Upload folder using huggingface_hub

README.md

@@ -4,23 +4,16 @@ base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
-- name: imdb_42
+- name: bert-base
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# imdb_42
+# bert-base
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.0003
-- eval_accuracy: 1.0000
-- eval_runtime: 75.737
-- eval_samples_per_second: 330.09
-- eval_steps_per_second: 1.294
-- step: 0
 
 ## Model description
 
@@ -45,11 +38,11 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 20
 
 ### Framework versions
 
-- Transformers 4.39.3
-- Pytorch 2.2.2+cu118
-- Datasets 2.18.0
+- Transformers 4.37.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
 - Tokenizers 0.15.2

all_results.json

@@ -1,14 +1,22 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.99996,
-    "eval_loss": 0.00027643845533020794,
-    "eval_runtime": 75.737,
-    "eval_samples": 25000,
-    "eval_samples_per_second": 330.09,
-    "eval_steps_per_second": 1.294,
-    "train_loss": 0.07364957506394447,
-    "train_runtime": 797.6475,
-    "train_samples": 25000,
-    "train_samples_per_second": 313.422,
-    "train_steps_per_second": 9.804
+    "dr_accuracy": 0.99996,
+    "dr_loss": 8.537256508134305e-05,
+    "dr_runtime": 31.5691,
+    "dr_samples_per_second": 791.914,
+    "dr_steps_per_second": 3.104,
+    "epoch": 20.0,
+    "ood_accuracy": 0.8090414556368412,
+    "ood_loss": 1.719015121459961,
+    "ood_runtime": 13.881,
+    "ood_samples_per_second": 768.102,
+    "ood_steps_per_second": 3.026,
+    "test_accuracy": 0.88608,
+    "test_loss": 1.0448594093322754,
+    "test_runtime": 30.948,
+    "test_samples_per_second": 807.807,
+    "test_steps_per_second": 3.167,
+    "train_loss": 0.043571622534404934,
+    "train_runtime": 2625.0815,
+    "train_samples_per_second": 190.47,
+    "train_steps_per_second": 5.958
 }

config.json

@@ -10,10 +10,6 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "0",
-    "1": "1"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
@@ -29,7 +25,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.28.0",
+  "transformers_version": "4.37.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

dr_results.json

@@ -0,0 +1,7 @@
+{
+    "dr_accuracy": 0.99996,
+    "dr_loss": 8.537256508134305e-05,
+    "dr_runtime": 31.5691,
+    "dr_samples_per_second": 791.914,
+    "dr_steps_per_second": 3.104
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e659611e4209065aefa1ca807a9c2e4b0b1e563522c0fd530d0ddaf7c86963fe
+size 437958648

ood_results.json

@@ -0,0 +1,7 @@
+{
+    "ood_accuracy": 0.8090414556368412,
+    "ood_loss": 1.719015121459961,
+    "ood_runtime": 13.881,
+    "ood_samples_per_second": 768.102,
+    "ood_steps_per_second": 3.026
+}

test_results.json

@@ -1,8 +1,7 @@
 {
-    "eval_accuracy": 0.88732,
-    "eval_loss": 0.8893803954124451,
-    "eval_runtime": 89.64,
-    "eval_samples": 25000,
-    "eval_samples_per_second": 278.893,
-    "eval_steps_per_second": 1.093
+    "test_accuracy": 0.88608,
+    "test_loss": 1.0448594093322754,
+    "test_runtime": 30.948,
+    "test_samples_per_second": 807.807,
+    "test_steps_per_second": 3.167
 }

tokenizer_config.json

@@ -1,4 +1,46 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,

train_results.json

@@ -1,8 +1,7 @@
 {
-    "eval_accuracy": 0.99996,
-    "eval_loss": 0.00027643845533020794,
-    "eval_runtime": 75.737,
-    "eval_samples": 25000,
-    "eval_samples_per_second": 330.09,
-    "eval_steps_per_second": 1.294
+    "epoch": 20.0,
+    "train_loss": 0.043571622534404934,
+    "train_runtime": 2625.0815,
+    "train_samples_per_second": 190.47,
+    "train_steps_per_second": 5.958
 }

