End of training

README.md

@@ -45,7 +45,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0794
+- Loss: 0.0266
 - Precision: 0.9936
 - Recall: 0.9934
 - F1: 0.9934
@@ -82,21 +82,24 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy | Top1 Accuracy | Error Rate |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
-| 1.576         | 1.0   | 38   | 1.5660          | 0.3007    | 0.3684 | 0.2952 | 0.3479   | 0.3684        | 0.6521     |
-| 1.5469        | 2.0   | 76   | 1.5353          | 0.3141    | 0.4079 | 0.3215 | 0.3854   | 0.4079        | 0.6146     |
-| 1.5081        | 3.0   | 114  | 1.4782          | 0.5684    | 0.4671 | 0.3961 | 0.4436   | 0.4671        | 0.5564     |
-| 1.4278        | 4.0   | 152  | 1.3718          | 0.7088    | 0.6053 | 0.5840 | 0.5866   | 0.6053        | 0.4134     |
-| 1.2938        | 5.0   | 190  | 1.1909          | 0.8582    | 0.8355 | 0.8378 | 0.8290   | 0.8355        | 0.1710     |
-| 1.0696        | 6.0   | 228  | 0.9353          | 0.9243    | 0.9211 | 0.9215 | 0.9205   | 0.9211        | 0.0795     |
-| 0.789         | 7.0   | 266  | 0.6347          | 0.9680    | 0.9671 | 0.9673 | 0.9691   | 0.9671        | 0.0309     |
-| 0.506         | 8.0   | 304  | 0.3910          | 0.9750    | 0.9737 | 0.9739 | 0.9752   | 0.9737        | 0.0248     |
-| 0.2876        | 9.0   | 342  | 0.2126          | 0.9808    | 0.9803 | 0.9802 | 0.9814   | 0.9803        | 0.0186     |
-| 0.1722        | 10.0  | 380  | 0.1409          | 0.9809    | 0.9803 | 0.9799 | 0.9818   | 0.9803        | 0.0182     |
-| 0.1082        | 11.0  | 418  | 0.0794          | 0.9936    | 0.9934 | 0.9934 | 0.9939   | 0.9934        | 0.0061     |
-| 0.0715        | 12.0  | 456  | 0.0577          | 0.9936    | 0.9934 | 0.9934 | 0.9939   | 0.9934        | 0.0061     |
-| 0.0492        | 13.0  | 494  | 0.0440          | 0.9872    | 0.9868 | 0.9867 | 0.9879   | 0.9868        | 0.0121     |
+| Training Loss | Epoch | Step | Accuracy | Error Rate | F1     | Validation Loss | Precision | Recall | Top1 Accuracy |
+|:-------------:|:-----:|:----:|:--------:|:----------:|:------:|:---------------:|:---------:|:------:|:-------------:|
+| 1.576         | 1.0   | 38   | 0.3479   | 0.6521     | 0.2952 | 1.5660          | 0.3007    | 0.3684 | 0.3684        |
+| 1.5469        | 2.0   | 76   | 0.3854   | 0.6146     | 0.3215 | 1.5353          | 0.3141    | 0.4079 | 0.4079        |
+| 1.5081        | 3.0   | 114  | 0.4436   | 0.5564     | 0.3961 | 1.4782          | 0.5684    | 0.4671 | 0.4671        |
+| 1.4278        | 4.0   | 152  | 0.5866   | 0.4134     | 0.5840 | 1.3718          | 0.7088    | 0.6053 | 0.6053        |
+| 1.2938        | 5.0   | 190  | 0.8290   | 0.1710     | 0.8378 | 1.1909          | 0.8582    | 0.8355 | 0.8355        |
+| 1.0696        | 6.0   | 228  | 0.9205   | 0.0795     | 0.9215 | 0.9353          | 0.9243    | 0.9211 | 0.9211        |
+| 0.789         | 7.0   | 266  | 0.9691   | 0.0309     | 0.9673 | 0.6347          | 0.9680    | 0.9671 | 0.9671        |
+| 0.506         | 8.0   | 304  | 0.9752   | 0.0248     | 0.9739 | 0.3910          | 0.9750    | 0.9737 | 0.9737        |
+| 0.2876        | 9.0   | 342  | 0.9814   | 0.0186     | 0.9802 | 0.2126          | 0.9808    | 0.9803 | 0.9803        |
+| 0.1722        | 10.0  | 380  | 0.9818   | 0.0182     | 0.9799 | 0.1409          | 0.9809    | 0.9803 | 0.9803        |
+| 0.1082        | 11.0  | 418  | 0.9939   | 0.0061     | 0.9934 | 0.0794          | 0.9936    | 0.9934 | 0.9934        |
+| 0.0715        | 12.0  | 456  | 0.9939   | 0.0061     | 0.9934 | 0.0577          | 0.9936    | 0.9934 | 0.9934        |
+| 0.0492        | 13.0  | 494  | 0.9879   | 0.0121     | 0.9867 | 0.0440          | 0.9872    | 0.9868 | 0.9868        |
+| 0.0375        | 14.0  | 532  | 0.0266   | 0.9936     | 0.9934 | 0.9934          | 0.9939    | 0.9934 | 0.0061        |
+| 0.029         | 15.0  | 570  | 0.0313   | 0.9936     | 0.9934 | 0.9934          | 0.9939    | 0.9934 | 0.0061        |
+| 0.0158        | 16.0  | 608  | 0.0408   | 0.9872     | 0.9868 | 0.9867          | 0.9879    | 0.9868 | 0.0121        |
 
