Training in progress, step 500

README.md

@@ -0,0 +1,56 @@
+---
+base_model: dccuchile/distilbert-base-spanish-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: distilbert-base-spanish-uncased
+  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. -->
+
+# distilbert-base-spanish-uncased
+
+This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3324
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.611         | 0.59  | 500  | 2.3444          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.3465805053710938,
+    "eval_runtime": 34.7916,
+    "eval_samples_per_second": 128.968,
+    "eval_steps_per_second": 8.077
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "vocab_size": 31002
+}

mlm_eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.3465805053710938,
+    "eval_runtime": 34.7916,
+    "eval_samples_per_second": 128.968,
+    "eval_steps_per_second": 8.077
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fd26286a495086c0d6cb8c7104d2a1fc60f0b85b24b00d46cac0ddb49db273
+size 269431248

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 2.3443617820739746,
+  "best_model_checkpoint": "output_dir/checkpoint-500",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 842,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.406175771971497e-05,
+      "loss": 3.5848,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.812351543942993e-05,
+      "loss": 3.0455,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.21852731591449e-05,
+      "loss": 2.8043,
+      "step": 300
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6247030878859858e-05,
+      "loss": 2.6995,
+      "step": 400
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.0308788598574824e-05,
+      "loss": 2.611,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 2.3443617820739746,
+      "eval_runtime": 34.7863,
+      "eval_samples_per_second": 128.988,
+      "eval_steps_per_second": 8.078,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4370546318289787e-05,
+      "loss": 2.5726,
+      "step": 600
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.432304038004752e-06,
+      "loss": 2.4666,
+      "step": 700
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.494061757719715e-06,
+      "loss": 2.4894,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "step": 842,
+      "total_flos": 1784293008629760.0,
+      "train_loss": 2.7663106034883693,
+      "train_runtime": 344.8745,
+      "train_samples_per_second": 39.029,
+      "train_steps_per_second": 2.441
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.3465805053710938,
+      "eval_runtime": 34.7916,
+      "eval_samples_per_second": 128.968,
+      "eval_steps_per_second": 8.077,
+      "step": 842
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.332395076751709,
+      "eval_runtime": 34.8727,
+      "eval_samples_per_second": 128.668,
+      "eval_steps_per_second": 8.058,
+      "step": 842
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 842,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1784293008629760.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59225db1c65a9be65684c3b77d42b385d846b72f805144559ebc2ff6f544ee6b
+size 4664