Upload folder using huggingface_hub

checkpoint-4098/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799e436ba9dae406587780e581adc068c714652b56e1cf47c479634c697a8111
+oid sha256:7584bee441a46ff02eaabaf77128796f7ce04506a497a42af795348c96b05551
 size 343368556

checkpoint-4098/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596e3fbc6266f3d044c381838444742f8585677383ebb9f0c0f36053a1f41bf0
+oid sha256:6506a7b9414316ab905d68d8fbc10617fc0981edf7ef6c2eb3ecc5f01eea5680
 size 686857605

checkpoint-4098/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 3.0359206199645996,
+  "best_metric": 2.96836519241333,
   "best_model_checkpoint": "military_aircraft_image_detection/checkpoint-4098",
   "epoch": 6.0,
   "eval_steps": 500,
@@ -10,112 +10,112 @@
   "log_history": [
     {
       "epoch": 0.7320644216691069,
-      "grad_norm": 1.6647233963012695,
+      "grad_norm": 1.73904550075531,
       "learning_rate": 1.7776679841897234e-07,
-      "loss": 2.9861,
+      "loss": 2.9196,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5055658627087198,
-      "eval_loss": 3.063667058944702,
-      "eval_runtime": 424.0571,
-      "eval_samples_per_second": 68.637,
-      "eval_steps_per_second": 2.146,
+      "eval_accuracy": 0.5273139558853844,
+      "eval_loss": 2.9956250190734863,
+      "eval_runtime": 433.4755,
+      "eval_samples_per_second": 67.146,
+      "eval_steps_per_second": 2.099,
       "step": 683
     },
     {
       "epoch": 1.4641288433382138,
-      "grad_norm": 1.5988911390304565,
+      "grad_norm": 1.7973357439041138,
       "learning_rate": 1.5306324110671935e-07,
-      "loss": 2.9774,
+      "loss": 2.9104,
       "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5072150072150072,
-      "eval_loss": 3.0537939071655273,
-      "eval_runtime": 426.3521,
-      "eval_samples_per_second": 68.268,
-      "eval_steps_per_second": 2.134,
+      "eval_accuracy": 0.5284477427334571,
+      "eval_loss": 2.985973596572876,
+      "eval_runtime": 429.4589,
+      "eval_samples_per_second": 67.774,
+      "eval_steps_per_second": 2.119,
       "step": 1366
     },
     {
       "epoch": 2.1961932650073206,
-      "grad_norm": 1.980846643447876,
+      "grad_norm": 1.7381324768066406,
       "learning_rate": 1.283596837944664e-07,
-      "loss": 2.9709,
+      "loss": 2.9038,
       "step": 1500
     },
     {
       "epoch": 2.9282576866764276,
-      "grad_norm": 1.8870298862457275,
+      "grad_norm": 1.8419060707092285,
       "learning_rate": 1.0365612648221343e-07,
-      "loss": 2.9632,
+      "loss": 2.8969,
       "step": 2000
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5092420806706521,
-      "eval_loss": 3.046130895614624,
-      "eval_runtime": 420.1974,
-      "eval_samples_per_second": 69.267,
-      "eval_steps_per_second": 2.166,
+      "eval_accuracy": 0.5296158867587439,
+      "eval_loss": 2.9781196117401123,
+      "eval_runtime": 416.4739,
+      "eval_samples_per_second": 69.887,
+      "eval_steps_per_second": 2.185,
       "step": 2049
     },
     {
       "epoch": 3.660322108345534,
-      "grad_norm": 1.7387105226516724,
+      "grad_norm": 1.8417006731033325,
       "learning_rate": 7.895256916996047e-08,
-      "loss": 2.9561,
+      "loss": 2.8889,
       "step": 2500
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5113035113035113,
-      "eval_loss": 3.040210485458374,
-      "eval_runtime": 421.3061,
-      "eval_samples_per_second": 69.085,
-      "eval_steps_per_second": 2.16,
+      "eval_accuracy": 0.5304061018346733,
+      "eval_loss": 2.972407341003418,
+      "eval_runtime": 417.0986,
+      "eval_samples_per_second": 69.782,
+      "eval_steps_per_second": 2.182,
       "step": 2732
     },
     {
       "epoch": 4.392386530014641,
-      "grad_norm": 1.7102471590042114,
+      "grad_norm": 2.0208425521850586,
       "learning_rate": 5.4249011857707506e-08,
-      "loss": 2.9553,
+      "loss": 2.8874,
       "step": 3000
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5126090840376555,
-      "eval_loss": 3.0369255542755127,
-      "eval_runtime": 421.777,
-      "eval_samples_per_second": 69.008,
-      "eval_steps_per_second": 2.158,
+      "eval_accuracy": 0.5309901738473167,
+      "eval_loss": 2.969489097595215,
+      "eval_runtime": 410.5775,
+      "eval_samples_per_second": 70.89,
+      "eval_steps_per_second": 2.216,
       "step": 3415
     },
     {
       "epoch": 5.124450951683748,
-      "grad_norm": 1.660888910293579,
+      "grad_norm": 2.0944771766662598,
       "learning_rate": 2.9545454545454546e-08,
-      "loss": 2.9493,
+      "loss": 2.8839,
       "step": 3500
     },
     {
       "epoch": 5.856515373352855,
-      "grad_norm": 1.8840000629425049,
+      "grad_norm": 2.000408172607422,
       "learning_rate": 4.8418972332015805e-09,
-      "loss": 2.9496,
+      "loss": 2.8841,
       "step": 4000
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5126777983920842,
-      "eval_loss": 3.0359206199645996,
-      "eval_runtime": 430.3036,
-      "eval_samples_per_second": 67.641,
-      "eval_steps_per_second": 2.115,
+      "eval_accuracy": 0.5313337456194599,
+      "eval_loss": 2.96836519241333,
+      "eval_runtime": 417.3097,
+      "eval_samples_per_second": 69.747,
+      "eval_steps_per_second": 2.181,
       "step": 4098
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923fc237a7178ad4f3cd707c2dc8fe102bafc4d70fff52937323240528eb0193
+oid sha256:7584bee441a46ff02eaabaf77128796f7ce04506a497a42af795348c96b05551
 size 343368556

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3c1aac80e6fe46ec431fce06da55507d3c3019a55448e3210fba2cc3f10ce0
+oid sha256:dd420b36012d3de1b843696fecff72de7b75f1e32a6360e988cfe1bc3561f0f6
 size 4603