Upload 11 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./results/checkpoint-9500",
+  "_name_or_path": "Falconsai/offensive_speech_detection",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673f7e8faafc2900bf4a85994f72ca80ca0eaa25661c2e02ac87c4226ca7f61d
+oid sha256:b899111ea3377e5da91f3d3a7b9a5469fe38a5d32f5d5de7ba78be8d9d05dd06
 size 535701061

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70dddf91e70a194298473e14829bcc7a7532a0b87a5da6230120834841a752b5
-size 267854125
+oid sha256:39d37f832bcc5130375bd55ff03fcdc605dd1b107daf02d94f9ab70bd5a03870
+size 267855533

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09cc498d55dc004d4b5c9aad1ced395abd939cae4e8d2b9da0e0073f465759a
+oid sha256:6d9d03279386093ef24a2471dd73f225aa2f5237d1d26d73d52e9e651e8a920e
 size 14511

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d40fb1a7f26e8683137c4b8cddc0f30db08f76a6b3d086416086ebaaa51cc5d5
+oid sha256:ff99d9499703f7b05e302fcc418b2bce824c378e94cf85fd2180fafca8a9e2c5
 size 627

trainer_state.json

@@ -1,286 +1,436 @@
 {
-  "best_metric": 0.01757008023560047,
-  "best_model_checkpoint": "./results/checkpoint-8500",
-  "epoch": 1.031873423526714,
-  "global_step": 9000,
+  "best_metric": 0.010238240472972393,
+  "best_model_checkpoint": "./results/checkpoint-14000",
+  "epoch": 0.8173273395995097,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.06,
-      "learning_rate": 1.9617824657953072e-05,
-      "loss": 0.058,
+      "epoch": 0.03,
+      "learning_rate": 1.9708097378714462e-05,
+      "loss": 0.014,
       "step": 500
     },
     {
-      "epoch": 0.06,
-      "eval_accuracy": 0.9880467809436451,
-      "eval_loss": 0.04749465361237526,
-      "eval_runtime": 369.9155,
-      "eval_samples_per_second": 94.308,
-      "eval_steps_per_second": 5.896,
+      "epoch": 0.03,
+      "eval_accuracy": 0.9974897107329461,
+      "eval_loss": 0.014051680453121662,
+      "eval_runtime": 272.9865,
+      "eval_samples_per_second": 125.497,
+      "eval_steps_per_second": 15.689,
       "step": 500
     },
     {
-      "epoch": 0.11,
-      "learning_rate": 1.923564931590614e-05,
-      "loss": 0.0513,
+      "epoch": 0.06,
+      "learning_rate": 1.9416194757428922e-05,
+      "loss": 0.0068,
       "step": 1000
     },
     {
-      "epoch": 0.11,
-      "eval_accuracy": 0.9892220374935504,
-      "eval_loss": 0.044388506561517715,
-      "eval_runtime": 313.5583,
-      "eval_samples_per_second": 111.258,
-      "eval_steps_per_second": 6.956,
+      "epoch": 0.06,
+      "eval_accuracy": 0.9936658980122012,
+      "eval_loss": 0.03880644589662552,
+      "eval_runtime": 271.4393,
+      "eval_samples_per_second": 126.212,
+      "eval_steps_per_second": 15.779,
       "step": 1000
     },
     {
-      "epoch": 0.17,
-      "learning_rate": 1.885347397385921e-05,
-      "loss": 0.0413,
+      "epoch": 0.09,
+      "learning_rate": 1.9124292136143383e-05,
+      "loss": 0.0065,
       "step": 1500
     },
     {
-      "epoch": 0.17,
-      "eval_accuracy": 0.9901393108983546,
-      "eval_loss": 0.044446878135204315,
-      "eval_runtime": 322.6458,
-      "eval_samples_per_second": 108.125,
-      "eval_steps_per_second": 6.76,
+      "epoch": 0.09,
+      "eval_accuracy": 0.9963221343296652,
+      "eval_loss": 0.034014396369457245,
+      "eval_runtime": 271.2782,
+      "eval_samples_per_second": 126.287,
+      "eval_steps_per_second": 15.788,
       "step": 1500
     },
     {
-      "epoch": 0.23,
-      "learning_rate": 1.847129863181228e-05,
-      "loss": 0.0364,
+      "epoch": 0.12,
+      "learning_rate": 1.8832389514857846e-05,
