Save best model. Best metric: val/loss:0.06462528556585312- epoch:0

README.md

@@ -82,7 +82,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 14831 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 7843 with parameters:
 ```
 {'batch_size': 14, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -94,16 +94,16 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 1,
+    "epochs": 5,
     "evaluation_steps": 0,
     "evaluator": "NoneType",
     "max_grad_norm": 1,
     "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
     "optimizer_params": {
-        "lr": 0.0005
+        "lr": 3e-05
     },
     "scheduler": "WarmupLinear",
-    "steps_per_epoch": 3,
+    "steps_per_epoch": null,
     "warmup_steps": 5000,
     "weight_decay": 0.0001
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
+  "_name_or_path": "D:\\Work\\Tasks\\mylong_ds/.cache\\quannguyenopus_tsdae-host\\",
   "architectures": [
     "BertModel"
   ],

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.2.2",
-    "transformers": "4.35.2",
-    "pytorch": "2.1.1+cpu"
+    "transformers": "4.31.0",
+    "pytorch": "2.0.1+cu118"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a913212af41cc25905701a4bd2b2c681aca9b48bf74221706ed8a4f04e4c8946
+oid sha256:dcccb6444c73d471ff3fc87a4c4f30481d4e9e8d143e27bb017e7ec0841d40e2
 size 90864192