🍻 cheers

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 base_model: panda992/fish_disease_datasets
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fish_disease_datasets
 
-This model is a fine-tuned version of [panda992/fish_disease_datasets](https://huggingface.co/panda992/fish_disease_datasets) on an unknown dataset.
+This model is a fine-tuned version of [panda992/fish_disease_datasets](https://huggingface.co/panda992/fish_disease_datasets) on the fish_disease_datasets dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0675
 - Accuracy: 0.9810

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9728260869565217,
-    "eval_loss": 0.10525541752576828,
-    "eval_runtime": 1.7228,
-    "eval_samples_per_second": 213.607,
-    "eval_steps_per_second": 26.701,
+    "eval_accuracy": 0.9809782608695652,
+    "eval_loss": 0.0674990862607956,
+    "eval_runtime": 1.7056,
+    "eval_samples_per_second": 215.763,
+    "eval_steps_per_second": 26.97,
     "total_flos": 6.45382209997357e+17,
-    "train_loss": 0.4479620875293062,
-    "train_runtime": 145.1835,
-    "train_samples_per_second": 57.362,
-    "train_steps_per_second": 3.609
+    "train_loss": 0.13892418100633694,
+    "train_runtime": 142.587,
+    "train_samples_per_second": 58.406,
+    "train_steps_per_second": 3.675
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9728260869565217,
-    "eval_loss": 0.10525541752576828,
-    "eval_runtime": 1.7228,
-    "eval_samples_per_second": 213.607,
-    "eval_steps_per_second": 26.701
+    "eval_accuracy": 0.9809782608695652,
+    "eval_loss": 0.0674990862607956,
+    "eval_runtime": 1.7056,
+    "eval_samples_per_second": 215.763,
+    "eval_steps_per_second": 26.97
 }

runs/May10_06-47-56_35deed949fff/events.out.tfevents.1746859873.35deed949fff.185.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9c7c10eebac90047314e50b42f8b2322a33fb966e97b57edd5d2f795b919cb
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 6.45382209997357e+17,
-    "train_loss": 0.4479620875293062,
-    "train_runtime": 145.1835,
-    "train_samples_per_second": 57.362,
-    "train_steps_per_second": 3.609
+    "train_loss": 0.13892418100633694,
+    "train_runtime": 142.587,
+    "train_samples_per_second": 58.406,
+    "train_steps_per_second": 3.675
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 500,
-  "best_metric": 0.10525541752576828,
+  "best_metric": 0.0674990862607956,
   "best_model_checkpoint": "fish_disease_datasets/checkpoint-500",
   "epoch": 4.0,
   "eval_steps": 100,
@@ -11,421 +11,421 @@
   "log_history": [
     {
       "epoch": 0.07633587786259542,
-      "grad_norm": 1.9409185647964478,
+      "grad_norm": 8.140775680541992,
       "learning_rate": 0.00019656488549618322,
-      "loss": 1.8218,
+      "loss": 0.2332,
       "step": 10
     },
     {
       "epoch": 0.15267175572519084,
-      "grad_norm": 2.1680898666381836,
+      "grad_norm": 5.731508731842041,
       "learning_rate": 0.00019274809160305345,
-      "loss": 1.5952,
+      "loss": 0.2397,
       "step": 20
     },
     {
       "epoch": 0.22900763358778625,
-      "grad_norm": 2.6097843647003174,
+      "grad_norm": 4.3719563484191895,
       "learning_rate": 0.00018893129770992367,
-      "loss": 1.3356,
+      "loss": 0.2881,
       "step": 30
     },
     {
       "epoch": 0.3053435114503817,
-      "grad_norm": 3.603273391723633,
+      "grad_norm": 2.272369623184204,
       "learning_rate": 0.0001851145038167939,
-      "loss": 1.2841,
+      "loss": 0.2598,
       "step": 40
     },
     {
       "epoch": 0.3816793893129771,
