commit files to HF hub

.gitignore

@@ -0,0 +1 @@
+checkpoint*

checkpoint-10000/config.json

@@ -5,7 +5,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",

checkpoint-10000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71038f71294ce4bea3278ad481be4f7813e2bdc40702821a0c36c8fbf2b3bf0
-size 1475512665
+oid sha256:f720256e4e70820d89c9e06666f88dbcad39f323aa192001b302a880db22b488
+size 1475512793

checkpoint-10000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9015c37d875002cc65e6ee1eea456f1901cfec172c12336855961046aa649d
+oid sha256:9a23605ea589e2551eb0df2eb5509e159ed31156dfca15b2eeba8eb53c93f51f
 size 737770027

checkpoint-10000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7d4a3cc28f7bedaf263d0aaa9d44d8e8dbbb9318d984a9f15d4b64025950ca
+oid sha256:8a41b1f8f5d265afac85d7d1219ee0f67a2407025613329d1f86629642de0409
 size 14503

checkpoint-10000/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0efbbbbf577f80c6508c5320fd27b2a182a4c5a083ba7b8c862c224c4c39e5ea
+oid sha256:cdbc1a65543b77f14ca91d846aa90008d71866cbb1b49f2d46285e1f600dd308
 size 559

checkpoint-10000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4417a71fdc6b2b190384e77f425c104230eb51d1e5affb60e61f3daefae553d3
+oid sha256:63309151ebd54520ac76370f164e851299d6d6a0b59b77db141c9a804e76fd13
 size 623

