Upload folder using huggingface_hub

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3872c3bca0bcaada8b7c91afab197a88f39c328e8aaded23ce282e996b32aac0
-size 686587077
+oid sha256:e24c2340e30017c7624660104e3a0fb850bbd378a2f7509d3004b44a447ce4f3
+size 686586885

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b6d2b1634d4e5818b3b03ba56b6ff5ea6a172e5705aad392ee633558360106
+oid sha256:a6c092d7c5b9f453b9c06ae90b5869ac471bb7a110aee92da14819d546852281
 size 343302829

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:132429c3ef48097d659f3fa34f0ca82d09f907b2d0b58363bcfefa9ddb19fe7f
+oid sha256:f8214c01f27f2aeae1e56fc7a28278e26d2d258088ec2bdf3bdc701698ad3524
 size 13553

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed8a156a22c309bb91c33d910110b63f1c190e1e24dadfe22b621d95df2fa8a
+oid sha256:9e9d1478932d95f604c248a1fe1362a1d07bf90d5ca17e1579a67752b11f2fc2
 size 627

trainer_state.json

@@ -1,247 +1,148 @@
 {
-  "best_metric": 0.43153366446495056,
-  "best_model_checkpoint": "./plant-classification/checkpoint-280",
-  "epoch": 3.5,
-  "global_step": 280,
+  "best_metric": 0.5926051735877991,
+  "best_model_checkpoint": "./plant-classification/checkpoint-160",
+  "epoch": 1.951219512195122,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.12,
-      "learning_rate": 0.00019375000000000002,
-      "loss": 2.4618,
+      "learning_rate": 0.0001878048780487805,
+      "loss": 2.4403,
       "step": 10
     },
     {
-      "epoch": 0.25,
-      "learning_rate": 0.0001875,
-      "loss": 2.0277,
+      "epoch": 0.24,
+      "learning_rate": 0.000175609756097561,
+      "loss": 1.9498,
       "step": 20
     },
     {
-      "epoch": 0.38,
-      "learning_rate": 0.00018125000000000001,
-      "loss": 1.6392,
+      "epoch": 0.37,
+      "learning_rate": 0.00016341463414634147,
+      "loss": 1.5422,
       "step": 30
     },
     {
-      "epoch": 0.5,
-      "learning_rate": 0.000175,
-      "loss": 1.3747,
+      "epoch": 0.49,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 1.2802,
       "step": 40
     },
     {
-      "epoch": 0.5,
-      "eval_accuracy": 0.7626168224299066,
-      "eval_loss": 1.1831709146499634,
-      "eval_runtime": 384.9557,
-      "eval_samples_per_second": 1.39,
-      "eval_steps_per_second": 0.174,
+      "epoch": 0.49,
+      "eval_accuracy": 0.7532467532467533,
+      "eval_loss": 1.1777054071426392,
+      "eval_runtime": 245.0854,
+      "eval_samples_per_second": 2.199,
+      "eval_steps_per_second": 0.277,
       "step": 40
     },
     {
-      "epoch": 0.62,
-      "learning_rate": 0.00016875,
-      "loss": 1.2425,
+      "epoch": 0.61,
+      "learning_rate": 0.00013902439024390245,
+      "loss": 1.1818,
       "step": 50
     },
     {
-      "epoch": 0.75,
-      "learning_rate": 0.00016250000000000002,
-      "loss": 1.1063,
+      "epoch": 0.73,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 1.0576,
       "step": 60
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.00015625,
-      "loss": 0.9224,
+      "epoch": 0.85,
+      "learning_rate": 0.00011463414634146342,
+      "loss": 0.9448,
       "step": 70
     },
     {
-      "epoch": 1.0,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 0.7905,
+      "epoch": 0.98,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 0.9498,
       "step": 80
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8130841121495327,
-      "eval_loss": 0.7577788233757019,
-      "eval_runtime": 381.7049,
-      "eval_samples_per_second": 1.402,
-      "eval_steps_per_second": 0.176,
+      "epoch": 0.98,
+      "eval_accuracy": 0.8311688311688312,
+      "eval_loss": 0.820961058139801,
+      "eval_runtime": 244.7769,
+      "eval_samples_per_second": 2.202,
+      "eval_steps_per_second": 0.278,
       "step": 80
     },
     {
-      "epoch": 1.12,
-      "learning_rate": 0.00014375,
-      "loss": 0.6613,
+      "epoch": 1.1,
+      "learning_rate": 9.02439024390244e-05,
+      "loss": 0.6939,
       "step": 90
     },
     {
-      "epoch": 1.25,
-      "learning_rate": 0.0001375,
-      "loss": 0.6946,
+      "epoch": 1.22,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.6009,
       "step": 100
     },
     {
-      "epoch": 1.38,
-      "learning_rate": 0.00013125000000000002,
-      "loss": 0.5187,
+      "epoch": 1.34,
+      "learning_rate": 6.585365853658538e-05,
+      "loss": 0.593,
       "step": 110
     },
     {
-      "epoch": 1.5,