 
 ### Framework versions

all_results.json

@@ -1,18 +1,18 @@
 {
-    "epoch": 13.0,
+    "epoch": 16.0,
     "eval_accuracy": 0.9939393939393939,
     "eval_error_rate": 0.0060606060606061,
     "eval_f1": 0.993419541966282,
-    "eval_loss": 0.0794038251042366,
+    "eval_loss": 0.02658209018409252,
     "eval_precision": 0.9936145510835913,
     "eval_recall": 0.993421052631579,
-    "eval_runtime": 51.0106,
-    "eval_samples_per_second": 2.98,
-    "eval_steps_per_second": 0.098,
+    "eval_runtime": 48.6228,
+    "eval_samples_per_second": 3.126,
+    "eval_steps_per_second": 0.103,
     "eval_top1_accuracy": 0.993421052631579,
-    "total_flos": 3.972506461105029e+17,
-    "train_loss": 0.8004542765347099,
-    "train_runtime": 7158.591,
-    "train_samples_per_second": 5.096,
-    "train_steps_per_second": 0.159
+    "total_flos": 4.889238721360036e+17,
+    "train_loss": 0.005142551405649436,
+    "train_runtime": 1686.6977,
+    "train_samples_per_second": 21.628,
+    "train_steps_per_second": 0.676
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 13.0,
+    "epoch": 16.0,
     "eval_accuracy": 0.9939393939393939,
     "eval_error_rate": 0.0060606060606061,
     "eval_f1": 0.993419541966282,
-    "eval_loss": 0.0794038251042366,
+    "eval_loss": 0.02658209018409252,
     "eval_precision": 0.9936145510835913,
     "eval_recall": 0.993421052631579,
-    "eval_runtime": 51.0106,
-    "eval_samples_per_second": 2.98,
-    "eval_steps_per_second": 0.098,
+    "eval_runtime": 48.6228,
+    "eval_samples_per_second": 3.126,
+    "eval_steps_per_second": 0.103,
     "eval_top1_accuracy": 0.993421052631579
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0799eed45249c597bd5706cd54239ba58459cb5916a27dddda3eccc89547767d
+oid sha256:62798162e3f57ffa189d6ee7c57129c330720ace9dcf029005622f20bf4eb7dd
 size 111317164

