End of training

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: PlanTL-GOB-ES/roberta-base-bne
+tags:
+- generated_from_trainer
+model-index:
+- name: final-ft__roberta-base-bne__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-bne__70k-ultrasounds
+
+This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6164
+
+## 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        | 1.0   | 259  | 1.1165          |
+| No log        | 2.0   | 518  | 0.9244          |
+| No log        | 3.0   | 777  | 0.8153          |
+| 1.0516        | 4.0   | 1036 | 0.7842          |
+| 1.0516        | 5.0   | 1295 | 0.7262          |
+| 1.0516        | 6.0   | 1554 | 0.7235          |
+| 1.0516        | 7.0   | 1813 | 0.6960          |
+| 0.7109        | 8.0   | 2072 | 0.6787          |
+| 0.7109        | 9.0   | 2331 | 0.6799          |
+| 0.7109        | 10.0  | 2590 | 0.6718          |
+| 0.7109        | 11.0  | 2849 | 0.6488          |
+| 0.6385        | 12.0  | 3108 | 0.6426          |
+| 0.6385        | 13.0  | 3367 | 0.6415          |
+| 0.6385        | 14.0  | 3626 | 0.6232          |
+| 0.6385        | 15.0  | 3885 | 0.6329          |
+| 0.6042        | 16.0  | 4144 | 0.6036          |
+| 0.6042        | 17.0  | 4403 | 0.6161          |
+| 0.6042        | 18.0  | 4662 | 0.6193          |
+| 0.6042        | 19.0  | 4921 | 0.6183          |
+| 0.587         | 20.0  | 5180 | 0.6164          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a107edf334f60ddad70819a280d03cdf7ec5cfb6e639dfbf4aaeb72639c21f2
+size 498804720

runs/May01_21-30-51_1b7546e8806d/events.out.tfevents.1714599353.1b7546e8806d.178.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd53f1f9296062c23eb3be96612e6ea7fdc3c45420a39c6281916d2109f8458
+size 11874

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
+    },
+    "4": {
+      "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:c075a818ccc51cdb2895c19760b4624597e1de1cba4d4dda2ae639f83c79ebd2
+size 5048