checkpoint-10000/trainer_state.json

@@ -1,296 +1,776 @@
 {
-  "best_metric": 0.6859038472175598,
-  "best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000",
+  "best_metric": 0.727655291557312,
+  "best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-10000",
   "epoch": 4.835287009063444,
   "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-07,
+      "loss": 1.0361,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.98e-07,
+      "loss": 0.9751,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.979999999999999e-07,
+      "loss": 0.9807,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.94e-07,
+      "loss": 0.9513,
+      "step": 400
+    },
     {
       "epoch": 0.24,
-      "learning_rate": 9.518375241779499e-06,
-      "loss": 0.8315,
+      "learning_rate": 9.94e-07,
+      "loss": 0.9237,
       "step": 500
     },
     {
       "epoch": 0.24,
-      "eval_loss": 0.7444673180580139,
-      "eval_runtime": 29.7252,
-      "eval_samples_per_second": 123.33,
-      "eval_steps_per_second": 30.849,
+      "eval_loss": 0.9464540481567383,
+      "eval_runtime": 37.5769,
+      "eval_samples_per_second": 97.587,
+      "eval_steps_per_second": 24.403,
       "step": 500
     },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.955915919781764e-07,
+      "loss": 0.9367,
+      "step": 600
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.81900265076038e-07,
+      "loss": 0.8993,
+      "step": 700
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.594490241150311e-07,
+      "loss": 0.8586,
+      "step": 800
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.282057505552949e-07,
+      "loss": 0.854,
+      "step": 900
+    },
     {
       "epoch": 0.48,
-      "learning_rate": 9.034816247582205e-06,
-      "loss": 0.7232,
+      "learning_rate": 8.889381125453379e-07,
+      "loss": 0.8642,
       "step": 1000
     },
     {
       "epoch": 0.48,
-      "eval_loss": 0.7441162467002869,
-      "eval_runtime": 29.4226,
-      "eval_samples_per_second": 124.598,
-      "eval_steps_per_second": 31.167,
+      "eval_loss": 0.8270628452301025,
+      "eval_runtime": 28.2214,
+      "eval_samples_per_second": 129.937,
+      "eval_steps_per_second": 32.493,
       "step": 1000
     },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.423819662432867e-07,
+      "loss": 0.8314,
+      "step": 1100
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.894097508558568e-07,
+      "loss": 0.8317,
+      "step": 1200
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.310141395581585e-07,
+      "loss": 0.7939,
+      "step": 1300
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.682894372882701e-07,
+      "loss": 0.803,
+      "step": 1400
+    },
     {
       "epoch": 0.73,
-      "learning_rate": 8.552224371373308e-06,
-      "loss": 0.7269,
+      "learning_rate": 6.024110740127264e-07,
+      "loss": 0.8029,
       "step": 1500
     },
     {
       "epoch": 0.73,
-      "eval_loss": 0.7453668117523193,
-      "eval_runtime": 29.5754,
-      "eval_samples_per_second": 123.955,
-      "eval_steps_per_second": 31.006,
+      "eval_loss": 0.7635419368743896,
+      "eval_runtime": 28.2809,
+      "eval_samples_per_second": 129.663,
+      "eval_steps_per_second": 32.425,
       "step": 1500
     },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.346135777490083e-07,
+      "loss": 0.7959,
+      "step": 1600
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.6616744011972247e-07,
+      "loss": 0.7708,
+      "step": 1700
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.9835530796656867e-07,
+      "loss": 0.7636,
+      "step": 1800
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3244794718149894e-07,
+      "loss": 0.7864,
+      "step": 1900
+    },
     {
       "epoch": 0.97,
-      "learning_rate": 8.068665377176016e-06,
-      "loss": 0.7185,
+      "learning_rate": 2.696804291810131e-07,
+      "loss": 0.8005,
       "step": 2000
     },
     {
       "epoch": 0.97,
-      "eval_loss": 0.6859038472175598,
-      "eval_runtime": 29.569,
-      "eval_samples_per_second": 123.981,
-      "eval_steps_per_second": 31.012,
+      "eval_loss": 0.7537589073181152,
+      "eval_runtime": 28.4034,
+      "eval_samples_per_second": 129.104,
+      "eval_steps_per_second": 32.285,
       "step": 2000
     },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.1122898627730768e-07,
+      "loss": 0.7924,
+      "step": 2100
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5818896966520534e-07,
+      "loss": 0.8072,
+      "step": 2200
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.1155432308130763e-07,
+      "loss": 0.7997,
+      "step": 2300
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.219895678887305e-08,
+      "loss": 0.7931,
+      "step": 2400
+    },
     {
       "epoch": 1.21,
-      "learning_rate": 7.585106382978724e-06,
-      "loss": 0.6611,
+      "learning_rate": 4.0860370930748286e-08,
+      "loss": 0.7734,
       "step": 2500
     },
     {
       "epoch": 1.21,
-      "eval_loss": 0.6883463263511658,
-      "eval_runtime": 29.5377,
-      "eval_samples_per_second": 124.113,
-      "eval_steps_per_second": 31.045,
+      "eval_loss": 0.7621562480926514,
+      "eval_runtime": 28.9226,
+      "eval_samples_per_second": 126.786,
+      "eval_steps_per_second": 31.705,
       "step": 2500
