End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-cased
+base_model: jinaai/jina-embeddings-v2-base-en
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-Classification-news-or-informational-nft
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
+This model is a fine-tuned version of [jinaai/jina-embeddings-v2-base-en](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0004
-- Accuracy: 0.9999
+- Loss: 0.1132
+- Accuracy: 0.9798
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0756        | 1.0   | 999  | 0.0204          | 0.9945   |
-| 0.0174        | 2.0   | 1998 | 0.0041          | 0.9989   |
-| 0.005         | 3.0   | 2997 | 0.0004          | 0.9999   |
+| 0.4497        | 1.0   | 999  | 0.4424          | 0.9255   |
+| 0.342         | 2.0   | 1998 | 0.1567          | 0.9696   |
+| 0.1728        | 3.0   | 2997 | 0.1132          | 0.9798   |
 
 
 ### Framework versions

config.json

@@ -1,10 +1,18 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "jinaai/jina-embeddings-v2-base-en",
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
+    "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
+    "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
+    "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
+  },
   "classifier_dropout": null,
+  "emb_pooler": "mean",
+  "feed_forward_type": "geglu",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -20,16 +28,17 @@
     "news": 0
   },
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 8192,
+  "model_max_length": 8192,
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "position_embedding_type": "alibi",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30528
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c174996ac6fb160bd36bd5062cacdb0723dce859088d2519d694ed91d1b56a71
-size 433270768
+oid sha256:185b47db94bcf62019c65816fc035dc3f2144aa99328eeb2a347944c7a722316
+size 461570056

runs/Dec15_09-16-27_40f3a3b152a2/events.out.tfevents.1702631795.40f3a3b152a2.566.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b115bb1f20dd6e835fb9e204ff9c884e36c0bc032c1d8cb5c3f2e8c794553da0
+size 7079

runs/Dec15_09-16-27_40f3a3b152a2/events.out.tfevents.1702632111.40f3a3b152a2.566.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533ab3058c5a9d4b839c026d48385ab34b379849d03eb3e6dba216134c01e432
+size 411

tokenizer_config.json

@@ -43,9 +43,11 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 2147483648,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9448e3e1886006d64bd927ba49dd507a2e4d491ea9002b46daf530fe45cd3543
+oid sha256:fb6784340da4dac933880e889909342d6899de221b3c7952cf754df7d813c3d0
 size 4664