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_hsm
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_hsm
 
-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_hsm dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1163
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.6382978723404253,
+    "eval_loss": 1.1163207292556763,
+    "eval_runtime": 4.2782,
+    "eval_samples_per_second": 36.698,
+    "eval_steps_per_second": 0.701,
+    "total_flos": 24916179025920.0,
+    "train_loss": 1.2561878522237142,
+    "train_runtime": 846.1079,
+    "train_samples_per_second": 10.513,
+    "train_steps_per_second": 0.018
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.6382978723404253,
+    "eval_loss": 1.1163207292556763,
+    "eval_runtime": 4.2782,
+    "eval_samples_per_second": 36.698,
+    "eval_steps_per_second": 0.701
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.6382978723404253,
+    "total_flos": 24916179025920.0,
+    "train_loss": 1.2561878522237142,
+    "train_runtime": 846.1079,
+    "train_samples_per_second": 10.513,
+    "train_steps_per_second": 0.018
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6382978723404253,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.851063829787234,
+      "eval_loss": 1.169114589691162,
+      "eval_runtime": 4.9282,
+      "eval_samples_per_second": 31.857,
+      "eval_steps_per_second": 0.609,
+      "step": 5
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 12.48722662538639,
+      "learning_rate": 5e-06,
+      "loss": 1.2801,
+      "step": 10
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "eval_loss": 1.1361857652664185,
+      "eval_runtime": 4.9057,
+      "eval_samples_per_second": 32.003,
+      "eval_steps_per_second": 0.612,
+      "step": 11
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "eval_loss": 1.1163207292556763,
+      "eval_runtime": 3.9053,
+      "eval_samples_per_second": 40.202,
+      "eval_steps_per_second": 0.768,
+      "step": 15
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "step": 15,
+      "total_flos": 24916179025920.0,
+      "train_loss": 1.2561878522237142,
+      "train_runtime": 846.1079,
+      "train_samples_per_second": 10.513,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15,
+  "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": 24916179025920.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}