     },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.812583514064109e-08,
+      "loss": 0.7487,
+      "step": 2600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 4.421383399995704e-09,
+      "loss": 0.7911,
+      "step": 2700
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 9.999961696285757e-07,
+      "loss": 0.7794,
+      "step": 2800
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9.950440411813353e-07,
+      "loss": 0.7922,
+      "step": 2900
+    },
     {
       "epoch": 1.45,
-      "learning_rate": 7.101547388781432e-06,
-      "loss": 0.6516,
+      "learning_rate": 9.810025090182484e-07,
+      "loss": 0.7842,
       "step": 3000
     },
     {
       "epoch": 1.45,
-      "eval_loss": 0.7088809013366699,
-      "eval_runtime": 29.1585,
-      "eval_samples_per_second": 125.727,
-      "eval_steps_per_second": 31.449,
+      "eval_loss": 0.748653769493103,
+      "eval_runtime": 27.9531,
+      "eval_samples_per_second": 131.184,
+      "eval_steps_per_second": 32.805,
       "step": 3000
     },
+    {
+      "epoch": 1.5,
+      "learning_rate": 9.581263257645987e-07,
+      "loss": 0.7731,
+      "step": 3100
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.264785067160785e-07,
+      "loss": 0.7849,
+      "step": 3200
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.868386909145071e-07,
+      "loss": 0.7745,
+      "step": 3300
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.399497089461603e-07,
+      "loss": 0.7611,
+      "step": 3400
+    },
     {
       "epoch": 1.69,
-      "learning_rate": 6.617988394584139e-06,
-      "loss": 0.6386,
+      "learning_rate": 7.872511787610445e-07,
+      "loss": 0.7543,
       "step": 3500
     },
     {
       "epoch": 1.69,
-      "eval_loss": 0.6939310431480408,
-      "eval_runtime": 29.2346,
-      "eval_samples_per_second": 125.399,
-      "eval_steps_per_second": 31.367,
+      "eval_loss": 0.7955728769302368,
+      "eval_runtime": 28.0818,
+      "eval_samples_per_second": 130.583,
+      "eval_steps_per_second": 32.655,
       "step": 3500
     },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.286677103241362e-07,
+      "loss": 0.7793,
+      "step": 3600
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 6.657991218409446e-07,
+      "loss": 0.7359,
+      "step": 3700
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 5.998235396346351e-07,
+      "loss": 0.7602,
+      "step": 3800
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 5.319773135574745e-07,
+      "loss": 0.7664,
+      "step": 3900
+    },
     {
       "epoch": 1.93,
-      "learning_rate": 6.134429400386848e-06,
-      "loss": 0.6435,
+      "learning_rate": 4.635318484047261e-07,
+      "loss": 0.7883,
       "step": 4000
     },
     {
       "epoch": 1.93,
-      "eval_loss": 0.6942200064659119,
-      "eval_runtime": 30.0324,
-      "eval_samples_per_second": 122.068,
-      "eval_steps_per_second": 30.534,
+      "eval_loss": 0.7467952370643616,
+      "eval_runtime": 28.6183,
+      "eval_samples_per_second": 128.135,
+      "eval_steps_per_second": 32.042,
       "step": 4000
     },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.9576977841621134e-07,
+      "loss": 0.7493,
+      "step": 4100
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 3.299609313436215e-07,
+      "loss": 0.7312,
+      "step": 4200
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.6733853250510007e-07,
+      "loss": 0.7387,
+      "step": 4300
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.0907609475136373e-07,
+      "loss": 0.7492,
+      "step": 4400
+    },
     {
       "epoch": 2.18,
-      "learning_rate": 5.650870406189556e-06,
-      "loss": 0.5823,
+      "learning_rate": 1.562654274139964e-07,
+      "loss": 0.7515,
       "step": 4500
     },
     {
       "epoch": 2.18,
-      "eval_loss": 0.771172821521759,
-      "eval_runtime": 29.4927,
-      "eval_samples_per_second": 124.302,
-      "eval_steps_per_second": 31.092,
+      "eval_loss": 0.7437878847122192,
+      "eval_runtime": 27.6555,
+      "eval_samples_per_second": 132.595,
+      "eval_steps_per_second": 33.158,
       "step": 4500
     },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.0989617633737314e-07,
+      "loss": 0.7218,
+      "step": 4600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 7.083727840391568e-08,
+      "loss": 0.7554,
+      "step": 4700
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 4.00889953873248e-08,
+      "loss": 0.768,
+      "step": 4800
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.7607339075303706e-08,
+      "loss": 0.725,
+      "step": 4900
+    },
     {
       "epoch": 2.42,
-      "learning_rate": 5.167311411992263e-06,
-      "loss": 0.5652,
+      "learning_rate": 4.165483173136253e-09,
+      "loss": 0.716,
       "step": 5000
     },
     {
       "epoch": 2.42,
-      "eval_loss": 0.7315438985824585,
-      "eval_runtime": 28.9938,
-      "eval_samples_per_second": 126.441,
-      "eval_steps_per_second": 31.627,
+      "eval_loss": 0.7440274953842163,
+      "eval_runtime": 28.4825,
+      "eval_samples_per_second": 128.746,
+      "eval_steps_per_second": 32.195,
       "step": 5000
     },
+    {
+      "epoch": 2.47,
+      "learning_rate": 9.999846785729901e-07,
+      "loss": 0.7534,
+      "step": 5100