-      "grad_norm": 2.5564615726470947,
+      "grad_norm": 3.4309451580047607,
       "learning_rate": 0.00018129770992366412,
-      "loss": 1.1569,
+      "loss": 0.1827,
       "step": 50
     },
     {
       "epoch": 0.4580152671755725,
-      "grad_norm": 1.7292225360870361,
+      "grad_norm": 1.1197692155838013,
       "learning_rate": 0.00017748091603053437,
-      "loss": 0.9338,
+      "loss": 0.152,
       "step": 60
     },
     {
       "epoch": 0.5343511450381679,
-      "grad_norm": 2.0024733543395996,
+      "grad_norm": 4.275225639343262,
       "learning_rate": 0.0001736641221374046,
-      "loss": 0.8578,
+      "loss": 0.2208,
       "step": 70
     },
     {
       "epoch": 0.6106870229007634,
-      "grad_norm": 3.2344448566436768,
+      "grad_norm": 3.2157912254333496,
       "learning_rate": 0.00016984732824427482,
-      "loss": 0.9114,
+      "loss": 0.3555,
       "step": 80
     },
     {
       "epoch": 0.6870229007633588,
-      "grad_norm": 2.080090045928955,
+      "grad_norm": 5.242416858673096,
       "learning_rate": 0.00016603053435114505,
-      "loss": 0.7153,
+      "loss": 0.163,
       "step": 90
     },
     {
       "epoch": 0.7633587786259542,
-      "grad_norm": 3.047137975692749,
+      "grad_norm": 0.5541224479675293,
       "learning_rate": 0.00016221374045801527,
-      "loss": 0.7341,
+      "loss": 0.2052,
       "step": 100
     },
     {
       "epoch": 0.7633587786259542,
-      "eval_accuracy": 0.8994565217391305,
-      "eval_loss": 0.47246649861335754,
-      "eval_runtime": 1.6845,
-      "eval_samples_per_second": 218.467,
-      "eval_steps_per_second": 27.308,
+      "eval_accuracy": 0.9483695652173914,
+      "eval_loss": 0.1684044897556305,
+      "eval_runtime": 1.6021,
+      "eval_samples_per_second": 229.704,
+      "eval_steps_per_second": 28.713,
       "step": 100
     },
     {
       "epoch": 0.8396946564885496,
-      "grad_norm": 2.9488649368286133,
+      "grad_norm": 0.14907874166965485,
       "learning_rate": 0.0001583969465648855,
-      "loss": 0.6839,
+      "loss": 0.1426,
       "step": 110
     },
     {
       "epoch": 0.916030534351145,
-      "grad_norm": 7.901376724243164,
+      "grad_norm": 1.8745291233062744,
       "learning_rate": 0.00015458015267175574,
-      "loss": 0.6448,
+      "loss": 0.1216,
       "step": 120
     },
     {
       "epoch": 0.9923664122137404,
-      "grad_norm": 2.6855387687683105,
+      "grad_norm": 5.384662628173828,
       "learning_rate": 0.00015076335877862594,
-      "loss": 0.5792,
+      "loss": 0.17,
       "step": 130
     },
     {
       "epoch": 1.0687022900763359,
-      "grad_norm": 3.498868703842163,
+      "grad_norm": 4.790631294250488,
       "learning_rate": 0.0001469465648854962,
-      "loss": 0.4598,
+      "loss": 0.0845,
       "step": 140
     },
     {
       "epoch": 1.1450381679389312,
-      "grad_norm": 1.6161444187164307,
+      "grad_norm": 4.6353230476379395,
       "learning_rate": 0.00014312977099236642,
-      "loss": 0.346,
+      "loss": 0.1092,
       "step": 150
     },
     {
       "epoch": 1.2213740458015268,
-      "grad_norm": 3.7343335151672363,
+      "grad_norm": 0.8423321843147278,
       "learning_rate": 0.00013931297709923664,
-      "loss": 0.3722,
+      "loss": 0.126,
       "step": 160
     },
     {
       "epoch": 1.297709923664122,
-      "grad_norm": 3.1330108642578125,
+      "grad_norm": 0.4985540211200714,
       "learning_rate": 0.0001354961832061069,
-      "loss": 0.3455,
+      "loss": 0.1103,
       "step": 170
     },
     {
