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: llama3-1_8b_mlfoundations-dev-stackexchange_puzzling
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackexchange_puzzling
 
-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_puzzling dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9340
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9724770642201834,
+    "eval_loss": 0.9339568018913269,
+    "eval_runtime": 84.5286,
+    "eval_samples_per_second": 8.683,
+    "eval_steps_per_second": 0.272,
+    "total_flos": 135573327052800.0,
+    "train_loss": 0.9809838378870929,
+    "train_runtime": 13278.7272,
+    "train_samples_per_second": 3.15,
+    "train_steps_per_second": 0.006
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9724770642201834,
+    "eval_loss": 0.9339568018913269,
+    "eval_runtime": 84.5286,
+    "eval_samples_per_second": 8.683,
+    "eval_steps_per_second": 0.272
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9724770642201834,
+    "total_flos": 135573327052800.0,
+    "train_loss": 0.9809838378870929,
+    "train_runtime": 13278.7272,
+    "train_samples_per_second": 3.15,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9724770642201834,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 15.223515124052987,
+      "learning_rate": 5e-06,
+      "loss": 1.1932,
+      "step": 10
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 2.19506481158568,
+      "learning_rate": 5e-06,
+      "loss": 1.0612,
+      "step": 20
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "eval_loss": 1.006506085395813,
+      "eval_runtime": 85.0324,
+      "eval_samples_per_second": 8.632,
+      "eval_steps_per_second": 0.27,
+      "step": 27
+    },
+    {
+      "epoch": 1.1009174311926606,
+      "grad_norm": 4.12557913604333,
+      "learning_rate": 5e-06,
+      "loss": 1.0044,
+      "step": 30
+    },
+    {
+      "epoch": 1.4678899082568808,
+      "grad_norm": 2.873184668037523,
+      "learning_rate": 5e-06,
+      "loss": 0.9667,
+      "step": 40
+    },
+    {
+      "epoch": 1.834862385321101,
+      "grad_norm": 2.185324880239001,
+      "learning_rate": 5e-06,
+      "loss": 0.9481,
+      "step": 50
+    },
+    {
+      "epoch": 1.981651376146789,
+      "eval_loss": 0.9613564610481262,
+      "eval_runtime": 84.6961,
+      "eval_samples_per_second": 8.666,
+      "eval_steps_per_second": 0.272,
+      "step": 54
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 1.6556333126334992,
+      "learning_rate": 5e-06,
+      "loss": 0.9173,
+      "step": 60
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 1.040600621325176,
+      "learning_rate": 5e-06,
+      "loss": 0.8827,
+      "step": 70
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 1.0042947441731673,
+      "learning_rate": 5e-06,
+      "loss": 0.8819,
+      "step": 80
+    },
+    {
+      "epoch": 2.9724770642201834,
+      "eval_loss": 0.9339568018913269,
+      "eval_runtime": 84.5066,
+      "eval_samples_per_second": 8.686,
+      "eval_steps_per_second": 0.272,
+      "step": 81
+    },
+    {
+      "epoch": 2.9724770642201834,
+      "step": 81,
+      "total_flos": 135573327052800.0,
+      "train_loss": 0.9809838378870929,
+      "train_runtime": 13278.7272,
+      "train_samples_per_second": 3.15,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 81,
+  "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": 135573327052800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}