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 9.947653741800156e-07,
+      "loss": 0.7644,
+      "step": 5200
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 9.80274410836591e-07,
+      "loss": 0.7631,
+      "step": 5300
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.567833420446291e-07,
+      "loss": 0.7624,
+      "step": 5400
+    },
     {
       "epoch": 2.66,
-      "learning_rate": 4.683752417794971e-06,
-      "loss": 0.5701,
+      "learning_rate": 9.24732378840687e-07,
+      "loss": 0.743,
       "step": 5500
     },
     {
       "epoch": 2.66,
-      "eval_loss": 0.7429590225219727,
-      "eval_runtime": 29.2482,
-      "eval_samples_per_second": 125.341,
-      "eval_steps_per_second": 31.352,
+      "eval_loss": 0.7312911152839661,
+      "eval_runtime": 28.3334,
+      "eval_samples_per_second": 129.423,
+      "eval_steps_per_second": 32.365,
       "step": 5500
     },
+    {
+      "epoch": 2.71,
+      "learning_rate": 8.847221404583831e-07,
+      "loss": 0.7522,
+      "step": 5600
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 8.380074821716343e-07,
+      "loss": 0.7367,
+      "step": 5700
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 7.845215744177952e-07,
+      "loss": 0.7557,
+      "step": 5800
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 7.257038727678722e-07,
+      "loss": 0.7329,
+      "step": 5900
+    },
     {
       "epoch": 2.9,
-      "learning_rate": 4.20019342359768e-06,
-      "loss": 0.5583,
+      "learning_rate": 6.626565919248464e-07,
+      "loss": 0.726,
       "step": 6000
     },
     {
       "epoch": 2.9,
-      "eval_loss": 0.74286949634552,
-      "eval_runtime": 28.9549,
-      "eval_samples_per_second": 126.611,
-      "eval_steps_per_second": 31.67,
+      "eval_loss": 0.7325854301452637,
+      "eval_runtime": 27.7597,
+      "eval_samples_per_second": 132.098,
+      "eval_steps_per_second": 33.034,
       "step": 6000
     },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.965612068185233e-07,
+      "loss": 0.7804,
+      "step": 6100
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.286563123483964e-07,
+      "loss": 0.7319,
+      "step": 6200
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 4.602144127264582e-07,
+      "loss": 0.732,
+      "step": 6300
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 3.925180753762438e-07,
+      "loss": 0.7665,
+      "step": 6400
+    },
     {
       "epoch": 3.14,
-      "learning_rate": 3.7176015473887818e-06,
-      "loss": 0.5145,
+      "learning_rate": 3.268358962522407e-07,
+      "loss": 0.7499,
       "step": 6500
     },
     {
       "epoch": 3.14,
-      "eval_loss": 0.8086823225021362,
-      "eval_runtime": 29.0547,
-      "eval_samples_per_second": 126.176,
-      "eval_steps_per_second": 31.561,
+      "eval_loss": 0.7382772564888,
+      "eval_runtime": 27.6004,
+      "eval_samples_per_second": 132.86,
+      "eval_steps_per_second": 33.224,
       "step": 6500
     },
+    {
+      "epoch": 3.19,
+      "learning_rate": 2.64398726977746e-07,
+      "loss": 0.739,
+      "step": 6600
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 2.063766092928542e-07,
+      "loss": 0.7201,
+      "step": 6700
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.5385684904965596e-07,
+      "loss": 0.7013,
+      "step": 6800
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 1.0782364063714005e-07,
+      "loss": 0.7234,
+      "step": 6900
+    },
     {
       "epoch": 3.38,
-      "learning_rate": 3.23404255319149e-06,
-      "loss": 0.4795,
+      "learning_rate": 6.913962366403719e-08,
+      "loss": 0.7377,
       "step": 7000
     },
     {
       "epoch": 3.38,
-      "eval_loss": 0.8026116490364075,
-      "eval_runtime": 28.8514,
-      "eval_samples_per_second": 127.065,
-      "eval_steps_per_second": 31.784,
+      "eval_loss": 0.7334151864051819,
+      "eval_runtime": 27.6353,
+      "eval_samples_per_second": 132.693,
+      "eval_steps_per_second": 33.182,
       "step": 7000
     },
+    {
+      "epoch": 3.43,
+      "learning_rate": 3.852971751825379e-08,
+      "loss": 0.7272,
+      "step": 7100
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.6567536735284103e-08,
+      "loss": 0.7323,
+      "step": 7200
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 3.664641744888397e-09,
+      "loss": 0.6981,
+      "step": 7300
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 9.99937173568261e-07,
+      "loss": 0.6917,
+      "step": 7400
+    },
     {
       "epoch": 3.63,
-      "learning_rate": 2.7504835589941973e-06,
-      "loss": 0.4784,
+      "learning_rate": 9.94170412962655e-07,
+      "loss": 0.7459,
       "step": 7500
     },
     {
       "epoch": 3.63,
-      "eval_loss": 0.7970021963119507,
-      "eval_runtime": 28.8445,
-      "eval_samples_per_second": 127.095,
-      "eval_steps_per_second": 31.791,
+      "eval_loss": 0.7427003979682922,
+      "eval_runtime": 27.4459,
+      "eval_samples_per_second": 133.608,
+      "eval_steps_per_second": 33.411,
       "step": 7500
     },
+    {
+      "epoch": 3.67,
+      "learning_rate": 9.79143142686205e-07,
+      "loss": 0.7406,
+      "step": 7600
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 9.551369663680862e-07,
+      "loss": 0.7304,
+      "step": 7700
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 9.226017479056962e-07,
