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: alpaca_seeding_stackexchange_codegolf
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # alpaca_seeding_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/alpaca_seeding_stackexchange_codegolf dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2421
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.4545454545454546,
+    "eval_loss": 1.2421070337295532,
+    "eval_runtime": 4.7132,
+    "eval_samples_per_second": 15.701,
+    "eval_steps_per_second": 0.424,
+    "total_flos": 9840843816960.0,
+    "train_loss": 1.594728946685791,
+    "train_runtime": 642.0075,
+    "train_samples_per_second": 6.481,
+    "train_steps_per_second": 0.009
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.4545454545454546,
+    "eval_loss": 1.2421070337295532,
+    "eval_runtime": 4.7132,
+    "eval_samples_per_second": 15.701,
+    "eval_steps_per_second": 0.424
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.4545454545454546,
+    "total_flos": 9840843816960.0,
+    "train_loss": 1.594728946685791,
+    "train_runtime": 642.0075,
+    "train_samples_per_second": 6.481,
+    "train_steps_per_second": 0.009
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4545454545454546,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7272727272727273,
+      "eval_loss": 1.316480040550232,
+      "eval_runtime": 5.1069,
+      "eval_samples_per_second": 14.49,
+      "eval_steps_per_second": 0.392,
+      "step": 2
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "eval_loss": 1.2342954874038696,
+      "eval_runtime": 5.0438,
+      "eval_samples_per_second": 14.671,
+      "eval_steps_per_second": 0.397,
+      "step": 4
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "eval_loss": 1.2421070337295532,
+      "eval_runtime": 4.0485,
+      "eval_samples_per_second": 18.278,
+      "eval_steps_per_second": 0.494,
+      "step": 6
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "step": 6,
+      "total_flos": 9840843816960.0,
+      "train_loss": 1.594728946685791,
+      "train_runtime": 642.0075,
+      "train_samples_per_second": 6.481,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6,
+  "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": 9840843816960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}