+      "loss": 0.0088,
       "step": 2000
     },
     {
-      "epoch": 0.23,
-      "eval_accuracy": 0.9911712434787594,
-      "eval_loss": 0.037910301238298416,
-      "eval_runtime": 258.562,
-      "eval_samples_per_second": 134.923,
-      "eval_steps_per_second": 8.435,
+      "epoch": 0.12,
+      "eval_accuracy": 0.9975189001430281,
+      "eval_loss": 0.01912350207567215,
+      "eval_runtime": 271.5387,
+      "eval_samples_per_second": 126.166,
+      "eval_steps_per_second": 15.773,
       "step": 2000
     },
     {
-      "epoch": 0.29,
-      "learning_rate": 1.8089123289765345e-05,
-      "loss": 0.0389,
+      "epoch": 0.15,
+      "learning_rate": 1.8540486893572303e-05,
+      "loss": 0.0081,
       "step": 2500
     },
     {
-      "epoch": 0.29,
-      "eval_accuracy": 0.9921171816774638,
-      "eval_loss": 0.03007333353161812,
-      "eval_runtime": 258.8834,
-      "eval_samples_per_second": 134.756,
-      "eval_steps_per_second": 8.425,
+      "epoch": 0.15,
+      "eval_accuracy": 0.9977816048337663,
+      "eval_loss": 0.01667490415275097,
+      "eval_runtime": 271.3282,
+      "eval_samples_per_second": 126.264,
+      "eval_steps_per_second": 15.785,
       "step": 2500
     },
     {
-      "epoch": 0.34,
-      "learning_rate": 1.7706947947718412e-05,
-      "loss": 0.0343,
+      "epoch": 0.18,
+      "learning_rate": 1.8248584272286767e-05,
+      "loss": 0.0142,
       "step": 3000
     },
     {
-      "epoch": 0.34,
-      "eval_accuracy": 0.9923465000286648,
-      "eval_loss": 0.03364783525466919,
-      "eval_runtime": 258.3829,
-      "eval_samples_per_second": 135.017,
-      "eval_steps_per_second": 8.441,
+      "epoch": 0.18,
+      "eval_accuracy": 0.9969351119413876,
+      "eval_loss": 0.017350222915410995,
+      "eval_runtime": 271.4826,
+      "eval_samples_per_second": 126.192,
+      "eval_steps_per_second": 15.776,
       "step": 3000
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 1.7324772605671482e-05,
-      "loss": 0.0351,
+      "epoch": 0.2,
+      "learning_rate": 1.7956681651001227e-05,
+      "loss": 0.0066,
       "step": 3500
     },
     {
-      "epoch": 0.4,
-      "eval_accuracy": 0.9918591985323626,
-      "eval_loss": 0.030066516250371933,
-      "eval_runtime": 258.5585,
-      "eval_samples_per_second": 134.925,
-      "eval_steps_per_second": 8.435,
+      "epoch": 0.2,
+      "eval_accuracy": 0.9967891648909776,
+      "eval_loss": 0.025246594101190567,
+      "eval_runtime": 271.289,
+      "eval_samples_per_second": 126.282,
+      "eval_steps_per_second": 15.788,
       "step": 3500
     },
     {
-      "epoch": 0.46,
-      "learning_rate": 1.6942597263624552e-05,
-      "loss": 0.0343,
+      "epoch": 0.23,
+      "learning_rate": 1.7664779029715688e-05,
+      "loss": 0.0078,
       "step": 4000
     },
     {
-      "epoch": 0.46,
-      "eval_accuracy": 0.9925471535859657,
-      "eval_loss": 0.02801605314016342,
-      "eval_runtime": 308.2791,
-      "eval_samples_per_second": 113.164,
-      "eval_steps_per_second": 7.075,
+      "epoch": 0.23,
+      "eval_accuracy": 0.9965848390204034,
+      "eval_loss": 0.02241995558142662,
+      "eval_runtime": 271.2726,
+      "eval_samples_per_second": 126.29,
+      "eval_steps_per_second": 15.789,
       "step": 4000
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 1.6560421921577622e-05,
-      "loss": 0.0328,
+      "epoch": 0.26,
+      "learning_rate": 1.7372876408430148e-05,
+      "loss": 0.0062,
       "step": 4500
     },
     {
-      "epoch": 0.52,