       "epoch": 1.3740458015267176,
-      "grad_norm": 3.1974072456359863,
+      "grad_norm": 4.837319850921631,
       "learning_rate": 0.0001316793893129771,
-      "loss": 0.4522,
+      "loss": 0.1849,
       "step": 180
     },
     {
       "epoch": 1.450381679389313,
-      "grad_norm": 4.500912189483643,
+      "grad_norm": 4.57224702835083,
       "learning_rate": 0.00012786259541984734,
-      "loss": 0.5162,
+      "loss": 0.195,
       "step": 190
     },
     {
       "epoch": 1.5267175572519083,
-      "grad_norm": 1.8331102132797241,
+      "grad_norm": 0.5998224020004272,
       "learning_rate": 0.00012404580152671757,
-      "loss": 0.4232,
+      "loss": 0.05,
       "step": 200
     },
     {
       "epoch": 1.5267175572519083,
-      "eval_accuracy": 0.9538043478260869,
-      "eval_loss": 0.24539989233016968,
-      "eval_runtime": 1.9758,
-      "eval_samples_per_second": 186.25,
-      "eval_steps_per_second": 23.281,
+      "eval_accuracy": 0.9592391304347826,
+      "eval_loss": 0.16003353893756866,
+      "eval_runtime": 1.5924,
+      "eval_samples_per_second": 231.101,
+      "eval_steps_per_second": 28.888,
       "step": 200
     },
     {
       "epoch": 1.6030534351145038,
-      "grad_norm": 5.288910388946533,
+      "grad_norm": 2.8493752479553223,
       "learning_rate": 0.0001202290076335878,
-      "loss": 0.3414,
+      "loss": 0.3001,
       "step": 210
     },
     {
       "epoch": 1.6793893129770994,
-      "grad_norm": 3.0168659687042236,
+      "grad_norm": 0.12870310246944427,
       "learning_rate": 0.00011641221374045803,
-      "loss": 0.3141,
+      "loss": 0.0944,
       "step": 220
     },
     {
       "epoch": 1.7557251908396947,
-      "grad_norm": 3.6415915489196777,
+      "grad_norm": 6.482563018798828,
       "learning_rate": 0.00011259541984732824,
-      "loss": 0.3561,
+      "loss": 0.0905,
       "step": 230
     },
     {
       "epoch": 1.83206106870229,
-      "grad_norm": 4.600650787353516,
+      "grad_norm": 1.615530252456665,
       "learning_rate": 0.00010877862595419848,
-      "loss": 0.3937,
+      "loss": 0.1326,
       "step": 240
     },
     {
       "epoch": 1.9083969465648853,
-      "grad_norm": 1.985364317893982,
+      "grad_norm": 2.059842586517334,
       "learning_rate": 0.00010496183206106871,
-      "loss": 0.325,
+      "loss": 0.1274,
       "step": 250
     },
     {
       "epoch": 1.984732824427481,
-      "grad_norm": 4.19254732131958,
+      "grad_norm": 2.750730276107788,
       "learning_rate": 0.00010114503816793894,
-      "loss": 0.3214,
+      "loss": 0.2225,
       "step": 260
     },
     {
       "epoch": 2.0610687022900764,
-      "grad_norm": 0.3229253888130188,
+      "grad_norm": 0.04552418366074562,
       "learning_rate": 9.732824427480916e-05,
-      "loss": 0.2053,
+      "loss": 0.0418,
       "step": 270
     },
     {
       "epoch": 2.1374045801526718,
-      "grad_norm": 4.743760108947754,
+      "grad_norm": 3.4131999015808105,
       "learning_rate": 9.351145038167939e-05,
-      "loss": 0.3318,
+      "loss": 0.1439,
       "step": 280
     },
     {
       "epoch": 2.213740458015267,
-      "grad_norm": 2.43632435798645,
+      "grad_norm": 1.8281826972961426,
       "learning_rate": 8.969465648854962e-05,
-      "loss": 0.2364,
+      "loss": 0.1084,
       "step": 290
     },
     {
       "epoch": 2.2900763358778624,
-      "grad_norm": 0.9254801869392395,
+      "grad_norm": 0.03664281591773033,
       "learning_rate": 8.587786259541986e-05,
-      "loss": 0.1134,
+      "loss": 0.0579,
       "step": 300
