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: seed_math_tiger_math
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # seed_math_tiger_math
 
-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/seed_math_tiger_math dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4292
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.937269372693727,
+    "eval_loss": 0.4291580617427826,
+    "eval_runtime": 37.678,
+    "eval_samples_per_second": 24.179,
+    "eval_steps_per_second": 0.398,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.4649389295866995,
+    "train_runtime": 6123.8498,
+    "train_samples_per_second": 8.472,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.937269372693727,
+    "eval_loss": 0.4291580617427826,
+    "eval_runtime": 37.678,
+    "eval_samples_per_second": 24.179,
+    "eval_steps_per_second": 0.398
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.937269372693727,
+    "total_flos": 165619307642880.0,
+    "train_loss": 0.4649389295866995,
+    "train_runtime": 6123.8498,
+    "train_samples_per_second": 8.472,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.937269372693727,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2952029520295203,
+      "grad_norm": 5.4085511759711276,
+      "learning_rate": 5e-06,
+      "loss": 0.6143,
+      "step": 10
+    },
+    {
+      "epoch": 0.5904059040590406,
+      "grad_norm": 2.6041347666353243,
+      "learning_rate": 5e-06,
+      "loss": 0.5162,
+      "step": 20
+    },
+    {
+      "epoch": 0.8856088560885609,
+      "grad_norm": 0.695670165106577,
+      "learning_rate": 5e-06,
+      "loss": 0.4914,
+      "step": 30
+    },
+    {
+      "epoch": 0.974169741697417,
+      "eval_loss": 0.46729105710983276,
+      "eval_runtime": 37.9544,
+      "eval_samples_per_second": 24.002,
+      "eval_steps_per_second": 0.395,
+      "step": 33
+    },
+    {
+      "epoch": 1.188191881918819,
+      "grad_norm": 0.8836295893714152,
+      "learning_rate": 5e-06,
+      "loss": 0.4769,
+      "step": 40
+    },
+    {
+      "epoch": 1.4833948339483394,
+      "grad_norm": 0.5905444508669719,
+      "learning_rate": 5e-06,
+      "loss": 0.4447,
+      "step": 50
+    },
+    {
+      "epoch": 1.7785977859778597,
+      "grad_norm": 0.5041492482609334,
+      "learning_rate": 5e-06,
+      "loss": 0.4395,
+      "step": 60
+    },
+    {
+      "epoch": 1.985239852398524,
+      "eval_loss": 0.43678900599479675,
+      "eval_runtime": 37.8715,
+      "eval_samples_per_second": 24.055,
+      "eval_steps_per_second": 0.396,
+      "step": 67
+    },
+    {
+      "epoch": 2.081180811808118,
+      "grad_norm": 1.099147176799641,
+      "learning_rate": 5e-06,
+      "loss": 0.4374,
+      "step": 70
+    },
+    {
+      "epoch": 2.376383763837638,
+      "grad_norm": 0.6887908318488757,
+      "learning_rate": 5e-06,
+      "loss": 0.4127,
+      "step": 80
+    },
+    {
+      "epoch": 2.671586715867159,
+      "grad_norm": 0.6171417066251588,
+      "learning_rate": 5e-06,
+      "loss": 0.4063,
+      "step": 90
+    },
+    {
+      "epoch": 2.937269372693727,
+      "eval_loss": 0.4291580617427826,
+      "eval_runtime": 37.1515,
+      "eval_samples_per_second": 24.521,
+      "eval_steps_per_second": 0.404,
+      "step": 99
+    },
+    {
+      "epoch": 2.937269372693727,
+      "step": 99,
+      "total_flos": 165619307642880.0,
+      "train_loss": 0.4649389295866995,
+      "train_runtime": 6123.8498,
+      "train_samples_per_second": 8.472,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 99,
+  "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": 165619307642880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}