Model save

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+base_model: bert-large-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: BERT_pretraining_h_100
+  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_pretraining_h_100
+
+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: 7.2729
+- Accuracy: 0.0466
+
+## 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: 0.0001
+- train_batch_size: 36
+- eval_batch_size: 36
+- seed: 10
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100000
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Accuracy |
+|:-------------:|:-----:|:------:|:---------------:|:--------:|
+| 6.5136        | 0.06  | 10000  | 6.4841          | 0.1332   |
+| 6.3225        | 0.12  | 20000  | 6.2865          | 0.1452   |
+| 6.0806        | 0.18  | 30000  | 6.1945          | 0.1482   |
+| 6.1449        | 0.25  | 40000  | 6.1284          | 0.1497   |
+| 5.7325        | 0.31  | 50000  | 5.8403          | 0.1609   |
+| 4.0177        | 0.37  | 60000  | 3.7789          | 0.3887   |
+| 3.3942        | 0.43  | 70000  | 3.1742          | 0.4638   |
+| 3.2801        | 0.49  | 80000  | 3.0618          | 0.4775   |
+| 7.2562        | 0.55  | 90000  | 7.2798          | 0.0432   |
+| 7.226         | 0.61  | 100000 | 7.2771          | 0.0465   |
+| 7.2174        | 0.68  | 110000 | 7.2764          | 0.0465   |
+| 7.232         | 0.74  | 120000 | 7.2745          | 0.0465   |
+| 7.2003        | 0.8   | 130000 | 7.2730          | 0.0465   |
+| 7.0964        | 0.86  | 140000 | 7.2725          | 0.0466   |
+| 7.5174        | 0.92  | 150000 | 7.2729          | 0.0465   |
+| 7.2674        | 0.98  | 160000 | 7.2729          | 0.0465   |
+| 7.2044        | 1.04  | 170000 | 7.2729          | 0.0466   |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.1"
+}

logs/events.out.tfevents.1706191999.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603fc3b2f295255914c365d7a4a48d19c31f7a7f4bd9e1f99dac4400c4e6d275
+size 4330

logs/events.out.tfevents.1706192136.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990027e13bcd63ba4f683ad79a983d4e6a25419da26fdb32248ef788590846df
+size 4330

logs/events.out.tfevents.1706192656.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6ba5e80c71dd29520257f1dd3cd0ea15548c800cfcc5f14dd94e8aeb216e83
+size 29084

logs/events.out.tfevents.1706193206.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb1874bea9bd115d2a370e6cabc47c257bd238058b530caefc35adef01775c2
+size 4345

logs/events.out.tfevents.1706193278.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e973f879fdebedb8e174f7d26213530b5acb33515c1e48f97ecc2a482ec3a97
+size 8811

logs/events.out.tfevents.1706193403.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07644111d8fecdcc07dd298dad212d6318b81b601a92365716fecc60288ab631
+size 59699

logs/events.out.tfevents.1706194020.ki-g0009

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980a3b0ec5043a430779a9a7da98fb6608fbc984931f6cbd528f3c98ea640523
+size 28110202

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc538da1cb976ea766d164cf4d4663c1d59a0f1dd78069be4e0bdbbf1a14dea
+size 1465885424

special_tokens_map.json

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

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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6924ef1775fc4634b69b53111f02df3760b218854f9e7c05344310947604f63c
+size 5688