End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: PlanTL-GOB-ES/roberta-base-bne
 tags:
 - generated_from_trainer
-base_model: PlanTL-GOB-ES/roberta-base-bne
 model-index:
 - name: ClasificadorV5
   results: []
@@ -15,16 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.0302
-- eval_accuracy: 0.5838
-- eval_off_by_one_accuracy: 0.9506
-- eval_f1: 0.5853
-- eval_recall: 0.5838
-- eval_runtime: 14.4621
-- eval_samples_per_second: 345.732
-- eval_steps_per_second: 13.829
-- epoch: 2.2917
-- step: 11000
+- eval_loss: 1.0128
+- eval_accuracy: 0.5798
+- eval_off_by_one_accuracy: 0.9462
+- eval_f1: 0.5792
+- eval_recall: 0.5798
+- eval_runtime: 17.5917
+- eval_samples_per_second: 284.225
+- eval_steps_per_second: 14.211
+- epoch: 2.1333
+- step: 8000
 
 ## Model description
 
@@ -44,13 +44,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 25
-- eval_batch_size: 25
+- train_batch_size: 20
+- eval_batch_size: 20
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 40
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Framework versions

best_model/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.6,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.6,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

best_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f17dd4c4837fabcb9c266b52723e15a9f333717c5bca9ca904000eb02fab4b
+size 498612836

best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfa0cb7058bd945c678652a3c51d5569c9c3a6c0c16dc96f45fa3ee1ce0e4ac
+size 4920

config.json

@@ -3,13 +3,13 @@
   "architectures": [
     "RobertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.55,
+  "attention_probs_dropout_prob": 0.6,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.55,
+  "hidden_dropout_prob": 0.6,
   "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ef098f8a4e1566dc47cd2c21ccebc64afbb8fbce15309372420d3861897c1d
+oid sha256:78f17dd4c4837fabcb9c266b52723e15a9f333717c5bca9ca904000eb02fab4b
 size 498612836

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cd9f48994e9abe6931a303bf52e7e8a0f898889cce8f11a91ab7480ff24afd
+oid sha256:ebfa0cb7058bd945c678652a3c51d5569c9c3a6c0c16dc96f45fa3ee1ce0e4ac
 size 4920