Training in progress, epoch 1

config.json

@@ -67,6 +67,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 1,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3",

logs/events.out.tfevents.1740292328.11dab37db9f7.3604.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a817bc1dd10d1c3ccce95624e079e2f2521f849d672184c56dbe8088251e17a1
-size 88
+oid sha256:3375c9529f44eb77e95f553bdae5152421b6035b2fe7cec9b87a74e8b799e22b
+size 6780

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d1726d9f802a176ceb5b493892341feeaeee87859cf4f015e4c83d64c20e01
+oid sha256:a3f44859553a8baef5aca49491c7187ec191ef8235b7c8f0db05398f11f40170
 size 392799384

trainer_state.json

@@ -9,7 +9,7 @@
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 500,
-  "max_steps": 1875,
+  "max_steps": 3750,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 15,
   "save_steps": 500,
@@ -26,7 +26,7 @@
     }
   },
   "total_flos": 0,
-  "train_batch_size": 64,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }