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:
+- lucadiliello/naturalquestionsshortqa
 model-index:
 - name: natqa_albert_xl_finetuned
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # natqa_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 lucadiliello/naturalquestionsshortqa dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 68.28451230913058,
+    "eval_f1": 80.64002561092481,
+    "eval_runtime": 696.7007,
+    "eval_samples": 22353,
+    "eval_samples_per_second": 32.084,
+    "eval_steps_per_second": 4.012,
+    "total_flos": 1.1835349261279949e+17,
+    "train_loss": 0.40276029996411805,
+    "train_runtime": 83212.3563,
+    "train_samples": 169109,
+    "train_samples_per_second": 12.194,
+    "train_steps_per_second": 0.381
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7261365a9904fee6b822f33ff1768531cbc0534d665956babfc7fe068d556b
+size 58415320

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 68.28451230913058,
+    "eval_f1": 80.64002561092481,
+    "eval_runtime": 696.7007,
+    "eval_samples": 22353,
+    "eval_samples_per_second": 32.084,
+    "eval_steps_per_second": 4.012
+}

runs/Feb06_09-14-43_xgpi6/events.out.tfevents.1738888549.xgpi6.40233.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b20ddbf85ab9b55e0665412ca1cf86be6e516b68ca863df42bbbd1fd2973c60
+size 418

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1.1835349261279949e+17,
+    "train_loss": 0.40276029996411805,
+    "train_runtime": 83212.3563,
+    "train_samples": 169109,
+    "train_samples_per_second": 12.194,
+    "train_steps_per_second": 0.381
+}

trainer_state.json

@@ -0,0 +1,483 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 31710,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0946073793755913,
+      "grad_norm": 20.991043090820312,
+      "learning_rate": 2.9526963103122042e-05,
+      "loss": 1.5316,
+      "step": 500
+    },
+    {
+      "epoch": 0.1892147587511826,
+      "grad_norm": 14.59710693359375,
+      "learning_rate": 2.905392620624409e-05,
+      "loss": 0.9584,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28382213812677387,
+      "grad_norm": 9.1723051071167,
+      "learning_rate": 2.8580889309366132e-05,
+      "loss": 0.8737,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3784295175023652,
+      "grad_norm": 11.44797420501709,
+      "learning_rate": 2.8107852412488173e-05,
+      "loss": 0.8115,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47303689687795647,
+      "grad_norm": 11.459091186523438,
+      "learning_rate": 2.763481551561022e-05,
+      "loss": 0.7984,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5676442762535477,
+      "grad_norm": 15.557708740234375,
+      "learning_rate": 2.7161778618732263e-05,
+      "loss": 0.7689,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 9.84305477142334,
+      "learning_rate": 2.6688741721854305e-05,
+      "loss": 0.7113,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "grad_norm": 7.9723639488220215,
+      "learning_rate": 2.6215704824976346e-05,
+      "loss": 0.736,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8514664143803217,
+      "grad_norm": 12.051334381103516,
+      "learning_rate": 2.5742667928098394e-05,
+      "loss": 0.7206,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9460737937559129,
+      "grad_norm": 7.458990097045898,
+      "learning_rate": 2.5269631031220436e-05,
+      "loss": 0.7032,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0406811731315042,
+      "grad_norm": 11.645970344543457,
+      "learning_rate": 2.4796594134342477e-05,
+      "loss": 0.6551,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1352885525070955,
+      "grad_norm": 14.581408500671387,
+      "learning_rate": 2.4323557237464526e-05,
+      "loss": 0.5752,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2298959318826868,
+      "grad_norm": 8.860761642456055,
+      "learning_rate": 2.3850520340586567e-05,
+      "loss": 0.5836,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3245033112582782,
+      "grad_norm": 5.775502681732178,
+      "learning_rate": 2.337748344370861e-05,
+      "loss": 0.5738,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4191106906338695,
+      "grad_norm": 15.440156936645508,
+      "learning_rate": 2.2904446546830654e-05,
+      "loss": 0.5777,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5137180700094608,
+      "grad_norm": 10.90083122253418,
+      "learning_rate": 2.24314096499527e-05,
+      "loss": 0.5636,
+      "step": 8000
+    },
+    {
+      "epoch": 1.608325449385052,
+      "grad_norm": 6.780233860015869,
+      "learning_rate": 2.195837275307474e-05,
+      "loss": 0.5729,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7029328287606433,
+      "grad_norm": 9.615424156188965,
+      "learning_rate": 2.148533585619678e-05,
+      "loss": 0.5746,
+      "step": 9000
+    },
+    {
+      "epoch": 1.7975402081362346,
+      "grad_norm": 14.771319389343262,
+      "learning_rate": 2.101229895931883e-05,
+      "loss": 0.5676,
+      "step": 9500
+    },
+    {
+      "epoch": 1.8921475875118259,
+      "grad_norm": 17.73270034790039,
+      "learning_rate": 2.053926206244087e-05,
+      "loss": 0.567,
+      "step": 10000
+    },
+    {
+      "epoch": 1.9867549668874172,
+      "grad_norm": 7.3162431716918945,
+      "learning_rate": 2.0066225165562913e-05,
+      "loss": 0.5784,
+      "step": 10500
+    },
+    {
+      "epoch": 2.0813623462630084,
+      "grad_norm": 6.879025936126709,
+      "learning_rate": 1.959318826868496e-05,
+      "loss": 0.4232,
+      "step": 11000
+    },
+    {
+      "epoch": 2.1759697256385997,
+      "grad_norm": 7.238683223724365,
+      "learning_rate": 1.9120151371807002e-05,
+      "loss": 0.4126,
+      "step": 11500
+    },
+    {
+      "epoch": 2.270577105014191,
+      "grad_norm": 6.322164058685303,
+      "learning_rate": 1.8647114474929044e-05,
+      "loss": 0.4065,
+      "step": 12000
+    },
+    {
+      "epoch": 2.3651844843897822,
+      "grad_norm": 15.04572582244873,
+      "learning_rate": 1.8174077578051085e-05,
+      "loss": 0.4136,
+      "step": 12500
+    },
+    {
+      "epoch": 2.4597918637653735,
+      "grad_norm": 9.399176597595215,
+      "learning_rate": 1.7701040681173134e-05,
+      "loss": 0.4256,
+      "step": 13000
+    },
+    {
+      "epoch": 2.5543992431409652,
+      "grad_norm": 17.93691062927246,
+      "learning_rate": 1.7228003784295175e-05,
+      "loss": 0.436,
+      "step": 13500
+    },
+    {
+      "epoch": 2.6490066225165565,
+      "grad_norm": 14.960176467895508,
+      "learning_rate": 1.6754966887417217e-05,
+      "loss": 0.4176,
+      "step": 14000
+    },
+    {
+      "epoch": 2.7436140018921478,
+      "grad_norm": 14.551431655883789,
+      "learning_rate": 1.6281929990539265e-05,
+      "loss": 0.4154,
+      "step": 14500
+    },
+    {
+      "epoch": 2.838221381267739,
+      "grad_norm": 9.115693092346191,
+      "learning_rate": 1.5808893093661306e-05,
+      "loss": 0.4168,
+      "step": 15000
+    },
+    {
+      "epoch": 2.9328287606433303,
+      "grad_norm": 16.4350643157959,
+      "learning_rate": 1.5335856196783348e-05,
+      "loss": 0.4151,
+      "step": 15500
+    },
+    {
+      "epoch": 3.0274361400189216,
+      "grad_norm": 10.356840133666992,
+      "learning_rate": 1.4862819299905393e-05,
+      "loss": 0.3837,
+      "step": 16000
+    },
+    {
+      "epoch": 3.122043519394513,
+      "grad_norm": 17.35466766357422,
+      "learning_rate": 1.4389782403027438e-05,
