End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: khalidrajan/roberta-base_legal_ner_finetuned
+base_model: FacebookAI/roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta_crf_ner_finetuned
 
-This model is a fine-tuned version of [khalidrajan/roberta-base_legal_ner_finetuned](https://huggingface.co/khalidrajan/roberta-base_legal_ner_finetuned) on an unknown dataset.
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1013
-- Precision: 0.7334
-- Recall: 0.7484
-- F1: 0.7400
-- Accuracy: 0.9582
+- Loss: nan
+- Precision: 0.8044
+- Recall: 0.6309
+- F1: 0.7014
+- Accuracy: 0.8064
 
 ## Model description
 
@@ -43,21 +43,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 3.4124        | 1.0   | 340  | 14.5361         | 0.6441    | 0.7224 | 0.6809 | 0.9483   |
-| -8.6258       | 2.0   | 680  | 5.2745          | 0.7019    | 0.7273 | 0.7136 | 0.9521   |
-| -14.1587      | 3.0   | 1020 | 1.1013          | 0.7334    | 0.7484 | 0.7400 | 0.9582   |
+| 0.0           | 1.0   | 85   | nan             | 1.0       | 0.0    | 0.0    | 0.7707   |
+| 0.0           | 2.0   | 170  | nan             | 0.5105    | 0.1412 | 0.1284 | 0.8910   |
+| 0.0           | 3.0   | 255  | nan             | 0.3443    | 0.3458 | 0.3346 | 0.9210   |
+| 0.0           | 4.0   | 340  | nan             | 0.5898    | 0.5990 | 0.5930 | 0.9423   |
+| 0.0           | 5.0   | 425  | nan             | 0.5650    | 0.5795 | 0.5606 | 0.9421   |
+| 0.0           | 6.0   | 510  | nan             | 0.6261    | 0.6867 | 0.6515 | 0.9470   |
+| 0.0           | 7.0   | 595  | nan             | 0.6874    | 0.6640 | 0.6724 | 0.9457   |
+| 0.0           | 8.0   | 680  | nan             | 0.6825    | 0.7224 | 0.7011 | 0.9549   |
+| 0.0           | 9.0   | 765  | nan             | 0.6744    | 0.7224 | 0.6972 | 0.9551   |
+| 0.0           | 10.0  | 850  | nan             | 0.7020    | 0.7062 | 0.7035 | 0.9552   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a788f4bfe3474cb9f4a419ebd39379db3178804c7af84defc2654e9b55b593
+oid sha256:996c81c4c002120e76fa2fa5d95e9ddd639e6131735c934c7068ddeac5db1f20
 size 496273984

special_tokens_map.json

@@ -1,25 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -27,25 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "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

@@ -48,17 +48,10 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "max_length": 512,
   "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>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e11b25e30631dcd08f71a36b77175eec22d3cdda7626067fc008f376299c40a
-size 5112
+oid sha256:01eea6c2b72a7dbcae7fb6a6ce419fa6ffc52a1947e1038276d30adf795d5b12
+size 5176