Training in progress, epoch 1

config.json

@@ -37,6 +37,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3"

logs/events.out.tfevents.1740248557.372cc108f014.685.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de7013242e0565c78acf66864f7e0cfbeff07c8dd0ca00e91fa46b2b7bb5d3e
-size 88
+oid sha256:86e8231d5bb75a07f1a671fc261735ed0e58ab70b05f4c490092d101782e4dbd
+size 6192

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239b41f1d8afebfa2b4ca95d6b80ca863bf42551eca9f06db4e2a69c55203ddc
+oid sha256:046cf930344732d93e41a4317298633aabaa030fa7aa804dd17d99fc563675d0
 size 343242432

trainer_state.json

@@ -9,7 +9,7 @@
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 500,
-  "max_steps": 2500,
+  "max_steps": 1260,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
@@ -26,7 +26,7 @@
     }
   },
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null
 }