Upload folder using huggingface_hub

checkpoint-10945/config.json

@@ -224,5 +224,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.2"
+  "transformers_version": "4.39.3"
 }

checkpoint-10945/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf47aecf2a5fe3fd2c3f2724fbbfb6295e0d057bb189850fbdf7f05b8d977d3
+oid sha256:6df9d6bd9f12074fbbeba04adf05e42f2d5b750360625482975e711cacae747a
 size 343525432

checkpoint-10945/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34f9061525e3d68314e07eba8fc9c7c851ebcc9f5ec6a69ea45435c3e3c6c7a
+oid sha256:a8379a7676830aca29c3492b682fdeebb23b3720e5d1b01a041d42a67c5b9d2a
 size 687171333

checkpoint-10945/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6230026483535767,
+  "best_metric": 0.6021606922149658,
   "best_model_checkpoint": "mushrooms_image_detection/checkpoint-10945",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,158 +10,158 @@
   "log_history": [
     {
       "epoch": 0.05,
-      "grad_norm": 5.758909702301025,
+      "grad_norm": 5.143975734710693,
       "learning_rate": 1.9173932996787516e-07,
-      "loss": 0.7238,
+      "loss": 0.6876,
       "step": 500
     },
     {
       "epoch": 0.09,
-      "grad_norm": 7.06810188293457,
+      "grad_norm": 5.595354080200195,
       "learning_rate": 1.825608077099587e-07,
-      "loss": 0.7267,
+      "loss": 0.705,
       "step": 1000
     },
     {
       "epoch": 0.14,
-      "grad_norm": 6.429927349090576,
+      "grad_norm": 8.542109489440918,
       "learning_rate": 1.733822854520422e-07,
-      "loss": 0.711,
+      "loss": 0.6908,
       "step": 1500
     },
     {
       "epoch": 0.18,
-      "grad_norm": 7.55098819732666,
+      "grad_norm": 5.49858283996582,
       "learning_rate": 1.6420376319412576e-07,
-      "loss": 0.7174,
+      "loss": 0.6763,
       "step": 2000
     },
     {
       "epoch": 0.23,
-      "grad_norm": 7.272024154663086,
+      "grad_norm": 5.070239067077637,
       "learning_rate": 1.5502524093620926e-07,
-      "loss": 0.713,
+      "loss": 0.6807,
       "step": 2500
     },
     {
       "epoch": 0.27,
-      "grad_norm": 8.493428230285645,
+      "grad_norm": 3.0705084800720215,
       "learning_rate": 1.458467186782928e-07,
-      "loss": 0.6996,
+      "loss": 0.6879,
       "step": 3000
     },
     {
       "epoch": 0.32,
-      "grad_norm": 4.434696197509766,
+      "grad_norm": 3.836571455001831,
       "learning_rate": 1.366681964203763e-07,
-      "loss": 0.7165,
+      "loss": 0.69,
       "step": 3500
     },
     {
       "epoch": 0.37,
-      "grad_norm": 6.052495956420898,
+      "grad_norm": 7.066412448883057,
       "learning_rate": 1.2748967416245983e-07,
-      "loss": 0.7169,
+      "loss": 0.6808,
       "step": 4000
     },
     {
       "epoch": 0.41,
-      "grad_norm": 10.02051067352295,
+      "grad_norm": 5.1906328201293945,
       "learning_rate": 1.1831115190454337e-07,
-      "loss": 0.6994,
+      "loss": 0.6842,
       "step": 4500
     },
     {
       "epoch": 0.46,
-      "grad_norm": 4.502712726593018,
+      "grad_norm": 6.5265703201293945,
       "learning_rate": 1.0913262964662688e-07,
-      "loss": 0.7075,
+      "loss": 0.6911,
       "step": 5000
     },
     {
       "epoch": 0.5,
-      "grad_norm": 4.787944793701172,
+      "grad_norm": 8.26229190826416,
       "learning_rate": 9.995410738871042e-08,
-      "loss": 0.7136,
+      "loss": 0.6743,
       "step": 5500
     },
     {
       "epoch": 0.55,
-      "grad_norm": 8.738495826721191,
+      "grad_norm": 5.895538330078125,
       "learning_rate": 9.077558513079394e-08,
-      "loss": 0.6976,
+      "loss": 0.6734,
       "step": 6000
     },
     {
       "epoch": 0.59,
-      "grad_norm": 6.709692001342773,
+      "grad_norm": 9.030574798583984,
       "learning_rate": 8.159706287287747e-08,
-      "loss": 0.6994,
+      "loss": 0.6718,
       "step": 6500
     },
     {
       "epoch": 0.64,
-      "grad_norm": 2.5347442626953125,
+      "grad_norm": 7.243845462799072,
       "learning_rate": 7.241854061496099e-08,
-      "loss": 0.6996,
+      "loss": 0.6698,
       "step": 7000
     },
     {
       "epoch": 0.69,
-      "grad_norm": 5.286170482635498,
+      "grad_norm": 5.422345161437988,
       "learning_rate": 6.32400183570445e-08,
-      "loss": 0.6961,
+      "loss": 0.6627,
       "step": 7500
     },
     {
       "epoch": 0.73,
-      "grad_norm": 5.30819034576416,
+      "grad_norm": 3.86919903755188,
       "learning_rate": 5.406149609912804e-08,
-      "loss": 0.6897,
+      "loss": 0.667,
       "step": 8000
     },
     {
       "epoch": 0.78,
-      "grad_norm": 7.743193626403809,
+      "grad_norm": 8.272964477539062,
       "learning_rate": 4.488297384121156e-08,
-      "loss": 0.6855,
+      "loss": 0.6542,
       "step": 8500
     },
     {
       "epoch": 0.82,
-      "grad_norm": 8.52515697479248,
+      "grad_norm": 7.44323205947876,
       "learning_rate": 3.5704451583295086e-08,
-      "loss": 0.6966,
+      "loss": 0.6729,
       "step": 9000
     },
     {
       "epoch": 0.87,
-      "grad_norm": 5.206400394439697,
+      "grad_norm": 3.3304898738861084,
       "learning_rate": 2.6525929325378617e-08,
-      "loss": 0.7043,
+      "loss": 0.6822,
       "step": 9500
     },
     {
       "epoch": 0.91,
-      "grad_norm": 6.084430694580078,
+      "grad_norm": 7.638361930847168,
       "learning_rate": 1.7347407067462138e-08,
-      "loss": 0.6943,
+      "loss": 0.6749,
       "step": 10000
     },
     {
       "epoch": 0.96,
-      "grad_norm": 8.045140266418457,
+      "grad_norm": 4.384842395782471,
       "learning_rate": 8.168884809545663e-09,
-      "loss": 0.6869,
+      "loss": 0.6733,
       "step": 10500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8854163097481583,
-      "eval_loss": 0.6230026483535767,
-      "eval_runtime": 2891.1403,
-      "eval_samples_per_second": 80.757,
-      "eval_steps_per_second": 10.095,
+      "eval_accuracy": 0.8896693506938496,
+      "eval_loss": 0.6021606922149658,
+      "eval_runtime": 3122.8795,
+      "eval_samples_per_second": 74.764,
+      "eval_steps_per_second": 9.346,
       "step": 10945
     }
   ],

config.json

@@ -224,5 +224,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.2"
+  "transformers_version": "4.39.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf47aecf2a5fe3fd2c3f2724fbbfb6295e0d057bb189850fbdf7f05b8d977d3
+oid sha256:6df9d6bd9f12074fbbeba04adf05e42f2d5b750360625482975e711cacae747a
 size 343525432