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_airoboros
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh_v1-2_only_airoboros
 
-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_airoboros dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8367
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.7745664739884393,
+    "eval_loss": 0.8367447257041931,
+    "eval_runtime": 16.1947,
+    "eval_samples_per_second": 9.015,
+    "eval_steps_per_second": 0.185,
+    "total_flos": 25073213767680.0,
+    "train_loss": 0.936284065246582,
+    "train_runtime": 4393.8745,
+    "train_samples_per_second": 1.887,
+    "train_steps_per_second": 0.003
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.7745664739884393,
+    "eval_loss": 0.8367447257041931,
+    "eval_runtime": 16.1947,
+    "eval_samples_per_second": 9.015,
+    "eval_steps_per_second": 0.185
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.7745664739884393,
+    "total_flos": 25073213767680.0,
+    "train_loss": 0.936284065246582,
+    "train_runtime": 4393.8745,
+    "train_samples_per_second": 1.887,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7745664739884393,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9248554913294798,
+      "eval_loss": 0.948443591594696,
+      "eval_runtime": 17.2335,
+      "eval_samples_per_second": 8.472,
+      "eval_steps_per_second": 0.174,
+      "step": 5
+    },
+    {
+      "epoch": 1.8497109826589595,
+      "grad_norm": 2.0815279543947365,
+      "learning_rate": 5e-06,
+      "loss": 0.9953,
+      "step": 10
+    },
+    {
+      "epoch": 1.8497109826589595,
+      "eval_loss": 0.8798985481262207,
+      "eval_runtime": 17.4079,
+      "eval_samples_per_second": 8.387,
+      "eval_steps_per_second": 0.172,
+      "step": 10
+    },
+    {
+      "epoch": 2.7745664739884393,
+      "eval_loss": 0.8367447257041931,
+      "eval_runtime": 17.0323,
+      "eval_samples_per_second": 8.572,
+      "eval_steps_per_second": 0.176,
+      "step": 15
+    },
+    {
+      "epoch": 2.7745664739884393,
+      "step": 15,
+      "total_flos": 25073213767680.0,
+      "train_loss": 0.936284065246582,
+      "train_runtime": 4393.8745,
+      "train_samples_per_second": 1.887,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15,
+  "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": 25073213767680.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}