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

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 75.40663630448927,
+    "eval_f1": 79.50348921131032,
+    "eval_runtime": 109.1736,
+    "eval_samples": 3398,
+    "eval_samples_per_second": 31.125,
+    "eval_steps_per_second": 3.893,
+    "total_flos": 9479673213373440.0,
+    "train_loss": 1.1461569756831762,
+    "train_runtime": 6870.8994,
+    "train_samples": 13545,
+    "train_samples_per_second": 11.828,
+    "train_steps_per_second": 0.37
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ece278e581fdacaa19d135f96eab4b9c6dc621a7c2155251fd021d71da4958
+size 13712303

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 75.40663630448927,
+    "eval_f1": 79.50348921131032,
+    "eval_runtime": 109.1736,
+    "eval_samples": 3398,
+    "eval_samples_per_second": 31.125,
+    "eval_steps_per_second": 3.893
+}

runs/Feb02_05-11-35_xgpi2/events.out.tfevents.1738451324.xgpi2.2490936.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abea0d3f3c9a5db7ef40c45fa6e0c8138baa89c418c793ac4c2e7d3c757c80ac
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 9479673213373440.0,
+    "train_loss": 1.1461569756831762,
+    "train_runtime": 6870.8994,
+    "train_samples": 13545,
+    "train_samples_per_second": 11.828,
+    "train_steps_per_second": 0.37
+}

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": 28.103540420532227,
+      "learning_rate": 2.410377358490566e-05,
+      "loss": 2.2352,
+      "step": 500
+    },
+    {
+      "epoch": 2.358490566037736,
+      "grad_norm": 16.953514099121094,
+      "learning_rate": 1.8207547169811322e-05,
+      "loss": 1.5029,
+      "step": 1000
+    },
+    {
+      "epoch": 3.5377358490566038,
+      "grad_norm": 31.308820724487305,
+      "learning_rate": 1.2311320754716983e-05,
+      "loss": 1.1127,
+      "step": 1500
+    },
+    {
+      "epoch": 4.716981132075472,
+      "grad_norm": 26.33289337158203,
+      "learning_rate": 6.415094339622642e-06,
+      "loss": 0.7052,
+      "step": 2000
+    },
+    {
+      "epoch": 5.89622641509434,
+      "grad_norm": 106.1405258178711,
+      "learning_rate": 5.188679245283019e-07,
+      "loss": 0.2618,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "step": 2544,
+      "total_flos": 9479673213373440.0,
+      "train_loss": 1.1461569756831762,
+      "train_runtime": 6870.8994,
+      "train_samples_per_second": 11.828,
+      "train_steps_per_second": 0.37
+    }
+  ],
+  "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": 9479673213373440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}