End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1107
+- Loss: 0.1577
 - Accuracy: 1.0
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 8.88888888888889,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.15774576365947723,
+    "eval_runtime": 0.7882,
+    "eval_samples_per_second": 24.105,
+    "eval_steps_per_second": 1.269,
+    "total_flos": 5.784002104833147e+17,
+    "train_loss": 0.22095599969228108,
+    "train_runtime": 349.6304,
+    "train_samples_per_second": 23.94,
+    "train_steps_per_second": 0.172
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.88888888888889,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.15774576365947723,
+    "eval_runtime": 0.7882,
+    "eval_samples_per_second": 24.105,
+    "eval_steps_per_second": 1.269
+}

runs/May06_23-00-41_6f336873e3ec/events.out.tfevents.1715037313.6f336873e3ec.1386.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907f90b5fcff6a622e9ece86020cd11a4ccd3ab78352afe91457906888f28824
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.88888888888889,
+    "total_flos": 5.784002104833147e+17,
+    "train_loss": 0.22095599969228108,
+    "train_runtime": 349.6304,
+    "train_samples_per_second": 23.94,
+    "train_steps_per_second": 0.172
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "vit-base-patch16-224-perros-y-gatos/checkpoint-27",
+  "epoch": 8.88888888888889,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8888888888888888,
+      "eval_accuracy": 0.5789473684210527,
+      "eval_loss": 0.6543071866035461,
+      "eval_runtime": 0.6563,
+      "eval_samples_per_second": 28.95,
+      "eval_steps_per_second": 1.524,
+      "step": 6
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.9131128787994385,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.5484,
+      "step": 12
+    },
+    {
+      "epoch": 1.925925925925926,
+      "eval_accuracy": 0.8421052631578947,
+      "eval_loss": 0.33853769302368164,
+      "eval_runtime": 0.5779,
+      "eval_samples_per_second": 32.875,
+      "eval_steps_per_second": 1.73,
+      "step": 13
+    },
+    {
+      "epoch": 2.962962962962963,
+      "eval_accuracy": 0.9473684210526315,
+      "eval_loss": 0.21231365203857422,
+      "eval_runtime": 0.7516,
+      "eval_samples_per_second": 25.278,
+      "eval_steps_per_second": 1.33,
+      "step": 20
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 1.116196870803833,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.2164,
+      "step": 24
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.15774576365947723,
+      "eval_runtime": 0.5695,
+      "eval_samples_per_second": 33.363,
+      "eval_steps_per_second": 1.756,
+      "step": 27
+    },
+    {
+      "epoch": 4.888888888888889,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.14037586748600006,
+      "eval_runtime": 0.576,
+      "eval_samples_per_second": 32.985,
+      "eval_steps_per_second": 1.736,
+      "step": 33
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 1.6009061336517334,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.1367,
+      "step": 36
+    },
+    {
+      "epoch": 5.925925925925926,
+      "eval_accuracy": 0.9473684210526315,
+      "eval_loss": 0.13751420378684998,
+      "eval_runtime": 0.5653,
+      "eval_samples_per_second": 33.609,
+      "eval_steps_per_second": 1.769,
+      "step": 40
+    },
+    {
+      "epoch": 6.962962962962963,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.13118219375610352,
+      "eval_runtime": 0.5765,
+      "eval_samples_per_second": 32.956,
+      "eval_steps_per_second": 1.735,
+      "step": 47
+    },
+    {
+      "epoch": 7.111111111111111,
+      "grad_norm": 1.245722770690918,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1155,
+      "step": 48
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.1139664426445961,
+      "eval_runtime": 0.5725,
+      "eval_samples_per_second": 33.189,
+      "eval_steps_per_second": 1.747,
+      "step": 54
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 1.4993633031845093,
+      "learning_rate": 0.0,
+      "loss": 0.0878,
+      "step": 60
+    },
+    {
+      "epoch": 8.88888888888889,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.11070940643548965,
+      "eval_runtime": 0.7286,
+      "eval_samples_per_second": 26.078,
+      "eval_steps_per_second": 1.373,
+      "step": 60
+    },
+    {
+      "epoch": 8.88888888888889,
+      "step": 60,
+      "total_flos": 5.784002104833147e+17,
+      "train_loss": 0.22095599969228108,
+      "train_runtime": 349.6304,
+      "train_samples_per_second": 23.94,
+      "train_steps_per_second": 0.172
+    }
+  ],
+  "logging_steps": 12,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5.784002104833147e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}