add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- null
+model_index:
+- name: bert-base-cased-wikitext2
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+---
+
+<!-- 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-base-cased-wikitext2
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.8565
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.0916        | 1.0   | 2346 | 7.0492          |
+| 6.9074        | 2.0   | 4692 | 6.8727          |
+| 6.8588        | 3.0   | 7038 | 6.8914          |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a57edae73019867752d63cc099f6b9cf746e61eb5312cd30fec48ffed24f77
+size 433448043

runs/Aug06_14-32-15_67165c4eb041/1628260343.1447463/events.out.tfevents.1628260343.67165c4eb041.61.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13074ff5d0b8d32173eb23ebe3352a12fa4fede7ac3a0b4d6e4e462c346be47e
+size 4186

runs/Aug06_14-32-15_67165c4eb041/events.out.tfevents.1628260343.67165c4eb041.61.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5137e47f5bdcbb82356e01dbe772c2286bea3c6bfefb3e1f02f2379d269260f
+size 6241

runs/Aug06_14-32-15_67165c4eb041/events.out.tfevents.1628262483.67165c4eb041.61.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931ea866c51fd7f66aec595564a48f325172160d57c1741e0a44de26070b6e28
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45282146d7b25fa57fcd9347f582b85d3c5486b074b5a094ca1df7b257a14ff6
+size 2671