End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.6529126213592233
+      value: 0.6808059384941676
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6814
-- F1: 0.6529
+- Loss: 0.6882
+- F1: 0.6808
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.6808059384941676,
+    "eval_loss": 0.6882463097572327,
+    "eval_runtime": 15.1393,
+    "eval_samples_per_second": 42.274,
+    "eval_steps_per_second": 1.321,
+    "total_flos": 1.3494104908807864e+18,
+    "train_loss": 0.7046969166508428,
+    "train_runtime": 848.1758,
+    "train_samples_per_second": 20.345,
+    "train_steps_per_second": 0.159
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.6808059384941676,
+    "eval_loss": 0.6882463097572327,
+    "eval_runtime": 15.1393,
+    "eval_samples_per_second": 42.274,
+    "eval_steps_per_second": 1.321
+}

runs/Apr29_07-42-21_22d85605c382/events.out.tfevents.1714377472.22d85605c382.2088.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eba7866502c6f148f3c4f35e7de1ca54ea5c6d39f452c6abfbaefaa6df68d4a
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3494104908807864e+18,
+    "train_loss": 0.7046969166508428,
+    "train_runtime": 848.1758,
+    "train_samples_per_second": 20.345,
+    "train_steps_per_second": 0.159
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": 0.6808059384941676,
+  "best_model_checkpoint": "dinov2-base-finetuned-eurosat/checkpoint-90",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 8.703512191772461,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.7234,
+      "step": 10
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.468322277069092,
+      "learning_rate": 4.75206611570248e-05,
+      "loss": 0.7517,
+      "step": 20
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 6.569424629211426,
+      "learning_rate": 4.338842975206612e-05,
+      "loss": 0.7212,
+      "step": 30
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 3.0393030643463135,
+      "learning_rate": 3.925619834710744e-05,
+      "loss": 0.6972,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5401929260450161,
+      "eval_loss": 0.6850488781929016,
+      "eval_runtime": 14.9955,
+      "eval_samples_per_second": 42.679,
+      "eval_steps_per_second": 1.334,
+      "step": 45
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 19.1541748046875,
+      "learning_rate": 3.512396694214876e-05,
+      "loss": 0.7277,
+      "step": 50
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 16.108083724975586,
+      "learning_rate": 3.099173553719008e-05,
+      "loss": 0.7382,
+      "step": 60
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.285812258720398,
+      "learning_rate": 2.6859504132231405e-05,
+      "loss": 0.7041,
+      "step": 70
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 3.1954760551452637,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 0.6853,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.845994472503662,
+      "learning_rate": 1.859504132231405e-05,
+      "loss": 0.6839,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6808059384941676,
+      "eval_loss": 0.6882463097572327,
+      "eval_runtime": 15.0867,
+      "eval_samples_per_second": 42.421,
+      "eval_steps_per_second": 1.326,
+      "step": 90
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 6.143222808837891,
+      "learning_rate": 1.4462809917355372e-05,
+      "loss": 0.6805,
+      "step": 100
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.5121873617172241,
+      "learning_rate": 1.0330578512396695e-05,
+      "loss": 0.6844,
+      "step": 110
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.6525880694389343,
+      "learning_rate": 6.198347107438017e-06,
+      "loss": 0.6964,
+      "step": 120
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 4.430673599243164,
+      "learning_rate": 2.066115702479339e-06,
+      "loss": 0.6829,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6529126213592233,
+      "eval_loss": 0.6814367175102234,
+      "eval_runtime": 15.0867,
+      "eval_samples_per_second": 42.421,
+      "eval_steps_per_second": 1.326,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "step": 135,
+      "total_flos": 1.3494104908807864e+18,
+      "train_loss": 0.7046969166508428,
+      "train_runtime": 848.1758,
+      "train_samples_per_second": 20.345,
+      "train_steps_per_second": 0.159
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.3494104908807864e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}