Training in progress, step 100

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: PORTULAN/albertina-ptbr-base
+base_model: FacebookAI/xlm-roberta-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # e3_lr2e-05
 
-This model is a fine-tuned version of [PORTULAN/albertina-ptbr-base](https://huggingface.co/PORTULAN/albertina-ptbr-base) on an unknown dataset.
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9338
+- Loss: 1.6436
 
 ## Model description
 
@@ -49,39 +49,32 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.4061        | 0.1040 | 100  | 1.1920          |
-| 1.2553        | 0.2080 | 200  | 1.1209          |
-| 1.2102        | 0.3120 | 300  | 1.0971          |
-| 1.1773        | 0.4160 | 400  | 1.0738          |
-| 1.1432        | 0.5200 | 500  | 1.0481          |
-| 1.1302        | 0.6240 | 600  | 1.0320          |
-| 1.1153        | 0.7280 | 700  | 1.0243          |
-| 1.1057        | 0.8320 | 800  | 1.0107          |
-| 1.0976        | 0.9360 | 900  | 1.0002          |
-| 1.0889        | 1.0400 | 1000 | 0.9907          |
-| 1.0797        | 1.1440 | 1100 | 0.9836          |
-| 1.0633        | 1.2480 | 1200 | 0.9788          |
-| 1.0582        | 1.3521 | 1300 | 0.9761          |
-| 1.0578        | 1.4561 | 1400 | 0.9635          |
-| 1.0423        | 1.5601 | 1500 | 0.9601          |
-| 1.0411        | 1.6641 | 1600 | 0.9578          |
-| 1.0406        | 1.7681 | 1700 | 0.9527          |
-| 1.0436        | 1.8721 | 1800 | 0.9520          |
-| 1.0363        | 1.9761 | 1900 | 0.9443          |
-| 1.0274        | 2.0801 | 2000 | 0.9419          |
-| 1.03          | 2.1841 | 2100 | 0.9417          |
-| 1.0232        | 2.2881 | 2200 | 0.9392          |
-| 1.0237        | 2.3921 | 2300 | 0.9374          |
-| 1.0199        | 2.4961 | 2400 | 0.9354          |
-| 1.0095        | 2.6001 | 2500 | 0.9399          |
-| 1.0145        | 2.7041 | 2600 | 0.9343          |
-| 1.0179        | 2.8081 | 2700 | 0.9297          |
-| 1.0148        | 2.9121 | 2800 | 0.9328          |
+| 2.9961        | 0.1404 | 100  | 1.9416          |
+| 2.0472        | 0.2808 | 200  | 1.8589          |
+| 1.9766        | 0.4212 | 300  | 1.8095          |
+| 1.9319        | 0.5616 | 400  | 1.7736          |
+| 1.897         | 0.7021 | 500  | 1.7447          |
+| 1.8743        | 0.8425 | 600  | 1.7370          |
+| 1.86          | 0.9829 | 700  | 1.7156          |
+| 1.8431        | 1.1233 | 800  | 1.7071          |
+| 1.8217        | 1.2637 | 900  | 1.6939          |
+| 1.8212        | 1.4041 | 1000 | 1.6900          |
+| 1.8053        | 1.5445 | 1100 | 1.6774          |
+| 1.7899        | 1.6849 | 1200 | 1.6736          |
+| 1.799         | 1.8254 | 1300 | 1.6644          |
+| 1.7845        | 1.9658 | 1400 | 1.6559          |
+| 1.7704        | 2.1062 | 1500 | 1.6531          |
+| 1.776         | 2.2466 | 1600 | 1.6528          |
+| 1.773         | 2.3870 | 1700 | 1.6417          |
+| 1.7632        | 2.5274 | 1800 | 1.6452          |
+| 1.7451        | 2.6678 | 1900 | 1.6460          |
+| 1.7505        | 2.8088 | 2000 | 1.6455          |
+| 1.7602        | 2.9492 | 2100 | 1.6399          |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.20.0
+- Datasets 2.19.2
 - Tokenizers 0.19.1

config.json

@@ -1,32 +1,28 @@
 {
-  "_name_or_path": "PORTULAN/albertina-ptbr-base",
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
   "architectures": [
-    "DebertaForMaskedLM"
+    "XLMRobertaForMaskedLM"
   ],
   "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-07,
-  "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
-  "pos_att_type": [
-    "c2p",
-    "p2c"
-  ],
-  "position_biased_input": false,
-  "relative_attention": true,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 0,
-  "vocab_size": 50265
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a85a6a8b3af6395d11c94e5f6e370c8e87f7ef519f178ecd69693f7dc3f72c
-size 557000804
+oid sha256:ec0c1da0e2c253a93f182aa3b1f765b438375de7a550b7d6156b9bb8eeaae8d5
+size 1113205088

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6625608206e0211e37aea30e8795c5d9ac17a3078892d73782e5c65f5ae941b0
+oid sha256:8176ab32e064b0b381bdbb0bd9a1484f61332adc97cc10eed787cd57ad090710
 size 5240