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_ell
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_ell
 
-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_ell dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8475
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.888888888888889,
+    "eval_loss": 0.8475070595741272,
+    "eval_runtime": 10.8697,
+    "eval_samples_per_second": 36.247,
+    "eval_steps_per_second": 0.644,
+    "total_flos": 70142184652800.0,
+    "train_loss": 0.9507874647776285,
+    "train_runtime": 1676.2003,
+    "train_samples_per_second": 13.366,
+    "train_steps_per_second": 0.025
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.888888888888889,
+    "eval_loss": 0.8475070595741272,
+    "eval_runtime": 10.8697,
+    "eval_samples_per_second": 36.247,
+    "eval_steps_per_second": 0.644
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.888888888888889,
+    "total_flos": 70142184652800.0,
+    "train_loss": 0.9507874647776285,
+    "train_runtime": 1676.2003,
+    "train_samples_per_second": 13.366,
+    "train_steps_per_second": 0.025
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.888888888888889,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 21.63528355313981,
+      "learning_rate": 5e-06,
+      "loss": 1.0949,
+      "step": 10
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "eval_loss": 0.9537151455879211,
+      "eval_runtime": 11.7681,
+      "eval_samples_per_second": 33.48,
+      "eval_steps_per_second": 0.595,
+      "step": 14
+    },
+    {
+      "epoch": 1.376068376068376,
+      "grad_norm": 2.2918871351055623,
+      "learning_rate": 5e-06,
+      "loss": 0.9836,
+      "step": 20
+    },
+    {
+      "epoch": 1.9914529914529915,
+      "eval_loss": 0.8846853971481323,
+      "eval_runtime": 11.1256,
+      "eval_samples_per_second": 35.414,
+      "eval_steps_per_second": 0.629,
+      "step": 29
+    },
+    {
+      "epoch": 2.0683760683760686,
+      "grad_norm": 3.000112645713609,
+      "learning_rate": 5e-06,
+      "loss": 0.9321,
+      "step": 30
+    },
+    {
+      "epoch": 2.752136752136752,
+      "grad_norm": 1.3804652331854828,
+      "learning_rate": 5e-06,
+      "loss": 0.824,
+      "step": 40
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_loss": 0.8475070595741272,
+      "eval_runtime": 10.2058,
+      "eval_samples_per_second": 38.605,
+      "eval_steps_per_second": 0.686,
+      "step": 42
+    },
+    {
+      "epoch": 2.888888888888889,
+      "step": 42,
+      "total_flos": 70142184652800.0,
+      "train_loss": 0.9507874647776285,
+      "train_runtime": 1676.2003,
+      "train_samples_per_second": 13.366,
+      "train_steps_per_second": 0.025
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 42,
+  "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": 70142184652800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}