add model

.gitignore

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

README.md

@@ -0,0 +1,84 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- null
+model_index:
+- name: bart-mlm
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+---
+
+<!-- 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. -->
+
+# bart-mlm
+
+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: 7.0454
+
+## 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: cosine_with_restarts
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 7.3964        | 0.08  | 10000  | 7.4260          |
+| 7.3303        | 0.16  | 20000  | 7.3293          |
+| 7.2823        | 0.25  | 30000  | 7.2939          |
+| 7.2526        | 0.33  | 40000  | 7.2624          |
+| 7.224         | 0.41  | 50000  | 7.2391          |
+| 7.204         | 0.49  | 60000  | 7.2192          |
+| 7.1693        | 0.57  | 70000  | 7.2053          |
+| 7.1845        | 0.66  | 80000  | 7.1815          |
+| 7.1538        | 0.74  | 90000  | 7.1610          |
+| 7.1278        | 0.82  | 100000 | 7.1459          |
+| 7.1158        | 0.9   | 110000 | 7.1332          |
+| 7.1126        | 0.98  | 120000 | 7.1200          |
+| 7.0827        | 1.07  | 130000 | 7.1105          |
+| 7.0857        | 1.15  | 140000 | 7.0978          |
+| 7.0646        | 1.23  | 150000 | 7.0784          |
+| 7.0606        | 1.31  | 160000 | 7.0716          |
+| 7.0539        | 1.39  | 170000 | 7.0659          |
+| 7.0282        | 1.48  | 180000 | 7.0602          |
+| 7.0427        | 1.56  | 190000 | 7.0553          |
+| 7.0366        | 1.64  | 200000 | 7.0486          |
+| 7.0133        | 1.72  | 210000 | 7.0529          |
+| 7.0235        | 1.8   | 220000 | 7.0458          |
+| 7.0167        | 1.89  | 230000 | 7.0434          |
+| 7.0208        | 1.97  | 240000 | 7.0435          |
+
+
+### Framework versions
+
+- Transformers 4.8.1
+- Pytorch 1.9.0
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,44 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": true,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "transformers_version": "4.8.1",
+  "use_cache": false,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2aa1bb3bf469d1b814e3e644507d983c3944ef45780b5bf28a926f8c3cc69ef
+size 1625557313

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6715133c83b5593f520595bfe4a43dfb0af1e2b1b0e07dcbff95159068b6e11
+size 2607