Training in progress, epoch 0

config.json

@@ -50,6 +50,8 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 8,
   "num_key_value_heads": 4,
+  "pad_token_id": 32000,
+  "problem_type": "single_label_classification",
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
@@ -57,5 +59,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf84eb494a091d824e06f1d2428b65d7fbfdd6350e3151da795a224c7bd171e3
-size 791224448
+oid sha256:528cf549b1b8c0012b407006375fc2f1c56d354e56e6b131ebe4049aad31d194
+size 791226496

runs/Apr15_15-44-33_94e4afc178d5/events.out.tfevents.1713195875.94e4afc178d5.63.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c53e4a24034e04a0b32560355a5c09940882cd338b868d2988bf6ca5e743d81
+size 6829

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c6b9cbe876c0093576e51f885a2239b578616f94d6e083139c0e3229d7299b
+oid sha256:7b19af2e80a9ba6829dae5fe23b91e5de59bc3dc224364dca91962f9f4daf3ef
 size 4920