update model with adjusted corpus

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

@@ -0,0 +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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b67eb187e60c07d0b3389e2553f828483b8396a67b3ac661adbf2f815235df1
+oid sha256:7b114d27450122a79631f3e70e5f993549e165d051a7c80ce2645b0a526bf6df
 size 498606684

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1d86d77cf8a747e8acba4c228c9952fa0938862eb1cc969a98f21d1d47e2e31
+oid sha256:af3ecf6d848a47a23e0f58ce7e993b4ba7c9fd33c56a201776ce768cd6e0055e
 size 997333242

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b07870366742244f712c99808f9f687dc85bd4bf5b13e5b9490e478b2a32ecb
+oid sha256:4f753249e6e05a99e4c20b9f6975ad02a63ca0f1e4cdb54441b4628482980e8c
 size 1064

trainer_state.json

@@ -1,159 +1,34 @@
 {
-  "best_metric": 0.5272276997566223,
-  "best_model_checkpoint": "./results/run-fa19ee57/checkpoint-3740",
-  "epoch": 4.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 14960,
+  "global_step": 414,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.00026737967914438503,
-      "grad_norm": 1.5169804096221924,
-      "learning_rate": 6.677122018388977e-08,
-      "loss": 1.1106,
+      "epoch": 0.0024154589371980675,
+      "grad_norm": 1.6261011362075806,
+      "learning_rate": 1.862366777446536e-07,
+      "loss": 1.1,
       "step": 1
     },
-    {
-      "epoch": 0.26737967914438504,
-      "grad_norm": 11.680069923400879,
-      "learning_rate": 1.584171029515808e-05,
-      "loss": 0.7897,
-      "step": 1000
-    },
-    {
-      "epoch": 0.5347593582887701,
-      "grad_norm": 11.042302131652832,
-      "learning_rate": 1.4706917294072254e-05,
-      "loss": 0.6084,
-      "step": 2000
-    },
-    {
-      "epoch": 0.8021390374331551,
-      "grad_norm": 17.39794921875,
-      "learning_rate": 1.3572124292986432e-05,
-      "loss": 0.5471,
-      "step": 3000
-    },
     {
       "epoch": 1.0,
-      "eval_f1": 0.7848222201687379,
-      "eval_loss": 0.5272276997566223,
-      "eval_runtime": 29.3574,
-      "eval_samples_per_second": 339.745,
-      "eval_steps_per_second": 42.477,
-      "step": 3740
-    },
-    {
-      "epoch": 1.0695187165775402,
-      "grad_norm": 2.134364604949951,
-      "learning_rate": 1.243733129190061e-05,
-      "loss": 0.4751,
-      "step": 4000
-    },
-    {
-      "epoch": 1.3368983957219251,
-      "grad_norm": 41.253849029541016,
-      "learning_rate": 1.1302538290814788e-05,
-      "loss": 0.3362,
-      "step": 5000
-    },
-    {
-      "epoch": 1.6042780748663101,
-      "grad_norm": 17.477731704711914,
-      "learning_rate": 1.0167745289728967e-05,
-      "loss": 0.343,
-      "step": 6000
-    },
-    {
-      "epoch": 1.8716577540106951,
-      "grad_norm": 31.10905647277832,
-      "learning_rate": 9.032952288643143e-06,
-      "loss": 0.3246,
-      "step": 7000
-    },
-    {
-      "epoch": 2.0,
-      "eval_f1": 0.807926137512124,
-      "eval_loss": 0.6871171593666077,
-      "eval_runtime": 29.3563,
-      "eval_samples_per_second": 339.757,
-      "eval_steps_per_second": 42.478,
-      "step": 7480
-    },
-    {
-      "epoch": 2.1390374331550803,
-      "grad_norm": 38.711708068847656,
-      "learning_rate": 7.89815928755732e-06,
-      "loss": 0.2229,
-      "step": 8000
-    },
-    {
-      "epoch": 2.406417112299465,
-      "grad_norm": 22.373706817626953,
-      "learning_rate": 6.7633662864715e-06,
-      "loss": 0.1367,
-      "step": 9000
-    },
-    {
-      "epoch": 2.6737967914438503,
-      "grad_norm": 53.95636749267578,
-      "learning_rate": 5.628573285385677e-06,
-      "loss": 0.1458,
-      "step": 10000
-    },
-    {
-      "epoch": 2.9411764705882355,
-      "grad_norm": 1.9054352045059204,
-      "learning_rate": 4.493780284299856e-06,
-      "loss": 0.1314,
-      "step": 11000
-    },
-    {
-      "epoch": 3.0,
-      "eval_f1": 0.8155244394452302,
-      "eval_loss": 0.9170186519622803,
-      "eval_runtime": 29.3912,
-      "eval_samples_per_second": 339.353,
-      "eval_steps_per_second": 42.428,
-      "step": 11220
-    },
-    {
-      "epoch": 3.2085561497326203,
-      "grad_norm": 0.004946542903780937,
-      "learning_rate": 3.358987283214033e-06,
-      "loss": 0.0585,
-      "step": 12000
-    },
-    {
-      "epoch": 3.4759358288770055,
-      "grad_norm": 0.1009206771850586,
-      "learning_rate": 2.224194282128211e-06,
-      "loss": 0.037,
-      "step": 13000
-    },
-    {
-      "epoch": 3.7433155080213902,
-      "grad_norm": 0.021053463220596313,
-      "learning_rate": 1.0894012810423893e-06,
-      "loss": 0.0432,
-      "step": 14000
-    },
-    {
-      "epoch": 4.0,
-      "eval_f1": 0.8205950902835818,
-      "eval_loss": 1.032849669456482,
-      "eval_runtime": 29.3592,
-      "eval_samples_per_second": 339.723,
-      "eval_steps_per_second": 42.474,
-      "step": 14960
+      "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
     }
   ],
   "logging_steps": 1000,
-  "max_steps": 14960,
+  "max_steps": 414,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -167,14 +42,14 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9467913445282816e+16,
-  "train_batch_size": 8,
+  "total_flos": 4209814683648.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.6692805045972443e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 8,
+    "learning_rate": 4.65591694361634e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
     "warmup_steps": 250,
-    "weight_decay": 0.14200719532179423
+    "weight_decay": 0.2103754328402818
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba9a4ffaa70c7e045b0900e8e84762b50381bc617e266ba61c82c6d7eda6333
+oid sha256:83b594183cbe9f09ddaf478eae629dcdb3d51b9bcb4757de1f514b20d09ee833
 size 5240

training_resume.json

@@ -19,7 +19,7 @@
     "resources_per_trial": {
         "gpu": 1
     },
-    "run_id": "fa19ee57",
+    "run_id": "24fa3a3c",
     "task": "",
     "task_type": "classification",
     "tokenizer_field": "tweet",