Upload folder using huggingface_hub

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: bert-large-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-large
+  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. -->
+
+# bert-large
+
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9621
+- Accuracy: 0.8887
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| No log        | 1.0   | 782   | 0.2848          | 0.8852   |
+| 0.3133        | 2.0   | 1564  | 0.3038          | 0.8888   |
+| 0.1751        | 3.0   | 2346  | 0.5035          | 0.8791   |
+| 0.1057        | 4.0   | 3128  | 0.5942          | 0.885    |
+| 0.1057        | 5.0   | 3910  | 0.5220          | 0.8764   |
+| 0.0733        | 6.0   | 4692  | 0.6981          | 0.8823   |
+| 0.0439        | 7.0   | 5474  | 0.6775          | 0.8833   |
+| 0.0371        | 8.0   | 6256  | 0.6118          | 0.8891   |
+| 0.0277        | 9.0   | 7038  | 0.7128          | 0.8864   |
+| 0.0277        | 10.0  | 7820  | 0.7555          | 0.8868   |
+| 0.0202        | 11.0  | 8602  | 0.7618          | 0.8888   |
+| 0.0141        | 12.0  | 9384  | 0.7654          | 0.8842   |
+| 0.0125        | 13.0  | 10166 | 0.8345          | 0.8867   |
+| 0.0125        | 14.0  | 10948 | 0.8073          | 0.8844   |
+| 0.0077        | 15.0  | 11730 | 0.7047          | 0.8887   |
+| 0.0071        | 16.0  | 12512 | 0.8622          | 0.8891   |
+| 0.004         | 17.0  | 13294 | 0.8655          | 0.8900   |
+| 0.0031        | 18.0  | 14076 | 0.9096          | 0.8898   |
+| 0.0031        | 19.0  | 14858 | 0.9454          | 0.8892   |
+| 0.0016        | 20.0  | 15640 | 0.9621          | 0.8887   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,22 @@
+{
+    "dr_accuracy": 0.9998,
+    "dr_loss": 0.0014581895666196942,
+    "dr_runtime": 108.3951,
+    "dr_samples_per_second": 230.638,
+    "dr_steps_per_second": 0.904,
+    "epoch": 20.0,
+    "ood_accuracy": 0.8211404989682987,
+    "ood_loss": 1.3243283033370972,
+    "ood_runtime": 46.2772,
+    "ood_samples_per_second": 230.394,
+    "ood_steps_per_second": 0.908,
+    "test_accuracy": 0.89004,
+    "test_loss": 0.8655158877372742,
+    "test_runtime": 107.9984,
+    "test_samples_per_second": 231.485,
+    "test_steps_per_second": 0.907,
+    "train_loss": 0.054148883717444245,
+    "train_runtime": 8090.5095,
+    "train_samples_per_second": 61.801,
+    "train_steps_per_second": 1.933
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "text-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

dr_results.json

@@ -0,0 +1,8 @@
+{
+    "dr_accuracy": 0.9998,
+    "dr_loss": 0.0014581895666196942,
+    "dr_runtime": 108.3951,
+    "dr_samples_per_second": 230.638,
+    "dr_steps_per_second": 0.904,
+    "epoch": 20.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb153cf5450d8a6135b5d4f4634a641bb5548791b647b7893299cafa3f83c06f
+size 1340622760

ood_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "ood_accuracy": 0.8211404989682987,
+    "ood_loss": 1.3243283033370972,
+    "ood_runtime": 46.2772,
+    "ood_samples_per_second": 230.394,
+    "ood_steps_per_second": 0.908
+}

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 @@
+{
+    "epoch": 20.0,
+    "test_accuracy": 0.89004,
+    "test_loss": 0.8655158877372742,
+    "test_runtime": 107.9984,
+    "test_samples_per_second": 231.485,
+    "test_steps_per_second": 0.907
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.054148883717444245,
+    "train_runtime": 8090.5095,
+    "train_samples_per_second": 61.801,
+    "train_steps_per_second": 1.933
+}

