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_formulas
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # seed_math_formulas
 
-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_formulas dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4002
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.968503937007874,
+    "eval_loss": 0.400202214717865,
+    "eval_runtime": 35.0308,
+    "eval_samples_per_second": 24.35,
+    "eval_steps_per_second": 0.4,
+    "total_flos": 155569084170240.0,
+    "train_loss": 0.44060584293898714,
+    "train_runtime": 5764.8207,
+    "train_samples_per_second": 8.431,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.968503937007874,
+    "eval_loss": 0.400202214717865,
+    "eval_runtime": 35.0308,
+    "eval_samples_per_second": 24.35,
+    "eval_steps_per_second": 0.4
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.968503937007874,
+    "total_flos": 155569084170240.0,
+    "train_loss": 0.44060584293898714,
+    "train_runtime": 5764.8207,
+    "train_samples_per_second": 8.431,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.968503937007874,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 1.294643369195835,
+      "learning_rate": 5e-06,
+      "loss": 0.5641,
+      "step": 10
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 1.060018140758457,
+      "learning_rate": 5e-06,
+      "loss": 0.4778,
+      "step": 20
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.5953668352477545,
+      "learning_rate": 5e-06,
+      "loss": 0.4472,
+      "step": 30
+    },
+    {
+      "epoch": 0.9763779527559056,
+      "eval_loss": 0.43012088537216187,
+      "eval_runtime": 35.2773,
+      "eval_samples_per_second": 24.18,
+      "eval_steps_per_second": 0.397,
+      "step": 31
+    },
+    {
+      "epoch": 1.279527559055118,
+      "grad_norm": 0.6538569266356088,
+      "learning_rate": 5e-06,
+      "loss": 0.4667,
+      "step": 40
+    },
+    {
+      "epoch": 1.594488188976378,
+      "grad_norm": 0.645139528716553,
+      "learning_rate": 5e-06,
+      "loss": 0.4113,
+      "step": 50
+    },
+    {
+      "epoch": 1.909448818897638,
+      "grad_norm": 0.7317531680073737,
+      "learning_rate": 5e-06,
+      "loss": 0.4167,
+      "step": 60
+    },
+    {
+      "epoch": 1.9724409448818898,
+      "eval_loss": 0.4076673686504364,
+      "eval_runtime": 35.4357,
+      "eval_samples_per_second": 24.072,
+      "eval_steps_per_second": 0.395,
+      "step": 62
+    },
+    {
+      "epoch": 2.2440944881889764,
+      "grad_norm": 0.5584333423027347,
+      "learning_rate": 5e-06,
+      "loss": 0.4311,
+      "step": 70
+    },
+    {
+      "epoch": 2.559055118110236,
+      "grad_norm": 0.4057574507208694,
+      "learning_rate": 5e-06,
+      "loss": 0.3895,
+      "step": 80
+    },
+    {
+      "epoch": 2.8740157480314963,
+      "grad_norm": 0.3929556421643816,
+      "learning_rate": 5e-06,
+      "loss": 0.3872,
+      "step": 90
+    },
+    {
+      "epoch": 2.968503937007874,
+      "eval_loss": 0.400202214717865,
+      "eval_runtime": 34.5171,
+      "eval_samples_per_second": 24.712,
+      "eval_steps_per_second": 0.406,
+      "step": 93
+    },
+    {
+      "epoch": 2.968503937007874,
+      "step": 93,
+      "total_flos": 155569084170240.0,
+      "train_loss": 0.44060584293898714,
+      "train_runtime": 5764.8207,
+      "train_samples_per_second": 8.431,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 93,
+  "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": 155569084170240.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}