Model save

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: distilroberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: platzi-distilroberta-base-mrpc-wgcv
+  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-wgcv
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown 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: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8357843137254902,
+    "eval_f1": 0.8846815834767642,
+    "eval_loss": 0.4053478538990021,
+    "eval_runtime": 35.0691,
+    "eval_samples_per_second": 11.634,
+    "eval_steps_per_second": 0.371,
+    "total_flos": 235624315556256.0,
+    "train_loss": 0.4036261074784873,
+    "train_runtime": 3078.6117,
+    "train_samples_per_second": 3.574,
+    "train_steps_per_second": 0.112
+}

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": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8357843137254902,
+    "eval_f1": 0.8846815834767642,
+    "eval_loss": 0.4053478538990021,
+    "eval_runtime": 35.0691,
+    "eval_samples_per_second": 11.634,
+    "eval_steps_per_second": 0.371
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e64d15791a5ec0ecf2047582eb431b4417116d83dbbf53badb537793caf5062
+size 328492280

runs/Jun23_16-21-02_44df2b91e38b/events.out.tfevents.1719161052.44df2b91e38b.17693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeebcb45289f38cfc143f8a91e37653aeb59da91e8a0778046bf869608909871
+size 10453

runs/Jun23_16-21-02_44df2b91e38b/events.out.tfevents.1719164314.44df2b91e38b.17693.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4459f04c13d236012100afbba6322f404b6fb1db2f6382a0dc8b04a5d07038bc
+size 457

runs/Jun23_17-41-51_44df2b91e38b/events.out.tfevents.1719164518.44df2b91e38b.17693.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417ed7d510c3d6f0b2be6912b7a22d1f134bdc259822a3a4fe6c452827d1a155
+size 5159

runs/Jun23_18-09-08_44df2b91e38b/events.out.tfevents.1719166180.44df2b91e38b.42802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be6e9eb79c5f90611eac87ce9c9b85e18207683feb63b8e2780c5267394ddc1
+size 5416

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 +1,57 @@
+{
+  "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
+    }
+  },
+  "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": 3.0,
+    "total_flos": 235624315556256.0,
+    "train_loss": 0.4036261074784873,
+    "train_runtime": 3078.6117,
+    "train_samples_per_second": 3.574,
+    "train_steps_per_second": 0.112
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 345,
+      "total_flos": 235624315556256.0,
+      "train_loss": 0.4036261074784873,
+      "train_runtime": 3078.6117,
+      "train_samples_per_second": 3.574,
+      "train_steps_per_second": 0.112
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 235624315556256.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2678b0b2a7858fe6fce6b30ea70025bc57101350333fb4a79e355e060dc860b1
+size 5176