Upload 11 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Falconsai/offensive_speech_detection",
+  "_name_or_path": "./results/checkpoint-11000",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df7121aec1c35c069337a74d42c53b4a5b4923ca88aca3f5b33a51e937ced73
+oid sha256:38a118be7202aa4db1e3d37d22adcfc6b4e3be00af436b916228fadd4dc2e40c
 size 535701061

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc0d5fa6c859f571867e1c85354a56e06713c815ab1694e8dfcf40c64f92978
+oid sha256:cfcd56f2d823a9cdc2cfccb44e5e823d3200112622082e5cd94e93d019b9fc67
 size 267855533

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6160847c51c08356e853c3bca23f598a8d8a42785e2458b0c5fc923e4f1dadf
+oid sha256:01da4f1236b1946afbe43e51bdf7717aeb209652b7d7314cda674a4ca1e36a16
 size 14511

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e06238497f705c88cffe1b96791159faf151e3e1acd4bc0004a4c3260ed549
+oid sha256:1cc86f59df564bec394c86356ab586d662aa80b1cf79a7016636c67697d6ef91
 size 627

trainer_state.json

@@ -1,151 +1,196 @@
 {
-  "best_metric": 0.01884845644235611,
-  "best_model_checkpoint": "./results/checkpoint-4500",
-  "epoch": 0.9439899307740718,
-  "global_step": 4500,
+  "best_metric": 0.022033799439668655,
+  "best_model_checkpoint": "./results/checkpoint-6000",
+  "epoch": 0.687915615684476,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "learning_rate": 1.9300748199426614e-05,
-      "loss": 0.0391,
+      "epoch": 0.06,
+      "learning_rate": 1.9617824657953072e-05,
+      "loss": 0.058,
       "step": 500
     },
     {
-      "epoch": 0.1,
-      "eval_accuracy": 0.990558615263572,
-      "eval_loss": 0.04349859058856964,
-      "eval_runtime": 154.2476,
-      "eval_samples_per_second": 123.6,
-      "eval_steps_per_second": 7.728,
+      "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,
       "step": 500
     },
     {
-      "epoch": 0.21,
-      "learning_rate": 1.860149639885323e-05,
-      "loss": 0.0327,
+      "epoch": 0.11,
+      "learning_rate": 1.923564931590614e-05,
+      "loss": 0.0513,
       "step": 1000
     },
     {
-      "epoch": 0.21,
-      "eval_accuracy": 0.9903488067138736,
-      "eval_loss": 0.04805811867117882,
-      "eval_runtime": 154.05,
-      "eval_samples_per_second": 123.759,
-      "eval_steps_per_second": 7.738,
+      "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,
       "step": 1000
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 1.790224459827984e-05,
-      "loss": 0.0266,
+      "epoch": 0.17,
+      "learning_rate": 1.885347397385921e-05,
+      "loss": 0.0413,
       "step": 1500
     },
     {
-      "epoch": 0.31,
-      "eval_accuracy": 0.9911355887752425,
-      "eval_loss": 0.0459710918366909,
-      "eval_runtime": 154.4944,
-      "eval_samples_per_second": 123.403,
-      "eval_steps_per_second": 7.715,
+      "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,
       "step": 1500
     },
     {
-      "epoch": 0.42,
-      "learning_rate": 1.7202992797706454e-05,
-      "loss": 0.035,
+      "epoch": 0.23,
+      "learning_rate": 1.847129863181228e-05,
+      "loss": 0.0364,
       "step": 2000
     },
     {
-      "epoch": 0.42,
-      "eval_accuracy": 0.9916601101494886,
-      "eval_loss": 0.03351669758558273,
-      "eval_runtime": 154.0214,
-      "eval_samples_per_second": 123.782,
-      "eval_steps_per_second": 7.739,
+      "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,
       "step": 2000
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 1.650374099713307e-05,
-      "loss": 0.0371,
+      "epoch": 0.29,
+      "learning_rate": 1.8089123289765345e-05,
+      "loss": 0.0389,
       "step": 2500
     },
     {
-      "epoch": 0.52,
-      "eval_accuracy": 0.9930763178599528,
-      "eval_loss": 0.025116313248872757,
-      "eval_runtime": 153.2057,
-      "eval_samples_per_second": 124.441,
-      "eval_steps_per_second": 7.78,
+      "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,
       "step": 2500
     },
     {
-      "epoch": 0.63,
-      "learning_rate": 1.580448919655968e-05,
-      "loss": 0.026,
+      "epoch": 0.34,
+      "learning_rate": 1.7706947947718412e-05,
+      "loss": 0.0343,
       "step": 3000
     },
     {
-      "epoch": 0.63,
-      "eval_accuracy": 0.9938630999213218,
-      "eval_loss": 0.027913494035601616,
-      "eval_runtime": 153.7631,
-      "eval_samples_per_second": 123.989,
-      "eval_steps_per_second": 7.752,
+      "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,
       "step": 3000
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 1.5105237395986297e-05,
-      "loss": 0.0299,
+      "epoch": 0.4,
+      "learning_rate": 1.7324772605671482e-05,
+      "loss": 0.0351,
       "step": 3500
     },
     {
-      "epoch": 0.73,
-      "eval_accuracy": 0.9934959349593496,
-      "eval_loss": 0.027549268677830696,
-      "eval_runtime": 153.8917,
-      "eval_samples_per_second": 123.886,
-      "eval_steps_per_second": 7.746,
+      "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,
       "step": 3500
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 1.4405985595412911e-05,
-      "loss": 0.0254,
+      "epoch": 0.46,
+      "learning_rate": 1.6942597263624552e-05,
+      "loss": 0.0343,
       "step": 4000
     },
     {
-      "epoch": 0.84,
-      "eval_accuracy": 0.9945449777078416,
-      "eval_loss": 0.024684084579348564,
-      "eval_runtime": 153.4415,
-      "eval_samples_per_second": 124.249,
-      "eval_steps_per_second": 7.768,
+      "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,
       "step": 4000
     },
     {
-      "epoch": 0.94,
-      "learning_rate": 1.3706733794839521e-05,
-      "loss": 0.0219,
+      "epoch": 0.52,
+      "learning_rate": 1.6560421921577622e-05,
+      "loss": 0.0328,
       "step": 4500
     },
     {
-      "epoch": 0.94,
-      "eval_accuracy": 0.9954366640440598,
-      "eval_loss": 0.01884845644235611,
-      "eval_runtime": 153.901,
-      "eval_samples_per_second": 123.878,
-      "eval_steps_per_second": 7.745,
+      "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,
       "step": 4500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.617824657953069e-05,
+      "loss": 0.0322,
+      "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,
+      "step": 5000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.579607123748376e-05,
+      "loss": 0.0275,
+      "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,
+      "step": 5500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.541389589543683e-05,
+      "loss": 0.0288,
+      "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,
+      "step": 6000
     }
   ],
-  "max_steps": 14301,
+  "max_steps": 26166,
   "num_train_epochs": 3,
-  "total_flos": 9537652703232000.0,
+  "total_flos": 1.2716870270976e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1317ed9b28a901fc802c67584193ee79f96fe31da7695bec1e79e610e483cf78
+oid sha256:fb244d95b7b47fb97bc09ca9a88060acdd00da87d07494e09e71d9be17b7177a
 size 3963