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_literature
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_literature
 
-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_literature dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1455
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.8051948051948052,
+    "eval_loss": 1.1454670429229736,
+    "eval_runtime": 6.9387,
+    "eval_samples_per_second": 37.039,
+    "eval_steps_per_second": 0.721,
+    "total_flos": 45016625971200.0,
+    "train_loss": 1.254220097153275,
+    "train_runtime": 1225.5235,
+    "train_samples_per_second": 11.946,
+    "train_steps_per_second": 0.022
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.8051948051948052,
+    "eval_loss": 1.1454670429229736,
+    "eval_runtime": 6.9387,
+    "eval_samples_per_second": 37.039,
+    "eval_steps_per_second": 0.721
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.8051948051948052,
+    "total_flos": 45016625971200.0,
+    "train_loss": 1.254220097153275,
+    "train_runtime": 1225.5235,
+    "train_samples_per_second": 11.946,
+    "train_steps_per_second": 0.022
+}

trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8051948051948052,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.935064935064935,
+      "eval_loss": 1.2399028539657593,
+      "eval_runtime": 8.1119,
+      "eval_samples_per_second": 31.682,
+      "eval_steps_per_second": 0.616,
+      "step": 9
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 4.78200644518203,
+      "learning_rate": 5e-06,
+      "loss": 1.3749,
+      "step": 10
+    },
+    {
+      "epoch": 1.974025974025974,
+      "eval_loss": 1.1733253002166748,
+      "eval_runtime": 8.0269,
+      "eval_samples_per_second": 32.017,
+      "eval_steps_per_second": 0.623,
+      "step": 19
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 3.1022408445591787,
+      "learning_rate": 5e-06,
+      "loss": 1.2254,
+      "step": 20
+    },
+    {
+      "epoch": 2.8051948051948052,
+      "eval_loss": 1.1454670429229736,
+      "eval_runtime": 6.9346,
+      "eval_samples_per_second": 37.061,
+      "eval_steps_per_second": 0.721,
+      "step": 27
+    },
+    {
+      "epoch": 2.8051948051948052,
+      "step": 27,
+      "total_flos": 45016625971200.0,
+      "train_loss": 1.254220097153275,
+      "train_runtime": 1225.5235,
+      "train_samples_per_second": 11.946,
+      "train_steps_per_second": 0.022
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 27,
+  "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": 45016625971200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}