End of training

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: filtered_cooking_train_data
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # filtered_cooking_train_data
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the identity and the filtered_cooking_train_data datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3791
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9959839357429718,
+    "eval_loss": 0.3790915906429291,
+    "eval_runtime": 2.8743,
+    "eval_samples_per_second": 28.529,
+    "eval_steps_per_second": 2.087,
+    "total_flos": 15726579548160.0,
+    "train_loss": 0.5279744325145599,
+    "train_runtime": 524.7324,
+    "train_samples_per_second": 7.592,
+    "train_steps_per_second": 0.059
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9959839357429718,
+    "eval_loss": 0.3790915906429291,
+    "eval_runtime": 2.8743,
+    "eval_samples_per_second": 28.529,
+    "eval_steps_per_second": 2.087
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9959839357429718,
+    "total_flos": 15726579548160.0,
+    "train_loss": 0.5279744325145599,
+    "train_runtime": 524.7324,
+    "train_samples_per_second": 7.592,
+    "train_steps_per_second": 0.059
+}

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9959839357429718,
+  "eval_steps": 50,
+  "global_step": 31,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.321285140562249,
+      "grad_norm": 5.37024074789258,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.705,
+      "step": 10
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 4.914160704913099,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.4668,
+      "step": 20
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 3.6841539865225745,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.4299,
+      "step": 30
+    },
+    {
+      "epoch": 0.9959839357429718,
+      "step": 31,
+      "total_flos": 15726579548160.0,
+      "train_loss": 0.5279744325145599,
+      "train_runtime": 524.7324,
+      "train_samples_per_second": 7.592,
+      "train_steps_per_second": 0.059
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 31,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 15726579548160.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}