End of training

README.md

@@ -1,69 +1,51 @@
 ---
-language:
-- es
 license: apache-2.0
+base_model: lucasbiagettia/gpt2-base-borges
 tags:
-- "borges"
-- "spanish"
-- "text-generation"
-datasets:
-- "borges_works"
-widget:
-- text: "El modelo del lenguaje GPT es capaz de"
-- text: "Las obras de Borges son una fuente rica de conocimiento y creatividad"
+- generated_from_trainer
+model-index:
+- name: gpt2-base-borges
+  results: []
 ---
 
-# GPT2-borges (gpt2-borges)
+<!-- 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. -->
 
+# gpt2-base-borges
 
-## Overview
-
-- **Architecture:** gpt2-base
-- **Language:** Spanish
-- **Task:** text-generation
-- **Data:** Borges Works
+This model is a fine-tuned version of [lucasbiagettia/gpt2-base-borges](https://huggingface.co/lucasbiagettia/gpt2-base-borges) on an unknown dataset.
 
 ## Model description
 
-**GPT2-borges** is a transformer-based model for the Spanish language. It is based on the PlanTL-GOB-ES/gpt2-base-bne model and has been pre-trained using a curated dataset consisting of the complete works of Jorge Luis Borges, a renowned Argentine writer.
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
 
-## Intended uses and limitations
-You can use the raw model for text generation or fine-tune it to a downstream task.
+More information needed
 
-## How to Use
-Here is how to use this model:
+## Training procedure
 
-You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:
+### Training hyperparameters
 
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-model_name = 'lucasbiagettia/gpt2-base-borges'
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
-```
+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
 
-```python
-input_text = "La arena me recuerda el profundo dolor de la nostalgia"
+### Training results
 
-input_ids = self.tokenizer.encode(input_text, return_tensors="pt")
-attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
-    
 
-generated_text = self.model.generate(
-            input_ids=input_ids,
-            attention_mask=attention_mask,
-            max_new_tokens = 100,
-            num_return_sequences=1,
-            no_repeat_ngram_size=6,
-            top_k=35,
-            top_p=0.95,
-            temperature=0.8,
-            pad_token_id=50256,
-            do_sample=True,
-)
-```
 
-## Training
-was trained with the following dataset:
+### Framework versions
 
-https://github.com/lucasbiagettia/borges_plain_text_dataset
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Tokenizers 0.15.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "PlanTL-GOB-ES/gpt2-base-bne",
+  "_name_or_path": "lucasbiagettia/gpt2-base-borges",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 50261
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f244f5a8ffc6e11a5ebe0d680c59ca8d435d58f104dcc4b3670a29dfd0f3538
+oid sha256:b4d99981215b97db1a60d20005d9a12065789bb1975ba13974181455d9755583
 size 496213632

runs/Mar22_23-58-05_9aca86da8fe2/events.out.tfevents.1711151885.9aca86da8fe2.5226.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7220a95965af40eba7a0dc2ddf8cd18b209d05bc7bbb3c08f988df10a024bb30
+size 5231

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53e1863a1a7f3da730f829d2615da843002d73c0cf1cc85d9cef2cadddaba10
+size 4856