End of training

README.md

@@ -41,22 +41,27 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 10
+- num_epochs: 15
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.6943        | 1.0   | 3125  | 0.7023          |
-| 0.7018        | 2.0   | 6250  | 0.6934          |
-| 0.7085        | 3.0   | 9375  | 0.6960          |
-| 0.6999        | 4.0   | 12500 | 0.6943          |
-| 0.6859        | 5.0   | 15625 | 0.6941          |
-| 0.7064        | 6.0   | 18750 | 0.6932          |
-| 0.6947        | 7.0   | 21875 | 0.6931          |
-| 0.6862        | 8.0   | 25000 | 0.6939          |
-| 0.6946        | 9.0   | 28125 | 0.6959          |
-| 0.6973        | 10.0  | 31250 | 0.6932          |
+| 0.6884        | 1.0   | 3125  | 0.7034          |
+| 0.6953        | 2.0   | 6250  | 0.6931          |
+| 0.6901        | 3.0   | 9375  | 0.6980          |
+| 0.6982        | 4.0   | 12500 | 0.6935          |
+| 0.6963        | 5.0   | 15625 | 0.6935          |
+| 0.6904        | 6.0   | 18750 | 0.6932          |
+| 0.6876        | 7.0   | 21875 | 0.6932          |
+| 0.7063        | 8.0   | 25000 | 0.6933          |
+| 0.7211        | 9.0   | 28125 | 0.7049          |
+| 0.6967        | 10.0  | 31250 | 0.6933          |
+| 0.6903        | 11.0  | 34375 | 0.6932          |
+| 0.6945        | 12.0  | 37500 | 0.6945          |
+| 0.6899        | 13.0  | 40625 | 0.6932          |
+| 0.6883        | 14.0  | 43750 | 0.6936          |
+| 0.7075        | 15.0  | 46875 | 0.6931          |
 
 
 ### Framework versions

config.json

@@ -17,7 +17,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
+  "max_position_embeddings": 1024,
   "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,

logs/events.out.tfevents.1705577745.330c0a73200a.3251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f481a1c3200010af717984808817f47d8c2a61d1f124fc3273076294c0758910
+size 35770

logs/events.out.tfevents.1705578008.330c0a73200a.3251.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856310abcefa010681f51105824ccc66bed0cda9b0e5fb057a23731169a68168
+size 753743

logs/events.out.tfevents.1705584833.330c0a73200a.3251.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4339c88c300631955ad79235f5d5aa22d34e608740d3db39175bd27ea9d95cca
+size 316

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6ace2eaa95a44d1140197f15a5b7060c8726d1ecb16120c6a3b30e3e46abe0
-size 498612824
+oid sha256:1a422f3d271906f3969eda2898ce787ea5cb6ee23b811f4a70fe8b407c943509
+size 500179544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d97facbba4cce6a7070ca98500b8854d4cb96f2a5f0b086d76dcd3c0d41aa4
+oid sha256:f05926a59262c4d1866c2c2a016a60fb0f4e21486d1d7b05c99d57e639dced5a
 size 4600