End of training

README.md

@@ -0,0 +1,60 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- text-classification
+- generated_from_trainer
+model-index:
+- name: nsfw-pt-br
+  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. -->
+
+# nsfw-pt-br
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6324
+
+## 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: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 9    | 0.6437          |
+| No log        | 2.0   | 18   | 0.6364          |
+| No log        | 3.0   | 27   | 0.6324          |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 56042654791680.0,
+    "train_loss": 0.6852263697871456,
+    "train_runtime": 23.2921,
+    "train_samples_per_second": 9.145,
+    "train_steps_per_second": 1.159
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ac30346dc23712f20f38e7be707468d9cca0327f000e7c317c4ea1318a9f5d
+size 1112205008

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 56042654791680.0,
+    "train_loss": 0.6852263697871456,
+    "train_runtime": 23.2921,
+    "train_samples_per_second": 9.145,
+    "train_steps_per_second": 1.159
+}

trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6436542272567749,
+      "eval_runtime": 0.5454,
+      "eval_samples_per_second": 33.001,
+      "eval_steps_per_second": 5.5,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6364022493362427,
+      "eval_runtime": 0.5564,
+      "eval_samples_per_second": 32.353,
+      "eval_steps_per_second": 5.392,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6323569416999817,
+      "eval_runtime": 0.56,
+      "eval_samples_per_second": 32.145,
+      "eval_steps_per_second": 5.357,
+      "step": 27
+    },
+    {
+      "epoch": 3.0,
+      "step": 27,
+      "total_flos": 56042654791680.0,
+      "train_loss": 0.6852263697871456,
+      "train_runtime": 23.2921,
+      "train_samples_per_second": 9.145,
+      "train_steps_per_second": 1.159
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 27,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 56042654791680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f00475ef398edc44de50ea120735a8c40c7d01a19053ead291a9de708985cf
+size 4984