Training complete

README.md

@@ -1,8 +1,8 @@
 ---
 library_name: transformers
-license: mit
-base_model: SamLowe/roberta-base-go_emotions
+base_model: mrm8488/electricidad-base-discriminator
 tags:
+- classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clasificador-tweets
 
-This model is a fine-tuned version of [SamLowe/roberta-base-go_emotions](https://huggingface.co/SamLowe/roberta-base-go_emotions) on an unknown dataset.
+This model is a fine-tuned version of [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6660
-- Accuracy: 0.3830
+- Loss: 1.1770
+- Accuracy: 0.7021
 
 ## Model description
 
@@ -44,16 +44,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 23   | 1.7741          | 0.3404   |
-| No log        | 2.0   | 46   | 1.7247          | 0.3404   |
-| No log        | 3.0   | 69   | 1.6892          | 0.3830   |
-| No log        | 4.0   | 92   | 1.6660          | 0.3830   |
+| No log        | 1.0   | 23   | 1.7530          | 0.3404   |
+| No log        | 2.0   | 46   | 1.4882          | 0.5319   |
+| No log        | 3.0   | 69   | 1.3349          | 0.5745   |
+| No log        | 4.0   | 92   | 1.1940          | 0.6596   |
+| No log        | 5.0   | 115  | 1.1773          | 0.6383   |
+| No log        | 6.0   | 138  | 1.1364          | 0.6383   |
+| No log        | 7.0   | 161  | 1.1633          | 0.6596   |
+| No log        | 8.0   | 184  | 1.1439          | 0.6809   |
+| No log        | 9.0   | 207  | 1.1955          | 0.6170   |
+| No log        | 10.0  | 230  | 1.1770          | 0.7021   |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "SamLowe/roberta-base-go_emotions",
+  "_name_or_path": "mrm8488/electricidad-base-discriminator",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "ElectraForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "embedding_size": 768,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -32,17 +31,21 @@
     "LABEL_6": 6,
     "LABEL_7": 7
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 31002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a0ef4312d1d9419ed6697d3ca2a7ab1397835a9cf6e085eb8e5fbd103615668
-size 498631280
+oid sha256:99812a37d099dce5aecdbdd42420a36dbaf5b60b15b6151014f526e5a491a28b
+size 439452264

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,8 +1,7 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,56 +9,50 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "4": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
-  "max_length": 128,
-  "model_max_length": 512,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
-  "stride": 0,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada6e21c566c01d1b9cbf86722cceddad350117b43a76b0d140f60d1977d550b
+oid sha256:f4f7bb3fd21fcf61c2bd4f5fb8f968ff0ad241abd6a5ad76e82d5ebabb8b7fd3
 size 5304