End of training

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: BSC-LT/roberta-base-biomedical-clinical-es
+tags:
+- generated_from_trainer
+model-index:
+- name: final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds
+  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. -->
+
+# final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds
+
+This model is a fine-tuned version of [BSC-LT/roberta-base-biomedical-clinical-es](https://huggingface.co/BSC-LT/roberta-base-biomedical-clinical-es) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5971
+
+## 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: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| No log        | 0.9978  | 229  | 0.9388          |
+| No log        | 2.0     | 459  | 0.8139          |
+| No log        | 2.9978  | 688  | 0.7544          |
+| 0.9622        | 4.0     | 918  | 0.7302          |
+| 0.9622        | 4.9978  | 1147 | 0.6878          |
+| 0.9622        | 6.0     | 1377 | 0.6754          |
+| 0.9622        | 6.9978  | 1606 | 0.6625          |
+| 0.715         | 8.0     | 1836 | 0.6431          |
+| 0.715         | 8.9978  | 2065 | 0.6278          |
+| 0.715         | 10.0    | 2295 | 0.6361          |
+| 0.715         | 10.9978 | 2524 | 0.6296          |
+| 0.6597        | 12.0    | 2754 | 0.6164          |
+| 0.6597        | 12.9978 | 2983 | 0.6117          |
+| 0.6597        | 14.0    | 3213 | 0.6052          |
+| 0.6597        | 14.9978 | 3442 | 0.6064          |
+| 0.6354        | 16.0    | 3672 | 0.6225          |
+| 0.6354        | 16.9978 | 3901 | 0.5974          |
+| 0.6354        | 18.0    | 4131 | 0.6010          |
+| 0.6354        | 18.9978 | 4360 | 0.5816          |
+| 0.6354        | 19.9564 | 4580 | 0.5971          |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BSC-LT/roberta-base-biomedical-clinical-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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-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": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931fd63aa4075de1074731a96c2bb5e39ab008800dddc0d1a5bc429f6184fa0c
+size 504150808

runs/Apr30_11-33-29_a3c05c6d56c0/events.out.tfevents.1714476822.a3c05c6d56c0.405.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbeb3a84c4be8fa23ad48c2e034432fa9ed1dc1c496e98de1e8e2a1eab426b32
+size 4393

runs/Apr30_11-34-46_a3c05c6d56c0/events.out.tfevents.1714476904.a3c05c6d56c0.405.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095195184415edeb8df18cb4b2cc2911f87a418ea4bf028880cac165fb9148ab
+size 4393

runs/Apr30_11-37-22_a3c05c6d56c0/events.out.tfevents.1714477055.a3c05c6d56c0.2619.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3484c972948c882030ea28bc3095ffdeb405845de979a801408b55277d15c0
+size 11731

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "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
+    },
+    "51999": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 sha256:68749c7be56154cd1de880fad20d313149164c3ca6cba4053b880d78fbe0261b
+size 5112