Upload folder using huggingface_hub

checkpoint-4750/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2dce075dc8264926d97f5097da9e00d11a29e94ef6d0334c7260e8dc847df2
+oid sha256:a25a9f61b85f1c98057f82fd04d48bdb056c895ceb4e94d314e17db1b3a3895b
 size 343362404

checkpoint-4750/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac71543e83afeb748bfe7468d001fc70ecada9468adc3042377dfe825a041cb
+oid sha256:628919a91b142995813a1e27e2c088f17fb70e33bde885df437426d767f4b688
 size 686845626

checkpoint-4750/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 2.9626526832580566,
+  "best_metric": 2.0490753650665283,
   "best_model_checkpoint": "house-plant-image-detection/checkpoint-4750",
   "epoch": 10.0,
   "eval_steps": 500,
@@ -10,165 +10,165 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7829090191434774,
-      "eval_loss": 3.274250030517578,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 431.1188,
-      "eval_samples_per_second": 23.506,
-      "eval_steps_per_second": 2.939,
+      "eval_accuracy": 0.8897769883560293,
+      "eval_loss": 2.259671688079834,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 442.047,
+      "eval_samples_per_second": 22.925,
+      "eval_steps_per_second": 2.866,
       "step": 475
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 1.5620105266571045,
+      "grad_norm": 2.0764782428741455,
       "learning_rate": 6.329787234042553e-07,
-      "loss": 3.2644,
+      "loss": 2.2248,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8028419182948491,
-      "eval_loss": 3.2079219818115234,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 429.2124,
-      "eval_samples_per_second": 23.611,
-      "eval_steps_per_second": 2.952,
+      "eval_accuracy": 0.8926386421945924,
+      "eval_loss": 2.2142693996429443,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 434.2278,
+      "eval_samples_per_second": 23.338,
+      "eval_steps_per_second": 2.918,
       "step": 950
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 1.4659667015075684,
+      "grad_norm": 2.076075553894043,
       "learning_rate": 5.585106382978723e-07,
-      "loss": 3.1878,
+      "loss": 2.1717,
       "step": 1000
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8171501874876653,
-      "eval_loss": 3.1499454975128174,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 428.1214,
-      "eval_samples_per_second": 23.671,
-      "eval_steps_per_second": 2.959,
+      "eval_accuracy": 0.8944148411288732,
+      "eval_loss": 2.1735944747924805,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 425.2796,
+      "eval_samples_per_second": 23.829,
+      "eval_steps_per_second": 2.979,
       "step": 1425
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 1.603775143623352,
+      "grad_norm": 2.188196897506714,
       "learning_rate": 4.840425531914894e-07,
-      "loss": 3.118,
+      "loss": 2.1256,
       "step": 1500
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8248470495362147,
-      "eval_loss": 3.099377393722534,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 426.1632,
-      "eval_samples_per_second": 23.78,
-      "eval_steps_per_second": 2.973,
+      "eval_accuracy": 0.8951055851588712,
+      "eval_loss": 2.139596700668335,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 430.0565,
+      "eval_samples_per_second": 23.564,
+      "eval_steps_per_second": 2.946,
       "step": 1900
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 1.6411057710647583,
+      "grad_norm": 2.10166335105896,
       "learning_rate": 4.0957446808510637e-07,
-      "loss": 3.0627,
+      "loss": 2.0849,
       "step": 2000
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8316558121176238,
-      "eval_loss": 3.0566673278808594,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 429.8749,
-      "eval_samples_per_second": 23.574,
-      "eval_steps_per_second": 2.947,
+      "eval_accuracy": 0.8973751726860075,
+      "eval_loss": 2.1117050647735596,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 427.448,
+      "eval_samples_per_second": 23.708,
+      "eval_steps_per_second": 2.964,
       "step": 2375
     },
