Training in progress, step 500

README.md

@@ -11,10 +11,6 @@ metrics:
 model-index:
 - name: fine_tuned_XLMROBERTA_cs_wikann
   results: []
-datasets:
-- wikiann
-language:
-- cs
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine_tuned_XLMROBERTA_cs_wikann
 
-This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on a wikiann dataset for Czech language.
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1699
 - Precision: 0.9133
@@ -40,14 +36,7 @@ More information needed
 
 ## Training and evaluation data
 
-'eval_loss': 0.1738048791885376,
-'eval_precision': 0.8908104442183791,
-'eval_recall': 0.9106981903903487,
-'eval_f1': 0.9006445419637958,
-'eval_accuracy': 0.9643901766004415,
-'eval_runtime': 26.2581,
-'eval_samples_per_second': 380.835,
-'eval_steps_per_second': 23.802}
+More information needed
 
 ## Training procedure
 
@@ -108,4 +97,4 @@ The following hyperparameters were used during training:
 - Transformers 4.36.2
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0

config.json

@@ -3,12 +3,12 @@
   "architectures": [
     "XLMRobertaForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.25,
+  "attention_probs_dropout_prob": 0.15,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.25,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 1024,
   "id2label": {
     "0": "O",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20af9a751d436789cd853a066d0e655162130860d858cd5aa2687eaa450faa10
+oid sha256:45fa6139de32c58025d1edad89e64bc3f85d7d339bebdefc8d3f763c115f3d35
 size 2235440556

runs/Feb21_18-51-35_n21/events.out.tfevents.1708537975.n21.1435977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f19f001125933d1f09a5a4c9bd47308dc143d189abbe4fb7c0542a571feccac
+size 438

runs/Feb21_18-54-19_n21/events.out.tfevents.1708538090.n21.1435977.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951cf14a7cd6443b5217839b729288a5558aa9218fd9be3a61b21ec7a7b0160f
+size 438

runs/Feb21_19-04-07_n21/events.out.tfevents.1708538654.n21.1436555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317fc824035ceecdd26a03f7c9642c45f9a5e1ad0e12c01652a6069f22ab207a
+size 5307

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e574e12df1cdcfd0d6e69a9d957586918031255bcca01fc882275133086c168a
+oid sha256:e0dea11f66eda5e178ab2e3ad38c305b7ddaa16ed6dc2a763c15562a05fcb750
 size 4728