End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: thenlper/gte-small
+base_model: thenlper/gte-base
 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-base](https://huggingface.co/thenlper/gte-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3781
-- Accuracy: 0.9189
+- Loss: 0.4658
+- Accuracy: 0.8571
 
 ## Model description
 
@@ -37,28 +37,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0001
 - train_batch_size: 128
 - eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4957        | 1.0   | 11   | 1.0003          | 0.8198   |
-| 0.7073        | 2.0   | 22   | 0.4647          | 0.9099   |
-| 0.3011        | 3.0   | 33   | 0.4240          | 0.8919   |
-| 0.1714        | 4.0   | 44   | 0.3864          | 0.9099   |
-| 0.1143        | 5.0   | 55   | 0.3695          | 0.9009   |
-| 0.0973        | 6.0   | 66   | 0.3944          | 0.9009   |
-| 0.0593        | 7.0   | 77   | 0.3459          | 0.9189   |
-| 0.048         | 8.0   | 88   | 0.3662          | 0.9189   |
-| 0.037         | 9.0   | 99   | 0.3752          | 0.9189   |
-| 0.0369        | 10.0  | 110  | 0.3781          | 0.9189   |
+| 1.5854        | 1.0   | 11   | 1.2455          | 0.5982   |
+| 1.0011        | 2.0   | 22   | 0.7630          | 0.7679   |
+| 0.5023        | 3.0   | 33   | 0.5095          | 0.8393   |
+| 0.2185        | 4.0   | 44   | 0.4658          | 0.8304   |
+| 0.0995        | 5.0   | 55   | 0.4605          | 0.8571   |
+| 0.0582        | 6.0   | 66   | 0.4858          | 0.8482   |
+| 0.0392        | 7.0   | 77   | 0.4658          | 0.8571   |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "thenlper/gte-small",
+  "_name_or_path": "thenlper/gte-base",
   "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": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -17,7 +18,7 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6762227f4f47e2a1e26a169d2698b9dd8744b186daaf32bbbeb2ce06ec5ea658
-size 133472536
+oid sha256:c100356729b3dd5fbdf87535b5dacc34ee10e089af7848831033001cd667ccf1
+size 437970952

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": {
     "strategy": "BatchLongest",
     "direction": "Right",

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,
+  "model_max_length": 512,
   "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 sha256:454e3f7206d13a396fb648efe068a5f565013658c3a6cf9b2fc08b1729338255
+oid sha256:8eda77e730b2be62b53ce3762284532f364bbc4600fa1b655399fcb7c70d9e0d
 size 4984