Upload folder using huggingface_hub (#11)

- Upload folder using huggingface_hub (0ed2ba6d45ed3dbf58d492636d5053b584e2ab4b)

config.json

@@ -9,17 +9,15 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "Benign",
-    "1": "Malignant",
-    "2": "NoTumor"
+    "0": "no",
+    "1": "yes"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Benign": "0",
-    "Malignant": "1",
-    "NoTumor": "2"
+    "no": "0",
+    "yes": "1"
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea415bb632e876ae512336a607af6840280bf456bb5c30658265c62bacd8732e
-size 686524869
+oid sha256:97622a42fad17fda9f4e3e2968936f5d8154521765d06218209a3f8d57bf84f3
+size 686518917

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c78c09461862f59df553d91ae01c18dc010f7012574bb553a4aea495dfa339
-size 343271789
+oid sha256:ed4a452acd361b9df965fa879ed0694bf5a220837b7a43535949173d7aef818e
+size 343268717

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
+oid sha256:8bb3860d98363e44bc4704fb9458deec927fd96997d1d09c80639070db959d22
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102c64654091da92418743f04a2cd860e670dced82d2da75143ba070fc004661
+oid sha256:c8a54c653e954cbfd76e7193d163778c2617b720e1d8c400bd852fdfbf02140d
 size 627