-      "eval_accuracy": 0.9937224101358711,
-      "eval_loss": 0.022993654012680054,
-      "eval_runtime": 304.7606,
-      "eval_samples_per_second": 114.47,
-      "eval_steps_per_second": 7.156,
+      "epoch": 0.26,
+      "eval_accuracy": 0.9968183543010596,
+      "eval_loss": 0.021609827876091003,
+      "eval_runtime": 271.3057,
+      "eval_samples_per_second": 126.275,
+      "eval_steps_per_second": 15.787,
       "step": 4500
     },
     {
-      "epoch": 0.57,
-      "learning_rate": 1.617824657953069e-05,
-      "loss": 0.0322,
+      "epoch": 0.29,
+      "learning_rate": 1.7080973787144612e-05,
+      "loss": 0.0047,
       "step": 5000
     },
     {
-      "epoch": 0.57,
-      "eval_accuracy": 0.9930631198761681,
-      "eval_loss": 0.022875914350152016,
-      "eval_runtime": 509.8625,
-      "eval_samples_per_second": 68.422,
-      "eval_steps_per_second": 4.278,
+      "epoch": 0.29,
+      "eval_accuracy": 0.9971978166321258,
+      "eval_loss": 0.01993330754339695,
+      "eval_runtime": 271.1898,
+      "eval_samples_per_second": 126.328,
+      "eval_steps_per_second": 15.793,
       "step": 5000
     },
     {
-      "epoch": 0.63,
-      "learning_rate": 1.579607123748376e-05,
-      "loss": 0.0275,
+      "epoch": 0.32,
+      "learning_rate": 1.678907116585907e-05,
+      "loss": 0.0035,
       "step": 5500
     },
     {
-      "epoch": 0.63,
-      "eval_accuracy": 0.994353035601674,
-      "eval_loss": 0.024034755304455757,
-      "eval_runtime": 296.8109,
-      "eval_samples_per_second": 117.536,
-      "eval_steps_per_second": 7.348,
+      "epoch": 0.32,
+      "eval_accuracy": 0.9968767331212236,
+      "eval_loss": 0.025054221972823143,
+      "eval_runtime": 272.0376,
+      "eval_samples_per_second": 125.935,
+      "eval_steps_per_second": 15.744,
       "step": 5500
     },
     {
-      "epoch": 0.69,
-      "learning_rate": 1.541389589543683e-05,
-      "loss": 0.0288,
+      "epoch": 0.35,
+      "learning_rate": 1.6497168544573532e-05,
+      "loss": 0.0147,
       "step": 6000
     },
     {
-      "epoch": 0.69,
-      "eval_accuracy": 0.9946396835406753,
-      "eval_loss": 0.022033799439668655,
-      "eval_runtime": 293.7762,
-      "eval_samples_per_second": 118.75,
-      "eval_steps_per_second": 7.424,
+      "epoch": 0.35,
+      "eval_accuracy": 0.997343763682536,
+      "eval_loss": 0.017792223021388054,
+      "eval_runtime": 271.3522,
+      "eval_samples_per_second": 126.253,
+      "eval_steps_per_second": 15.784,
       "step": 6000
     },
     {
-      "epoch": 0.75,
-      "learning_rate": 1.5031720553389898e-05,
-      "loss": 0.0244,
+      "epoch": 0.38,
+      "learning_rate": 1.6205265923287993e-05,
+      "loss": 0.0093,
       "step": 6500
     },
     {
-      "epoch": 0.75,
-      "eval_accuracy": 0.9947543427162758,
-      "eval_loss": 0.02473697066307068,
-      "eval_runtime": 331.6878,
-      "eval_samples_per_second": 105.177,
-      "eval_steps_per_second": 6.575,
+      "epoch": 0.38,
+      "eval_accuracy": 0.9971102484018798,
+      "eval_loss": 0.019385505467653275,
+      "eval_runtime": 270.7817,
+      "eval_samples_per_second": 126.519,
+      "eval_steps_per_second": 15.817,
       "step": 6500
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 1.4649545211342966e-05,
-      "loss": 0.0243,
+      "epoch": 0.41,
+      "learning_rate": 1.5913363302002453e-05,
+      "loss": 0.0084,
       "step": 7000
     },
     {
-      "epoch": 0.8,
-      "eval_accuracy": 0.9946970131284756,
-      "eval_loss": 0.02222474291920662,
-      "eval_runtime": 343.6254,
