End of training

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
-- F1: 0.0176
+- F1: 0.0021
 
 ## Model description
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 29   | nan             | 0.0176 |
-| No log        | 2.0   | 58   | nan             | 0.0176 |
-| No log        | 3.0   | 87   | nan             | 0.0176 |
-| 0.0           | 4.0   | 116  | nan             | 0.0176 |
-| 0.0           | 5.0   | 145  | nan             | 0.0176 |
+| No log        | 1.0   | 29   | nan             | 0.0021 |
+| No log        | 2.0   | 58   | nan             | 0.0021 |
+| No log        | 3.0   | 87   | nan             | 0.0021 |
+| 0.0           | 4.0   | 116  | nan             | 0.0021 |
+| 0.0           | 5.0   | 145  | nan             | 0.0021 |
 
 
 ### Framework versions

runs/Jun06_19-54-48_5aefe4f9a840/events.out.tfevents.1749239689.5aefe4f9a840.5036.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef1ed808175acccca612e46d4d41b1c61b982d360a82c5513d029a905d40aeb
-size 8999
+oid sha256:1c571d5d047991772aa4ed107b8794ae97fed060f2eebaea479a592cef6c589d
+size 9353

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 8192,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50283,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -933,20 +933,13 @@
   "cls_token": "[CLS]",
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 512,
-  "pad_to_multiple_of": null,
+  "model_max_length": 8192,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }