End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: thenlper/gte-small
+base_model: thenlper/gte-large
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Classify-model-v1.2
 
-This model is a fine-tuned version of [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) on an unknown dataset.
+This model is a fine-tuned version of [thenlper/gte-large](https://huggingface.co/thenlper/gte-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5958
-- Accuracy: 0.8929
+- Loss: 0.3536
+- Accuracy: 0.9107
 
 ## Model description
 
@@ -43,20 +43,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7205        | 1.0   | 11   | 1.5983          | 0.5      |
-| 1.4503        | 2.0   | 22   | 1.2289          | 0.7321   |
-| 1.0877        | 3.0   | 33   | 0.9504          | 0.8393   |
-| 0.8143        | 4.0   | 44   | 0.7757          | 0.875    |
-| 0.6363        | 5.0   | 55   | 0.6700          | 0.8929   |
-| 0.5222        | 6.0   | 66   | 0.6382          | 0.8839   |
-| 0.4521        | 7.0   | 77   | 0.6073          | 0.8839   |
-| 0.4202        | 8.0   | 88   | 0.5958          | 0.8929   |
+| 1.3025        | 1.0   | 11   | 0.7724          | 0.7411   |
+| 0.5536        | 2.0   | 22   | 0.4194          | 0.9018   |
+| 0.2468        | 3.0   | 33   | 0.4068          | 0.875    |
+| 0.111         | 4.0   | 44   | 0.3455          | 0.8839   |
+| 0.0531        | 5.0   | 55   | 0.3453          | 0.8929   |
+| 0.0305        | 6.0   | 66   | 0.3536          | 0.9107   |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "thenlper/gte-small",
+  "_name_or_path": "thenlper/gte-large",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -17,7 +18,7 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -29,8 +30,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3d7025b3cd821365598d9f7f2903e4f1a0c9bc77fa26481535c3e2d0c2d9da
-size 133472536
+oid sha256:906f698748c591ee0384de3a429b69e97858ed4fa9554310225bf6bf5b17e8a3
+size 1340639160

tokenizer_config.json

@@ -43,12 +43,10 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "max_length": 128,
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
   "pad_token_type_id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1ff87648f960661294a0342d63abccab74c7f61f8f328831f14ad30ea61786
+oid sha256:e525a6f2cf5abc222a232545bacf1ed1e5885b59ccb79591274719284777ff7a
 size 4984