     {
       "epoch": 5.2631578947368425,
-      "grad_norm": 1.6472663879394531,
+      "grad_norm": 2.0126123428344727,
       "learning_rate": 3.3510638297872343e-07,
-      "loss": 3.0104,
+      "loss": 2.0596,
       "step": 2500
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.835800276297612,
-      "eval_loss": 3.0226495265960693,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 433.9596,
-      "eval_samples_per_second": 23.352,
-      "eval_steps_per_second": 2.92,
+      "eval_accuracy": 0.8980659167160056,
+      "eval_loss": 2.088592052459717,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 422.9606,
+      "eval_samples_per_second": 23.96,
+      "eval_steps_per_second": 2.996,
       "step": 2850
     },
     {
       "epoch": 6.315789473684211,
-      "grad_norm": 1.7341008186340332,
+      "grad_norm": 1.966229796409607,
       "learning_rate": 2.606382978723404e-07,
-      "loss": 2.9695,
+      "loss": 2.0257,
       "step": 3000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.8404381290704559,
-      "eval_loss": 2.9962480068206787,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 432.5356,
-      "eval_samples_per_second": 23.429,
-      "eval_steps_per_second": 2.929,
+      "eval_accuracy": 0.8985593053088613,
+      "eval_loss": 2.071624517440796,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 428.9505,
+      "eval_samples_per_second": 23.625,
+      "eval_steps_per_second": 2.954,
       "step": 3325
     },
     {
       "epoch": 7.368421052631579,
-      "grad_norm": 1.8458765745162964,
+      "grad_norm": 2.1821231842041016,
       "learning_rate": 1.8617021276595742e-07,
-      "loss": 2.9413,
+      "loss": 2.0068,
       "step": 3500
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8428063943161634,
-      "eval_loss": 2.9772186279296875,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 425.4068,
-      "eval_samples_per_second": 23.822,
-      "eval_steps_per_second": 2.978,
+      "eval_accuracy": 0.8995460824945727,
+      "eval_loss": 2.0589468479156494,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 430.3389,
+      "eval_samples_per_second": 23.549,
+      "eval_steps_per_second": 2.944,
       "step": 3800
     },
     {
       "epoch": 8.421052631578947,
-      "grad_norm": 1.627718448638916,
+      "grad_norm": 1.9570984840393066,
       "learning_rate": 1.1170212765957447e-07,
-      "loss": 2.9192,
+      "loss": 1.9954,
       "step": 4000
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.8439905269390172,
-      "eval_loss": 2.9663496017456055,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 427.5243,
-      "eval_samples_per_second": 23.704,
-      "eval_steps_per_second": 2.964,
+      "eval_accuracy": 0.8996447602131439,
+      "eval_loss": 2.051574468612671,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 428.5234,
+      "eval_samples_per_second": 23.649,
+      "eval_steps_per_second": 2.957,
       "step": 4275
     },
     {
       "epoch": 9.473684210526315,
-      "grad_norm": 1.6587204933166504,
+      "grad_norm": 2.8008673191070557,
       "learning_rate": 3.723404255319149e-08,
-      "loss": 2.9038,
+      "loss": 1.9844,
       "step": 4500
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.844582593250444,
-      "eval_loss": 2.9626526832580566,
-      "eval_model_preparation_time": 0.0054,
-      "eval_runtime": 426.6341,
-      "eval_samples_per_second": 23.753,
-      "eval_steps_per_second": 2.97,
+      "eval_accuracy": 0.8997434379317151,
+      "eval_loss": 2.0490753650665283,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 432.9221,
+      "eval_samples_per_second": 23.408,
+      "eval_steps_per_second": 2.927,
       "step": 4750
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae771d8b8a5b0bf96fd1563182563b2a5ad9fe7f6ef6c7c81f632dd6557c63f5
+oid sha256:a25a9f61b85f1c98057f82fd04d48bdb056c895ceb4e94d314e17db1b3a3895b
 size 343362404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a38a62fd9510e28cde6e58bdf664ac1cef1385b03dee911eea552b4cd4d465b
+oid sha256:42ec4753dffbff690b817bd454c5119744cfc4c75e4286896cac115bd1e65d28
 size 5112