Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae32286831883c3b1833ed0c21764008ee3cb690aa947501478767a461c5a83
+oid sha256:5f2afdc8a317e49097600321b2dfb755c839a630cc1f71155b585d3ceaa59c45
 size 88267432

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef0d344dc7c5e9180eda212cdb90b24bbc7adb1e6748db6d283d9c84790b76a
+oid sha256:ac88973c2d55093d476f47113a923099eefec1ffa04aea584d69b41b2c9192db
 size 176666106

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d8f282f995a3c1a59d83dfe504bd41bcdf8f79e071dbd6f372623251fc02b2
+oid sha256:9fd1ce5b56368017ca604769d5a033115cd645195ee71523b8fc56abe270f26f
 size 1064

trainer_state.json

@@ -1,160 +1,112 @@
 {
-  "best_metric": 0.9713101001869517,
-  "best_model_checkpoint": "./results/checkpoint-1500",
-  "epoch": 0.2901353965183752,
+  "best_metric": 0.9534415899175958,
+  "best_model_checkpoint": "./results/checkpoint-1000",
+  "epoch": 0.1547269070091289,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.019342359767891684,
-      "grad_norm": 1871413.875,
+      "epoch": 0.01547269070091289,
+      "grad_norm": 2257314.0,
       "learning_rate": 1e-05,
-      "loss": 0.6564,
+      "loss": 0.6363,
       "step": 100
     },
     {
-      "epoch": 0.03868471953578337,
-      "grad_norm": 3112622.75,
+      "epoch": 0.03094538140182578,
+      "grad_norm": 3129538.0,
       "learning_rate": 2e-05,
-      "loss": 0.4794,
+      "loss": 0.4287,
       "step": 200
     },
     {
-      "epoch": 0.058027079303675046,
-      "grad_norm": 2537678.5,
+      "epoch": 0.04641807210273867,
+      "grad_norm": 3898528.75,
       "learning_rate": 3e-05,
-      "loss": 0.4037,
+      "loss": 0.3508,
       "step": 300
     },
     {
-      "epoch": 0.07736943907156674,
-      "grad_norm": 2662464.0,
+      "epoch": 0.06189076280365156,
+      "grad_norm": 1689890.875,
       "learning_rate": 4e-05,
-      "loss": 0.3265,
+      "loss": 0.4636,
       "step": 400
     },
     {
-      "epoch": 0.09671179883945841,
-      "grad_norm": 1437540.625,
+      "epoch": 0.07736345350456444,
+      "grad_norm": 2084754.375,
       "learning_rate": 5e-05,
-      "loss": 0.3744,
+      "loss": 0.268,
       "step": 500
     },
     {
-      "epoch": 0.09671179883945841,
-      "eval_accuracy": 0.8466634429400387,
-      "eval_f1": 0.8663012543480553,
-      "eval_loss": 0.33316776156425476,
-      "eval_precision": 0.7684238083662135,
-      "eval_recall": 0.9927523977484116,
-      "eval_roc_auc": 0.8465467895292255,
-      "eval_runtime": 1179.0948,
-      "eval_samples_per_second": 140.311,
-      "eval_steps_per_second": 0.549,
+      "epoch": 0.07736345350456444,
+      "eval_accuracy": 0.9384707581369304,
+      "eval_f1": 0.9266550339028704,
+      "eval_loss": 0.16631442308425903,
+      "eval_precision": 0.877639751552795,
+      "eval_recall": 0.9814690779191784,
+      "eval_roc_auc": 0.945872962460679,
+      "eval_runtime": 764.2798,
+      "eval_samples_per_second": 266.366,
+      "eval_steps_per_second": 1.042,
       "step": 500
     },
     {
-      "epoch": 0.11605415860735009,
-      "grad_norm": 2934780.75,
-      "learning_rate": 4.892933618843683e-05,
-      "loss": 0.3006,
+      "epoch": 0.09283614420547734,
+      "grad_norm": 2382709.75,
+      "learning_rate": 4.916149589132987e-05,
+      "loss": 0.2394,
       "step": 600
     },
     {
-      "epoch": 0.13539651837524178,
-      "grad_norm": 1091141.375,
-      "learning_rate": 4.785867237687366e-05,
-      "loss": 0.2714,
+      "epoch": 0.10830883490639022,
+      "grad_norm": 936833.5,
+      "learning_rate": 4.832299178265974e-05,
