End of training

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
+predict_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: albert/albert-xxlarge-v2
 tags:
 - generated_from_trainer
+datasets:
+- TimoImhof/TriviaQA-in-SQuAD-format
 model-index:
 - name: trivia_albert_XXL_finetuned
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trivia_albert_XXL_finetuned
 
-This model is a fine-tuned version of [albert/albert-xxlarge-v2](https://huggingface.co/albert/albert-xxlarge-v2) on an unknown dataset.
+This model is a fine-tuned version of [albert/albert-xxlarge-v2](https://huggingface.co/albert/albert-xxlarge-v2) on the TimoImhof/TriviaQA-in-SQuAD-format dataset.
 
 ## Model description
 

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22cedffb1049eabfb5166a61c9a01d2d85c2b5790530a3c2401ebc138a834a3
+size 18829488

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 80.0910865322056,
+    "eval_f1": 84.56093533580793,
+    "eval_runtime": 179.6918,
+    "eval_samples": 3398,
+    "eval_samples_per_second": 18.91,
+    "eval_steps_per_second": 2.365
+}

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22cedffb1049eabfb5166a61c9a01d2d85c2b5790530a3c2401ebc138a834a3
+size 18829488

predict_tr_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_samples_tr": 13545,
+    "test_exact_match": 94.1516186757768,
+    "test_f1": 96.27167174803232,
+    "test_runtime": 725.0484,
+    "test_samples_per_second": 18.682,
+    "test_steps_per_second": 2.336
+}

predict_val_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_samples_val": 3398,
+    "test_exact_match": 80.0910865322056,
+    "test_f1": 84.56093533580793,
+    "test_runtime": 180.7077,
+    "test_samples_per_second": 18.804,
+    "test_steps_per_second": 2.352
+}

runs/Feb09_18-46-57_xgpi2/events.out.tfevents.1739102543.xgpi2.7405.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0f1e9ac1cab182b7226494a403d195c00f8a4b721dda787c5173aebb4a46f2
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.260270189771264e+16,
+    "train_loss": 1.4897090983840655,
+    "train_runtime": 4249.2251,
+    "train_samples": 13545,
+    "train_samples_per_second": 6.375,
+    "train_steps_per_second": 0.2
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 848,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.179245283018868,
+      "grad_norm": 16.47541046142578,
+      "learning_rate": 2.0518867924528304e-05,
+      "loss": 1.7593,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "step": 848,
+      "total_flos": 1.260270189771264e+16,
+      "train_loss": 1.4897090983840655,
+      "train_runtime": 4249.2251,
+      "train_samples_per_second": 6.375,
+      "train_steps_per_second": 0.2
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 848,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.260270189771264e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}