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: oh_v1-2_only_camel_biology
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v1-2_only_camel_biology
 
-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/oh_v1-2_only_camel_biology dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8893
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.954954954954955,
+    "eval_loss": 0.8892803192138672,
+    "eval_runtime": 18.7176,
+    "eval_samples_per_second": 39.802,
+    "eval_steps_per_second": 0.641,
+    "total_flos": 135468637224960.0,
+    "train_loss": 0.9256458105864348,
+    "train_runtime": 2784.0769,
+    "train_samples_per_second": 15.243,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.954954954954955,
+    "eval_loss": 0.8892803192138672,
+    "eval_runtime": 18.7176,
+    "eval_samples_per_second": 39.802,
+    "eval_steps_per_second": 0.641
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.954954954954955,
+    "total_flos": 135468637224960.0,
+    "train_loss": 0.9256458105864348,
+    "train_runtime": 2784.0769,
+    "train_samples_per_second": 15.243,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.954954954954955,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 2.0452822799656194,
+      "learning_rate": 5e-06,
+      "loss": 1.0659,
+      "step": 10
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 5.950450528611833,
+      "learning_rate": 5e-06,
+      "loss": 0.9838,
+      "step": 20
+    },
+    {
+      "epoch": 0.972972972972973,
+      "eval_loss": 0.9350727200508118,
+      "eval_runtime": 19.9428,
+      "eval_samples_per_second": 37.357,
+      "eval_steps_per_second": 0.602,
+      "step": 27
+    },
+    {
+      "epoch": 1.0990990990990992,
+      "grad_norm": 0.8521141181184599,
+      "learning_rate": 5e-06,
+      "loss": 1.0096,
+      "step": 30
+    },
+    {
+      "epoch": 1.4594594594594594,
+      "grad_norm": 1.2564739871677004,
+      "learning_rate": 5e-06,
+      "loss": 0.8988,
+      "step": 40
+    },
+    {
+      "epoch": 1.8198198198198199,
+      "grad_norm": 0.9182622550561225,
+      "learning_rate": 5e-06,
+      "loss": 0.8864,
+      "step": 50
+    },
+    {
+      "epoch": 1.9639639639639639,
+      "eval_loss": 0.8990292549133301,
+      "eval_runtime": 20.0828,
+      "eval_samples_per_second": 37.096,
+      "eval_steps_per_second": 0.598,
+      "step": 54
+    },
+    {
+      "epoch": 2.1981981981981984,
+      "grad_norm": 0.9529821022078722,
+      "learning_rate": 5e-06,
+      "loss": 0.9212,
+      "step": 60
+    },
+    {
+      "epoch": 2.5585585585585586,
+      "grad_norm": 0.8041190022517808,
+      "learning_rate": 5e-06,
+      "loss": 0.8262,
+      "step": 70
+    },
+    {
+      "epoch": 2.918918918918919,
+      "grad_norm": 0.7500522421627415,
+      "learning_rate": 5e-06,
+      "loss": 0.819,
+      "step": 80
+    },
+    {
+      "epoch": 2.954954954954955,
+      "eval_loss": 0.8892803192138672,
+      "eval_runtime": 18.4837,
+      "eval_samples_per_second": 40.306,
+      "eval_steps_per_second": 0.649,
+      "step": 81
+    },
+    {
+      "epoch": 2.954954954954955,
+      "step": 81,
+      "total_flos": 135468637224960.0,
+      "train_loss": 0.9256458105864348,
+      "train_runtime": 2784.0769,
+      "train_samples_per_second": 15.243,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 81,
+  "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": 135468637224960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}