Training in progress, epoch 121

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7153846153846154
+      value: 0.5846153846153846
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1003
-- Accuracy: 0.7154
+- Loss: 2.5403
+- Accuracy: 0.5846
 
 ## Model description
 
@@ -60,7 +60,7 @@ The following hyperparameters were used during training:
 - seed: 1337
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 150.0
+- num_epochs: 120.0
 
 ### Training results
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 150.0,
-    "eval_accuracy": 0.7153846153846154,
-    "eval_loss": 2.100327730178833,
-    "eval_runtime": 2.528,
-    "eval_samples_per_second": 51.425,
-    "eval_steps_per_second": 0.791,
-    "train_loss": 0.2745589065551758,
-    "train_runtime": 1386.6967,
-    "train_samples_per_second": 56.249,
-    "train_steps_per_second": 0.757
+    "epoch": 120.0,
+    "eval_accuracy": 0.5846153846153846,
+    "eval_loss": 2.5402629375457764,
+    "eval_runtime": 2.5184,
+    "eval_samples_per_second": 51.619,
+    "eval_steps_per_second": 0.794,
+    "train_loss": 0.3072653747740246,
+    "train_runtime": 892.0889,
+    "train_samples_per_second": 69.948,
+    "train_steps_per_second": 0.942
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 150.0,
-    "eval_accuracy": 0.7153846153846154,
-    "eval_loss": 2.100327730178833,
-    "eval_runtime": 2.528,
-    "eval_samples_per_second": 51.425,
-    "eval_steps_per_second": 0.791
+    "epoch": 120.0,
+    "eval_accuracy": 0.5846153846153846,
+    "eval_loss": 2.5402629375457764,
+    "eval_runtime": 2.5184,
+    "eval_samples_per_second": 51.619,
+    "eval_steps_per_second": 0.794
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3cf5a5801c077654e03d1e4d3c08ef6f8e4aa414bd85c0b781d010a05b521c9
+oid sha256:e852752758dbcffb10d194303246407fb0e3152eade28c3cc950cef69ed147cc
 size 343377784

runs/Jan17_20-08-24_d06676088071/events.out.tfevents.1705522127.d06676088071.30248.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337736ec6d4369c0c807a5806b557302add774f4eb1a24730b77f8448d05612b
-size 19591
+oid sha256:c0e21286437dafa65d2446bed5a42350562a39927ce8fec1ac417b06e9b81d35
+size 16994

runs/Jan17_21-31-37_c6ad14a30b7d/events.out.tfevents.1705527135.c6ad14a30b7d.8359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b21097c39781b4afceb06efff2c95cba66586f50e01533f837a74c9b54bb7cf
+size 6325

