new model

hyperparameters.csv

@@ -1,11 +1,11 @@
 objective,best,learning_rate,num_train_epochs,per_device_train_batch_size,warmup_steps,weight_decay,time_this_iter_s
-0.585795322825296,True,2.7790954197781407e-05,2,16,250,0.27440436845088456,188.93630051612854
-0.5403308930283185,False,3.7814091027622886e-05,2,8,1000,0.1538840941218964,217.0473895072937
-0.5444770730498769,False,3.32179557296645e-05,4,16,500,0.16179634310824192,189.567147731781
-0.5588174791467849,False,1.1504988654860045e-05,5,16,500,0.01734062039773394,190.21717524528503
-0.580070364008772,False,4.8487400003981596e-05,1,8,0,0.06409376822222429,219.16021513938904
-0.5418848883243373,False,4.1163569633169964e-05,2,8,500,0.11476947426883025,218.05247330665588
-0.5614360549687367,False,3.577023497296174e-05,2,16,1000,0.019970396453250393,189.73834896087646
-0.5822306986164425,False,4.176691733490237e-05,1,8,1000,0.0762936568728031,219.25422358512878
-0.5583033816322266,False,3.563806920310468e-05,5,16,1000,0.07122837923660795,190.06790375709534
-0.5410159442467878,False,4.216937363471069e-05,2,8,0,0.17991049930425,218.05449318885803
+0.635863107603759,False,3.487183059077524e-05,5,16,0,0.16271145844833626,56.91134285926819
+0.5713238859688857,False,3.92751967399588e-05,4,16,250,0.0061185848088987855,58.02219867706299
+0.641436354838909,False,3.9497762762426766e-05,3,8,250,0.044230525736229806,62.00673007965088
+0.6449889137818522,False,2.3273470571085874e-05,3,16,1000,0.09207606882549886,57.14790916442871
+0.660660334863665,False,2.5113275842289397e-05,4,8,500,0.1809870185862566,62.34332537651062
+0.5987772133234199,False,1.7492926677930877e-05,5,8,1000,0.05366028217715286,63.19422936439514
+0.648060368915552,False,4.7394780811102786e-05,4,16,500,0.1475032763776485,56.89936542510986
+0.6674442219731551,True,2.9456252296428165e-05,2,16,250,0.22747954091633416,56.93232560157776
+0.5823305961166283,False,4.179982776009024e-05,3,8,500,0.052250462762862,63.28155493736267
+0.5644954235807155,False,4.6929190913739005e-05,5,8,500,0.07469826013421123,63.23927354812622

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d08b27797a18fc2d245b7f491cb1b24152316a2902b22e3ead2e1e71826de47
+oid sha256:01ecb8da88a38e6361c3763e3270d513d10a876220f702c540b116965d3831a0
 size 498606684

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efd6ffd5083cff2e4d806c6dcaa720d7cc9b207f982274fbe5a31aadfbea628
+oid sha256:4cd814e920a50e33f69bee3307d10b0249397b5411b51bd62292cb069b242645
 size 997333242

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c11846eae1a717de3a335649e31add72e7cd98f8bfe0d0551bb18428458ab2
+oid sha256:c24956e398ad60127304c49f511c572209abfd09352648bc248f4ceb4c7819ed
 size 1064

trainer_state.json

@@ -1,55 +1,41 @@
 {
-  "best_metric": 0.8141798973083496,
-  "best_model_checkpoint": "./results/run-7a00201a/checkpoint-1275",
+  "best_metric": 0.8178452253341675,
+  "best_model_checkpoint": "./results/run-a80efcad/checkpoint-344",
   "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 2550,
+  "global_step": 688,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.000784313725490196,
-      "grad_norm": 0.6707581281661987,
-      "learning_rate": 1.1116381679112563e-07,
-      "loss": 1.0997,
+      "epoch": 0.0029069767441860465,
+      "grad_norm": 1.1931110620498657,
+      "learning_rate": 1.1782500918571267e-07,
+      "loss": 1.0951,
       "step": 1
     },
-    {
-      "epoch": 0.7843137254901961,
-      "grad_norm": 2.603963613510132,
-      "learning_rate": 1.8728686524591818e-05,
-      "loss": 0.8879,
-      "step": 1000
-    },
     {
       "epoch": 1.0,
-      "eval_f1": 0.5636810375356157,
-      "eval_loss": 0.8141798973083496,
-      "eval_runtime": 19.9525,
-      "eval_samples_per_second": 340.71,
-      "eval_steps_per_second": 42.601,
-      "step": 1275
-    },
-    {
-      "epoch": 1.5686274509803921,
-      "grad_norm": 5.432121276855469,
-      "learning_rate": 6.645662960339033e-06,
-      "loss": 0.7432,
-      "step": 2000
+      "eval_f1": 0.621996151996152,
+      "eval_loss": 0.8178452253341675,
+      "eval_runtime": 1.0,
+      "eval_samples_per_second": 1831.952,
+      "eval_steps_per_second": 228.994,
+      "step": 344
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.585795322825296,
-      "eval_loss": 0.8491290807723999,
-      "eval_runtime": 19.9821,
-      "eval_samples_per_second": 340.205,
-      "eval_steps_per_second": 42.538,
-      "step": 2550
+      "eval_f1": 0.6674442219731551,
+      "eval_loss": 0.8049888014793396,
+      "eval_runtime": 0.9934,
+      "eval_samples_per_second": 1844.13,
+      "eval_steps_per_second": 230.516,
+      "step": 688
     }
   ],
   "logging_steps": 1000,
-  "max_steps": 2550,
+  "max_steps": 688,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
@@ -65,14 +51,14 @@
       "attributes": {}
     }
   },
-  "total_flos": 6987202920860400.0,
+  "total_flos": 4209814683648.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.7790954197781407e-05,
+    "learning_rate": 2.9456252296428165e-05,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 16,
     "warmup_steps": 250,
-    "weight_decay": 0.27440436845088456
+    "weight_decay": 0.22747954091633416
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9c68b7f2c1a165772c07fdda547a991f041674086b03e586624ae202c5e1b2
+oid sha256:a5afbd7f8771645a9efe81630284ed528da552fb284078c9d417059b32bc9eeb
 size 5240

training_resume.json

@@ -19,7 +19,7 @@
     "resources_per_trial": {
         "gpu": 1
     },
-    "run_id": "7a00201a",
+    "run_id": "a80efcad",
     "task": "",
     "task_type": "classification",
     "tokenizer_field": "tweet",