-      "eval_samples_per_second": 101.523,
-      "eval_steps_per_second": 6.347,
+      "epoch": 0.41,
+      "eval_accuracy": 0.9974897107329461,
+      "eval_loss": 0.01369693223387003,
+      "eval_runtime": 270.7077,
+      "eval_samples_per_second": 126.553,
+      "eval_steps_per_second": 15.821,
       "step": 7000
     },
     {
-      "epoch": 0.86,
-      "learning_rate": 1.4267369869296034e-05,
-      "loss": 0.0204,
+      "epoch": 0.44,
+      "learning_rate": 1.5621460680716913e-05,
+      "loss": 0.0135,
       "step": 7500
     },
     {
-      "epoch": 0.86,
-      "eval_accuracy": 0.9944390299833744,
-      "eval_loss": 0.020777888596057892,
-      "eval_runtime": 342.3258,
-      "eval_samples_per_second": 101.909,
-      "eval_steps_per_second": 6.371,
+      "epoch": 0.44,
+      "eval_accuracy": 0.9967307860708136,
+      "eval_loss": 0.023163480684161186,
+      "eval_runtime": 270.9905,
+      "eval_samples_per_second": 126.421,
+      "eval_steps_per_second": 15.805,
       "step": 7500
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 1.3885194527249105e-05,
-      "loss": 0.0219,
+      "epoch": 0.47,
+      "learning_rate": 1.5329558059431374e-05,
+      "loss": 0.0131,
       "step": 8000
     },
     {
-      "epoch": 0.92,
-      "eval_accuracy": 0.9955569569454795,
-      "eval_loss": 0.023240169510245323,
-      "eval_runtime": 340.3493,
-      "eval_samples_per_second": 102.501,
-      "eval_steps_per_second": 6.408,
+      "epoch": 0.47,
+      "eval_accuracy": 0.9974605213228641,
+      "eval_loss": 0.015544239431619644,
+      "eval_runtime": 270.8012,
+      "eval_samples_per_second": 126.51,
+      "eval_steps_per_second": 15.816,
       "step": 8000
     },
     {
-      "epoch": 0.97,
-      "learning_rate": 1.3503019185202171e-05,
-      "loss": 0.0298,
+      "epoch": 0.5,
+      "learning_rate": 1.5037655438145836e-05,
+      "loss": 0.0196,
       "step": 8500
     },
     {
-      "epoch": 0.97,
-      "eval_accuracy": 0.9955282921515795,
-      "eval_loss": 0.01757008023560047,
-      "eval_runtime": 307.8345,
-      "eval_samples_per_second": 113.327,
-      "eval_steps_per_second": 7.085,
+      "epoch": 0.5,
+      "eval_accuracy": 0.9965556496103214,
+      "eval_loss": 0.01619912125170231,
+      "eval_runtime": 272.0032,
+      "eval_samples_per_second": 125.951,
+      "eval_steps_per_second": 15.746,
       "step": 8500
     },
     {
-      "epoch": 1.03,
-      "learning_rate": 1.312084384315524e-05,
-      "loss": 0.0098,
+      "epoch": 0.53,
+      "learning_rate": 1.4745752816860298e-05,
+      "loss": 0.0207,
       "step": 9000
     },
     {
-      "epoch": 1.03,
-      "eval_accuracy": 0.9951843146247779,
-      "eval_loss": 0.026897920295596123,
-      "eval_runtime": 318.0815,
-      "eval_samples_per_second": 109.676,
-      "eval_steps_per_second": 6.857,
+      "epoch": 0.53,
+      "eval_accuracy": 0.9978691730640123,
+      "eval_loss": 0.011031306348741055,
+      "eval_runtime": 270.862,
+      "eval_samples_per_second": 126.481,
+      "eval_steps_per_second": 15.812,
       "step": 9000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.4453850195574756e-05,
+      "loss": 0.0172,
+      "step": 9500
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.9969059225313056,
+      "eval_loss": 0.013371887616813183,
+      "eval_runtime": 270.9823,
+      "eval_samples_per_second": 126.425,
+      "eval_steps_per_second": 15.805,
+      "step": 9500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.4161947574289218e-05,
+      "loss": 0.0147,
+      "step": 10000
