Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: google/electra-base-discriminator
+tags:
+- generated_from_trainer
+model-index:
+- name: imdb_42
+  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
+
+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
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "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
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.90888,
+    "eval_loss": 0.6276622414588928,
+    "eval_runtime": 44.1174,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 566.67,
+    "eval_steps_per_second": 2.221
+}

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462690d0106a3ac59092b5b3a95bc93f2bdb2db684db4e9ad25416ad812572aa
+size 200128

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462690d0106a3ac59092b5b3a95bc93f2bdb2db684db4e9ad25416ad812572aa
+size 200128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d00b0f191ba17c3cb47d8fa13ceba382c1aeb4183311e580c287a6073885aee
+size 200128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044ec9f99f751142ee318e6cff4ab49c5ab0c7c2455b377644a4825cd8d63419
+size 438006701

runs/Apr17_12-28-18_clu/events.out.tfevents.1713356970.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d98b97b7517fdd4dff02920dbb204f17a40da398a3d47115919e30bd5e7ca45
+size 298

runs/Apr21_18-55-07_clu/events.out.tfevents.1713725769.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbabac543571e86c1f5f645e58693a8e41fc94e72952f3a2f0bcb443a306422a
+size 814

runs/Mar18_11-35-05_clu/1710761732.41874/events.out.tfevents.1710761732.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69614210e6265f8c4dd867dc18239a0586a04c0fe575404da64826d34c3fdbf
+size 5631

runs/Mar18_11-35-05_clu/events.out.tfevents.1710761732.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e40ba1bf3800bbdadac89f8726096d06c5c36a3302e0b1882f23c4c58b22e91
+size 9007

runs/Mar18_11-35-05_clu/events.out.tfevents.1710762541.clu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c46626d424196aa49c3efae4b9636c221bd0a14dfedb1129042a65edb26ccff
+size 363

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "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
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "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
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.90888,
+  "best_model_checkpoint": "checkpoint/electra-base/imdb_42/checkpoint-7038",
+  "epoch": 10.0,
+  "global_step": 7820,
+  "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,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.2699,
+      "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,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.1432,
+      "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,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.072,
+      "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,
+      "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,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0384,
+      "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,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0227,
+      "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,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0144,
+      "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,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.01,
+      "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,
+      "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,
+      "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
+    }
+  ],
+  "max_steps": 7820,
+  "num_train_epochs": 10,
+  "total_flos": 1.644444096e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff0ef9332433f8dd6ce58dc2c676ee07395b285992da1808e5db997e35d1647
+size 3631