Model save

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: distilroberta-base
+tags:
+- generated_from_trainer
+datasets:
+- glue
+model-index:
+- name: platzi-distilroberta-base-mrpc-glue-eloi-campeny
+  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. -->
+
+# platzi-distilroberta-base-mrpc-glue-eloi-campeny
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue 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: 5e-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: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1
+- Datasets 2.14.5
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.8284313725490197,
+    "eval_f1": 0.8749999999999999,
+    "eval_loss": 0.3510310649871826,
+    "eval_runtime": 11.2647,
+    "eval_samples_per_second": 36.219,
+    "eval_steps_per_second": 4.527,
+    "total_flos": 68399748276336.0,
+    "train_loss": 0.5246236963209763,
+    "train_runtime": 477.4423,
+    "train_samples_per_second": 7.683,
+    "train_steps_per_second": 0.961
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": "1",
+    "not_equivalent": "0"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.8284313725490197,
+    "eval_f1": 0.8749999999999999,
+    "eval_loss": 0.3510310649871826,
+    "eval_runtime": 11.2647,
+    "eval_samples_per_second": 36.219,
+    "eval_steps_per_second": 4.527
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdda48fed80c326e8271a3623553429fe75e694d2470bca2a336f482033e7ae6
+size 328514033

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 68399748276336.0,
+    "train_loss": 0.5246236963209763,
+    "train_runtime": 477.4423,
+    "train_samples_per_second": 7.683,
+    "train_steps_per_second": 0.961
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b73f0c1667aecb90627941f6e83e68061273e921af9bc89cb0145447cb264d
+size 4155