074812967582,
+      "grad_norm": 1.3488536657915955,
+      "learning_rate": 5e-06,
+      "loss": 0.6217,
+      "step": 60
+    },
+    {
+      "epoch": 1.3965087281795512,
+      "grad_norm": 0.7654234458916354,
+      "learning_rate": 5e-06,
+      "loss": 0.555,
+      "step": 70
+    },
+    {
+      "epoch": 1.5960099750623442,
+      "grad_norm": 1.1374130411278827,
+      "learning_rate": 5e-06,
+      "loss": 0.5496,
+      "step": 80
+    },
+    {
+      "epoch": 1.7955112219451372,
+      "grad_norm": 0.6833448776058244,
+      "learning_rate": 5e-06,
+      "loss": 0.5567,
+      "step": 90
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "grad_norm": 0.5921564717905348,
+      "learning_rate": 5e-06,
+      "loss": 0.5416,
+      "step": 100
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "eval_loss": 0.5647123456001282,
+      "eval_runtime": 55.3866,
+      "eval_samples_per_second": 24.338,
+      "eval_steps_per_second": 0.397,
+      "step": 100
+    },
+    {
+      "epoch": 2.1945137157107233,
+      "grad_norm": 0.7816435404426337,
+      "learning_rate": 5e-06,
+      "loss": 0.5452,
+      "step": 110
+    },
+    {
+      "epoch": 2.3940149625935163,
+      "grad_norm": 0.8083163191936461,
+      "learning_rate": 5e-06,
+      "loss": 0.4933,
+      "step": 120
+    },
+    {
+      "epoch": 2.5935162094763093,
+      "grad_norm": 0.7453739368674692,
+      "learning_rate": 5e-06,
+      "loss": 0.4865,
+      "step": 130
+    },
+    {
+      "epoch": 2.7930174563591024,
+      "grad_norm": 0.6095605072913075,
+      "learning_rate": 5e-06,
+      "loss": 0.4884,
+      "step": 140
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "grad_norm": 0.722389875412173,
+      "learning_rate": 5e-06,
+      "loss": 0.4848,
+      "step": 150
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "eval_loss": 0.5612708926200867,
+      "eval_runtime": 55.0401,
+      "eval_samples_per_second": 24.491,
+      "eval_steps_per_second": 0.4,
+      "step": 150
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "step": 150,
+      "total_flos": 251046207160320.0,
+      "train_loss": 0.5803195349375407,
+      "train_runtime": 9079.4053,
+      "train_samples_per_second": 8.46,
+      "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
+}