End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: riotu-lab/ArabianGPT-01B
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: test-egy_aragpt
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # test-egy_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: 3.3262
+- Bleu: 0.1060
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_bleu": 0.10603800831832183,
+    "eval_loss": 3.326219081878662,
+    "eval_runtime": 15.6341,
+    "eval_samples": 847,
+    "eval_samples_per_second": 54.177,
+    "eval_steps_per_second": 6.78,
+    "perplexity": 27.832908563445223,
+    "total_flos": 1000225898496000.0,
+    "train_loss": 3.812888405539773,
+    "train_runtime": 118.532,
+    "train_samples": 2552,
+    "train_samples_per_second": 21.53,
+    "train_steps_per_second": 2.691
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_bleu": 0.10603800831832183,
+    "eval_loss": 3.326219081878662,
+    "eval_runtime": 15.6341,
+    "eval_samples": 847,
+    "eval_samples_per_second": 54.177,
+    "eval_steps_per_second": 6.78,
+    "perplexity": 27.832908563445223
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1000225898496000.0,
+    "train_loss": 3.812888405539773,
+    "train_runtime": 118.532,
+    "train_samples": 2552,
+    "train_samples_per_second": 21.53,
+    "train_steps_per_second": 2.691
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 319,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 319,
+      "total_flos": 1000225898496000.0,
+      "train_loss": 3.812888405539773,
+      "train_runtime": 118.532,
+      "train_samples_per_second": 21.53,
+      "train_steps_per_second": 2.691
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 319,
+  "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": 1000225898496000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}