+      "loss": 0.7278,
+      "step": 7800
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 8.821471812372215e-07,
+      "loss": 0.7273,
+      "step": 7900
+    },
     {
       "epoch": 3.87,
-      "learning_rate": 2.2669245647969055e-06,
-      "loss": 0.4793,
+      "learning_rate": 8.345313649781101e-07,
+      "loss": 0.7186,
       "step": 8000
     },
     {
       "epoch": 3.87,
-      "eval_loss": 0.7971013784408569,
-      "eval_runtime": 29.079,
-      "eval_samples_per_second": 126.07,
-      "eval_steps_per_second": 31.535,
+      "eval_loss": 0.7306970953941345,
+      "eval_runtime": 27.6504,
+      "eval_samples_per_second": 132.62,
+      "eval_steps_per_second": 33.164,
       "step": 8000
     },
+    {
+      "epoch": 3.92,
+      "learning_rate": 7.806465960271379e-07,
+      "loss": 0.6956,
+      "step": 8100
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 7.215026483628598e-07,
+      "loss": 0.7794,
+      "step": 8200
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 6.582078503775666e-07,
+      "loss": 0.7304,
+      "step": 8300
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 5.919483153501647e-07,
+      "loss": 0.7477,
+      "step": 8400
+    },
     {
       "epoch": 4.11,
-      "learning_rate": 1.784332688588008e-06,
-      "loss": 0.4544,
+      "learning_rate": 5.239657142686591e-07,
+      "loss": 0.723,
       "step": 8500
     },
     {
       "epoch": 4.11,
-      "eval_loss": 0.8546438813209534,
-      "eval_runtime": 29.1238,
-      "eval_samples_per_second": 125.877,
-      "eval_steps_per_second": 31.486,
+      "eval_loss": 0.7324436902999878,
+      "eval_runtime": 27.6456,
+      "eval_samples_per_second": 132.643,
+      "eval_steps_per_second": 33.17,
       "step": 8500
     },
+    {
+      "epoch": 4.16,
+      "learning_rate": 4.555340075285952e-07,
+      "loss": 0.7081,
+      "step": 8600
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 3.8793557154393083e-07,
+      "loss": 0.717,
+      "step": 8700
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 3.2243716764587667e-07,
+      "loss": 0.7229,
+      "step": 8800
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 2.602662036006858e-07,
+      "loss": 0.713,
+      "step": 8900
+    },
     {
       "epoch": 4.35,
-      "learning_rate": 1.3007736943907157e-06,
-      "loss": 0.4115,
+      "learning_rate": 2.025877325938261e-07,
+      "loss": 0.7275,
       "step": 9000
     },
     {
       "epoch": 4.35,
-      "eval_loss": 0.8430052995681763,
-      "eval_runtime": 29.3455,
-      "eval_samples_per_second": 124.926,
-      "eval_steps_per_second": 31.248,
+      "eval_loss": 0.7325617074966431,
+      "eval_runtime": 27.8844,
+      "eval_samples_per_second": 131.507,
+      "eval_steps_per_second": 32.886,
       "step": 9000
     },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.504826207082261e-07,
+      "loss": 0.693,
+      "step": 9100
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 1.049272920272809e-07,
+      "loss": 0.689,
+      "step": 9200
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 6.677543092937843e-08,
+      "loss": 0.7001,
+      "step": 9300
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 3.674198446393789e-08,
+      "loss": 0.7398,
+      "step": 9400
+    },
     {
       "epoch": 4.59,
-      "learning_rate": 8.172147001934237e-07,
-      "loss": 0.4192,
+      "learning_rate": 1.538976459652064e-08,
+      "loss": 0.7371,
       "step": 9500
     },
     {
       "epoch": 4.59,
-      "eval_loss": 0.8553691506385803,
-      "eval_runtime": 30.0888,
-      "eval_samples_per_second": 121.839,
-      "eval_steps_per_second": 30.476,
+      "eval_loss": 0.7348757982254028,
+      "eval_runtime": 27.6591,
+      "eval_samples_per_second": 132.579,
+      "eval_steps_per_second": 33.154,
       "step": 9500
     },
+    {
+      "epoch": 4.64,
+      "learning_rate": 3.1189013903395455e-09,
+      "loss": 0.7164,
+      "step": 9600
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 9.998406552336684e-07,
+      "loss": 0.7045,
+      "step": 9700
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 9.934334446448806e-07,
+      "loss": 0.7095,
+      "step": 9800
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 9.777795348078374e-07,
+      "loss": 0.7265,
+      "step": 9900
+    },
     {
       "epoch": 4.84,
-      "learning_rate": 3.3365570599613157e-07,
-      "loss": 0.4101,
+      "learning_rate": 9.531722722678393e-07,
+      "loss": 0.7267,
       "step": 10000
     },
     {
       "epoch": 4.84,
-      "eval_loss": 0.863072395324707,
-      "eval_runtime": 29.1167,
-      "eval_samples_per_second": 125.907,
-      "eval_steps_per_second": 31.494,
+      "eval_loss": 0.727655291557312,
+      "eval_runtime": 27.3264,
+      "eval_samples_per_second": 134.193,
+      "eval_steps_per_second": 33.557,
       "step": 10000
     }
   ],
-  "max_steps": 10340,
-  "num_train_epochs": 5,
-  "total_flos": 9148295382909930.0,
+  "max_steps": 16544,
+  "num_train_epochs": 8,
+  "total_flos": 9147892997166300.0,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-10000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c733ade4e8726b7d2050d20982a2b640dde2dd40f5221ce54a078013d218d18
+oid sha256:3ffb2d40861e346c298ecb026926b1cd6fcf3c2ff8a5a38a5b78b121f9949508
 size 3375