trainer_state.json

@@ -1,157 +1,300 @@
 {
-  "best_metric": 0.88732,
-  "best_model_checkpoint": "checkpoint/bert-base/imdb_42/checkpoint-7820",
-  "epoch": 10.0,
-  "global_step": 7820,
+  "best_metric": 0.88608,
+  "best_model_checkpoint": "../../checkpoint/imdb/bert-base/checkpoint-12512",
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 15640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.885,
-      "eval_loss": 0.2771714925765991,
-      "eval_runtime": 15.7601,
-      "eval_samples_per_second": 1586.288,
-      "eval_steps_per_second": 6.218,
+      "eval_accuracy": 0.88012,
+      "eval_loss": 0.2792210280895233,
+      "eval_runtime": 34.1095,
+      "eval_samples_per_second": 732.933,
+      "eval_steps_per_second": 2.873,
       "step": 782
     },
     {
       "epoch": 1.28,
-      "learning_rate": 4.360613810741688e-05,
-      "loss": 0.3091,
+      "learning_rate": 4.680306905370844e-05,
+      "loss": 0.307,
       "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.88332,
-      "eval_loss": 0.3185863494873047,
-      "eval_runtime": 14.8791,
-      "eval_samples_per_second": 1680.206,
-      "eval_steps_per_second": 6.586,
+      "eval_accuracy": 0.86836,
+      "eval_loss": 0.3073737621307373,
+      "eval_runtime": 34.1017,
+      "eval_samples_per_second": 733.1,
+      "eval_steps_per_second": 2.874,
       "step": 1564
     },
     {
       "epoch": 2.56,
-      "learning_rate": 3.721227621483376e-05,
-      "loss": 0.1446,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.1491,
       "step": 2000
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.88372,
-      "eval_loss": 0.4319324493408203,
-      "eval_runtime": 15.634,
-      "eval_samples_per_second": 1599.077,
-      "eval_steps_per_second": 6.268,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.5035193562507629,
+      "eval_runtime": 33.9308,
+      "eval_samples_per_second": 736.793,
+      "eval_steps_per_second": 2.888,
       "step": 2346
     },
     {
       "epoch": 3.84,
-      "learning_rate": 3.081841432225064e-05,
-      "loss": 0.0654,
+      "learning_rate": 4.040920716112532e-05,
+      "loss": 0.0719,
       "step": 3000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.88224,
-      "eval_loss": 0.527112603187561,
-      "eval_runtime": 15.5935,
-      "eval_samples_per_second": 1603.233,
-      "eval_steps_per_second": 6.285,
+      "eval_accuracy": 0.88072,
+      "eval_loss": 0.5898228287696838,
+      "eval_runtime": 34.0598,
+      "eval_samples_per_second": 734.004,
+      "eval_steps_per_second": 2.877,
       "step": 3128
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.882,
-      "eval_loss": 0.7103033065795898,
-      "eval_runtime": 15.6832,
-      "eval_samples_per_second": 1594.061,
-      "eval_steps_per_second": 6.249,
+      "eval_accuracy": 0.8714,
+      "eval_loss": 0.763311505317688,
+      "eval_runtime": 34.1843,
+      "eval_samples_per_second": 731.33,
+      "eval_steps_per_second": 2.867,
       "step": 3910
     },
     {
       "epoch": 5.12,
-      "learning_rate": 2.442455242966752e-05,
-      "loss": 0.0255,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.0366,
       "step": 4000
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.88156,
-      "eval_loss": 0.7340117692947388,
-      "eval_runtime": 15.5378,
-      "eval_samples_per_second": 1608.978,
-      "eval_steps_per_second": 6.307,
+      "eval_accuracy": 0.87656,
+      "eval_loss": 0.6611727476119995,
+      "eval_runtime": 34.137,
+      "eval_samples_per_second": 732.344,
+      "eval_steps_per_second": 2.871,
       "step": 4692
     },
     {
       "epoch": 6.39,
-      "learning_rate": 1.80306905370844e-05,
-      "loss": 0.0144,
+      "learning_rate": 3.40153452685422e-05,
+      "loss": 0.0308,
       "step": 5000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.88624,
-      "eval_loss": 0.8043656945228577,
-      "eval_runtime": 15.5601,
-      "eval_samples_per_second": 1606.673,
-      "eval_steps_per_second": 6.298,
+      "eval_accuracy": 0.88068,
+      "eval_loss": 0.642299234867096,
+      "eval_runtime": 34.2471,
+      "eval_samples_per_second": 729.99,
+      "eval_steps_per_second": 2.862,
       "step": 5474
     },
     {
       "epoch": 7.67,
-      "learning_rate": 1.163682864450128e-05,
-      "loss": 0.0106,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.0237,
       "step": 6000
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.88544,
-      "eval_loss": 0.8684703707695007,
-      "eval_runtime": 15.6281,
-      "eval_samples_per_second": 1599.681,
-      "eval_steps_per_second": 6.271,
+      "eval_accuracy": 0.87888,
+      "eval_loss": 0.9059407711029053,
+      "eval_runtime": 34.0813,
+      "eval_samples_per_second": 733.539,
+      "eval_steps_per_second": 2.875,
       "step": 6256
     },
     {
       "epoch": 8.95,
-      "learning_rate": 5.242966751918159e-06,
-      "loss": 0.0049,
+      "learning_rate": 2.7621483375959077e-05,
+      "loss": 0.015,
       "step": 7000