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 13.0,
-    "total_flos": 3.972506461105029e+17,
-    "train_loss": 0.8004542765347099,
-    "train_runtime": 7158.591,
-    "train_samples_per_second": 5.096,
-    "train_steps_per_second": 0.159
+    "epoch": 16.0,
+    "total_flos": 4.889238721360036e+17,
+    "train_loss": 0.005142551405649436,
+    "train_runtime": 1686.6977,
+    "train_samples_per_second": 21.628,
+    "train_steps_per_second": 0.676
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9939393939393939,
-  "best_model_checkpoint": "convnext-tiny-224-finetuned-barkley\\checkpoint-418",
-  "epoch": 13.0,
+  "best_metric": 0.02658209018409252,
+  "best_model_checkpoint": "convnext-tiny-224-finetuned-barkley\\checkpoint-532",
+  "epoch": 16.0,
   "eval_steps": 500,
-  "global_step": 494,
+  "global_step": 608,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -334,13 +334,88 @@
       "step": 494
     },
     {
-      "epoch": 13.0,
-      "step": 494,
-      "total_flos": 3.972506461105029e+17,
-      "train_loss": 0.8004542765347099,
-      "train_runtime": 7158.591,
-      "train_samples_per_second": 5.096,
-      "train_steps_per_second": 0.159
+      "epoch": 14.0,
+      "train_accuracy": 0.9950657894736842
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.6904532313346863,
+      "learning_rate": 1.9527753116224055e-05,
+      "loss": 0.0375,
+      "step": 532
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9939393939393939,
+      "eval_error_rate": 0.0060606060606061,
+      "eval_f1": 0.993419541966282,
+      "eval_loss": 0.02658209018409252,
+      "eval_precision": 0.9936145510835913,
+      "eval_recall": 0.993421052631579,
+      "eval_runtime": 52.868,
+      "eval_samples_per_second": 2.875,
+      "eval_steps_per_second": 0.095,
+      "eval_top1_accuracy": 0.993421052631579,
+      "step": 532
+    },
+    {
+      "epoch": 15.0,
+      "train_accuracy": 0.993421052631579
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.3837875127792358,
+      "learning_rate": 1.911506206288264e-05,
+      "loss": 0.029,
+      "step": 570
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9939393939393939,
+      "eval_error_rate": 0.0060606060606061,
+      "eval_f1": 0.993419541966282,
+      "eval_loss": 0.03128606453537941,
+      "eval_precision": 0.9936145510835913,
+      "eval_recall": 0.993421052631579,
+      "eval_runtime": 52.6477,
+      "eval_samples_per_second": 2.887,
+      "eval_steps_per_second": 0.095,
+      "eval_top1_accuracy": 0.993421052631579,
+      "step": 570
+    },
+    {
+      "epoch": 16.0,
+      "train_accuracy": 0.9985380116959064
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.590073823928833,
+      "learning_rate": 1.8565251293796298e-05,
+      "loss": 0.0158,
+      "step": 608
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9878787878787879,
+      "eval_error_rate": 0.012121212121212088,
+      "eval_f1": 0.9867362170674966,
+      "eval_loss": 0.04083804041147232,
+      "eval_precision": 0.9872349657566376,
+      "eval_recall": 0.9868421052631579,
+      "eval_runtime": 52.9598,
+      "eval_samples_per_second": 2.87,
+      "eval_steps_per_second": 0.094,
+      "eval_top1_accuracy": 0.9868421052631579,
+      "step": 608
+    },
+    {
+      "epoch": 16.0,
+      "step": 608,
+      "total_flos": 4.889238721360036e+17,
+      "train_loss": 0.005142551405649436,
+      "train_runtime": 1686.6977,
+      "train_samples_per_second": 21.628,
+      "train_steps_per_second": 0.676
     }
   ],
   "logging_steps": 500,
@@ -369,7 +444,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.972506461105029e+17,
+  "total_flos": 4.889238721360036e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32c9a024fd0fe5d70f0247b1ad721619779776bf233e0e5351cdb8332e17696
+oid sha256:d1b57bacbaaf9003431d769cf77cb4ade538a6e4c81615d2dad23b4a752322a3
 size 5176