checkpoint-2000/config.json

@@ -5,7 +5,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",

checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473042aa6b50e90eeafe35a0eb6c00fdf7e8130b0c124e8e6bae633a7aaeb83e
-size 1475512665
+oid sha256:626d2c0f57e0d16c0069652656de4057825c16712166a707211c8fe154203bc8
+size 1475512793

checkpoint-2000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152f4de359aa4e010c15c54e93a34fb1197afb81c06c241d2c177d699fd0641c
+oid sha256:0ab0240bd69843fd06b929f55bc2e760f01226d976e947792a27a2de9cf7783d
 size 737770027

checkpoint-2000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7cb5f5ba70a378637f312cfcaa024819078650cf5a9b71109c9eef84768726b
+oid sha256:3be3a7e37abbb30b18f1d72e9e82d80209a1ffafba792a578625451aef21e954
 size 14503

checkpoint-2000/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9630290c2855c60ed3fcbed4eeefb978189ee21116d8c9e5613dc0cf8dde2d3
+oid sha256:4eccc082304cdb1b781a00d1171288ffa36d40ca690860809f81bcac4e20adae
 size 559

checkpoint-2000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33176767ded0ce16da286202ede558cb1cf892fa297e9e9cca486a46978b6600
+oid sha256:3abeb5aa5be592899ee5dc8748f9e3bf735434f8a9f384cf814f8b27ee9adb78
 size 623

