End of training

.gitattributes

@@ -33,3 +33,4 @@ 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

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
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 81.62003903708523,
+    "eval_f1": 85.2479782921377,
+    "eval_runtime": 173.6434,
+    "eval_samples": 3398,
+    "eval_samples_per_second": 19.569,
+    "eval_steps_per_second": 2.448,
+    "total_flos": 3.780810569313792e+16,
+    "train_loss": 0.7023615477220068,
+    "train_runtime": 12579.5465,
+    "train_samples": 13545,
+    "train_samples_per_second": 6.46,
+    "train_steps_per_second": 0.202
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b098fac52cef51ab68b6650b98418c8f01fbdff8b51dffd370eded766c71f7bc
+size 13908243

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 81.62003903708523,
+    "eval_f1": 85.2479782921377,
+    "eval_runtime": 173.6434,
+    "eval_samples": 3398,
+    "eval_samples_per_second": 19.569,
+    "eval_steps_per_second": 2.448
+}

runs/Feb03_17-11-53_xgpi8/events.out.tfevents.1738586786.xgpi8.461731.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4968a2d76d105f72b6fa6826353208f0b3dc0473c8d5975a48957e9f84b47887
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 3.780810569313792e+16,
+    "train_loss": 0.7023615477220068,
+    "train_runtime": 12579.5465,
+    "train_samples": 13545,
+    "train_samples_per_second": 6.46,
+    "train_steps_per_second": 0.202
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2544,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.179245283018868,
+      "grad_norm": 15.49643325805664,
+      "learning_rate": 2.410377358490566e-05,
+      "loss": 1.8144,
+      "step": 500
+    },
+    {
+      "epoch": 2.358490566037736,
+      "grad_norm": 19.69099998474121,
+      "learning_rate": 1.8207547169811322e-05,
+      "loss": 1.0437,
+      "step": 1000
+    },
+    {
+      "epoch": 3.5377358490566038,
+      "grad_norm": 13.478647232055664,
+      "learning_rate": 1.2311320754716983e-05,
+      "loss": 0.4616,
+      "step": 1500
+    },
+    {
+      "epoch": 4.716981132075472,
+      "grad_norm": 2.125852108001709,
+      "learning_rate": 6.415094339622642e-06,
+      "loss": 0.148,
+      "step": 2000
+    },
+    {
+      "epoch": 5.89622641509434,
+      "grad_norm": 0.09522629529237747,
+      "learning_rate": 5.188679245283019e-07,
+      "loss": 0.0987,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "step": 2544,
+      "total_flos": 3.780810569313792e+16,
+      "train_loss": 0.7023615477220068,
+      "train_runtime": 12579.5465,
+      "train_samples_per_second": 6.46,
+      "train_steps_per_second": 0.202
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2544,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 3.780810569313792e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}