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_4o_annotated_olympiads
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_4o_annotated_olympiads
 
-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/4o_annotated_olympiads dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7641
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.764080822467804,
+    "eval_runtime": 2.7378,
+    "eval_samples_per_second": 242.898,
+    "eval_steps_per_second": 1.096,
+    "total_flos": 125627793408000.0,
+    "train_loss": 0.78931853612264,
+    "train_runtime": 843.7096,
+    "train_samples_per_second": 44.88,
+    "train_steps_per_second": 0.089
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.764080822467804,
+    "eval_runtime": 2.7378,
+    "eval_samples_per_second": 242.898,
+    "eval_steps_per_second": 1.096
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 125627793408000.0,
+    "train_loss": 0.78931853612264,
+    "train_runtime": 843.7096,
+    "train_samples_per_second": 44.88,
+    "train_steps_per_second": 0.089
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.143056875903662,
+      "learning_rate": 5e-06,
+      "loss": 0.9368,
+      "step": 10
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.838996397889602,
+      "learning_rate": 5e-06,
+      "loss": 0.8464,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8046166300773621,
+      "eval_runtime": 2.7606,
+      "eval_samples_per_second": 240.886,
+      "eval_steps_per_second": 1.087,
+      "step": 25
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.6672359501540905,
+      "learning_rate": 5e-06,
+      "loss": 0.7963,
+      "step": 30
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7586626375485055,
+      "learning_rate": 5e-06,
+      "loss": 0.7677,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4973490989428714,
+      "learning_rate": 5e-06,
+      "loss": 0.7628,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7725305557250977,
+      "eval_runtime": 2.7237,
+      "eval_samples_per_second": 244.152,
+      "eval_steps_per_second": 1.101,
+      "step": 50
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5434695331875599,
+      "learning_rate": 5e-06,
+      "loss": 0.7199,
+      "step": 60
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.5377017664368798,
+      "learning_rate": 5e-06,
+      "loss": 0.7237,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.764080822467804,
+      "eval_runtime": 2.8075,
+      "eval_samples_per_second": 236.869,
+      "eval_steps_per_second": 1.069,
+      "step": 75
+    },
+    {
+      "epoch": 3.0,
+      "step": 75,
+      "total_flos": 125627793408000.0,
+      "train_loss": 0.78931853612264,
+      "train_runtime": 843.7096,
+      "train_samples_per_second": 44.88,
+      "train_steps_per_second": 0.089
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 75,
+  "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": 125627793408000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}