End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: thenlper/gte-base
+base_model: thenlper/gte-small
 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-base](https://huggingface.co/thenlper/gte-base) on an unknown dataset.
+This model is a fine-tuned version of [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4658
-- Accuracy: 0.8571
+- Loss: 0.5391
+- Accuracy: 0.8661
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0002
 - train_batch_size: 128
 - eval_batch_size: 128
 - seed: 42
@@ -49,13 +49,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 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   |
+| 1.6187        | 1.0   | 11   | 1.2743          | 0.6875   |
+| 1.0031        | 2.0   | 22   | 0.8051          | 0.8482   |
+| 0.5518        | 3.0   | 33   | 0.5952          | 0.8661   |
+| 0.3103        | 4.0   | 44   | 0.5251          | 0.8571   |
+| 0.2119        | 5.0   | 55   | 0.5139          | 0.8661   |
+| 0.162         | 6.0   | 66   | 0.5225          | 0.8661   |
+| 0.1419        | 7.0   | 77   | 0.5391          | 0.8661   |
 
 
 ### Framework versions

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "thenlper/gte-base",
+  "_name_or_path": "thenlper/gte-small",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -18,7 +17,7 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c100356729b3dd5fbdf87535b5dacc34ee10e089af7848831033001cd667ccf1
-size 437970952
+oid sha256:6f52ed949fb35f8e9be63cf7349148bc52ed82c95a01a3be1f82448e34a5cece
+size 133472536

tokenizer.json

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

tokenizer_config.json

@@ -43,10 +43,12 @@
   },
   "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": 512,
+  "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 sha256:8eda77e730b2be62b53ce3762284532f364bbc4600fa1b655399fcb7c70d9e0d
+oid sha256:0d7dd1077417b948707a37f9fa3297bf4fa29ec5b1ea08dc6d0b1b5372c48855
 size 4984