Upload folder using huggingface_hub

README.md

@@ -4,23 +4,16 @@ base_model: google/electra-base-discriminator
 tags:
 - generated_from_trainer
 model-index:
-- name: imdb_42
+- name: electra-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
+# electra-base
 
 This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.0027
-- eval_accuracy: 0.9995
-- eval_runtime: 40.0833
-- eval_samples_per_second: 623.7
-- eval_steps_per_second: 2.445
-- 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": 0.99948,
-    "eval_loss": 0.002695722272619605,
-    "eval_runtime": 40.0833,
-    "eval_samples": 25000,
-    "eval_samples_per_second": 623.7,
-    "eval_steps_per_second": 2.445,
-    "train_loss": 0.0733462499535602,
-    "train_runtime": 793.1279,
-    "train_samples": 25000,
-    "train_samples_per_second": 315.208,
-    "train_steps_per_second": 9.86
+    "dr_accuracy": 1.0,
+    "dr_loss": 2.2834794435766526e-05,
+    "dr_runtime": 30.7301,
+    "dr_samples_per_second": 813.534,
+    "dr_steps_per_second": 3.189,
+    "epoch": 20.0,
+    "ood_accuracy": 0.8552804351903958,
+    "ood_loss": 1.3304697275161743,
+    "ood_runtime": 13.3419,
+    "ood_samples_per_second": 799.134,
+    "ood_steps_per_second": 3.148,
+    "test_accuracy": 0.90932,
+    "test_loss": 0.8650785088539124,
+    "test_runtime": 29.989,
+    "test_samples_per_second": 833.64,
+    "test_steps_per_second": 3.268,
+    "train_loss": 0.0428766398688259,
+    "train_runtime": 2610.1004,
+    "train_samples_per_second": 191.564,
+    "train_steps_per_second": 5.992
 }

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": {
@@ -33,7 +29,7 @@
   "summary_type": "first",
   "summary_use_proj": true,
   "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": 1.0,
+    "dr_loss": 2.2834794435766526e-05,
+    "dr_runtime": 30.7301,
+    "dr_samples_per_second": 813.534,
+    "dr_steps_per_second": 3.189
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6feb1e14578713937993c4ad2594b0842b07979fd0f1e8006ded531ceed42b47
+size 437959248

ood_results.json

@@ -0,0 +1,7 @@
+{
+    "ood_accuracy": 0.8552804351903958,
+    "ood_loss": 1.3304697275161743,
+    "ood_runtime": 13.3419,
+    "ood_samples_per_second": 799.134,
+    "ood_steps_per_second": 3.148
+}

test_results.json

@@ -1,8 +1,7 @@
 {
-    "eval_accuracy": 0.90888,
-    "eval_loss": 0.6276622414588928,
-    "eval_runtime": 40.0814,
-    "eval_samples": 25000,
-    "eval_samples_per_second": 623.73,
-    "eval_steps_per_second": 2.445
+    "test_accuracy": 0.90932,
+    "test_loss": 0.8650785088539124,
+    "test_runtime": 29.989,
+    "test_samples_per_second": 833.64,
+    "test_steps_per_second": 3.268
 }

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": 0.99948,
-    "eval_loss": 0.002695722272619605,
-    "eval_runtime": 40.0833,
-    "eval_samples": 25000,
-    "eval_samples_per_second": 623.7,
-    "eval_steps_per_second": 2.445
+    "epoch": 20.0,
+    "train_loss": 0.0428766398688259,
+    "train_runtime": 2610.1004,
+    "train_samples_per_second": 191.564,
+    "train_steps_per_second": 5.992
 }