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 150.0,
-    "train_loss": 0.2745589065551758,
-    "train_runtime": 1386.6967,
-    "train_samples_per_second": 56.249,
-    "train_steps_per_second": 0.757
+    "epoch": 120.0,
+    "train_loss": 0.3072653747740246,
+    "train_runtime": 892.0889,
+    "train_samples_per_second": 69.948,
+    "train_steps_per_second": 0.942
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.100327730178833,
-  "best_model_checkpoint": "./drive/MyDrive/repositories/torch_example_image-classification/outputs_letter3/checkpoint-1043",
-  "epoch": 150.0,
+  "best_metric": 2.5402629375457764,
+  "best_model_checkpoint": "./drive/MyDrive/repositories/torch_example_image-classification/outputs_letter3/checkpoint-840",
+  "epoch": 120.0,
   "eval_steps": 500,
-  "global_step": 1050,
+  "global_step": 840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1609,419 +1609,14 @@
       "train_runtime": 892.0889,
       "train_samples_per_second": 69.948,
       "train_steps_per_second": 0.942
-    },
-    {
-      "epoch": 121.0,
-      "eval_accuracy": 0.6307692307692307,
-      "eval_loss": 2.5144028663635254,
-      "eval_runtime": 2.3105,
-      "eval_samples_per_second": 56.264,
-      "eval_steps_per_second": 0.866,
-      "step": 847
-    },
-    {
-      "epoch": 121.43,
-      "learning_rate": 1.980952380952381e-05,
-      "loss": 1.654,
-      "step": 850
-    },
-    {
-      "epoch": 122.0,
-      "eval_accuracy": 0.6153846153846154,
-      "eval_loss": 2.498945474624634,
-      "eval_runtime": 2.3196,
-      "eval_samples_per_second": 56.043,
-      "eval_steps_per_second": 0.862,
-      "step": 854
-    },
-    {
-      "epoch": 122.86,
-      "learning_rate": 1.961904761904762e-05,
-      "loss": 1.5863,
-      "step": 860
-    },
-    {
-      "epoch": 123.0,
-      "eval_accuracy": 0.6230769230769231,
-      "eval_loss": 2.476050853729248,
-      "eval_runtime": 2.4097,
-      "eval_samples_per_second": 53.949,
-      "eval_steps_per_second": 0.83,
-      "step": 861
-    },
-    {
-      "epoch": 124.0,
-      "eval_accuracy": 0.6,
-      "eval_loss": 2.4536540508270264,
-      "eval_runtime": 2.5779,
-      "eval_samples_per_second": 50.428,
-      "eval_steps_per_second": 0.776,
-      "step": 868
-    },
-    {
-      "epoch": 124.29,
-      "learning_rate": 1.942857142857143e-05,
-      "loss": 1.5915,
-      "step": 870
-    },
-    {
-      "epoch": 125.0,
-      "eval_accuracy": 0.6076923076923076,
-      "eval_loss": 2.4367971420288086,
-      "eval_runtime": 2.4941,
-      "eval_samples_per_second": 52.123,
-      "eval_steps_per_second": 0.802,
-      "step": 875
-    },
-    {
-      "epoch": 125.71,
-      "learning_rate": 1.923809523809524e-05,
-      "loss": 1.5221,
-      "step": 880
-    },
-    {
-      "epoch": 126.0,
-      "eval_accuracy": 0.5923076923076923,
-      "eval_loss": 2.4394454956054688,
-      "eval_runtime": 2.3616,
-      "eval_samples_per_second": 55.047,
-      "eval_steps_per_second": 0.847,
-      "step": 882
-    },
-    {
-      "epoch": 127.0,
-      "eval_accuracy": 0.6076923076923076,
-      "eval_loss": 2.3990907669067383,
-      "eval_runtime": 2.6083,
-      "eval_samples_per_second": 49.84,
-      "eval_steps_per_second": 0.767,
-      "step": 889
-    },
-    {
-      "epoch": 127.14,
-      "learning_rate": 1.904761904761905e-05,
-      "loss": 1.5231,
-      "step": 890
-    },
-    {
-      "epoch": 128.0,
-      "eval_accuracy": 0.6153846153846154,
-      "eval_loss": 2.3942794799804688,
-      "eval_runtime": 2.6252,
-      "eval_samples_per_second": 49.519,
-      "eval_steps_per_second": 0.762,
-      "step": 896
-    },
-    {
-      "epoch": 128.57,
-      "learning_rate": 1.885714285714286e-05,
-      "loss": 1.4753,
-      "step": 900
-    },
-    {
-      "epoch": 129.0,
-      "eval_accuracy": 0.6307692307692307,
-      "eval_loss": 2.3880045413970947,
-      "eval_runtime": 2.4163,
-      "eval_samples_per_second": 53.801,