+      "loss": 0.2785,
+      "step": 16500
+    },
+    {
+      "epoch": 3.216650898770104,
+      "grad_norm": 9.468245506286621,
+      "learning_rate": 1.3916745506149479e-05,
+      "loss": 0.2893,
+      "step": 17000
+    },
+    {
+      "epoch": 3.3112582781456954,
+      "grad_norm": 10.251808166503906,
+      "learning_rate": 1.3443708609271524e-05,
+      "loss": 0.2889,
+      "step": 17500
+    },
+    {
+      "epoch": 3.4058656575212867,
+      "grad_norm": 8.767330169677734,
+      "learning_rate": 1.2970671712393567e-05,
+      "loss": 0.2894,
+      "step": 18000
+    },
+    {
+      "epoch": 3.500473036896878,
+      "grad_norm": 16.839839935302734,
+      "learning_rate": 1.249763481551561e-05,
+      "loss": 0.2855,
+      "step": 18500
+    },
+    {
+      "epoch": 3.595080416272469,
+      "grad_norm": 8.218119621276855,
+      "learning_rate": 1.2024597918637655e-05,
+      "loss": 0.2933,
+      "step": 19000
+    },
+    {
+      "epoch": 3.6896877956480605,
+      "grad_norm": 14.895683288574219,
+      "learning_rate": 1.1551561021759697e-05,
+      "loss": 0.2956,
+      "step": 19500
+    },
+    {
+      "epoch": 3.7842951750236518,
+      "grad_norm": 9.546406745910645,
+      "learning_rate": 1.1078524124881742e-05,
+      "loss": 0.287,
+      "step": 20000
+    },
+    {
+      "epoch": 3.878902554399243,
+      "grad_norm": 11.646368980407715,
+      "learning_rate": 1.0605487228003785e-05,
+      "loss": 0.2947,
+      "step": 20500
+    },
+    {
+      "epoch": 3.9735099337748343,
+      "grad_norm": 10.756194114685059,
+      "learning_rate": 1.0132450331125828e-05,
+      "loss": 0.2938,
+      "step": 21000
+    },
+    {
+      "epoch": 4.068117313150426,
+      "grad_norm": 6.343067646026611,
+      "learning_rate": 9.659413434247873e-06,
+      "loss": 0.2013,
+      "step": 21500
+    },
+    {
+      "epoch": 4.162724692526017,
+      "grad_norm": 13.217527389526367,
+      "learning_rate": 9.186376537369914e-06,
+      "loss": 0.1851,
+      "step": 22000
+    },
+    {
+      "epoch": 4.257332071901608,
+      "grad_norm": 11.804835319519043,
+      "learning_rate": 8.713339640491959e-06,
+      "loss": 0.1861,
+      "step": 22500
+    },
+    {
+      "epoch": 4.351939451277199,
+      "grad_norm": 8.68942928314209,
+      "learning_rate": 8.240302743614002e-06,
+      "loss": 0.184,
+      "step": 23000
+    },
+    {
+      "epoch": 4.446546830652791,
+      "grad_norm": 4.478140830993652,
+      "learning_rate": 7.767265846736046e-06,
+      "loss": 0.1878,
+      "step": 23500
+    },
+    {
+      "epoch": 4.541154210028382,
+      "grad_norm": 2.938448190689087,
+      "learning_rate": 7.2942289498580895e-06,
+      "loss": 0.1878,
+      "step": 24000
+    },
+    {
+      "epoch": 4.635761589403973,
+      "grad_norm": 8.990928649902344,
+      "learning_rate": 6.821192052980133e-06,
+      "loss": 0.1834,
+      "step": 24500
+    },
+    {
+      "epoch": 4.7303689687795645,
+      "grad_norm": 6.007904052734375,
+      "learning_rate": 6.348155156102176e-06,
+      "loss": 0.1899,
+      "step": 25000
+    },
+    {
+      "epoch": 4.824976348155156,
+      "grad_norm": 12.605597496032715,
+      "learning_rate": 5.87511825922422e-06,
+      "loss": 0.1889,
+      "step": 25500
+    },
+    {
+      "epoch": 4.919583727530747,
+      "grad_norm": 8.449039459228516,
+      "learning_rate": 5.402081362346263e-06,
+      "loss": 0.1708,
+      "step": 26000
+    },
+    {
+      "epoch": 5.014191106906338,
+      "grad_norm": 4.606452941894531,
+      "learning_rate": 4.929044465468307e-06,
+      "loss": 0.1704,
+      "step": 26500
+    },
+    {
+      "epoch": 5.10879848628193,
+      "grad_norm": 8.18777084350586,
+      "learning_rate": 4.45600756859035e-06,
+      "loss": 0.107,
+      "step": 27000
+    },
+    {
+      "epoch": 5.203405865657521,
+      "grad_norm": 6.136015892028809,
+      "learning_rate": 3.9829706717123935e-06,
+      "loss": 0.1047,
+      "step": 27500
+    },
+    {
+      "epoch": 5.298013245033113,
+      "grad_norm": 70.6666259765625,
+      "learning_rate": 3.509933774834437e-06,
+      "loss": 0.0957,
+      "step": 28000
+    },
+    {
+      "epoch": 5.392620624408704,
+      "grad_norm": 1.9723526239395142,
+      "learning_rate": 3.0368968779564807e-06,
+      "loss": 0.1055,
+      "step": 28500
+    },
+    {
+      "epoch": 5.4872280037842955,
+      "grad_norm": 4.301974296569824,
+      "learning_rate": 2.5638599810785243e-06,
+      "loss": 0.0981,
+      "step": 29000
+    },
+    {
+      "epoch": 5.581835383159887,
+      "grad_norm": 10.873367309570312,
+      "learning_rate": 2.0908230842005675e-06,
+      "loss": 0.1007,
+      "step": 29500
+    },
+    {
+      "epoch": 5.676442762535478,
+      "grad_norm": 9.325891494750977,
+      "learning_rate": 1.6177861873226113e-06,
+      "loss": 0.0989,
+      "step": 30000
+    },
+    {
+      "epoch": 5.771050141911069,
+      "grad_norm": 10.931228637695312,
+      "learning_rate": 1.1447492904446547e-06,
+      "loss": 0.1009,
+      "step": 30500
+    },
+    {
+      "epoch": 5.865657521286661,
+      "grad_norm": 3.8816733360290527,
+      "learning_rate": 6.717123935666982e-07,
+      "loss": 0.0964,
+      "step": 31000
+    },
+    {
+      "epoch": 5.960264900662252,
+      "grad_norm": 28.40899658203125,
+      "learning_rate": 1.9867549668874173e-07,
+      "loss": 0.0918,
+      "step": 31500
+    },
+    {
+      "epoch": 6.0,
+      "step": 31710,
+      "total_flos": 1.1835349261279949e+17,
+      "train_loss": 0.40276029996411805,
+      "train_runtime": 83212.3563,
+      "train_samples_per_second": 12.194,
+      "train_steps_per_second": 0.381
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 31710,
+  "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": 1.1835349261279949e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}