trainer_state.json

@@ -1,157 +1,300 @@
 {
-  "best_metric": 0.90888,
-  "best_model_checkpoint": "checkpoint/electra-base/imdb_42/checkpoint-7038",
-  "epoch": 10.0,
-  "global_step": 7820,
+  "best_metric": 0.90932,
+  "best_model_checkpoint": "../../checkpoint/imdb/electra-base/checkpoint-14076",
+  "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": 0.90536,
-      "eval_loss": 0.23193472623825073,
-      "eval_runtime": 14.9471,
-      "eval_samples_per_second": 1672.56,
-      "eval_steps_per_second": 6.556,
+      "eval_accuracy": 0.89252,
+      "eval_loss": 0.2527729868888855,
+      "eval_runtime": 33.8056,
+      "eval_samples_per_second": 739.522,
+      "eval_steps_per_second": 2.899,
       "step": 782
     },
     {
       "epoch": 1.28,
-      "learning_rate": 4.360613810741688e-05,
-      "loss": 0.2699,
+      "learning_rate": 4.680306905370844e-05,
+      "loss": 0.272,
       "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.90432,
-      "eval_loss": 0.2524752616882324,
-      "eval_runtime": 14.5935,
-      "eval_samples_per_second": 1713.094,
-      "eval_steps_per_second": 6.715,
+      "eval_accuracy": 0.90448,
+      "eval_loss": 0.2465250939130783,
+      "eval_runtime": 33.8629,
+      "eval_samples_per_second": 738.272,
+      "eval_steps_per_second": 2.894,
       "step": 1564
     },
     {
       "epoch": 2.56,
-      "learning_rate": 3.721227621483376e-05,
-      "loss": 0.1432,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.1451,
       "step": 2000
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.90284,
-      "eval_loss": 0.4573332369327545,
-      "eval_runtime": 14.9943,
-      "eval_samples_per_second": 1667.297,
-      "eval_steps_per_second": 6.536,
+      "eval_accuracy": 0.9034,
+      "eval_loss": 0.39296430349349976,
+      "eval_runtime": 33.8123,
+      "eval_samples_per_second": 739.377,
+      "eval_steps_per_second": 2.898,
       "step": 2346
     },
     {
       "epoch": 3.84,
-      "learning_rate": 3.081841432225064e-05,
-      "loss": 0.072,
+      "learning_rate": 4.040920716112532e-05,
+      "loss": 0.0804,
       "step": 3000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8994,
-      "eval_loss": 0.411539226770401,
-      "eval_runtime": 14.9739,
-      "eval_samples_per_second": 1669.577,
-      "eval_steps_per_second": 6.545,
+      "eval_accuracy": 0.898,
+      "eval_loss": 0.45841386914253235,
+      "eval_runtime": 33.8469,
+      "eval_samples_per_second": 738.621,
+      "eval_steps_per_second": 2.895,
       "step": 3128
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9038,
-      "eval_loss": 0.45995330810546875,
-      "eval_runtime": 14.943,
-      "eval_samples_per_second": 1673.022,
-      "eval_steps_per_second": 6.558,
+      "eval_accuracy": 0.9056,
+      "eval_loss": 0.5110316872596741,
+      "eval_runtime": 33.885,
+      "eval_samples_per_second": 737.789,
+      "eval_steps_per_second": 2.892,
       "step": 3910
     },
     {
       "epoch": 5.12,
-      "learning_rate": 2.442455242966752e-05,
-      "loss": 0.0384,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.0499,
       "step": 4000
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9056,
-      "eval_loss": 0.47831761837005615,
-      "eval_runtime": 15.0585,
-      "eval_samples_per_second": 1660.194,
-      "eval_steps_per_second": 6.508,
+      "eval_accuracy": 0.89784,
+      "eval_loss": 0.5765578746795654,
+      "eval_runtime": 33.9081,
+      "eval_samples_per_second": 737.288,
+      "eval_steps_per_second": 2.89,
       "step": 4692
     },
     {
       "epoch": 6.39,
-      "learning_rate": 1.80306905370844e-05,
-      "loss": 0.0227,
+      "learning_rate": 3.40153452685422e-05,
+      "loss": 0.0334,
       "step": 5000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.90184,
-      "eval_loss": 0.5771753787994385,
-      "eval_runtime": 15.0276,
-      "eval_samples_per_second": 1663.606,
-      "eval_steps_per_second": 6.521,
+      "eval_accuracy": 0.89992,
+      "eval_loss": 0.5621291995048523,
+      "eval_runtime": 34.0076,
+      "eval_samples_per_second": 735.13,
+      "eval_steps_per_second": 2.882,
       "step": 5474
     },
     {
       "epoch": 7.67,
-      "learning_rate": 1.163682864450128e-05,
-      "loss": 0.0144,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.0243,
       "step": 6000
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.90868,
-      "eval_loss": 0.5959281921386719,
-      "eval_runtime": 14.9693,
-      "eval_samples_per_second": 1670.087,
-      "eval_steps_per_second": 6.547,
+      "eval_accuracy": 0.9016,
+      "eval_loss": 0.6355283856391907,
+      "eval_runtime": 33.9931,
+      "eval_samples_per_second": 735.443,
+      "eval_steps_per_second": 2.883,
       "step": 6256
     },
     {
       "epoch": 8.95,
-      "learning_rate": 5.242966751918159e-06,
-      "loss": 0.01,
+      "learning_rate": 2.7621483375959077e-05,