+      "loss": 0.2343,
       "step": 700
     },
     {
-      "epoch": 0.15473887814313347,
-      "grad_norm": 3842419.0,
-      "learning_rate": 4.6788008565310496e-05,
-      "loss": 0.1778,
+      "epoch": 0.12378152560730311,
+      "grad_norm": 1470909.625,
+      "learning_rate": 4.7484487673989605e-05,
+      "loss": 0.1875,
       "step": 800
     },
     {
-      "epoch": 0.17408123791102514,
-      "grad_norm": 1596435.75,
-      "learning_rate": 4.571734475374733e-05,
-      "loss": 0.1743,
+      "epoch": 0.139254216308216,
+      "grad_norm": 1565031.125,
+      "learning_rate": 4.664598356531947e-05,
+      "loss": 0.1592,
       "step": 900
     },
     {
-      "epoch": 0.19342359767891681,
-      "grad_norm": 1802532.125,
-      "learning_rate": 4.4646680942184155e-05,
-      "loss": 0.1531,
+      "epoch": 0.1547269070091289,
+      "grad_norm": 450809.3125,
+      "learning_rate": 4.580747945664934e-05,
+      "loss": 0.1575,
       "step": 1000
     },
     {
-      "epoch": 0.19342359767891681,
-      "eval_accuracy": 0.9334683268858801,
-      "eval_f1": 0.929946602343387,
-      "eval_loss": 0.16633380949497223,
-      "eval_precision": 0.9827945706714019,
-      "eval_recall": 0.8824922088275795,
-      "eval_roc_auc": 0.9335090317978244,
-      "eval_runtime": 970.6452,
-      "eval_samples_per_second": 170.443,
-      "eval_steps_per_second": 0.667,
+      "epoch": 0.1547269070091289,
+      "eval_accuracy": 0.9622552535146234,
+      "eval_f1": 0.9534415899175958,
+      "eval_loss": 0.11282139271497726,
+      "eval_precision": 0.9320050226255064,
+      "eval_recall": 0.9758874748827864,
+      "eval_roc_auc": 0.9646020542376454,
+      "eval_runtime": 752.2615,
+      "eval_samples_per_second": 270.621,
+      "eval_steps_per_second": 1.058,
       "step": 1000
-    },
-    {
-      "epoch": 0.2127659574468085,
-      "grad_norm": 1385128.5,
-      "learning_rate": 4.357601713062099e-05,
-      "loss": 0.1432,
-      "step": 1100
-    },
-    {
-      "epoch": 0.23210831721470018,
-      "grad_norm": 306230.6875,
-      "learning_rate": 4.2505353319057815e-05,
-      "loss": 0.1386,
-      "step": 1200
-    },
-    {
-      "epoch": 0.2514506769825919,
-      "grad_norm": 1276595.5,
-      "learning_rate": 4.143468950749465e-05,
-      "loss": 0.1273,
-      "step": 1300
-    },
-    {
-      "epoch": 0.27079303675048355,
-      "grad_norm": 417115.5625,
-      "learning_rate": 4.036402569593148e-05,
-      "loss": 0.1075,
-      "step": 1400
-    },
-    {
-      "epoch": 0.2901353965183752,
-      "grad_norm": 1014551.625,
-      "learning_rate": 3.9293361884368315e-05,
-      "loss": 0.1314,
-      "step": 1500
-    },
-    {
-      "epoch": 0.2901353965183752,
-      "eval_accuracy": 0.971058994197292,
-      "eval_f1": 0.9713101001869517,
-      "eval_loss": 0.08320203423500061,
-      "eval_precision": 0.9637107322061307,
-      "eval_recall": 0.9790302708187375,
-      "eval_roc_auc": 0.971052629057589,
-      "eval_runtime": 954.2031,
-      "eval_samples_per_second": 173.38,
-      "eval_steps_per_second": 0.678,
-      "step": 1500
     }
   ],
   "logging_steps": 100,
-  "max_steps": 5170,
+  "max_steps": 6463,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -170,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.9963434246144e+18,
+  "total_flos": 2.5502169563136e+18,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061af69f446ec4684d6cdb1ee48c5bd4e0e460f08c3bbc6485e12e3606db3bfa
+oid sha256:a13da7ad5f6f6f9a3e14fb23bf538ce181b942a01961411ee74d105b0f0a404c
 size 5304