End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 base_model: castorini/afriberta_small
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: afriberta-om-flores
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # afriberta-om-flores
 
 This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.6838
+- Accuracy: 0.3806
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.092050209205021,
+    "eval_accuracy": 0.3805601317957166,
+    "eval_loss": 3.6838042736053467,
+    "eval_runtime": 0.597,
+    "eval_samples": 100,
+    "eval_samples_per_second": 167.494,
+    "eval_steps_per_second": 41.874,
+    "perplexity": 39.7975070584133,
+    "total_flos": 38337612204768.0,
+    "train_loss": 3.658340881347656,
+    "train_runtime": 58.6954,
+    "train_samples": 1909,
+    "train_samples_per_second": 68.148,
+    "train_steps_per_second": 8.519
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.092050209205021,
+    "eval_accuracy": 0.3805601317957166,
+    "eval_loss": 3.6838042736053467,
+    "eval_runtime": 0.597,
+    "eval_samples": 100,
+    "eval_samples_per_second": 167.494,
+    "eval_steps_per_second": 41.874,
+    "perplexity": 39.7975070584133
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.092050209205021,
+    "total_flos": 38337612204768.0,
+    "train_loss": 3.658340881347656,
+    "train_runtime": 58.6954,
+    "train_samples": 1909,
+    "train_samples_per_second": 68.148,
+    "train_steps_per_second": 8.519
+}

trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.092050209205021,
+  "eval_steps": 250,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 19.030786514282227,
+      "learning_rate": 1.8833333333333335e-05,
+      "loss": 3.7517,
+      "step": 50
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 20.634578704833984,
+      "learning_rate": 1.675e-05,
+      "loss": 3.6778,
+      "step": 100
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 17.215373992919922,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 3.7684,
+      "step": 150
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 17.602941513061523,
+      "learning_rate": 1.2583333333333334e-05,
+      "loss": 3.7645,
+      "step": 200
+    },
+    {
+      "epoch": 1.0460251046025104,
+      "grad_norm": 20.645366668701172,
+      "learning_rate": 1.0500000000000001e-05,
+      "loss": 3.6481,
+      "step": 250
+    },
+    {
+      "epoch": 1.2552301255230125,
+      "grad_norm": 17.175325393676758,
+      "learning_rate": 8.416666666666667e-06,
+      "loss": 3.7027,
+      "step": 300
+    },
+    {
+      "epoch": 1.4644351464435146,
+      "grad_norm": 21.4941349029541,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 3.4982,
+      "step": 350
+    },
+    {
+      "epoch": 1.6736401673640167,
+      "grad_norm": 17.862903594970703,
+      "learning_rate": 4.25e-06,
+      "loss": 3.4812,
+      "step": 400
+    },
+    {
+      "epoch": 1.8828451882845187,
+      "grad_norm": 17.78984260559082,
+      "learning_rate": 2.166666666666667e-06,
+      "loss": 3.5468,
+      "step": 450
+    },
+    {
+      "epoch": 2.092050209205021,
+      "grad_norm": 22.636425018310547,
+      "learning_rate": 8.333333333333334e-08,
+      "loss": 3.744,
+      "step": 500
+    },
+    {
+      "epoch": 2.092050209205021,
+      "step": 500,
+      "total_flos": 38337612204768.0,
+      "train_loss": 3.658340881347656,
+      "train_runtime": 58.6954,
+      "train_samples_per_second": 68.148,
+      "train_steps_per_second": 8.519
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 38337612204768.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}