End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: cc-by-nc-sa-4.0
-base_model: ufal/robeczech-base
+license: mit
+base_model: FacebookAI/xlm-roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # robeczech_lr3e-05_bs16_train287
 
-This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-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: 0.1742
-- Precision: 0.9465
-- Recall: 0.9588
-- F1: 0.9526
-- Accuracy: 0.9719
+- Loss: 0.1179
+- Precision: 0.9454
+- Recall: 0.9595
+- F1: 0.9524
+- Accuracy: 0.9714
 
 ## Model description
 
@@ -56,24 +56,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 18   | 1.2586          | 0.3462    | 0.0217 | 0.0409 | 0.5760   |
-| No log        | 2.0   | 36   | 0.8008          | 0.6946    | 0.6972 | 0.6959 | 0.8562   |
-| No log        | 3.0   | 54   | 0.5170          | 0.7920    | 0.7904 | 0.7912 | 0.9000   |
-| No log        | 4.0   | 72   | 0.3632          | 0.8889    | 0.8885 | 0.8887 | 0.9433   |
-| No log        | 5.0   | 90   | 0.3043          | 0.8967    | 0.8967 | 0.8967 | 0.9475   |
-| No log        | 6.0   | 108  | 0.2746          | 0.8952    | 0.8996 | 0.8974 | 0.9485   |
-| No log        | 7.0   | 126  | 0.2490          | 0.9023    | 0.9092 | 0.9057 | 0.9523   |
-| No log        | 8.0   | 144  | 0.2249          | 0.9252    | 0.9314 | 0.9283 | 0.9619   |
-| No log        | 9.0   | 162  | 0.2103          | 0.9333    | 0.9387 | 0.9360 | 0.9657   |
-| No log        | 10.0  | 180  | 0.2057          | 0.9408    | 0.9358 | 0.9383 | 0.9661   |
-| No log        | 11.0  | 198  | 0.1937          | 0.9439    | 0.9421 | 0.9430 | 0.9684   |
-| No log        | 12.0  | 216  | 0.1963          | 0.9342    | 0.9387 | 0.9364 | 0.9659   |
-| No log        | 13.0  | 234  | 0.1851          | 0.9458    | 0.9430 | 0.9444 | 0.9688   |
-| No log        | 14.0  | 252  | 0.1734          | 0.9447    | 0.9493 | 0.9470 | 0.9707   |
-| No log        | 15.0  | 270  | 0.1686          | 0.9457    | 0.9503 | 0.9480 | 0.9713   |
-| No log        | 16.0  | 288  | 0.1745          | 0.9446    | 0.9459 | 0.9452 | 0.9701   |
-| No log        | 17.0  | 306  | 0.1730          | 0.9429    | 0.9416 | 0.9423 | 0.9686   |
-| No log        | 18.0  | 324  | 0.1707          | 0.9464    | 0.9464 | 0.9464 | 0.9705   |
+| No log        | 1.0   | 18   | 1.1550          | 1.0       | 0.0005 | 0.0010 | 0.5668   |
+| No log        | 2.0   | 36   | 0.4725          | 0.7099    | 0.7006 | 0.7052 | 0.8587   |
+| No log        | 3.0   | 54   | 0.2293          | 0.8740    | 0.8643 | 0.8691 | 0.9351   |
+| No log        | 4.0   | 72   | 0.1474          | 0.9224    | 0.9126 | 0.9175 | 0.9565   |
+| No log        | 5.0   | 90   | 0.1210          | 0.9457    | 0.9411 | 0.9434 | 0.9697   |
+| No log        | 6.0   | 108  | 0.1212          | 0.9409    | 0.9382 | 0.9396 | 0.9674   |
+| No log        | 7.0   | 126  | 0.1067          | 0.9540    | 0.9517 | 0.9529 | 0.9740   |
+| No log        | 8.0   | 144  | 0.0918          | 0.9574    | 0.9551 | 0.9562 | 0.9753   |
+| No log        | 9.0   | 162  | 0.1076          | 0.9549    | 0.9517 | 0.9533 | 0.9749   |
+| No log        | 10.0  | 180  | 0.0990          | 0.9599    | 0.9585 | 0.9592 | 0.9774   |
+| No log        | 11.0  | 198  | 0.1027          | 0.9673    | 0.9570 | 0.9621 | 0.9778   |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,11 @@
 {
   "architectures": [
-    "RobertaForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -44,14 +43,15 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 51997
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47ecb94ac5f8b577d3abf55b982950e3e2270b3411866e47f71713d9ed65ed2
-size 501604780
+oid sha256:cd5ddaf56443ed926d9db9b29d05ebdda35b1bf1357bd511e563cadb5fee26de
+size 1109876260

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,51 +1,15 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
-    "content": "[MASK]",
+    "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -2,57 +2,55 @@
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "[CLS]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "[SEP]",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "[UNK]",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "51960": {
-      "content": "[MASK]",
+    "250001": {
+      "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "errors": "replace",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa54fc9fb5a9a5a7f829d6cacbc46e2e73172d1de3d627169e160018036e54a
+oid sha256:72dbaf1afa3d24118d9b081fe26e204945f7f39bdf265210b20a287337532e5b
 size 5368