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_parenting
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_parenting
 
-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_parenting dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9315
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.8874172185430464,
+    "eval_loss": 0.9315438270568848,
+    "eval_runtime": 12.5942,
+    "eval_samples_per_second": 40.257,
+    "eval_steps_per_second": 0.635,
+    "total_flos": 90242631598080.0,
+    "train_loss": 0.9955270731890643,
+    "train_runtime": 2055.2531,
+    "train_samples_per_second": 14.055,
+    "train_steps_per_second": 0.026
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.8874172185430464,
+    "eval_loss": 0.9315438270568848,
+    "eval_runtime": 12.5942,
+    "eval_samples_per_second": 40.257,
+    "eval_steps_per_second": 0.635
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.8874172185430464,
+    "total_flos": 90242631598080.0,
+    "train_loss": 0.9955270731890643,
+    "train_runtime": 2055.2531,
+    "train_samples_per_second": 14.055,
+    "train_steps_per_second": 0.026
+}

trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8874172185430464,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 13.310886669889483,
+      "learning_rate": 5e-06,
+      "loss": 1.1508,
+      "step": 10
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "eval_loss": 1.0110349655151367,
+      "eval_runtime": 13.3832,
+      "eval_samples_per_second": 37.883,
+      "eval_steps_per_second": 0.598,
+      "step": 18
+    },
+    {
+      "epoch": 1.0728476821192052,
+      "grad_norm": 1.6760260821233446,
+      "learning_rate": 5e-06,
+      "loss": 1.0692,
+      "step": 20
+    },
+    {
+      "epoch": 1.6026490066225165,
+      "grad_norm": 1.7339744954824934,
+      "learning_rate": 5e-06,
+      "loss": 0.9634,
+      "step": 30
+    },
+    {
+      "epoch": 1.9735099337748343,
+      "eval_loss": 0.9528446197509766,
+      "eval_runtime": 12.7943,
+      "eval_samples_per_second": 39.627,
+      "eval_steps_per_second": 0.625,
+      "step": 37
+    },
+    {
+      "epoch": 2.1456953642384105,
+      "grad_norm": 1.7263147997285893,
+      "learning_rate": 5e-06,
+      "loss": 0.9627,
+      "step": 40
+    },
+    {
+      "epoch": 2.6754966887417218,
+      "grad_norm": 1.5383901851348518,
+      "learning_rate": 5e-06,
+      "loss": 0.8805,
+      "step": 50
+    },
+    {
+      "epoch": 2.8874172185430464,
+      "eval_loss": 0.9315438270568848,
+      "eval_runtime": 11.4511,
+      "eval_samples_per_second": 44.275,
+      "eval_steps_per_second": 0.699,
+      "step": 54
+    },
+    {
+      "epoch": 2.8874172185430464,
+      "step": 54,
+      "total_flos": 90242631598080.0,
+      "train_loss": 0.9955270731890643,
+      "train_runtime": 2055.2531,
+      "train_samples_per_second": 14.055,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 54,
+  "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": 90242631598080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}