End of training

README.md

@@ -3,6 +3,9 @@ license: apache-2.0
 base_model: riotu-lab/ArabianGPT-01B
 tags:
 - generated_from_trainer
+metrics:
+- bleu
+- rouge
 model-index:
 - name: results
   results: []
@@ -14,6 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 # results
 
 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: 3.4630
+- Bleu: 0.0984
+- Rouge1: 0.3093
+- Rouge2: 0.0718
+- Rougel: 0.2296
 
 ## Model description
 

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 1.0,
+    "eval_bleu": 0.09842217214841122,
+    "eval_loss": 3.4630110263824463,
+    "eval_rouge1": 0.3093411104418377,
+    "eval_rouge2": 0.07177511381538038,
+    "eval_rougeL": 0.22957881226204224,
+    "eval_runtime": 27.1725,
+    "eval_samples": 847,
+    "eval_samples_per_second": 31.171,
+    "eval_steps_per_second": 3.901,
+    "perplexity": 31.912922646039927,
+    "total_flos": 1000225898496000.0,
+    "train_loss": 4.835940561324452,
+    "train_runtime": 121.5981,
+    "train_samples": 2552,
+    "train_samples_per_second": 20.987,
+    "train_steps_per_second": 2.623
+}

egy_training_log.txt

@@ -141,3 +141,5 @@ INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_maren
 INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-0637777c38512acf/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-4ddbb6e08bb37d3f.arrow
 WARNING:accelerate.utils.other:Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
 WARNING:root:Epoch 1.0: No losses recorded yet.
+INFO:__main__:*** Evaluate ***
+INFO:absl:Using default tokenizer.

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_bleu": 0.09842217214841122,
+    "eval_loss": 3.4630110263824463,
+    "eval_rouge1": 0.3093411104418377,
+    "eval_rouge2": 0.07177511381538038,
+    "eval_rougeL": 0.22957881226204224,
+    "eval_runtime": 27.1725,
+    "eval_samples": 847,
+    "eval_samples_per_second": 31.171,
+    "eval_steps_per_second": 3.901,
+    "perplexity": 31.912922646039927
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1000225898496000.0,
+    "train_loss": 4.835940561324452,
+    "train_runtime": 121.5981,
+    "train_samples": 2552,
+    "train_samples_per_second": 20.987,
+    "train_steps_per_second": 2.623
+}

trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "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": 4.835940561324452,
+      "train_runtime": 121.5981,
+      "train_samples_per_second": 20.987,
+      "train_steps_per_second": 2.623
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 319,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "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
+}