End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/convnext-xlarge-224-22k-1k](https://huggingface.co/facebook/convnext-xlarge-224-22k-1k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0165
+- Loss: 0.0354
 - Accuracy: 0.9921
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9921259842519685,
+    "eval_loss": 0.035393521189689636,
+    "eval_runtime": 1.6865,
+    "eval_samples_per_second": 75.302,
+    "eval_steps_per_second": 2.372,
+    "total_flos": 1.0772707724270715e+18,
+    "train_loss": 0.12385351238427339,
+    "train_runtime": 162.1968,
+    "train_samples_per_second": 21.122,
+    "train_steps_per_second": 0.166
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9921259842519685,
+    "eval_loss": 0.035393521189689636,
+    "eval_runtime": 1.6865,
+    "eval_samples_per_second": 75.302,
+    "eval_steps_per_second": 2.372
+}

runs/Nov23_10-17-16_3f1d741a6c0e/events.out.tfevents.1732357473.3f1d741a6c0e.2768.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb1f38056f6ce1edbea78357ca26aa7f36af0ea3b665dbd1d5618cdb9302827
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0772707724270715e+18,
+    "train_loss": 0.12385351238427339,
+    "train_runtime": 162.1968,
+    "train_samples_per_second": 21.122,
+    "train_steps_per_second": 0.166
+}

trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.9921259842519685,
+  "best_model_checkpoint": "convnext-xlarge-224-22k-1k-v14/checkpoint-18",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9606299212598425,
+      "eval_loss": 0.1334373652935028,
+      "eval_runtime": 2.5798,
+      "eval_samples_per_second": 49.229,
+      "eval_steps_per_second": 1.551,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 135.50009155273438,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 0.2411,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9921259842519685,
+      "eval_loss": 0.03504885360598564,
+      "eval_runtime": 1.5915,
+      "eval_samples_per_second": 79.8,
+      "eval_steps_per_second": 2.513,
+      "step": 18
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 9.684277534484863,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 0.0722,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9921259842519685,
+      "eval_loss": 0.01645192690193653,
+      "eval_runtime": 1.6699,
+      "eval_samples_per_second": 76.05,
+      "eval_steps_per_second": 2.395,
+      "step": 27
+    },
+    {
+      "epoch": 3.0,
+      "step": 27,
+      "total_flos": 1.0772707724270715e+18,
+      "train_loss": 0.12385351238427339,
+      "train_runtime": 162.1968,
+      "train_samples_per_second": 21.122,
+      "train_steps_per_second": 0.166
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 27,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.0772707724270715e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}