End of training

README.md

@@ -33,7 +33,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

config.json

@@ -31,14 +31,16 @@
   "giou_loss_coefficient": 2,
   "id2label": {
     "0": "ZS",
-    "1": "ZNR"
+    "1": "ZNR",
+    "2": "ZST"
   },
   "init_std": 0.02,
   "init_xavier_std": 1.0,
   "is_encoder_decoder": true,
   "label2id": {
     "ZNR": 1,
-    "ZS": 0
+    "ZS": 0,
+    "ZST": 2
   },
   "mask_loss_coefficient": 1,
   "max_position_embeddings": 1024,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b03ee7b0f69ebbe018e444621b0883c69ca25af1b61c1aec80f11317b5edc5
-size 166495852
+oid sha256:acc6b5b808f7dac3c91377192547812d495d889fd68b8c7964e4bc18025c2d84
+size 166496880

runs/Apr19_13-40-55_3fde7a3b96f6/events.out.tfevents.1713534056.3fde7a3b96f6.31743.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de258c609d1247c6264369e986691c707d762ad07da03b8201e6f6de2ecaefd1
+size 5304

runs/Apr19_13-41-24_3fde7a3b96f6/events.out.tfevents.1713534084.3fde7a3b96f6.31743.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f05326fa70287c051b34698dd5e8426dcb8de9c20d2817c0da0942550549676
+size 5304

runs/Apr19_13-42-21_3fde7a3b96f6/events.out.tfevents.1713534141.3fde7a3b96f6.31743.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f479e14f9065c012cd446ce70a5feafeca15b5fabbd5f723803626d3f0b796e
+size 6066

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7936be6348841c6c1104f2c4edffd95495b717682f345c117b54985894d9b3e1
+oid sha256:6c72f803fd4d8314c946715f13f07fd1c72b28728106d3d094153545d3528dd5
 size 4984