another datasets

config.json

@@ -12,16 +12,16 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "Negative",
-    "1": "Neutral",
-    "2": "Positive"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Negative": 0,
-    "Neutral": 1,
-    "Positive": 2
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

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
-0.8308016875112519,False,2.1765787781353998e-05,1,16,0,0.2779928681001568,70.68486714363098
-0.8208579588481721,False,1.0571835122759025e-05,4,16,0,0.08349868710232541,69.73215866088867
-0.832166006303993,False,1.2795649540620917e-05,1,8,0,0.2704258566938061,76.97464203834534
-0.8394192385480443,True,4.65591694361634e-05,1,16,250,0.2103754328402818,70.83545136451721
-0.8366512897395006,False,2.6370464742949582e-05,1,8,250,0.26429846288311887,77.25557279586792
-0.8110507698879218,False,4.64238812312384e-05,4,8,500,0.13639810320763826,76.0791552066803
-0.8303948363746132,False,3.9043689561606625e-05,1,16,250,0.06075214917397778,71.24034976959229
-0.8015180450557305,False,2.2502123920264867e-05,3,8,250,0.21316207286076047,76.04998445510864
-0.793748592229527,False,2.7807755379517034e-05,1,8,1000,0.16241717486314383,77.22514963150024
-0.8033119941220733,False,4.858723883045379e-05,3,16,250,0.1574600638437009,69.87509036064148
+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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b114d27450122a79631f3e70e5f993549e165d051a7c80ce2645b0a526bf6df
+oid sha256:7d08b27797a18fc2d245b7f491cb1b24152316a2902b22e3ead2e1e71826de47
 size 498606684

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af3ecf6d848a47a23e0f58ce7e993b4ba7c9fd33c56a201776ce768cd6e0055e
+oid sha256:6efd6ffd5083cff2e4d806c6dcaa720d7cc9b207f982274fbe5a31aadfbea628
 size 997333242

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f753249e6e05a99e4c20b9f6975ad02a63ca0f1e4cdb54441b4628482980e8c
+oid sha256:a9c11846eae1a717de3a335649e31add72e7cd98f8bfe0d0551bb18428458ab2
 size 1064

trainer_state.json

@@ -1,34 +1,57 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "best_metric": 0.8141798973083496,
+  "best_model_checkpoint": "./results/run-7a00201a/checkpoint-1275",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 414,
+  "global_step": 2550,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0024154589371980675,
-      "grad_norm": 1.6261011362075806,
-      "learning_rate": 1.862366777446536e-07,
-      "loss": 1.1,
+      "epoch": 0.000784313725490196,
+      "grad_norm": 0.6707581281661987,
+      "learning_rate": 1.1116381679112563e-07,
+      "loss": 1.0997,
       "step": 1
     },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 2.603963613510132,
+      "learning_rate": 1.8728686524591818e-05,
+      "loss": 0.8879,
+      "step": 1000
+    },
     {
       "epoch": 1.0,
-      "eval_f1": 0.8394192385480443,
-      "eval_loss": 0.38631680607795715,
-      "eval_runtime": 2.1374,
-      "eval_samples_per_second": 1033.029,
-      "eval_steps_per_second": 129.129,
-      "step": 414
+      "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
+    },
+    {
+      "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
     }
   ],
   "logging_steps": 1000,
-  "max_steps": 414,
+  "max_steps": 2550,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -42,14 +65,14 @@
       "attributes": {}
     }
   },
-  "total_flos": 4209814683648.0,
+  "total_flos": 6987202920860400.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.65591694361634e-05,
-    "num_train_epochs": 1,
+    "learning_rate": 2.7790954197781407e-05,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 16,
     "warmup_steps": 250,
-    "weight_decay": 0.2103754328402818
+    "weight_decay": 0.27440436845088456
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83b594183cbe9f09ddaf478eae629dcdb3d51b9bcb4757de1f514b20d09ee833
+oid sha256:9d9c68b7f2c1a165772c07fdda547a991f041674086b03e586624ae202c5e1b2
 size 5240

training_resume.json

@@ -19,7 +19,7 @@
     "resources_per_trial": {
         "gpu": 1
     },
-    "run_id": "24fa3a3c",
+    "run_id": "7a00201a",
     "task": "",
     "task_type": "classification",
     "tokenizer_field": "tweet",