     },
     {
       "epoch": 2.2900763358778624,
-      "eval_accuracy": 0.9755434782608695,
-      "eval_loss": 0.16888892650604248,
-      "eval_runtime": 1.9035,
-      "eval_samples_per_second": 193.324,
-      "eval_steps_per_second": 24.166,
+      "eval_accuracy": 0.9510869565217391,
+      "eval_loss": 0.161894753575325,
+      "eval_runtime": 1.5917,
+      "eval_samples_per_second": 231.199,
+      "eval_steps_per_second": 28.9,
       "step": 300
     },
     {
       "epoch": 2.366412213740458,
-      "grad_norm": 6.0736894607543945,
+      "grad_norm": 10.416833877563477,
       "learning_rate": 8.206106870229007e-05,
-      "loss": 0.2712,
+      "loss": 0.1502,
       "step": 310
     },
     {
       "epoch": 2.4427480916030535,
-      "grad_norm": 7.306392192840576,
+      "grad_norm": 2.426678419113159,
       "learning_rate": 7.824427480916031e-05,
-      "loss": 0.3705,
+      "loss": 0.2334,
       "step": 320
     },
     {
       "epoch": 2.519083969465649,
-      "grad_norm": 0.37736839056015015,
+      "grad_norm": 5.191472053527832,
       "learning_rate": 7.442748091603053e-05,
-      "loss": 0.2431,
+      "loss": 0.0829,
       "step": 330
     },
     {
       "epoch": 2.595419847328244,
-      "grad_norm": 3.2378218173980713,
+      "grad_norm": 2.1241517066955566,
       "learning_rate": 7.061068702290077e-05,
-      "loss": 0.2495,
+      "loss": 0.066,
       "step": 340
     },
     {
       "epoch": 2.67175572519084,
-      "grad_norm": 4.0994086265563965,
+      "grad_norm": 0.10309349745512009,
       "learning_rate": 6.6793893129771e-05,
-      "loss": 0.2218,
+      "loss": 0.1356,
       "step": 350
     },
     {
       "epoch": 2.7480916030534353,
-      "grad_norm": 0.19563277065753937,
+      "grad_norm": 0.8078840374946594,
       "learning_rate": 6.297709923664122e-05,
-      "loss": 0.2717,
+      "loss": 0.09,
       "step": 360
     },
     {
       "epoch": 2.8244274809160306,
-      "grad_norm": 2.251434803009033,
+      "grad_norm": 0.7653095126152039,
       "learning_rate": 5.916030534351146e-05,
-      "loss": 0.134,
+      "loss": 0.0678,
       "step": 370
     },
     {
       "epoch": 2.900763358778626,
-      "grad_norm": 2.093945026397705,
+      "grad_norm": 0.1392490267753601,
       "learning_rate": 5.534351145038168e-05,
-      "loss": 0.1724,
+      "loss": 0.0532,
       "step": 380
     },
     {
       "epoch": 2.9770992366412212,
-      "grad_norm": 2.778428554534912,
+      "grad_norm": 7.884419918060303,
       "learning_rate": 5.152671755725191e-05,
-      "loss": 0.2283,
+      "loss": 0.1382,
       "step": 390
     },
     {
       "epoch": 3.053435114503817,
-      "grad_norm": 6.020068168640137,
+      "grad_norm": 10.337115287780762,
       "learning_rate": 4.7709923664122144e-05,
-      "loss": 0.2237,
+      "loss": 0.1181,
       "step": 400
     },
     {
       "epoch": 3.053435114503817,
-      "eval_accuracy": 0.9592391304347826,
-      "eval_loss": 0.16388548910617828,
-      "eval_runtime": 1.6041,
-      "eval_samples_per_second": 229.414,
-      "eval_steps_per_second": 28.677,
+      "eval_accuracy": 0.9809782608695652,
+      "eval_loss": 0.06854937225580215,
+      "eval_runtime": 2.5796,
+      "eval_samples_per_second": 142.659,
+      "eval_steps_per_second": 17.832,
       "step": 400
     },
     {
       "epoch": 3.1297709923664123,
-      "grad_norm": 0.23176027834415436,
+      "grad_norm": 0.06403453648090363,
       "learning_rate": 4.389312977099237e-05,
-      "loss": 0.2231,
+      "loss": 0.1245,
       "step": 410
