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: airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp
 
-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/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9654
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.6666666666666665,
+    "eval_loss": 0.9654369354248047,
+    "eval_runtime": 4.6447,
+    "eval_samples_per_second": 19.377,
+    "eval_steps_per_second": 0.431,
+    "total_flos": 14865955553280.0,
+    "train_loss": 1.0443739361233182,
+    "train_runtime": 2959.2696,
+    "train_samples_per_second": 1.716,
+    "train_steps_per_second": 0.003
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.6666666666666665,
+    "eval_loss": 0.9654369354248047,
+    "eval_runtime": 4.6447,
+    "eval_samples_per_second": 19.377,
+    "eval_steps_per_second": 0.431
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.6666666666666665,
+    "total_flos": 14865955553280.0,
+    "train_loss": 1.0443739361233182,
+    "train_runtime": 2959.2696,
+    "train_samples_per_second": 1.716,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6666666666666665,
+  "eval_steps": 500,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 1.0627363920211792,
+      "eval_runtime": 5.3463,
+      "eval_samples_per_second": 16.834,
+      "eval_steps_per_second": 0.374,
+      "step": 3
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 1.0114394426345825,
+      "eval_runtime": 5.232,
+      "eval_samples_per_second": 17.202,
+      "eval_steps_per_second": 0.382,
+      "step": 6
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 0.9654369354248047,
+      "eval_runtime": 4.7388,
+      "eval_samples_per_second": 18.992,
+      "eval_steps_per_second": 0.422,
+      "step": 9
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "step": 9,
+      "total_flos": 14865955553280.0,
+      "train_loss": 1.0443739361233182,
+      "train_runtime": 2959.2696,
+      "train_samples_per_second": 1.716,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9,
+  "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": 14865955553280.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}