checkpoint-2000/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6859038472175598,
+  "best_metric": 0.7537589073181152,
   "best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000",
   "epoch": 0.9667673716012085,
   "global_step": 2000,
@@ -7,66 +7,162 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-07,
+      "loss": 1.0361,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.98e-07,
+      "loss": 0.9751,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 5.979999999999999e-07,
+      "loss": 0.9807,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 7.94e-07,
+      "loss": 0.9513,
+      "step": 400
+    },
     {
       "epoch": 0.24,
-      "learning_rate": 9.518375241779499e-06,
-      "loss": 0.8315,
+      "learning_rate": 9.94e-07,
+      "loss": 0.9237,
       "step": 500
     },
     {
       "epoch": 0.24,
-      "eval_loss": 0.7444673180580139,
-      "eval_runtime": 29.7252,
-      "eval_samples_per_second": 123.33,
-      "eval_steps_per_second": 30.849,
+      "eval_loss": 0.9464540481567383,
+      "eval_runtime": 37.5769,
+      "eval_samples_per_second": 97.587,
+      "eval_steps_per_second": 24.403,
       "step": 500
     },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.955915919781764e-07,
+      "loss": 0.9367,
+      "step": 600
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.81900265076038e-07,
+      "loss": 0.8993,
+      "step": 700
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.594490241150311e-07,
+      "loss": 0.8586,
+      "step": 800
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.282057505552949e-07,
+      "loss": 0.854,
+      "step": 900
+    },
     {
       "epoch": 0.48,
-      "learning_rate": 9.034816247582205e-06,
-      "loss": 0.7232,
+      "learning_rate": 8.889381125453379e-07,
+      "loss": 0.8642,
       "step": 1000
     },
     {
       "epoch": 0.48,
-      "eval_loss": 0.7441162467002869,
-      "eval_runtime": 29.4226,
-      "eval_samples_per_second": 124.598,
-      "eval_steps_per_second": 31.167,
+      "eval_loss": 0.8270628452301025,
+      "eval_runtime": 28.2214,
+      "eval_samples_per_second": 129.937,
+      "eval_steps_per_second": 32.493,
       "step": 1000
     },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.423819662432867e-07,
+      "loss": 0.8314,
+      "step": 1100
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.894097508558568e-07,
+      "loss": 0.8317,
+      "step": 1200
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.310141395581585e-07,
+      "loss": 0.7939,
+      "step": 1300
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.682894372882701e-07,
+      "loss": 0.803,
+      "step": 1400
+    },
     {
       "epoch": 0.73,
-      "learning_rate": 8.552224371373308e-06,
-      "loss": 0.7269,
+      "learning_rate": 6.024110740127264e-07,
+      "loss": 0.8029,
       "step": 1500
     },
     {
       "epoch": 0.73,
-      "eval_loss": 0.7453668117523193,
-      "eval_runtime": 29.5754,
-      "eval_samples_per_second": 123.955,
-      "eval_steps_per_second": 31.006,
+      "eval_loss": 0.7635419368743896,
+      "eval_runtime": 28.2809,
+      "eval_samples_per_second": 129.663,
+      "eval_steps_per_second": 32.425,
       "step": 1500
     },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.346135777490083e-07,
+      "loss": 0.7959,
+      "step": 1600
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.6616744011972247e-07,
+      "loss": 0.7708,
+      "step": 1700
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.9835530796656867e-07,
+      "loss": 0.7636,
+      "step": 1800
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3244794718149894e-07,
+      "loss": 0.7864,
+      "step": 1900
+    },
     {
       "epoch": 0.97,
-      "learning_rate": 8.068665377176016e-06,
-      "loss": 0.7185,
+      "learning_rate": 2.696804291810131e-07,
+      "loss": 0.8005,
       "step": 2000
     },
     {
       "epoch": 0.97,
-      "eval_loss": 0.6859038472175598,
-      "eval_runtime": 29.569,
-      "eval_samples_per_second": 123.981,
-      "eval_steps_per_second": 31.012,
+      "eval_loss": 0.7537589073181152,
+      "eval_runtime": 28.4034,
+      "eval_samples_per_second": 129.104,
+      "eval_steps_per_second": 32.285,
       "step": 2000
     }
   ],
-  "max_steps": 10340,
-  "num_train_epochs": 5,
-  "total_flos": 1822810502059560.0,
+  "max_steps": 16544,
+  "num_train_epochs": 8,
+  "total_flos": 1828884830909760.0,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c733ade4e8726b7d2050d20982a2b640dde2dd40f5221ce54a078013d218d18
+oid sha256:3ffb2d40861e346c298ecb026926b1cd6fcf3c2ff8a5a38a5b78b121f9949508
 size 3375

config.json

@@ -5,7 +5,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152f4de359aa4e010c15c54e93a34fb1197afb81c06c241d2c177d699fd0641c
+oid sha256:183b92732073ecb3e37d10ffc34996ac6fe70d5a5295f1d211ad7775260a3e4f
 size 737770027

runs/Jul03_17-16-15_8a98c40ff775/events.out.tfevents.1656868588.8a98c40ff775.71.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b3617a801c60d083a94daa04872ab8100ae1aa4bc27f09980a749aaf121cb98
-size 12918

runs/Jul03_21-34-55_8a98c40ff775/events.out.tfevents.1656884100.8a98c40ff775.71.4

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5e60884f2f24cd30d861b6d76f2432d12a76a66f3a0189fb8ddbabac92b6b68
-size 9495

runs/Jul03_23-15-45_8a98c40ff775/1656890147.0297482/events.out.tfevents.1656890147.8a98c40ff775.71.7

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7841a1cc1f026e1d8f7e27ebfc6c2345433308cf68d12ab48b2256e8b26519a2
-size 5435

runs/Jul03_23-16-08_8a98c40ff775/1656890170.9030218/events.out.tfevents.1656890170.8a98c40ff775.71.9

