Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.5576923076923077,
-    "eval_loss": 1.051900863647461,
-    "eval_runtime": 3.8971,
-    "eval_samples_per_second": 40.03,
-    "eval_steps_per_second": 1.283,
-    "total_flos": 1.466646131344343e+17,
-    "train_loss": 1.021867815653483,
-    "train_runtime": 393.1559,
-    "train_samples_per_second": 4.761,
-    "train_steps_per_second": 0.038
+    "epoch": 2.77,
+    "eval_accuracy": 0.7051282051282052,
+    "eval_loss": 237.8072967529297,
+    "eval_runtime": 6.2332,
+    "eval_samples_per_second": 25.027,
+    "eval_steps_per_second": 1.604,
+    "total_flos": 1.353827198164009e+17,
+    "train_loss": 1153.0786901403355,
+    "train_runtime": 232.3575,
+    "train_samples_per_second": 8.057,
+    "train_steps_per_second": 0.116
 }

config.json

@@ -17,16 +17,14 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 1024,
   "id2label": {
-    "0": 0,
-    "1": 1,
-    "2": 2
+    "0": "MI",
+    "1": "Non_MI"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "label2id": {
-    "0": "0",
-    "1": "1",
-    "2": "2"
+    "MI": "0",
+    "Non_MI": "1"
   },
   "layer_norm_eps": 1e-05,
   "mlp_ratio": 4.0,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.5576923076923077,
-    "eval_loss": 1.051900863647461,
-    "eval_runtime": 3.8971,
-    "eval_samples_per_second": 40.03,
-    "eval_steps_per_second": 1.283
+    "epoch": 2.77,
+    "eval_accuracy": 0.7051282051282052,
+    "eval_loss": 237.8072967529297,
+    "eval_runtime": 6.2332,
+    "eval_samples_per_second": 25.027,
+    "eval_steps_per_second": 1.604
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9a1037d2f35d10e9510142427e117bac0fda93ac95773bff693a0adeeb2a94
-size 347502916
+oid sha256:c177ca70a27abbfd67f8d8c874ec31953b67609f8d46f7cb85fb859382004ce2
+size 347498816

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 1.466646131344343e+17,
-    "train_loss": 1.021867815653483,
-    "train_runtime": 393.1559,
-    "train_samples_per_second": 4.761,
-    "train_steps_per_second": 0.038
+    "epoch": 2.77,
+    "total_flos": 1.353827198164009e+17,
+    "train_loss": 1153.0786901403355,
+    "train_runtime": 232.3575,
+    "train_samples_per_second": 8.057,
+    "train_steps_per_second": 0.116
 }

trainer_state.json

@@ -1,63 +1,69 @@
 {
-  "best_metric": 0.5576923076923077,
-  "best_model_checkpoint": "swin-finetuned-food101\\checkpoint-5",
-  "epoch": 3.0,
+  "best_metric": 0.7051282051282052,
+  "best_model_checkpoint": "swin-finetuned-food101\\checkpoint-27",
+  "epoch": 2.769230769230769,
   "eval_steps": 500,
-  "global_step": 15,
+  "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": 0.5576923076923077,
-      "eval_loss": 1.051900863647461,
-      "eval_runtime": 3.8554,
-      "eval_samples_per_second": 40.463,
-      "eval_steps_per_second": 1.297,
-      "step": 5
+      "epoch": 0.92,
+      "eval_accuracy": 0.6474358974358975,
+      "eval_loss": 504.14202880859375,
+      "eval_runtime": 6.2461,
+      "eval_samples_per_second": 24.975,
+      "eval_steps_per_second": 1.601,
+      "step": 9
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 1.923076923076923e-05,
-      "loss": 1.0523,
+      "epoch": 1.03,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 2588.8625,
       "step": 10
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5576923076923077,
-      "eval_loss": 0.9787527918815613,
-      "eval_runtime": 4.2577,
-      "eval_samples_per_second": 36.64,
-      "eval_steps_per_second": 1.174,
-      "step": 10
+      "epoch": 1.95,
+      "eval_accuracy": 0.6858974358974359,
+      "eval_loss": 238.61343383789062,
+      "eval_runtime": 5.6613,
+      "eval_samples_per_second": 27.556,
+      "eval_steps_per_second": 1.766,
+      "step": 19
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 371.5631,
+      "step": 20
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.5576923076923077,
-      "eval_loss": 0.9525494575500488,
-      "eval_runtime": 3.9611,
-      "eval_samples_per_second": 39.383,
-      "eval_steps_per_second": 1.262,
-      "step": 15
+      "epoch": 2.77,
+      "eval_accuracy": 0.7051282051282052,
+      "eval_loss": 237.8072967529297,
+      "eval_runtime": 5.4143,
+      "eval_samples_per_second": 28.813,
+      "eval_steps_per_second": 1.847,
+      "step": 27
     },
     {
-      "epoch": 3.0,
-      "step": 15,
-      "total_flos": 1.466646131344343e+17,
-      "train_loss": 1.021867815653483,
-      "train_runtime": 393.1559,
-      "train_samples_per_second": 4.761,
-      "train_steps_per_second": 0.038
+      "epoch": 2.77,
+      "step": 27,
+      "total_flos": 1.353827198164009e+17,
+      "train_loss": 1153.0786901403355,
+      "train_runtime": 232.3575,
+      "train_samples_per_second": 8.057,
+      "train_steps_per_second": 0.116
     }
   ],
   "logging_steps": 10,
-  "max_steps": 15,
+  "max_steps": 27,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.466646131344343e+17,
-  "train_batch_size": 32,
+  "total_flos": 1.353827198164009e+17,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5947ce4df283acd10f2afda9a1d3f025547828e0a3b96a462b7f7874f5329f46
-size 4283
+oid sha256:0219ed4f0a1ba33cd1ec4a3c941ac1c82ab34d6bf0dd2d8c433f4f8889515498
+size 4728