Training in progress, step 30

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.808510638297872,
+    "eval_accuracy": 0.973404255319149,
+    "eval_loss": 0.0790429338812828,
+    "eval_runtime": 18.4211,
+    "eval_samples_per_second": 10.206,
+    "eval_steps_per_second": 1.303,
+    "total_flos": 1.8652389835014144e+18,
+    "train_loss": 0.3936928858656598,
+    "train_runtime": 1061.9717,
+    "train_samples_per_second": 3.522,
+    "train_steps_per_second": 0.108
+}

config.json

@@ -17,7 +17,7 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 1536,
   "id2label": {
-    "0": "Ron",
+    "0": "Ron00ml",
     "1": "Ron01ml",
     "2": "Ron02ml",
     "3": "Ron03ml",
@@ -27,7 +27,7 @@
   "image_size": 384,
   "initializer_range": 0.02,
   "label2id": {
-    "Ron": "0",
+    "Ron00ml": "0",
     "Ron01ml": "1",
     "Ron02ml": "2",
     "Ron03ml": "3",

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.808510638297872,
+    "eval_accuracy": 0.973404255319149,
+    "eval_loss": 0.0790429338812828,
+    "eval_runtime": 18.4211,
+    "eval_samples_per_second": 10.206,
+    "eval_steps_per_second": 1.303
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786ee0b4fbc6919a7304a03cc20dac658f96c3fe62a93acc0dca4bcf18eb0b4a
+oid sha256:32c11206ef6ec64578b3bca7905ce2e0b831cf3a70c765e6292de5d4b63e3055
 size 784869336

runs/Feb21_16-23-05_bbc35446ee3b/events.out.tfevents.1740156216.bbc35446ee3b.200.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83310dc3daaf793ad6b9ae40cf6482d73fa0b1e812fe6fbe8ca82184adb28a1
+size 722

runs/Feb21_17-06-43_bbc35446ee3b/events.out.tfevents.1740157611.bbc35446ee3b.200.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8a904b326df02aca9e78ae62dc80cadd1e675bccfa28099cc9518b6ea4e576
+size 6588

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.808510638297872,
+    "total_flos": 1.8652389835014144e+18,
+    "train_loss": 0.3936928858656598,
+    "train_runtime": 1061.9717,
+    "train_samples_per_second": 3.522,
+    "train_steps_per_second": 0.108
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.973404255319149,
+  "best_model_checkpoint": "./swin-tiny-patch4-window7-224/checkpoint-90",
+  "epoch": 4.808510638297872,
+  "eval_steps": 30,
+  "global_step": 115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 4.8144612312316895,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.8569,
+      "step": 10
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 15.450971603393555,
+      "learning_rate": 4.611650485436894e-05,
+      "loss": 1.4808,
+      "step": 20
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "grad_norm": 6.094246864318848,
+      "learning_rate": 4.12621359223301e-05,
+      "loss": 0.7408,
+      "step": 30
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "eval_accuracy": 0.9574468085106383,
+      "eval_loss": 0.3417845070362091,
+      "eval_runtime": 19.2245,
+      "eval_samples_per_second": 9.779,
+      "eval_steps_per_second": 1.248,
+      "step": 30
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 9.272632598876953,
+      "learning_rate": 3.6407766990291265e-05,
+      "loss": 0.1938,
+      "step": 40
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 7.808841228485107,
+      "learning_rate": 3.155339805825243e-05,
+      "loss": 0.1385,
+      "step": 50
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "grad_norm": 1.3285796642303467,
+      "learning_rate": 2.6699029126213593e-05,
+      "loss": 0.0476,
+      "step": 60
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "eval_accuracy": 0.9627659574468085,
+      "eval_loss": 0.08024272322654724,
+      "eval_runtime": 18.887,
+      "eval_samples_per_second": 9.954,
+      "eval_steps_per_second": 1.271,
+      "step": 60
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "grad_norm": 0.948991596698761,
+      "learning_rate": 2.1844660194174756e-05,
+      "loss": 0.0275,
+      "step": 70
+    },
+    {
+      "epoch": 3.3404255319148937,
+      "grad_norm": 0.3012545108795166,
+      "learning_rate": 1.6990291262135926e-05,
+      "loss": 0.0232,
+      "step": 80
+    },
+    {
+      "epoch": 3.7659574468085104,
+      "grad_norm": 0.9322492480278015,
+      "learning_rate": 1.2135922330097088e-05,
+      "loss": 0.0038,
+      "step": 90
+    },
+    {
+      "epoch": 3.7659574468085104,
+      "eval_accuracy": 0.973404255319149,
+      "eval_loss": 0.0790429338812828,
+      "eval_runtime": 18.7193,
+      "eval_samples_per_second": 10.043,
+      "eval_steps_per_second": 1.282,
+      "step": 90
+    },
+    {
+      "epoch": 4.170212765957447,
+      "grad_norm": 0.04761149734258652,
+      "learning_rate": 7.281553398058253e-06,
+      "loss": 0.0081,
+      "step": 100
+    },
+    {
+      "epoch": 4.595744680851064,
+      "grad_norm": 0.3751614987850189,
+      "learning_rate": 2.4271844660194174e-06,
+      "loss": 0.0056,
+      "step": 110
+    },
+    {
+      "epoch": 4.808510638297872,
+      "step": 115,
+      "total_flos": 1.8652389835014144e+18,
+      "train_loss": 0.3936928858656598,
+      "train_runtime": 1061.9717,
+      "train_samples_per_second": 3.522,
+      "train_steps_per_second": 0.108
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 115,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8652389835014144e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5df676354d1e132b4ea76fd5059ea347ff96dd57695245a4318bdbd1ae75b8
+oid sha256:d32371f7766ddb5ca9318b3156a7da91b8c27c69e79a79cb7cfd7d9505c6f329
 size 5368