-      "learning_rate": 0.000125,
-      "loss": 0.5223,
+      "epoch": 1.46,
+      "learning_rate": 5.365853658536586e-05,
+      "loss": 0.5132,
       "step": 120
     },
     {
-      "epoch": 1.5,
-      "eval_accuracy": 0.8186915887850468,
-      "eval_loss": 0.6094576120376587,
-      "eval_runtime": 389.3932,
-      "eval_samples_per_second": 1.374,
-      "eval_steps_per_second": 0.172,
+      "epoch": 1.46,
+      "eval_accuracy": 0.8330241187384044,
+      "eval_loss": 0.6491296887397766,
+      "eval_runtime": 247.5801,
+      "eval_samples_per_second": 2.177,
+      "eval_steps_per_second": 0.275,
       "step": 120
     },
     {
-      "epoch": 1.62,
-      "learning_rate": 0.00011875,
-      "loss": 0.5048,
+      "epoch": 1.59,
+      "learning_rate": 4.146341463414634e-05,
+      "loss": 0.5321,
       "step": 130
     },
     {
-      "epoch": 1.75,
-      "learning_rate": 0.00011250000000000001,
-      "loss": 0.5559,
+      "epoch": 1.71,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 0.4869,
       "step": 140
     },
     {
-      "epoch": 1.88,
-      "learning_rate": 0.00010625000000000001,
-      "loss": 0.4757,
+      "epoch": 1.83,
+      "learning_rate": 1.707317073170732e-05,
+      "loss": 0.4651,
       "step": 150
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 0.0001,
-      "loss": 0.3683,
+      "epoch": 1.95,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 0.5354,
       "step": 160
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8542056074766355,
-      "eval_loss": 0.5075709819793701,
-      "eval_runtime": 384.1646,
-      "eval_samples_per_second": 1.393,
-      "eval_steps_per_second": 0.174,
+      "epoch": 1.95,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.5926051735877991,
+      "eval_runtime": 248.1335,
+      "eval_samples_per_second": 2.172,
+      "eval_steps_per_second": 0.274,
       "step": 160
-    },
-    {
-      "epoch": 2.12,
-      "learning_rate": 9.375e-05,
-      "loss": 0.3126,
-      "step": 170
-    },
-    {
-      "epoch": 2.25,
-      "learning_rate": 8.75e-05,
-      "loss": 0.3093,
-      "step": 180
-    },
-    {
-      "epoch": 2.38,
-      "learning_rate": 8.125000000000001e-05,
-      "loss": 0.3063,
-      "step": 190
-    },
-    {
-      "epoch": 2.5,
-      "learning_rate": 7.500000000000001e-05,
-      "loss": 0.2401,
-      "step": 200
-    },
-    {
-      "epoch": 2.5,
-      "eval_accuracy": 0.8467289719626169,
-      "eval_loss": 0.4515593349933624,
-      "eval_runtime": 374.8793,
-      "eval_samples_per_second": 1.427,
-      "eval_steps_per_second": 0.179,
-      "step": 200
-    },
-    {
-      "epoch": 2.62,
-      "learning_rate": 6.875e-05,
-      "loss": 0.3209,
-      "step": 210
-    },
-    {
-      "epoch": 2.75,
-      "learning_rate": 6.25e-05,
-      "loss": 0.2538,
-      "step": 220
-    },
-    {
-      "epoch": 2.88,
-      "learning_rate": 5.6250000000000005e-05,
-      "loss": 0.2671,
-      "step": 230
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 5e-05,
-      "loss": 0.2688,
-      "step": 240
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8598130841121495,
-      "eval_loss": 0.4518713057041168,
-      "eval_runtime": 371.598,
-      "eval_samples_per_second": 1.44,
-      "eval_steps_per_second": 0.18,
-      "step": 240
-    },
-    {
-      "epoch": 3.12,
-      "learning_rate": 4.375e-05,
-      "loss": 0.1702,
-      "step": 250
-    },
-    {
-      "epoch": 3.25,
-      "learning_rate": 3.7500000000000003e-05,
-      "loss": 0.1993,
-      "step": 260
-    },
-    {
-      "epoch": 3.38,
-      "learning_rate": 3.125e-05,
-      "loss": 0.218,
-      "step": 270
-    },
-    {
-      "epoch": 3.5,
-      "learning_rate": 2.5e-05,
-      "loss": 0.1583,
-      "step": 280
-    },
-    {
-      "epoch": 3.5,
-      "eval_accuracy": 0.874766355140187,
-      "eval_loss": 0.43153366446495056,
-      "eval_runtime": 380.0584,
-      "eval_samples_per_second": 1.408,
-      "eval_steps_per_second": 0.176,
-      "step": 280
     }
   ],
-  "max_steps": 320,
-  "num_train_epochs": 4,
-  "total_flos": 3.467364497947607e+17,
+  "max_steps": 164,
+  "num_train_epochs": 2,
+  "total_flos": 1.9809082826897818e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa90b2bf99e43bd879b69acbb4d88ab9a0137685671e23de8df26be9573fb3d
+oid sha256:b235ff0483f9bbab0da85fe4a9ed55d0e6e523372e5e8e176c86ff866cd91f31
 size 3899