End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: riotu-lab/ArabianGPT-01B
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: test-aragpt
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # test-aragpt
 
 This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3387
+- Accuracy: 0.2541
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.25405778786754485,
+    "eval_loss": 4.3386945724487305,
+    "eval_runtime": 27.8088,
+    "eval_samples": 1627,
+    "eval_samples_per_second": 58.507,
+    "eval_steps_per_second": 7.336,
+    "perplexity": 76.60746853485647,
+    "total_flos": 534995435520000.0,
+    "train_loss": 4.0715499788697,
+    "train_runtime": 69.2711,
+    "train_samples": 455,
+    "train_samples_per_second": 19.705,
+    "train_steps_per_second": 2.469
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.25405778786754485,
+    "eval_loss": 4.3386945724487305,
+    "eval_runtime": 27.8088,
+    "eval_samples": 1627,
+    "eval_samples_per_second": 58.507,
+    "eval_steps_per_second": 7.336,
+    "perplexity": 76.60746853485647
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 534995435520000.0,
+    "train_loss": 4.0715499788697,
+    "train_runtime": 69.2711,
+    "train_samples": 455,
+    "train_samples_per_second": 19.705,
+    "train_steps_per_second": 2.469
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 171,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 171,
+      "total_flos": 534995435520000.0,
+      "train_loss": 4.0715499788697,
+      "train_runtime": 69.2711,
+      "train_samples_per_second": 19.705,
+      "train_steps_per_second": 2.469
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 171,
+  "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": 534995435520000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}