End of training

README.md

@@ -3,12 +3,29 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
 model-index:
 - name: vit-base-anime-e10_prompt_data
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9266666666666666
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 # vit-base-anime-e10_prompt_data
 
 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: 0.2713
+- Accuracy: 0.9267
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9266666666666666,
+    "eval_loss": 0.27128249406814575,
+    "eval_runtime": 63.9769,
+    "eval_samples_per_second": 9.378,
+    "eval_steps_per_second": 1.172,
+    "total_flos": 2.634727646896128e+18,
+    "train_loss": 0.21935006769965676,
+    "train_runtime": 2953.1098,
+    "train_samples_per_second": 11.513,
+    "train_steps_per_second": 1.439
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9266666666666666,
+    "eval_loss": 0.27128249406814575,
+    "eval_runtime": 63.9769,
+    "eval_samples_per_second": 9.378,
+    "eval_steps_per_second": 1.172
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.634727646896128e+18,
+    "train_loss": 0.21935006769965676,
+    "train_runtime": 2953.1098,
+    "train_samples_per_second": 11.513,
+    "train_steps_per_second": 1.439
+}

trainer_state.json

@@ -0,0 +1,337 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 3.403212308883667,
+      "learning_rate": 4.883529411764706e-05,
+      "loss": 0.5999,
+      "step": 100
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 3.9369142055511475,
+      "learning_rate": 4.765882352941177e-05,
+      "loss": 0.4832,
+      "step": 200
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 5.758166790008545,
+      "learning_rate": 4.6482352941176474e-05,
+      "loss": 0.429,
+      "step": 300
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 8.335492134094238,
+      "learning_rate": 4.530588235294118e-05,
+      "loss": 0.3882,
+      "step": 400
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 3.4791135787963867,
+      "learning_rate": 4.4129411764705886e-05,
+      "loss": 0.3203,
+      "step": 500
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 5.319788455963135,
+      "learning_rate": 4.295294117647059e-05,
+      "loss": 0.3308,
+      "step": 600
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 9.800257682800293,
+      "learning_rate": 4.177647058823529e-05,
+      "loss": 0.2995,
+      "step": 700
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 14.425982475280762,
+      "learning_rate": 4.0600000000000004e-05,
+      "loss": 0.313,
+      "step": 800
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.170698344707489,
+      "learning_rate": 3.942352941176471e-05,
+      "loss": 0.3574,
+      "step": 900
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.452454924583435,
+      "learning_rate": 3.8247058823529416e-05,
+      "loss": 0.2773,
+      "step": 1000
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.7341296076774597,
+      "learning_rate": 3.7070588235294115e-05,
+      "loss": 0.3076,
+      "step": 1100
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 5.775131702423096,
+      "learning_rate": 3.589411764705882e-05,
+      "loss": 0.2605,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 6.790212154388428,
+      "learning_rate": 3.4717647058823534e-05,
+      "loss": 0.2492,
+      "step": 1300
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 50.06572723388672,
+      "learning_rate": 3.354117647058824e-05,
+      "loss": 0.2808,
+      "step": 1400
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 13.668601989746094,
+      "learning_rate": 3.236470588235294e-05,
+      "loss": 0.2679,
+      "step": 1500
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 30.59315299987793,
+      "learning_rate": 3.1188235294117645e-05,
+      "loss": 0.1894,
+      "step": 1600
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.2560558617115021,
+      "learning_rate": 3.0011764705882355e-05,
+      "loss": 0.2447,
+      "step": 1700
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 6.998530387878418,
+      "learning_rate": 2.883529411764706e-05,
+      "loss": 0.1961,
+      "step": 1800
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 21.405479431152344,
+      "learning_rate": 2.7658823529411763e-05,
+      "loss": 0.1845,
+      "step": 1900
