add model

.gitignore

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

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- oscar
+model_index:
+- name: esberto-small
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: oscar
+      type: oscar
+      args: unshuffled_deduplicated_eo
+---
+
+<!-- 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. -->
+
+# esberto-small
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the oscar dataset.
+
+## 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: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.9.0.dev0
+- Pytorch 1.8.1+cu111
+- Datasets 1.10.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525d9edcc8c2990f53946211cca0222ac4244e20fdc9461069aec9ed778db791
+size 334060082

runs/Jul21_12-09-56_brahms/1626883805.7519002/events.out.tfevents.1626883805.brahms.2610114.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ff5a5307a03cba975efcd755ea4e124ffd10dc4d0c2ef70b0399395d4e44d6
+size 4171

runs/Jul21_12-09-56_brahms/events.out.tfevents.1626883805.brahms.2610114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8033912123266ecc574e322c75407dcf967bb25873e4fcf0242542ec284ad1ea
+size 2854

runs/Jul21_12-10-25_brahms/1626883861.7842593/events.out.tfevents.1626883861.brahms.2610114.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581fa82450c4c1ee13e48e578542d85866eef4c897f34a82f498e8aac0e216a5
+size 4168

runs/Jul21_12-10-25_brahms/events.out.tfevents.1626883861.brahms.2610114.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654a958555bfefaf544d75588902c7f42a96e56334cbd6720c217c4f3f6f789b
+size 6625

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafd910cf68f7dd98afb858d95e8f4a8e225538dcfb73b4b95a1012975b6bd30
+size 2607