End of training

README.md

@@ -3,7 +3,11 @@ library_name: transformers
 license: other
 base_model: nvidia/mit-b0
 tags:
+- image-classification
+- vision
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: newspaper_classifier_segformer
   results: []
@@ -14,7 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # newspaper_classifier_segformer
 
-This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the taresco/newspaper_ocr dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0198
+- Accuracy: 0.9962
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9961632368329264,
+    "eval_loss": 0.019796032458543777,
+    "eval_runtime": 122.6936,
+    "eval_samples_per_second": 23.367,
+    "eval_steps_per_second": 1.467,
+    "total_flos": 7.634005171780977e+17,
+    "train_loss": 0.014733173099793787,
+    "train_runtime": 3702.8729,
+    "train_samples_per_second": 13.161,
+    "train_steps_per_second": 0.823
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9961632368329264,
+    "eval_loss": 0.019796032458543777,
+    "eval_runtime": 122.6936,
+    "eval_samples_per_second": 23.367,
+    "eval_steps_per_second": 1.467
+}

runs/Apr28_22-35-24_1c0517da4b2e/events.out.tfevents.1745883617.1c0517da4b2e.97.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111d0213e42f0975e1a09144ef9d9c99d31db6389172e96b8257552cf0a6fd55
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.634005171780977e+17,
+    "train_loss": 0.014733173099793787,
+    "train_runtime": 3702.8729,
+    "train_samples_per_second": 13.161,
+    "train_steps_per_second": 0.823
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3048,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4921259842519685,
+      "grad_norm": 5.2201099606463686e-05,
+      "learning_rate": 4.181430446194226e-05,
+      "loss": 0.0255,
+      "step": 500
+    },
+    {
+      "epoch": 0.984251968503937,
+      "grad_norm": 0.0001974255428649485,
+      "learning_rate": 3.361220472440945e-05,
+      "loss": 0.0248,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4763779527559056,
+      "grad_norm": 0.0010723082814365625,
+      "learning_rate": 2.5410104986876644e-05,
+      "loss": 0.0115,
+      "step": 1500
+    },
+    {
+      "epoch": 1.968503937007874,
+      "grad_norm": 0.04216455668210983,
+      "learning_rate": 1.7208005249343835e-05,
+      "loss": 0.0121,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4606299212598426,
+      "grad_norm": 0.008129170164465904,
+      "learning_rate": 9.005905511811025e-06,
+      "loss": 0.0066,
+      "step": 2500
+    },
+    {
+      "epoch": 2.952755905511811,
+      "grad_norm": 0.0005369239370338619,
+      "learning_rate": 8.038057742782153e-07,
+      "loss": 0.0084,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3048,
+      "total_flos": 7.634005171780977e+17,
+      "train_loss": 0.014733173099793787,
+      "train_runtime": 3702.8729,
+      "train_samples_per_second": 13.161,
+      "train_steps_per_second": 0.823
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3048,
+  "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": 7.634005171780977e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}