clinical_transcripts_roberta

README.md

@@ -0,0 +1,77 @@
+---
+base_model: allenai/biomed_roberta_base
+tags:
+- generated_from_trainer
+model-index:
+- name: clinical_transcripts_roberta
+  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. -->
+
+# clinical_transcripts_roberta
+
+This model is a fine-tuned version of [allenai/biomed_roberta_base](https://huggingface.co/allenai/biomed_roberta_base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0798
+
+## 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: 0.0005
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_steps: 100
+- training_steps: 2000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.405         | 0.51  | 100  | 1.2925          |
+| 1.3155        | 1.01  | 200  | 1.2096          |
+| 1.276         | 1.52  | 300  | 1.1683          |
+| 1.2876        | 2.02  | 400  | 1.1698          |
+| 1.2189        | 2.53  | 500  | 1.1662          |
+| 1.1993        | 3.03  | 600  | 1.1183          |
+| 1.1656        | 3.54  | 700  | 1.1337          |
+| 1.1486        | 4.04  | 800  | 1.1396          |
+| 1.14          | 4.55  | 900  | 1.1034          |
+| 1.1411        | 5.05  | 1000 | 1.1279          |
+| 1.1132        | 5.56  | 1100 | 1.0999          |
+| 1.1039        | 6.06  | 1200 | 1.0912          |
+| 1.0986        | 6.57  | 1300 | 1.0948          |
+| 1.077         | 7.07  | 1400 | 1.0866          |
+| 1.0649        | 7.58  | 1500 | 1.0695          |
+| 1.0564        | 8.08  | 1600 | 1.0676          |
+| 1.028         | 8.59  | 1700 | 1.0567          |
+| 1.0917        | 9.09  | 1800 | 1.0642          |
+| 1.0456        | 9.6   | 1900 | 1.0386          |
+| 1.0353        | 10.1  | 2000 | 1.0798          |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 50264,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "allenai/biomed_roberta_base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25c88ad5c9a7bd7a5057a23ff8c050e4cfc80983f0fa3ce7386a0da0a20701c
+size 498859189

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f10fd92599479d44b10e18639c72a5c6512e9977695f540858c90d4ad1eaa43
+size 4091