Model save

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+image_0.png filter=lfs diff=lfs merge=lfs -text
+image_1.png filter=lfs diff=lfs merge=lfs -text
+image_2.png filter=lfs diff=lfs merge=lfs -text
+image_3.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -18,8 +18,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3390
 - Accuracy: 0.925
+- Loss: 1.3390
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3069        | 1.0   | 170  | 1.3390          | 0.925    |
+| Training Loss | Epoch | Step | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| 1.3069        | 1.0   | 170  | 0.925    | 1.3390          |
 
 
 ### Framework versions

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.925,
+    "eval_loss": 1.3389760255813599,
+    "eval_runtime": 3.7035,
+    "eval_samples_per_second": 64.803,
+    "eval_steps_per_second": 8.1,
+    "total_flos": 1.0539477329117184e+17,
+    "train_loss": 1.6158509927637437,
+    "train_runtime": 77.4929,
+    "train_samples_per_second": 17.55,
+    "train_steps_per_second": 2.194
+}

config.json

@@ -40,7 +40,6 @@
   "patch_size": 16,
   "pooler_act": "tanh",
   "pooler_output_size": 768,
-  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "transformers_version": "4.56.1"
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.925,
+    "eval_loss": 1.3389760255813599,
+    "eval_runtime": 3.7035,
+    "eval_samples_per_second": 64.803,
+    "eval_steps_per_second": 8.1
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.0539477329117184e+17,
+    "train_loss": 1.6158509927637437,
+    "train_runtime": 77.4929,
+    "train_samples_per_second": 17.55,
+    "train_steps_per_second": 2.194
+}

trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_global_step": 170,
+  "best_metric": 1.3389760255813599,
+  "best_model_checkpoint": "./mangoes/checkpoint-170",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 1.954006552696228,
+      "learning_rate": 1.8941176470588238e-05,
+      "loss": 2.0442,
+      "step": 10
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 3.1689231395721436,
+      "learning_rate": 1.776470588235294e-05,
+      "loss": 2.0181,
+      "step": 20
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 3.157071352005005,
+      "learning_rate": 1.658823529411765e-05,
+      "loss": 1.9073,
+      "step": 30
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 2.8379974365234375,
+      "learning_rate": 1.5411764705882356e-05,
+      "loss": 1.8325,
+      "step": 40
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 3.095369815826416,
+      "learning_rate": 1.423529411764706e-05,
+      "loss": 1.7749,
+      "step": 50
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 3.269249677658081,
+      "learning_rate": 1.3058823529411766e-05,
+      "loss": 1.7894,
+      "step": 60
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 2.953714370727539,
+      "learning_rate": 1.1882352941176472e-05,
+      "loss": 1.6664,
+      "step": 70
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 3.622612237930298,
+      "learning_rate": 1.0705882352941178e-05,
+      "loss": 1.6351,
+      "step": 80
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 3.304643154144287,
+      "learning_rate": 9.529411764705882e-06,
+      "loss": 1.5905,
+      "step": 90
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 3.047823667526245,
+      "learning_rate": 8.35294117647059e-06,
+      "loss": 1.4602,
+      "step": 100
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 3.3985748291015625,
+      "learning_rate": 7.176470588235295e-06,
+      "loss": 1.5058,
+      "step": 110
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 3.7313411235809326,
+      "learning_rate": 6e-06,
+      "loss": 1.4221,
+      "step": 120
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 3.2533087730407715,
+      "learning_rate": 4.823529411764706e-06,
+      "loss": 1.4311,
+      "step": 130
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 3.58194637298584,
+      "learning_rate": 3.6470588235294117e-06,
+      "loss": 1.3677,
+      "step": 140
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 2.956484317779541,
+      "learning_rate": 2.470588235294118e-06,
+      "loss": 1.3706,
+      "step": 150
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 3.5362460613250732,
+      "learning_rate": 1.2941176470588237e-06,
+      "loss": 1.3467,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1102607250213623,
+      "learning_rate": 1.1764705882352942e-07,
+      "loss": 1.3069,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.925,
+      "eval_loss": 1.3389760255813599,
+      "eval_runtime": 3.7037,
+      "eval_samples_per_second": 64.8,
+      "eval_steps_per_second": 8.1,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "step": 170,
+      "total_flos": 1.0539477329117184e+17,
+      "train_loss": 1.6158509927637437,
+      "train_runtime": 77.4929,
+      "train_samples_per_second": 17.55,
+      "train_steps_per_second": 2.194
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0539477329117184e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997a6e4fe36bfd648c3fb14e63a3370fd6401883641dbd5f408384d32a4d6c75
+oid sha256:5cb67eff64db67cd107ce7365441a071cd571805b0125c9e753dc3e1e7165c04
 size 5777