trainer_state.json

@@ -0,0 +1,300 @@
+{
+  "best_metric": 0.89004,
+  "best_model_checkpoint": "../../checkpoint/imdb/bert-large/checkpoint-13294",
+  "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": 0.88516,
+      "eval_loss": 0.2848346531391144,
+      "eval_runtime": 108.2274,
+      "eval_samples_per_second": 230.995,
+      "eval_steps_per_second": 0.906,
+      "step": 782
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.680306905370844e-05,
+      "loss": 0.3133,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.88884,
+      "eval_loss": 0.30378255248069763,
+      "eval_runtime": 107.9566,
+      "eval_samples_per_second": 231.574,
+      "eval_steps_per_second": 0.908,
+      "step": 1564
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.360613810741688e-05,
+      "loss": 0.1751,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.87908,
+      "eval_loss": 0.5034909248352051,
+      "eval_runtime": 108.1984,
+      "eval_samples_per_second": 231.057,
+      "eval_steps_per_second": 0.906,
+      "step": 2346
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 4.040920716112532e-05,
+      "loss": 0.1057,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.885,
+      "eval_loss": 0.5942110419273376,
+      "eval_runtime": 108.005,
+      "eval_samples_per_second": 231.471,
+      "eval_steps_per_second": 0.907,
+      "step": 3128
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.87644,
+      "eval_loss": 0.5219671726226807,
+      "eval_runtime": 107.7329,
+      "eval_samples_per_second": 232.055,
+      "eval_steps_per_second": 0.91,
+      "step": 3910
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 3.721227621483376e-05,
+      "loss": 0.0733,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.88228,
+      "eval_loss": 0.6980640888214111,
+      "eval_runtime": 107.7427,
+      "eval_samples_per_second": 232.034,
+      "eval_steps_per_second": 0.91,
+      "step": 4692
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 3.40153452685422e-05,
+      "loss": 0.0439,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.88328,
+      "eval_loss": 0.6775364279747009,
+      "eval_runtime": 107.8186,
+      "eval_samples_per_second": 231.871,
+      "eval_steps_per_second": 0.909,
+      "step": 5474
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 3.081841432225064e-05,
+      "loss": 0.0371,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.88908,
+      "eval_loss": 0.6118285059928894,
+      "eval_runtime": 108.1846,
+      "eval_samples_per_second": 231.086,
+      "eval_steps_per_second": 0.906,
+      "step": 6256
+    },
+    {
+      "epoch": 8.95,
+      "learning_rate": 2.7621483375959077e-05,
+      "loss": 0.0277,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.88644,
+      "eval_loss": 0.7127733826637268,
+      "eval_runtime": 108.2656,
+      "eval_samples_per_second": 230.914,
+      "eval_steps_per_second": 0.905,
+      "step": 7038
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8868,
+      "eval_loss": 0.7554897665977478,
+      "eval_runtime": 108.2355,
+      "eval_samples_per_second": 230.978,
+      "eval_steps_per_second": 0.905,
+      "step": 7820
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 2.442455242966752e-05,
+      "loss": 0.0202,
+      "step": 8000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.88876,
+      "eval_loss": 0.7617989182472229,
+      "eval_runtime": 107.7019,
+      "eval_samples_per_second": 232.122,
+      "eval_steps_per_second": 0.91,
+      "step": 8602
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 2.122762148337596e-05,
+      "loss": 0.0141,
+      "step": 9000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.88424,
+      "eval_loss": 0.765361487865448,
+      "eval_runtime": 108.098,
+      "eval_samples_per_second": 231.272,
+      "eval_steps_per_second": 0.907,
+      "step": 9384
+    },
+    {
+      "epoch": 12.79,
+      "learning_rate": 1.80306905370844e-05,
+      "loss": 0.0125,
+      "step": 10000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.88668,
+      "eval_loss": 0.834495484828949,
+      "eval_runtime": 108.2866,
+      "eval_samples_per_second": 230.869,
+      "eval_steps_per_second": 0.905,
+      "step": 10166
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8844,
+      "eval_loss": 0.8072969317436218,
+      "eval_runtime": 107.9547,
+      "eval_samples_per_second": 231.579,
+      "eval_steps_per_second": 0.908,
+      "step": 10948
+    },
+    {
+      "epoch": 14.07,
+      "learning_rate": 1.483375959079284e-05,
+      "loss": 0.0077,
+      "step": 11000
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.88872,
+      "eval_loss": 0.7046570181846619,
+      "eval_runtime": 108.2002,
+      "eval_samples_per_second": 231.053,
+      "eval_steps_per_second": 0.906,
+      "step": 11730
+    },
+    {
+      "epoch": 15.35,
+      "learning_rate": 1.163682864450128e-05,
+      "loss": 0.0071,
+      "step": 12000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.88908,
+      "eval_loss": 0.8622098565101624,
+      "eval_runtime": 108.34,
+      "eval_samples_per_second": 230.755,
+      "eval_steps_per_second": 0.905,
+      "step": 12512
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 8.439897698209718e-06,
+      "loss": 0.004,
+      "step": 13000
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.89004,
+      "eval_loss": 0.8655158877372742,
+      "eval_runtime": 108.4486,
+      "eval_samples_per_second": 230.524,
+      "eval_steps_per_second": 0.904,
+      "step": 13294
+    },
+    {
+      "epoch": 17.9,
+      "learning_rate": 5.242966751918159e-06,
+      "loss": 0.0031,
+      "step": 14000
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.88984,
+      "eval_loss": 0.9096148610115051,
+      "eval_runtime": 108.8181,
+      "eval_samples_per_second": 229.741,
+      "eval_steps_per_second": 0.901,
+      "step": 14076
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.88916,
+      "eval_loss": 0.945423424243927,
+      "eval_runtime": 108.3869,
+      "eval_samples_per_second": 230.655,
+      "eval_steps_per_second": 0.904,
+      "step": 14858
+    },
+    {
+      "epoch": 19.18,
+      "learning_rate": 2.0460358056265987e-06,
+      "loss": 0.0016,
+      "step": 15000
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.88868,
+      "eval_loss": 0.9621471762657166,
+      "eval_runtime": 108.2519,
+      "eval_samples_per_second": 230.943,
+      "eval_steps_per_second": 0.905,
+      "step": 15640
+    },
+    {
+      "epoch": 20.0,
+      "step": 15640,
+      "total_flos": 1.16491420416e+17,
+      "train_loss": 0.054148883717444245,
+      "train_runtime": 8090.5095,
+      "train_samples_per_second": 61.801,
+      "train_steps_per_second": 1.933
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 15640,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.16491420416e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de0b7c4ca4c0094bcc2661050e55092639b324d4b6e9ad4f0dbd5c8dd088a2a
+size 4792