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-base-v2
 tags:
 - generated_from_trainer
+datasets:
+- TimoImhof/TriviaQA-in-SQuAD-format
 model-index:
 - name: trivia_albert_finetuned
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trivia_albert_finetuned
 
-This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
+This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-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 sha256:6e3b5808eb509e205beed38d494bac52f683f8cdcfe1404bf580f1e967b51237
+size 18637995

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 64.28106701366298,
+    "eval_f1": 70.91440871034429,
+    "eval_runtime": 11.4515,
+    "eval_samples": 3398,
+    "eval_samples_per_second": 296.73,
+    "eval_steps_per_second": 37.113
+}

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3b5808eb509e205beed38d494bac52f683f8cdcfe1404bf580f1e967b51237
+size 18637995

predict_tr_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_samples_tr": 13545,
+    "test_exact_match": 91.63006344558322,
+    "test_f1": 95.08068270968953,
+    "test_runtime": 46.3663,
+    "test_samples_per_second": 292.13,
+    "test_steps_per_second": 36.535
+}

predict_val_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_samples_val": 3398,
+    "test_exact_match": 64.28106701366298,
+    "test_f1": 70.91440871034429,
+    "test_runtime": 11.3669,
+    "test_samples_per_second": 298.938,
+    "test_steps_per_second": 37.389
+}

runs/Feb09_16-31-11_xgpi3/events.out.tfevents.1739090333.xgpi3.6778.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e109fa29daeeb6b59a70c99433902602683a441d7d712652e9b70eb3e13c5b5
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 897375340431360.0,
+    "train_loss": 1.4507015551779379,
+    "train_runtime": 419.078,
+    "train_samples": 13545,
+    "train_samples_per_second": 129.284,
+    "train_steps_per_second": 2.701
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.76678445229682,
+      "grad_norm": 28.217533111572266,
+      "learning_rate": 1.674911660777385e-05,
+      "loss": 1.9708,
+      "step": 500
+    },
+    {
+      "epoch": 3.53356890459364,
+      "grad_norm": 29.53766441345215,
+      "learning_rate": 3.498233215547703e-06,
+      "loss": 1.0999,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "step": 1132,
+      "total_flos": 897375340431360.0,
+      "train_loss": 1.4507015551779379,
+      "train_runtime": 419.078,
+      "train_samples_per_second": 129.284,
+      "train_steps_per_second": 2.701
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1132,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 897375340431360.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}