End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: thenlper/gte-large
+license: apache-2.0
+base_model: Alibaba-NLP/gte-base-en-v1.5
 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-large](https://huggingface.co/thenlper/gte-large) on an unknown dataset.
+This model is a fine-tuned version of [Alibaba-NLP/gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3536
-- Accuracy: 0.9107
+- Loss: 0.2915
+- Accuracy: 0.9375
 
 ## Model description
 
@@ -37,24 +37,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 9.5e-05
+- 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: 6
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 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   |
+| 1.0241        | 1.0   | 11   | 0.3903          | 0.8482   |
+| 0.2103        | 2.0   | 22   | 0.2814          | 0.8929   |
+| 0.0637        | 3.0   | 33   | 0.2157          | 0.9196   |
+| 0.023         | 4.0   | 44   | 0.2686          | 0.9375   |
+| 0.0147        | 5.0   | 55   | 0.3088          | 0.9286   |
+| 0.0091        | 6.0   | 66   | 0.2554          | 0.9375   |
+| 0.0055        | 7.0   | 77   | 0.2785          | 0.9464   |
+| 0.0054        | 8.0   | 88   | 0.2852          | 0.9464   |
+| 0.0033        | 9.0   | 99   | 0.2899          | 0.9375   |
+| 0.0034        | 10.0  | 110  | 0.2915          | 0.9375   |
 
 
 ### Framework versions

config.json

@@ -1,14 +1,22 @@
 {
-  "_name_or_path": "thenlper/gte-large",
+  "_name_or_path": "Alibaba-NLP/gte-base-en-v1.5",
   "architectures": [
-    "BertForSequenceClassification"
+    "NewForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -18,7 +26,7 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -28,16 +36,26 @@
     "LABEL_5": 5
   },
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "position_embedding_type": "rope",
   "problem_type": "single_label_classification",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 500000,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 30528
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906f698748c591ee0384de3a429b69e97858ed4fa9554310225bf6bf5b17e8a3
-size 1340639160
+oid sha256:c31e825e54b9bc4da41f2280d716d3286424790d8ccf226186bcdbc3e11665b1
+size 549500832

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 32768,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": {
     "strategy": "BatchLongest",
     "direction": "Right",

tokenizer_config.json

@@ -45,8 +45,8 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 128,
-  "model_max_length": 1000000000000000019884624838656,
+  "max_length": 512,
+  "model_max_length": 32768,
   "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:e525a6f2cf5abc222a232545bacf1ed1e5885b59ccb79591274719284777ff7a
+oid sha256:2395a8c853e5d942df02a2e4b72617394e866cff32ac8e120dd6945f715fc162
 size 4984