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.9956799673078607,
+      "eval_loss": 0.018292322754859924,
+      "eval_runtime": 271.0579,
+      "eval_samples_per_second": 126.39,
+      "eval_steps_per_second": 15.801,
+      "step": 10000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.3870044953003679e-05,
+      "loss": 0.0115,
+      "step": 10500
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.9976356577833562,
+      "eval_loss": 0.013687117025256157,
+      "eval_runtime": 270.8313,
+      "eval_samples_per_second": 126.496,
+      "eval_steps_per_second": 15.814,
+      "step": 10500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.357814233171814e-05,
+      "loss": 0.0058,
+      "step": 11000
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.9978399836539303,
+      "eval_loss": 0.01474874746054411,
+      "eval_runtime": 270.6785,
+      "eval_samples_per_second": 126.567,
+      "eval_steps_per_second": 15.823,
+      "step": 11000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.32862397104326e-05,
+      "loss": 0.0127,
+      "step": 11500
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9975189001430281,
+      "eval_loss": 0.014400546438992023,
+      "eval_runtime": 271.0019,
+      "eval_samples_per_second": 126.416,
+      "eval_steps_per_second": 15.804,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.2994337089147061e-05,
+      "loss": 0.0158,
+      "step": 12000
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.9978399836539303,
+      "eval_loss": 0.011529939249157906,
+      "eval_runtime": 271.0144,
+      "eval_samples_per_second": 126.41,
+      "eval_steps_per_second": 15.804,
+      "step": 12000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.2702434467861522e-05,
+      "loss": 0.0149,
+      "step": 12500
+    },
+    {
+      "epoch": 0.73,
+      "eval_accuracy": 0.9978983624740944,
+      "eval_loss": 0.011057616211473942,
+      "eval_runtime": 270.832,
+      "eval_samples_per_second": 126.495,
+      "eval_steps_per_second": 15.814,
+      "step": 12500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.2410531846575984e-05,
+      "loss": 0.0112,
+      "step": 13000
+    },
+    {
+      "epoch": 0.76,
+      "eval_accuracy": 0.9975772789631921,
+      "eval_loss": 0.013288214802742004,
+      "eval_runtime": 270.8227,
+      "eval_samples_per_second": 126.5,
+      "eval_steps_per_second": 15.815,
+      "step": 13000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.2118629225290444e-05,
+      "loss": 0.0163,
+      "step": 13500
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.997372953092618,
+      "eval_loss": 0.012437746860086918,
+      "eval_runtime": 270.7754,
+      "eval_samples_per_second": 126.522,
+      "eval_steps_per_second": 15.818,
+      "step": 13500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.1826726604004906e-05,
+      "loss": 0.0107,
+      "step": 14000
+    },
+    {
+      "epoch": 0.82,
+      "eval_accuracy": 0.9979859307043405,
+      "eval_loss": 0.010238240472972393,
+      "eval_runtime": 271.1151,
+      "eval_samples_per_second": 126.363,
+      "eval_steps_per_second": 15.798,
+      "step": 14000
     }
   ],
-  "max_steps": 26166,
-  "num_train_epochs": 3,
-  "total_flos": 1.907424566727475e+16,
+  "max_steps": 34258,
+  "num_train_epochs": 2,
+  "total_flos": 1.4836348649472e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb244d95b7b47fb97bc09ca9a88060acdd00da87d07494e09e71d9be17b7177a
+oid sha256:4bcf015d7727fb95e74ccfb6fa4e500e13026ea93036073872f21f1c39aab86c
 size 3963