     },
     {
       "epoch": 3.2061068702290076,
-      "grad_norm": 2.9403698444366455,
+      "grad_norm": 3.0858404636383057,
       "learning_rate": 4.00763358778626e-05,
-      "loss": 0.1379,
+      "loss": 0.0901,
       "step": 420
     },
     {
       "epoch": 3.282442748091603,
-      "grad_norm": 3.401761531829834,
+      "grad_norm": 1.1947516202926636,
       "learning_rate": 3.625954198473282e-05,
-      "loss": 0.2339,
+      "loss": 0.1319,
       "step": 430
     },
     {
       "epoch": 3.3587786259541983,
-      "grad_norm": 2.4639177322387695,
+      "grad_norm": 2.4845542907714844,
       "learning_rate": 3.2442748091603054e-05,
-      "loss": 0.1795,
+      "loss": 0.0932,
       "step": 440
     },
     {
       "epoch": 3.435114503816794,
-      "grad_norm": 3.926365613937378,
+      "grad_norm": 0.7602748870849609,
       "learning_rate": 2.862595419847328e-05,
-      "loss": 0.1326,
+      "loss": 0.0749,
       "step": 450
     },
     {
       "epoch": 3.5114503816793894,
-      "grad_norm": 3.4511287212371826,
+      "grad_norm": 3.669577121734619,
       "learning_rate": 2.4809160305343512e-05,
-      "loss": 0.2162,
+      "loss": 0.1067,
       "step": 460
     },
     {
       "epoch": 3.5877862595419847,
-      "grad_norm": 0.1071397215127945,
+      "grad_norm": 0.02125421166419983,
       "learning_rate": 2.099236641221374e-05,
-      "loss": 0.0821,
+      "loss": 0.0278,
       "step": 470
     },
     {
       "epoch": 3.66412213740458,
-      "grad_norm": 0.11275670677423477,
+      "grad_norm": 0.025344278663396835,
       "learning_rate": 1.717557251908397e-05,
-      "loss": 0.0965,
+      "loss": 0.0717,
       "step": 480
     },
     {
       "epoch": 3.7404580152671754,
-      "grad_norm": 1.8266428709030151,
+      "grad_norm": 0.454380601644516,
       "learning_rate": 1.3358778625954198e-05,
-      "loss": 0.2015,
+      "loss": 0.1241,
       "step": 490
     },
     {
       "epoch": 3.816793893129771,
-      "grad_norm": 1.146474003791809,
+      "grad_norm": 0.49031591415405273,
       "learning_rate": 9.541984732824428e-06,
-      "loss": 0.1431,
+      "loss": 0.1321,
       "step": 500
     },
     {
       "epoch": 3.816793893129771,
-      "eval_accuracy": 0.9728260869565217,
-      "eval_loss": 0.10525541752576828,
-      "eval_runtime": 1.5956,
-      "eval_samples_per_second": 230.634,
-      "eval_steps_per_second": 28.829,
+      "eval_accuracy": 0.9809782608695652,
+      "eval_loss": 0.0674990862607956,
+      "eval_runtime": 1.6192,
+      "eval_samples_per_second": 227.276,
+      "eval_steps_per_second": 28.409,
       "step": 500
     },
     {
       "epoch": 3.8931297709923665,
-      "grad_norm": 4.4021992683410645,
+      "grad_norm": 7.950806617736816,
       "learning_rate": 5.725190839694657e-06,
-      "loss": 0.1294,
+      "loss": 0.1726,
       "step": 510
     },
     {
       "epoch": 3.969465648854962,
-      "grad_norm": 0.27708983421325684,
+      "grad_norm": 0.29777708649635315,
       "learning_rate": 1.908396946564886e-06,
-      "loss": 0.1359,
+      "loss": 0.0653,
       "step": 520
     },
     {
       "epoch": 4.0,
       "step": 524,
       "total_flos": 6.45382209997357e+17,
-      "train_loss": 0.4479620875293062,
-      "train_runtime": 145.1835,
-      "train_samples_per_second": 57.362,
-      "train_steps_per_second": 3.609
+      "train_loss": 0.13892418100633694,
+      "train_runtime": 142.587,
+      "train_samples_per_second": 58.406,
+      "train_steps_per_second": 3.675
     }
   ],
   "logging_steps": 10,