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: oh_teknium_scaling_down_random_0.2
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_teknium_scaling_down_random_0.2
 
-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/oh_teknium_scaling_down_random_0.2 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4692
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.987202925045704,
+    "eval_loss": 0.46915486454963684,
+    "eval_runtime": 46.3759,
+    "eval_samples_per_second": 39.676,
+    "eval_steps_per_second": 0.625,
+    "total_flos": 341498218414080.0,
+    "train_loss": 0.4590076675602034,
+    "train_runtime": 7001.299,
+    "train_samples_per_second": 14.978,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.987202925045704,
+    "eval_loss": 0.46915486454963684,
+    "eval_runtime": 46.3759,
+    "eval_samples_per_second": 39.676,
+    "eval_steps_per_second": 0.625
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.987202925045704,
+    "total_flos": 341498218414080.0,
+    "train_loss": 0.4590076675602034,
+    "train_runtime": 7001.299,
+    "train_samples_per_second": 14.978,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.987202925045704,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14625228519195613,
+      "grad_norm": 3.582301207210251,
+      "learning_rate": 5e-06,
+      "loss": 0.6264,
+      "step": 10
+    },
+    {
+      "epoch": 0.29250457038391225,
+      "grad_norm": 0.8448007859307827,
+      "learning_rate": 5e-06,
+      "loss": 0.5676,
+      "step": 20
+    },
+    {
+      "epoch": 0.43875685557586835,
+      "grad_norm": 1.1496603868484656,
+      "learning_rate": 5e-06,
+      "loss": 0.5365,
+      "step": 30
+    },
+    {
+      "epoch": 0.5850091407678245,
+      "grad_norm": 0.6501842231450267,
+      "learning_rate": 5e-06,
+      "loss": 0.5288,
+      "step": 40
+    },
+    {
+      "epoch": 0.7312614259597806,
+      "grad_norm": 0.6880486176943897,
+      "learning_rate": 5e-06,
+      "loss": 0.5117,
+      "step": 50
+    },
+    {
+      "epoch": 0.8775137111517367,
+      "grad_norm": 0.653270772148158,
+      "learning_rate": 5e-06,
+      "loss": 0.5034,
+      "step": 60
+    },
+    {
+      "epoch": 0.9945155393053017,
+      "eval_loss": 0.48675259947776794,
+      "eval_runtime": 48.1062,
+      "eval_samples_per_second": 38.249,
+      "eval_steps_per_second": 0.603,
+      "step": 68
+    },
+    {
+      "epoch": 1.0255941499085923,
+      "grad_norm": 0.8213019683138277,
+      "learning_rate": 5e-06,
+      "loss": 0.5267,
+      "step": 70
+    },
+    {
+      "epoch": 1.1718464351005484,
+      "grad_norm": 0.6316112543570708,
+      "learning_rate": 5e-06,
+      "loss": 0.4427,
+      "step": 80
+    },
+    {
+      "epoch": 1.3180987202925045,
+      "grad_norm": 0.5370226018361522,
+      "learning_rate": 5e-06,
+      "loss": 0.4395,
+      "step": 90
+    },
+    {
+      "epoch": 1.4643510054844606,
+      "grad_norm": 0.5840998374236711,
+      "learning_rate": 5e-06,
+      "loss": 0.4431,
+      "step": 100
+    },
+    {
+      "epoch": 1.610603290676417,
+      "grad_norm": 0.5441743828650639,
+      "learning_rate": 5e-06,
+      "loss": 0.4389,
+      "step": 110
+    },
+    {
+      "epoch": 1.7568555758683728,
+      "grad_norm": 0.4999808048028024,
+      "learning_rate": 5e-06,
+      "loss": 0.4379,
+      "step": 120
+    },
+    {
+      "epoch": 1.9031078610603291,
+      "grad_norm": 0.611839727056921,
+      "learning_rate": 5e-06,
+      "loss": 0.4325,
+      "step": 130
+    },
+    {
+      "epoch": 1.9908592321755028,
+      "eval_loss": 0.46772316098213196,
+      "eval_runtime": 47.4216,
+      "eval_samples_per_second": 38.801,
+      "eval_steps_per_second": 0.612,
+      "step": 136
+    },
+    {
+      "epoch": 2.0511882998171846,
+      "grad_norm": 0.8668059984866675,
+      "learning_rate": 5e-06,
+      "loss": 0.4489,
+      "step": 140
+    },
+    {
+      "epoch": 2.197440585009141,
+      "grad_norm": 0.6140471225460572,
+      "learning_rate": 5e-06,
+      "loss": 0.3845,
+      "step": 150
+    },
+    {
+      "epoch": 2.343692870201097,
+      "grad_norm": 0.6202755918802835,
+      "learning_rate": 5e-06,
+      "loss": 0.3819,
+      "step": 160
+    },
+    {
+      "epoch": 2.489945155393053,
+      "grad_norm": 0.6403659423565966,
+      "learning_rate": 5e-06,
+      "loss": 0.3839,
+      "step": 170
+    },
+    {
+      "epoch": 2.636197440585009,
+      "grad_norm": 0.604130131999038,
+      "learning_rate": 5e-06,
+      "loss": 0.3867,
+      "step": 180
+    },
+    {
+      "epoch": 2.7824497257769654,
+      "grad_norm": 0.592166338429596,
+      "learning_rate": 5e-06,
+      "loss": 0.3815,
+      "step": 190
+    },
+    {
+      "epoch": 2.9287020109689212,
+      "grad_norm": 0.47952199046688787,
+      "learning_rate": 5e-06,
+      "loss": 0.3893,
+      "step": 200
+    },
+    {
+      "epoch": 2.987202925045704,
+      "eval_loss": 0.46915486454963684,
+      "eval_runtime": 46.4418,
+      "eval_samples_per_second": 39.619,
+      "eval_steps_per_second": 0.624,
+      "step": 204
+    },
+    {
+      "epoch": 2.987202925045704,
+      "step": 204,
+      "total_flos": 341498218414080.0,
+      "train_loss": 0.4590076675602034,
+      "train_runtime": 7001.299,
+      "train_samples_per_second": 14.978,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 204,
+  "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": 341498218414080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}