-      "eval_steps_per_second": 0.828,
-      "step": 903
-    },
-    {
-      "epoch": 130.0,
-      "learning_rate": 1.866666666666667e-05,
-      "loss": 1.456,
-      "step": 910
-    },
-    {
-      "epoch": 130.0,
-      "eval_accuracy": 0.6230769230769231,
-      "eval_loss": 2.367373466491699,
-      "eval_runtime": 2.4274,
-      "eval_samples_per_second": 53.556,
-      "eval_steps_per_second": 0.824,
-      "step": 910
-    },
-    {
-      "epoch": 131.0,
-      "eval_accuracy": 0.6,
-      "eval_loss": 2.3696095943450928,
-      "eval_runtime": 2.3933,
-      "eval_samples_per_second": 54.319,
-      "eval_steps_per_second": 0.836,
-      "step": 917
-    },
-    {
-      "epoch": 131.43,
-      "learning_rate": 1.8476190476190478e-05,
-      "loss": 1.4353,
-      "step": 920
-    },
-    {
-      "epoch": 132.0,
-      "eval_accuracy": 0.6153846153846154,
-      "eval_loss": 2.3404488563537598,
-      "eval_runtime": 2.4129,
-      "eval_samples_per_second": 53.877,
-      "eval_steps_per_second": 0.829,
-      "step": 924
-    },
-    {
-      "epoch": 132.86,
-      "learning_rate": 1.8285714285714288e-05,
-      "loss": 1.4062,
-      "step": 930
-    },
-    {
-      "epoch": 133.0,
-      "eval_accuracy": 0.6461538461538462,
-      "eval_loss": 2.3368117809295654,
-      "eval_runtime": 2.423,
-      "eval_samples_per_second": 53.653,
-      "eval_steps_per_second": 0.825,
-      "step": 931
-    },
-    {
-      "epoch": 134.0,
-      "eval_accuracy": 0.6230769230769231,
-      "eval_loss": 2.3077619075775146,
-      "eval_runtime": 2.4048,
-      "eval_samples_per_second": 54.058,
-      "eval_steps_per_second": 0.832,
-      "step": 938
-    },
-    {
-      "epoch": 134.29,
-      "learning_rate": 1.8095238095238097e-05,
-      "loss": 1.3738,
-      "step": 940
-    },
-    {
-      "epoch": 135.0,
-      "eval_accuracy": 0.6307692307692307,
-      "eval_loss": 2.3112919330596924,
-      "eval_runtime": 2.391,
-      "eval_samples_per_second": 54.37,
-      "eval_steps_per_second": 0.836,
-      "step": 945
-    },
-    {
-      "epoch": 135.71,
-      "learning_rate": 1.7904761904761907e-05,
-      "loss": 1.3566,
-      "step": 950
-    },
-    {
-      "epoch": 136.0,
-      "eval_accuracy": 0.6230769230769231,
-      "eval_loss": 2.2861361503601074,
-      "eval_runtime": 2.4243,
-      "eval_samples_per_second": 53.624,
-      "eval_steps_per_second": 0.825,
-      "step": 952
-    },
-    {
-      "epoch": 137.0,
-      "eval_accuracy": 0.6538461538461539,
-      "eval_loss": 2.2651076316833496,
-      "eval_runtime": 2.4617,
-      "eval_samples_per_second": 52.808,
-      "eval_steps_per_second": 0.812,
-      "step": 959
-    },
-    {
-      "epoch": 137.14,
-      "learning_rate": 1.7714285714285717e-05,
-      "loss": 1.3463,
-      "step": 960
-    },
-    {
-      "epoch": 138.0,
-      "eval_accuracy": 0.6615384615384615,
-      "eval_loss": 2.2631070613861084,
-      "eval_runtime": 2.4282,
-      "eval_samples_per_second": 53.537,
-      "eval_steps_per_second": 0.824,
-      "step": 966
-    },
-    {
-      "epoch": 138.57,
-      "learning_rate": 1.7523809523809526e-05,
-      "loss": 1.3058,
-      "step": 970
-    },
-    {
-      "epoch": 139.0,
-      "eval_accuracy": 0.6615384615384615,
-      "eval_loss": 2.2603201866149902,
-      "eval_runtime": 2.5878,
-      "eval_samples_per_second": 50.235,
-      "eval_steps_per_second": 0.773,
-      "step": 973
-    },
-    {
-      "epoch": 140.0,
-      "learning_rate": 1.7333333333333336e-05,
-      "loss": 1.2967,
-      "step": 980
-    },
-    {
-      "epoch": 140.0,
-      "eval_accuracy": 0.6461538461538462,
-      "eval_loss": 2.2615151405334473,
-      "eval_runtime": 2.5189,
-      "eval_samples_per_second": 51.611,
-      "eval_steps_per_second": 0.794,
-      "step": 980
-    },
-    {
-      "epoch": 141.0,
-      "eval_accuracy": 0.6461538461538462,
-      "eval_loss": 2.218820810317993,
-      "eval_runtime": 2.4255,