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5dbfc67c518b8e9b6453cf23fcecb24d018090efab32201f1068779e87121f75
-size 5435

runs/Jul03_23-16-08_8a98c40ff775/events.out.tfevents.1656890170.8a98c40ff775.71.8

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aeaeddd48689ec141326ec77032494af4461bb353420d795c77f5dd6b7bae92d
-size 4005

runs/Jul03_23-26-33_8a98c40ff775/1656890797.636419/events.out.tfevents.1656890797.8a98c40ff775.5349.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83ee3cfe3d4c4e5adfe96c2d421fe9902f2b13d7880adfdaa4f942184344c537
-size 5435

runs/Jul03_23-26-33_8a98c40ff775/events.out.tfevents.1656890797.8a98c40ff775.5349.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15a8e80f13acce54563ebb8cb7c22816065730ffe17ebaba086b1299d54ba061
-size 7001

runs/Jul04_00-33-28_8a98c40ff775/1656894810.6894863/events.out.tfevents.1656894810.8a98c40ff775.8083.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f8db2b966d521d474da361acfa1a1d7fdbf1c646c12217f96f06b8c168f5766
-size 5435

runs/{Jul03_17-16-15_8a98c40ff775/1656868588.8381069/events.out.tfevents.1656868588.8a98c40ff775.71.1 → Jul26_21-03-46_1fe91f198d71/1658869435.620103/events.out.tfevents.1658869435.1fe91f198d71.71.1}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a91a894342ce694eb4bb9fcf877374867217236e883fbbdd94ac75ace1877e2
+oid sha256:c6485b7a2dffeb1975234009c45dcfd6419d71586d0e5c9b414f400258d1ce9b
 size 5435

runs/{Jul03_19-51-55_8a98c40ff775/events.out.tfevents.1656877916.8a98c40ff775.71.2 → Jul26_21-03-46_1fe91f198d71/events.out.tfevents.1658869435.1fe91f198d71.71.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35827bfa6445ea5a01d5ced03834737282e3b1f671fbd102582adee699417f07
-size 9494
+oid sha256:a4f66a750ddef0868289783b7c625cada735943a5b2c56c08ec75354fbdd384c
+size 6742

runs/{Jul03_21-34-55_8a98c40ff775/1656884100.2687025/events.out.tfevents.1656884100.8a98c40ff775.71.5 → Jul26_21-10-23_1fe91f198d71/1658869825.093272/events.out.tfevents.1658869825.1fe91f198d71.71.3}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f49eb3bde319c3f5ef9f807d1151facc106a9fb0c084815bae84a77df2fa45
+oid sha256:3507bdbfe9d3f6eb69447dba21acc822c993a5cb10a358dc39ed139bc7ca44ae
 size 5435

runs/{Jul03_23-15-45_8a98c40ff775/events.out.tfevents.1656890147.8a98c40ff775.71.6 → Jul26_21-10-23_1fe91f198d71/events.out.tfevents.1658869825.1fe91f198d71.71.2}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463d132c8dfcd42fb09abc4cc79c8623cbb23d16ee57b85cea3f2563e3d34fdb
+oid sha256:f04c78aa68e1a98a7ea678d1ec309091ec845b61e79e79a4e85923665acc8c20
 size 4100

runs/{Jul03_19-51-55_8a98c40ff775/1656877916.4434352/events.out.tfevents.1656877916.8a98c40ff775.71.3 → Jul26_21-13-22_1fe91f198d71/1658870005.9725268/events.out.tfevents.1658870005.1fe91f198d71.1213.1}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c99694ed2ab4d1146b576083af4bcb952ce499269cd1acf5266484e68c6e29
+oid sha256:d8514910d27122ee8e76b361c1ee7444303a7c1520614670837bc4fab14114a2
 size 5435

runs/{Jul04_00-33-28_8a98c40ff775/events.out.tfevents.1656894810.8a98c40ff775.8083.0 → Jul26_21-13-22_1fe91f198d71/events.out.tfevents.1658870005.1fe91f198d71.1213.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f961be96500c82d6a3b7e8868f1848795efdd257c198b4d4325150fd6d274217
+oid sha256:fb9bbc6749502c5c71b9d1df2d6d1835de4ccc9b642bed7b8318b2d995d27a47
 size 39221

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c733ade4e8726b7d2050d20982a2b640dde2dd40f5221ce54a078013d218d18
+oid sha256:3ffb2d40861e346c298ecb026926b1cd6fcf3c2ff8a5a38a5b78b121f9949508
 size 3375