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:
+- squad
 model-index:
 - name: squad_albert_xxl_finetuned
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squad_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 squad dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_exact_match": 89.3282876064333,
+    "eval_f1": 95.19020584030557,
+    "eval_runtime": 549.793,
+    "eval_samples": 10808,
+    "eval_samples_per_second": 19.658,
+    "eval_steps_per_second": 2.457,
+    "total_flos": 4.123581730562765e+16,
+    "train_loss": 0.7573485501836784,
+    "train_runtime": 13379.8798,
+    "train_samples": 88638,
+    "train_samples_per_second": 6.625,
+    "train_steps_per_second": 0.207
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959509544b9a21fd469d787e8cd834ab0fc90c4c3ed3ac6f634ceb426e377c9a
+size 48902870

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_exact_match": 89.3282876064333,
+    "eval_f1": 95.19020584030557,
+    "eval_runtime": 549.793,
+    "eval_samples": 10808,
+    "eval_samples_per_second": 19.658,
+    "eval_steps_per_second": 2.457
+}

runs/Dec22_10-39-15_xgpi4/events.out.tfevents.1734849211.xgpi4.3623.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462859e7918ab534f3612e98ebe1abccaa745a4db796a2ebe2771860efaf72f5
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.123581730562765e+16,
+    "train_loss": 0.7573485501836784,
+    "train_runtime": 13379.8798,
+    "train_samples": 88638,
+    "train_samples_per_second": 6.625,
+    "train_steps_per_second": 0.207
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2770,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18050541516245489,
+      "grad_norm": 9.565498352050781,
+      "learning_rate": 2.4584837545126353e-05,
+      "loss": 1.0408,
+      "step": 500
+    },
+    {
+      "epoch": 0.36101083032490977,
+      "grad_norm": 3.8937153816223145,
+      "learning_rate": 1.9169675090252708e-05,
+      "loss": 0.7637,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5415162454873647,
+      "grad_norm": 5.798653602600098,
+      "learning_rate": 1.3754512635379063e-05,
+      "loss": 0.716,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7220216606498195,
+      "grad_norm": 3.4039201736450195,
+      "learning_rate": 8.339350180505416e-06,
+      "loss": 0.681,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9025270758122743,
+      "grad_norm": 9.457993507385254,
+      "learning_rate": 2.924187725631769e-06,
+      "loss": 0.6554,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "step": 2770,
+      "total_flos": 4.123581730562765e+16,
+      "train_loss": 0.7573485501836784,
+      "train_runtime": 13379.8798,
+      "train_samples_per_second": 6.625,
+      "train_steps_per_second": 0.207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 4.123581730562765e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}