-      "eval_samples_per_second": 53.597,
-      "eval_steps_per_second": 0.825,
-      "step": 987
-    },
-    {
-      "epoch": 141.43,
-      "learning_rate": 1.7142857142857142e-05,
-      "loss": 1.2841,
-      "step": 990
-    },
-    {
-      "epoch": 142.0,
-      "eval_accuracy": 0.6615384615384615,
-      "eval_loss": 2.242035388946533,
-      "eval_runtime": 2.4254,
-      "eval_samples_per_second": 53.599,
-      "eval_steps_per_second": 0.825,
-      "step": 994
-    },
-    {
-      "epoch": 142.86,
-      "learning_rate": 1.6952380952380955e-05,
-      "loss": 1.24,
-      "step": 1000
-    },
-    {
-      "epoch": 143.0,
-      "eval_accuracy": 0.6307692307692307,
-      "eval_loss": 2.226486921310425,
-      "eval_runtime": 2.38,
-      "eval_samples_per_second": 54.621,
-      "eval_steps_per_second": 0.84,
-      "step": 1001
-    },
-    {
-      "epoch": 144.0,
-      "eval_accuracy": 0.6461538461538462,
-      "eval_loss": 2.212893486022949,
-      "eval_runtime": 2.5548,
-      "eval_samples_per_second": 50.885,
-      "eval_steps_per_second": 0.783,
-      "step": 1008
-    },
-    {
-      "epoch": 144.29,
-      "learning_rate": 1.6761904761904764e-05,
-      "loss": 1.2285,
-      "step": 1010
-    },
-    {
-      "epoch": 145.0,
-      "eval_accuracy": 0.6615384615384615,
-      "eval_loss": 2.227419376373291,
-      "eval_runtime": 2.4191,
-      "eval_samples_per_second": 53.738,
-      "eval_steps_per_second": 0.827,
-      "step": 1015
-    },
-    {
-      "epoch": 145.71,
-      "learning_rate": 1.6571428571428574e-05,
-      "loss": 1.2152,
-      "step": 1020
-    },
-    {
-      "epoch": 146.0,
-      "eval_accuracy": 0.6846153846153846,
-      "eval_loss": 2.18461537361145,
-      "eval_runtime": 2.34,
-      "eval_samples_per_second": 55.556,
-      "eval_steps_per_second": 0.855,
-      "step": 1022
-    },
-    {
-      "epoch": 147.0,
-      "eval_accuracy": 0.6615384615384615,
-      "eval_loss": 2.1721718311309814,
-      "eval_runtime": 2.5232,
-      "eval_samples_per_second": 51.522,
-      "eval_steps_per_second": 0.793,
-      "step": 1029
-    },
-    {
-      "epoch": 147.14,
-      "learning_rate": 1.6380952380952384e-05,
-      "loss": 1.187,
-      "step": 1030
-    },
-    {
-      "epoch": 148.0,
-      "eval_accuracy": 0.6846153846153846,
-      "eval_loss": 2.145458936691284,
-      "eval_runtime": 2.5242,
-      "eval_samples_per_second": 51.501,
-      "eval_steps_per_second": 0.792,
-      "step": 1036
-    },
-    {
-      "epoch": 148.57,
-      "learning_rate": 1.6190476190476193e-05,
-      "loss": 1.1794,
-      "step": 1040
-    },
-    {
-      "epoch": 149.0,
-      "eval_accuracy": 0.7153846153846154,
-      "eval_loss": 2.100327730178833,
-      "eval_runtime": 2.5331,
-      "eval_samples_per_second": 51.321,
-      "eval_steps_per_second": 0.79,
-      "step": 1043
-    },
-    {
-      "epoch": 150.0,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.1654,
-      "step": 1050
-    },
-    {
-      "epoch": 150.0,
-      "eval_accuracy": 0.7,
-      "eval_loss": 2.1009724140167236,
-      "eval_runtime": 2.3848,
-      "eval_samples_per_second": 54.512,
-      "eval_steps_per_second": 0.839,
-      "step": 1050
-    },
-    {
-      "epoch": 150.0,
-      "step": 1050,
-      "total_flos": 6.047083881086976e+18,
-      "train_loss": 0.2745589065551758,
-      "train_runtime": 1386.6967,
-      "train_samples_per_second": 56.249,
-      "train_steps_per_second": 0.757
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1050,
+  "max_steps": 840,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 150,
+  "num_train_epochs": 120,
   "save_steps": 500,
-  "total_flos": 6.047083881086976e+18,
+  "total_flos": 4.837667104869581e+18,
   "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b9794f8e1d194ce8b208459063679907a8cc824c4888328da098de85221d6d
-size 4984
+oid sha256:77b59a4c9ba56852593021933bca328cab101f76dc48bcef223b400e714cb46c
+size 4856