+      "loss": 0.0195,
       "step": 7000
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.90888,
-      "eval_loss": 0.6276312470436096,
-      "eval_runtime": 14.9974,
-      "eval_samples_per_second": 1666.955,
-      "eval_steps_per_second": 6.534,
+      "eval_accuracy": 0.90184,
+      "eval_loss": 0.6819501519203186,
+      "eval_runtime": 33.7784,
+      "eval_samples_per_second": 740.119,
+      "eval_steps_per_second": 2.901,
       "step": 7038
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.90888,
-      "eval_loss": 0.6741125583648682,
-      "eval_runtime": 14.9871,
-      "eval_samples_per_second": 1668.106,
-      "eval_steps_per_second": 6.539,
+      "eval_accuracy": 0.90152,
+      "eval_loss": 0.6723979115486145,
+      "eval_runtime": 33.9379,
+      "eval_samples_per_second": 736.639,
+      "eval_steps_per_second": 2.888,
       "step": 7820
     },
     {
-      "epoch": 10.0,
-      "step": 7820,
-      "total_flos": 1.644444096e+16,
-      "train_loss": 0.0733462499535602,
-      "train_runtime": 793.1279,
-      "train_samples_per_second": 315.208,
-      "train_steps_per_second": 9.86
+      "epoch": 10.23,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0132,
+      "step": 8000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.90308,
+      "eval_loss": 0.7561084628105164,
+      "eval_runtime": 33.739,
+      "eval_samples_per_second": 740.982,
+      "eval_steps_per_second": 2.905,
+      "step": 8602
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 2.122762148337596e-05,
+      "loss": 0.0095,
+      "step": 9000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.90576,
+      "eval_loss": 0.7514671087265015,
+      "eval_runtime": 33.7517,
+      "eval_samples_per_second": 740.704,
+      "eval_steps_per_second": 2.904,
+      "step": 9384
+    },
+    {
+      "epoch": 12.79,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0072,
+      "step": 10000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.90604,
+      "eval_loss": 0.7862638831138611,
+      "eval_runtime": 33.8938,
+      "eval_samples_per_second": 737.597,
+      "eval_steps_per_second": 2.891,
+      "step": 10166
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.90584,
+      "eval_loss": 0.7231158018112183,
+      "eval_runtime": 33.9086,
+      "eval_samples_per_second": 737.276,
+      "eval_steps_per_second": 2.89,
+      "step": 10948
+    },
+    {
+      "epoch": 14.07,
+      "learning_rate": 1.483375959079284e-05,
+      "loss": 0.0067,
+      "step": 11000
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.90152,
+      "eval_loss": 0.8694790005683899,
+      "eval_runtime": 33.8199,
+      "eval_samples_per_second": 739.211,
+      "eval_steps_per_second": 2.898,
+      "step": 11730
+    },
+    {
+      "epoch": 15.35,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0037,
+      "step": 12000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.90492,
+      "eval_loss": 0.8443425297737122,
+      "eval_runtime": 33.8917,
+      "eval_samples_per_second": 737.644,
+      "eval_steps_per_second": 2.892,
+      "step": 12512
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 8.439897698209718e-06,
+      "loss": 0.0033,
+      "step": 13000
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.90808,
+      "eval_loss": 0.8232758641242981,
+      "eval_runtime": 33.8581,
+      "eval_samples_per_second": 738.376,
+      "eval_steps_per_second": 2.894,
+      "step": 13294
+    },
+    {
+      "epoch": 17.9,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0019,
+      "step": 14000
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.90932,
+      "eval_loss": 0.8650785088539124,
+      "eval_runtime": 33.9491,
+      "eval_samples_per_second": 736.398,
+      "eval_steps_per_second": 2.887,
+      "step": 14076
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.90856,
+      "eval_loss": 0.8838527202606201,
+      "eval_runtime": 33.9568,
+      "eval_samples_per_second": 736.23,
+      "eval_steps_per_second": 2.886,
+      "step": 14858
+    },
+    {
+      "epoch": 19.18,
+      "learning_rate": 2.0460358056265987e-06,
+      "loss": 0.0003,
+      "step": 15000
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.908,
+      "eval_loss": 0.8944087624549866,
+      "eval_runtime": 33.9267,
+      "eval_samples_per_second": 736.882,
+      "eval_steps_per_second": 2.889,
+      "step": 15640
+    },
+    {
+      "epoch": 20.0,
+      "step": 15640,
+      "total_flos": 3.288888192e+16,
+      "train_loss": 0.0428766398688259,
+      "train_runtime": 2610.1004,
+      "train_samples_per_second": 191.564,
+      "train_steps_per_second": 5.992
     }
   ],
-  "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:cff0ef9332433f8dd6ce58dc2c676ee07395b285992da1808e5db997e35d1647
-size 3631
+oid sha256:cb2c7b98b2604983446ab363938f58bbe89846d6949e90a64ba139415a718839
+size 4792