trainer_state.json

@@ -1,148 +1,247 @@
 {
-  "best_metric": 0.12063875794410706,
-  "best_model_checkpoint": "./vit-base-beans/checkpoint-160",
-  "epoch": 0.43478260869565216,
-  "global_step": 160,
+  "best_metric": 0.036450520157814026,
+  "best_model_checkpoint": "./vit-base-beans/checkpoint-280",
+  "epoch": 1.8666666666666667,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
-      "learning_rate": 0.0001891304347826087,
-      "loss": 0.6558,
+      "epoch": 0.07,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.5095,
       "step": 10
     },
     {
-      "epoch": 0.05,
-      "learning_rate": 0.0001782608695652174,
-      "loss": 0.3045,
+      "epoch": 0.13,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.1264,
       "step": 20
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.0001673913043478261,
-      "loss": 0.2567,
+      "epoch": 0.2,
+      "learning_rate": 0.00018,
+      "loss": 0.2591,
       "step": 30
     },
     {
-      "epoch": 0.11,
-      "learning_rate": 0.0001565217391304348,
-      "loss": 0.2319,
+      "epoch": 0.27,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.2432,
       "step": 40
     },
     {
-      "epoch": 0.11,
-      "eval_accuracy": 0.8637602179836512,
-      "eval_loss": 0.2531130313873291,
-      "eval_runtime": 17.2839,
-      "eval_samples_per_second": 42.467,
-      "eval_steps_per_second": 5.323,
+      "epoch": 0.27,
+      "eval_accuracy": 0.96,
+      "eval_loss": 0.1231376901268959,
+      "eval_runtime": 6.2617,
+      "eval_samples_per_second": 47.911,
+      "eval_steps_per_second": 6.069,
       "step": 40
     },
     {
-      "epoch": 0.14,
-      "learning_rate": 0.0001456521739130435,
-      "loss": 0.2499,
+      "epoch": 0.33,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.0895,
       "step": 50
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0001347826086956522,
-      "loss": 0.2874,
+      "epoch": 0.4,
+      "learning_rate": 0.00016,
+      "loss": 0.0498,
       "step": 60
     },
     {
-      "epoch": 0.19,
-      "learning_rate": 0.00012391304347826086,
-      "loss": 0.1609,
+      "epoch": 0.47,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.212,
       "step": 70
     },
     {
-      "epoch": 0.22,
-      "learning_rate": 0.00011304347826086956,
-      "loss": 0.1306,
+      "epoch": 0.53,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.074,
       "step": 80
     },
     {
-      "epoch": 0.22,
-      "eval_accuracy": 0.9564032697547684,
-      "eval_loss": 0.1377830058336258,
-      "eval_runtime": 17.1335,
-      "eval_samples_per_second": 42.84,
-      "eval_steps_per_second": 5.37,
+      "epoch": 0.53,
+      "eval_accuracy": 0.9833333333333333,
+      "eval_loss": 0.07364834100008011,
+      "eval_runtime": 5.1068,
+      "eval_samples_per_second": 58.745,
+      "eval_steps_per_second": 7.441,
       "step": 80
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.00010217391304347828,
-      "loss": 0.228,
+      "epoch": 0.6,
+      "learning_rate": 0.00014,
+      "loss": 0.0992,
       "step": 90
     },
     {
-      "epoch": 0.27,
-      "learning_rate": 9.130434782608696e-05,
-      "loss": 0.1187,
+      "epoch": 0.67,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0764,
       "step": 100
     },
     {
-      "epoch": 0.3,
-      "learning_rate": 8.043478260869566e-05,
-      "loss": 0.1811,
+      "epoch": 0.73,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.0284,
       "step": 110
     },
     {
-      "epoch": 0.33,
-      "learning_rate": 6.956521739130436e-05,
-      "loss": 0.2075,
+      "epoch": 0.8,
+      "learning_rate": 0.00012,
+      "loss": 0.0787,
       "step": 120
     },
     {
-      "epoch": 0.33,
-      "eval_accuracy": 0.8419618528610354,
-      "eval_loss": 0.3006892800331116,
-      "eval_runtime": 17.1056,
-      "eval_samples_per_second": 42.91,
-      "eval_steps_per_second": 5.378,
+      "epoch": 0.8,
+      "eval_accuracy": 0.98,
+      "eval_loss": 0.08297358453273773,
+      "eval_runtime": 6.2497,
+      "eval_samples_per_second": 48.002,
+      "eval_steps_per_second": 6.08,
       "step": 120
     },
     {
-      "epoch": 0.35,
-      "learning_rate": 5.869565217391305e-05,
-      "loss": 0.2099,
+      "epoch": 0.87,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.0096,
       "step": 130
     },
     {
-      "epoch": 0.38,
-      "learning_rate": 4.782608695652174e-05,
-      "loss": 0.1518,
+      "epoch": 0.93,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.0387,
       "step": 140
     },
     {
-      "epoch": 0.41,
-      "learning_rate": 3.695652173913043e-05,
-      "loss": 0.1559,
+      "epoch": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0246,
       "step": 150
     },
     {
-      "epoch": 0.43,
-      "learning_rate": 2.608695652173913e-05,
-      "loss": 0.1573,
+      "epoch": 1.07,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.0132,
       "step": 160
     },
     {
-      "epoch": 0.43,
-      "eval_accuracy": 0.9618528610354223,
-      "eval_loss": 0.12063875794410706,
-      "eval_runtime": 16.7256,
-      "eval_samples_per_second": 43.885,
-      "eval_steps_per_second": 5.501,
+      "epoch": 1.07,
+      "eval_accuracy": 0.9866666666666667,
+      "eval_loss": 0.04826768860220909,
+      "eval_runtime": 5.1012,
+      "eval_samples_per_second": 58.809,
+      "eval_steps_per_second": 7.449,
       "step": 160
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.0056,
+      "step": 170
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8e-05,
+      "loss": 0.0379,
+      "step": 180
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.0277,
+      "step": 190
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0305,
+      "step": 200
+    },
+    {
+      "epoch": 1.33,
+      "eval_accuracy": 0.9866666666666667,
+      "eval_loss": 0.05280878767371178,
+      "eval_runtime": 6.211,
+      "eval_samples_per_second": 48.301,
+      "eval_steps_per_second": 6.118,
+      "step": 200
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 6e-05,
+      "loss": 0.0052,
+      "step": 210
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.0055,
+      "step": 220
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.0047,
+      "step": 230
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4e-05,
+      "loss": 0.0784,
+      "step": 240
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.98,
+      "eval_loss": 0.066566601395607,
+      "eval_runtime": 5.7633,
+      "eval_samples_per_second": 52.053,
+      "eval_steps_per_second": 6.593,
+      "step": 240
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0294,
+      "step": 250
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.036,
+      "step": 260
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2e-05,
+      "loss": 0.037,
+      "step": 270
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.006,
+      "step": 280
+    },
+    {
+      "epoch": 1.87,
+      "eval_accuracy": 0.99,
+      "eval_loss": 0.036450520157814026,
+      "eval_runtime": 5.101,
+      "eval_samples_per_second": 58.812,
+      "eval_steps_per_second": 7.45,
+      "step": 280
     }
   ],
-  "max_steps": 184,
-  "num_train_epochs": 1,
-  "total_flos": 1.9838127142600704e+17,
+  "max_steps": 300,
+  "num_train_epochs": 2,
+  "total_flos": 3.4716411347337216e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0da1c4783c907062c5599838de2c50fb7797f9e629770cd8d98b5e414c53d23
+oid sha256:6356fdac8f7ddf618557f635b47577515e3f93ecba50c63feb05831b44a3c970
 size 3963