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: stackexchange_astronomy
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stackexchange_astronomy
 
-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/stackexchange_astronomy dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9304
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.909090909090909,
+    "eval_loss": 0.930383026599884,
+    "eval_runtime": 21.5155,
+    "eval_samples_per_second": 25.795,
+    "eval_steps_per_second": 0.418,
+    "total_flos": 100292855070720.0,
+    "train_loss": 1.0080458323160808,
+    "train_runtime": 3801.2496,
+    "train_samples_per_second": 8.313,
+    "train_steps_per_second": 0.016
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.909090909090909,
+    "eval_loss": 0.930383026599884,
+    "eval_runtime": 21.5155,
+    "eval_samples_per_second": 25.795,
+    "eval_steps_per_second": 0.418
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.909090909090909,
+    "total_flos": 100292855070720.0,
+    "train_loss": 1.0080458323160808,
+    "train_runtime": 3801.2496,
+    "train_samples_per_second": 8.313,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.909090909090909,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 4.595314924239334,
+      "learning_rate": 5e-06,
+      "loss": 1.1263,
+      "step": 10
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 15.5166261384021,
+      "learning_rate": 5e-06,
+      "loss": 1.0663,
+      "step": 20
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "eval_loss": 1.1175479888916016,
+      "eval_runtime": 22.4342,
+      "eval_samples_per_second": 24.739,
+      "eval_steps_per_second": 0.401,
+      "step": 20
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 9.76010359551301,
+      "learning_rate": 5e-06,
+      "loss": 1.0693,
+      "step": 30
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 1.992807964625793,
+      "learning_rate": 5e-06,
+      "loss": 0.9594,
+      "step": 40
+    },
+    {
+      "epoch": 1.9878787878787878,
+      "eval_loss": 0.9644138813018799,
+      "eval_runtime": 22.5564,
+      "eval_samples_per_second": 24.605,
+      "eval_steps_per_second": 0.399,
+      "step": 41
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 1.0886748547587948,
+      "learning_rate": 5e-06,
+      "loss": 0.9436,
+      "step": 50
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 1.2145602359017604,
+      "learning_rate": 5e-06,
+      "loss": 0.8834,
+      "step": 60
+    },
+    {
+      "epoch": 2.909090909090909,
+      "eval_loss": 0.930383026599884,
+      "eval_runtime": 21.7398,
+      "eval_samples_per_second": 25.529,
+      "eval_steps_per_second": 0.414,
+      "step": 60
+    },
+    {
+      "epoch": 2.909090909090909,
+      "step": 60,
+      "total_flos": 100292855070720.0,
+      "train_loss": 1.0080458323160808,
+      "train_runtime": 3801.2496,
+      "train_samples_per_second": 8.313,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "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": 100292855070720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}