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.88596,
-      "eval_loss": 0.8513516187667847,
-      "eval_runtime": 15.5688,
-      "eval_samples_per_second": 1605.772,
-      "eval_steps_per_second": 6.295,
+      "eval_accuracy": 0.8794,
+      "eval_loss": 0.8373117446899414,
+      "eval_runtime": 34.0748,
+      "eval_samples_per_second": 733.679,
+      "eval_steps_per_second": 2.876,
       "step": 7038
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.88732,
-      "eval_loss": 0.8893799185752869,
-      "eval_runtime": 15.6721,
-      "eval_samples_per_second": 1595.191,
-      "eval_steps_per_second": 6.253,
+      "eval_accuracy": 0.879,
+      "eval_loss": 0.9557542204856873,
+      "eval_runtime": 34.1311,
+      "eval_samples_per_second": 732.469,
+      "eval_steps_per_second": 2.871,
       "step": 7820
     },
     {
-      "epoch": 10.0,
-      "step": 7820,
-      "total_flos": 1.644444096e+16,
-      "train_loss": 0.07364957506394447,
-      "train_runtime": 797.6475,
-      "train_samples_per_second": 313.422,
-      "train_steps_per_second": 9.804
+      "epoch": 10.23,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0155,
+      "step": 8000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.87836,
+      "eval_loss": 1.0240801572799683,
+      "eval_runtime": 33.9654,
+      "eval_samples_per_second": 736.042,
+      "eval_steps_per_second": 2.885,
+      "step": 8602
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 2.122762148337596e-05,
+      "loss": 0.01,
+      "step": 9000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.88172,
+      "eval_loss": 0.9570114016532898,
+      "eval_runtime": 34.077,
+      "eval_samples_per_second": 733.633,
+      "eval_steps_per_second": 2.876,
+      "step": 9384
+    },
+    {
+      "epoch": 12.79,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.009,
+      "step": 10000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.87288,
+      "eval_loss": 1.0905340909957886,
+      "eval_runtime": 34.2575,
+      "eval_samples_per_second": 729.768,
+      "eval_steps_per_second": 2.861,
+      "step": 10166
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.88284,
+      "eval_loss": 0.8721671104431152,
+      "eval_runtime": 34.093,
+      "eval_samples_per_second": 733.288,
+      "eval_steps_per_second": 2.874,
+      "step": 10948
+    },
+    {
+      "epoch": 14.07,
+      "learning_rate": 1.483375959079284e-05,
+      "loss": 0.0059,
+      "step": 11000
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.88448,
+      "eval_loss": 1.0063711404800415,
+      "eval_runtime": 34.0403,
+      "eval_samples_per_second": 734.424,
+      "eval_steps_per_second": 2.879,
+      "step": 11730
+    },
+    {
+      "epoch": 15.35,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0028,
+      "step": 12000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.88608,
+      "eval_loss": 1.0448594093322754,
+      "eval_runtime": 34.3573,
+      "eval_samples_per_second": 727.648,
+      "eval_steps_per_second": 2.852,
+      "step": 12512
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 8.439897698209718e-06,
+      "loss": 0.0018,
+      "step": 13000
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.8828,
+      "eval_loss": 1.1077994108200073,
+      "eval_runtime": 34.1209,
+      "eval_samples_per_second": 732.69,
+      "eval_steps_per_second": 2.872,
+      "step": 13294
+    },
+    {
+      "epoch": 17.9,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0014,
+      "step": 14000
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.88408,
+      "eval_loss": 1.1377348899841309,
+      "eval_runtime": 34.0133,
+      "eval_samples_per_second": 735.007,
+      "eval_steps_per_second": 2.881,
+      "step": 14076
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.88492,
+      "eval_loss": 1.1733046770095825,
+      "eval_runtime": 34.1578,
+      "eval_samples_per_second": 731.898,
+      "eval_steps_per_second": 2.869,
+      "step": 14858
+    },
+    {
+      "epoch": 19.18,
+      "learning_rate": 2.0460358056265987e-06,
+      "loss": 0.0003,
+      "step": 15000
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8846,
+      "eval_loss": 1.177056074142456,
+      "eval_runtime": 34.2367,
+      "eval_samples_per_second": 730.21,
+      "eval_steps_per_second": 2.862,
+      "step": 15640
+    },
+    {
+      "epoch": 20.0,
+      "step": 15640,
+      "total_flos": 3.288888192e+16,
+      "train_loss": 0.043571622534404934,
+      "train_runtime": 2625.0815,
+      "train_samples_per_second": 190.47,
+      "train_steps_per_second": 5.958
     }
   ],
-  "max_steps": 7820,
-  "num_train_epochs": 10,
-  "total_flos": 1.644444096e+16,
+  "logging_steps": 1000,
+  "max_steps": 15640,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 3.288888192e+16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894be00755fd41b0392e4629f82e6cf25f5f5238084fede785713bbc01311ad1
-size 3631
+oid sha256:c01651bce26838f9a693f1e2159a8ebb9f399f6ff7aa54c747d42a6e72be4b71
+size 4792