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.0605692863464355,
+      "learning_rate": 2.648235294117647e-05,
+      "loss": 0.2051,
+      "step": 2000
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.4075890779495239,
+      "learning_rate": 2.530588235294118e-05,
+      "loss": 0.2337,
+      "step": 2100
+    },
+    {
+      "epoch": 5.176470588235294,
+      "grad_norm": 0.1492820531129837,
+      "learning_rate": 2.4129411764705885e-05,
+      "loss": 0.1478,
+      "step": 2200
+    },
+    {
+      "epoch": 5.411764705882353,
+      "grad_norm": 17.102733612060547,
+      "learning_rate": 2.2952941176470587e-05,
+      "loss": 0.1272,
+      "step": 2300
+    },
+    {
+      "epoch": 5.647058823529412,
+      "grad_norm": 0.04777925834059715,
+      "learning_rate": 2.1776470588235297e-05,
+      "loss": 0.201,
+      "step": 2400
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 0.19522254168987274,
+      "learning_rate": 2.06e-05,
+      "loss": 0.2402,
+      "step": 2500
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 0.07973190397024155,
+      "learning_rate": 1.942352941176471e-05,
+      "loss": 0.1412,
+      "step": 2600
+    },
+    {
+      "epoch": 6.352941176470588,
+      "grad_norm": 1.31982421875,
+      "learning_rate": 1.824705882352941e-05,
+      "loss": 0.1503,
+      "step": 2700
+    },
+    {
+      "epoch": 6.588235294117647,
+      "grad_norm": 0.062359828501939774,
+      "learning_rate": 1.7070588235294117e-05,
+      "loss": 0.1466,
+      "step": 2800
+    },
+    {
+      "epoch": 6.823529411764706,
+      "grad_norm": 0.11714987456798553,
+      "learning_rate": 1.5894117647058823e-05,
+      "loss": 0.1276,
+      "step": 2900
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 29.877296447753906,
+      "learning_rate": 1.4717647058823531e-05,
+      "loss": 0.1515,
+      "step": 3000
+    },
+    {
+      "epoch": 7.294117647058823,
+      "grad_norm": 0.2120763063430786,
+      "learning_rate": 1.3541176470588235e-05,
+      "loss": 0.1284,
+      "step": 3100
+    },
+    {
+      "epoch": 7.529411764705882,
+      "grad_norm": 12.091958045959473,
+      "learning_rate": 1.2364705882352943e-05,
+      "loss": 0.1346,
+      "step": 3200
+    },
+    {
+      "epoch": 7.764705882352941,
+      "grad_norm": 0.07248464971780777,
+      "learning_rate": 1.1188235294117647e-05,
+      "loss": 0.1526,
+      "step": 3300
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.2186937779188156,
+      "learning_rate": 1.0011764705882353e-05,
+      "loss": 0.1607,
+      "step": 3400
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 2.143234968185425,
+      "learning_rate": 8.835294117647059e-06,
+      "loss": 0.127,
+      "step": 3500
+    },
+    {
+      "epoch": 8.470588235294118,
+      "grad_norm": 0.1842782199382782,
+      "learning_rate": 7.658823529411765e-06,
+      "loss": 0.09,
+      "step": 3600
+    },
+    {
+      "epoch": 8.705882352941176,
+      "grad_norm": 0.10567642003297806,
+      "learning_rate": 6.482352941176471e-06,
+      "loss": 0.1225,
+      "step": 3700
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 8.74448013305664,
+      "learning_rate": 5.305882352941176e-06,
+      "loss": 0.0993,
+      "step": 3800
+    },
+    {
+      "epoch": 9.176470588235293,
+      "grad_norm": 21.5183048248291,
+      "learning_rate": 4.129411764705882e-06,
+      "loss": 0.1746,
+      "step": 3900
+    },
+    {
+      "epoch": 9.411764705882353,
+      "grad_norm": 0.03366835415363312,
+      "learning_rate": 2.9529411764705886e-06,
+      "loss": 0.095,
+      "step": 4000
+    },
+    {
+      "epoch": 9.647058823529411,
+      "grad_norm": 0.2817438840866089,
+      "learning_rate": 1.7764705882352944e-06,
+      "loss": 0.0865,
+      "step": 4100
+    },
+    {
+      "epoch": 9.882352941176471,
+      "grad_norm": 22.497867584228516,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.0687,
+      "step": 4200
+    },
+    {
+      "epoch": 10.0,
+      "step": 4250,
+      "total_flos": 2.634727646896128e+18,
+      "train_loss": 0.21935006769965676,
+      "train_runtime": 2953.1098,
+      "train_samples_per_second": 11.513,
+      "train_steps_per_second": 1.439
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 2.634727646896128e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}