End of training

README.md

@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0389
+- Loss: 0.0452
 - Accuracy: 0.9914
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.85,
+    "eval_accuracy": 0.9913793103448276,
+    "eval_loss": 0.045198433101177216,
+    "eval_runtime": 1.064,
+    "eval_samples_per_second": 109.026,
+    "eval_steps_per_second": 3.76,
+    "total_flos": 3.914895315329188e+17,
+    "train_loss": 0.2852296233177185,
+    "train_runtime": 186.2852,
+    "train_samples_per_second": 27.887,
+    "train_steps_per_second": 0.215
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.85,
+    "eval_accuracy": 0.9913793103448276,
+    "eval_loss": 0.045198433101177216,
+    "eval_runtime": 1.064,
+    "eval_samples_per_second": 109.026,
+    "eval_steps_per_second": 3.76
+}

runs/May01_14-43-02_390a48ff2d93/events.out.tfevents.1714574845.390a48ff2d93.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187ee6dd7777de6335a71c67b317cc9469bd7cf171b907fb2c34912ad9f30ea6
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.85,
+    "total_flos": 3.914895315329188e+17,
+    "train_loss": 0.2852296233177185,
+    "train_runtime": 186.2852,
+    "train_samples_per_second": 27.887,
+    "train_steps_per_second": 0.215
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.9913793103448276,
+  "best_model_checkpoint": "deit-base-patch16-224-finetuned-footulcer/checkpoint-33",
+  "epoch": 4.848484848484849,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.2488032728433609,
+      "eval_runtime": 1.7452,
+      "eval_samples_per_second": 66.468,
+      "eval_steps_per_second": 2.292,
+      "step": 8
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 4.05413818359375,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5125,
+      "step": 10
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.9310344827586207,
+      "eval_loss": 0.1674669086933136,
+      "eval_runtime": 1.082,
+      "eval_samples_per_second": 107.209,
+      "eval_steps_per_second": 3.697,
+      "step": 16
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.395897388458252,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.2843,
+      "step": 20
+    },
+    {
+      "epoch": 2.91,
+      "eval_accuracy": 0.9827586206896551,
+      "eval_loss": 0.06786822527647018,
+      "eval_runtime": 1.0557,
+      "eval_samples_per_second": 109.877,
+      "eval_steps_per_second": 3.789,
+      "step": 24
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 4.113508701324463,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.1876,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9913793103448276,
+      "eval_loss": 0.045198433101177216,
+      "eval_runtime": 1.0467,
+      "eval_samples_per_second": 110.824,
+      "eval_steps_per_second": 3.822,
+      "step": 33
+    },
+    {
+      "epoch": 4.85,
+      "grad_norm": 2.2138736248016357,
+      "learning_rate": 0.0,
+      "loss": 0.1566,
+      "step": 40
+    },
+    {
+      "epoch": 4.85,
+      "eval_accuracy": 0.9913793103448276,
+      "eval_loss": 0.038901545107364655,
+      "eval_runtime": 1.0297,
+      "eval_samples_per_second": 112.652,
+      "eval_steps_per_second": 3.885,
+      "step": 40
+    },
+    {
+      "epoch": 4.85,
+      "step": 40,
+      "total_flos": 3.914895315329188e+17,
+      "train_loss": 0.2852296233177185,
+      "train_runtime": 186.2852,
+      "train_samples_per_second": 27.887,
+      "train_steps_per_second": 0.215
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3.914895315329188e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}