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_quantumcomputing
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_mlfoundations-dev-stackexchange_quantumcomputing
 
-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_quantumcomputing dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8230
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.953846153846154,
+    "eval_loss": 0.8229892253875732,
+    "eval_runtime": 55.654,
+    "eval_samples_per_second": 9.811,
+    "eval_steps_per_second": 0.323,
+    "total_flos": 100397544898560.0,
+    "train_loss": 0.8523021697998047,
+    "train_runtime": 8946.1058,
+    "train_samples_per_second": 3.477,
+    "train_steps_per_second": 0.007
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.953846153846154,
+    "eval_loss": 0.8229892253875732,
+    "eval_runtime": 55.654,
+    "eval_samples_per_second": 9.811,
+    "eval_steps_per_second": 0.323
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.953846153846154,
+    "total_flos": 100397544898560.0,
+    "train_loss": 0.8523021697998047,
+    "train_runtime": 8946.1058,
+    "train_samples_per_second": 3.477,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.953846153846154,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 19.64545203920716,
+      "learning_rate": 5e-06,
+      "loss": 0.9931,
+      "step": 10
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 2.6984642237074628,
+      "learning_rate": 5e-06,
+      "loss": 0.9091,
+      "step": 20
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "eval_loss": 0.8879945278167725,
+      "eval_runtime": 58.1255,
+      "eval_samples_per_second": 9.393,
+      "eval_steps_per_second": 0.31,
+      "step": 20
+    },
+    {
+      "epoch": 1.476923076923077,
+      "grad_norm": 1.217004142765871,
+      "learning_rate": 5e-06,
+      "loss": 0.8464,
+      "step": 30
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.8993970645431596,
+      "learning_rate": 5e-06,
+      "loss": 0.8243,
+      "step": 40
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "eval_loss": 0.840017557144165,
+      "eval_runtime": 55.5952,
+      "eval_samples_per_second": 9.821,
+      "eval_steps_per_second": 0.324,
+      "step": 40
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.2802289071806958,
+      "learning_rate": 5e-06,
+      "loss": 0.7799,
+      "step": 50
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": 1.041423288512039,
+      "learning_rate": 5e-06,
+      "loss": 0.7609,
+      "step": 60
+    },
+    {
+      "epoch": 2.953846153846154,
+      "eval_loss": 0.8229892253875732,
+      "eval_runtime": 55.512,
+      "eval_samples_per_second": 9.836,
+      "eval_steps_per_second": 0.324,
+      "step": 60
+    },
+    {
+      "epoch": 2.953846153846154,
+      "step": 60,
+      "total_flos": 100397544898560.0,
+      "train_loss": 0.8523021697998047,
+      "train_runtime": 8946.1058,
+      "train_samples_per_second": 3.477,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "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": 100397544898560.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}