Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c5f2e4b7af5dfabe0a82597f0ca12c1d1198482ba6a7431889a95bfa310bd2
+oid sha256:aa5d552307e20bdf37f3e07ebcc9086db3d952c1f82851fe03fb243f5a7062e6
 size 347502916

tmp-checkpoint-117/config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "microsoft/swin-base-patch4-window7-224",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

tmp-checkpoint-117/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5d552307e20bdf37f3e07ebcc9086db3d952c1f82851fe03fb243f5a7062e6
+size 347502916

tmp-checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fe6ffaaec8dbb59ee9b3c986f0fe02a993fa4e29b15208e8d630baacf7cfc7
+size 694325336

tmp-checkpoint-117/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

tmp-checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8c35c1ca2a49ffd01b90ce0331398c27b94477311653fbb05820b7179f94ce
+size 14575

tmp-checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8251ad6cc2f5fa4f2389d46456314b732c2006679a4e77bd60e6517adf275c
+size 627

tmp-checkpoint-117/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": 0.5576923076923077,
+  "best_model_checkpoint": "swin-finetuned-food101\\checkpoint-39",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.7714285714285716e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.485714285714286e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5576923076923077,
+      "eval_loss": NaN,
+      "eval_runtime": 3.4398,
+      "eval_samples_per_second": 45.352,
+      "eval_steps_per_second": 5.814,
+      "step": 39
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.2e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.9142857142857143e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.6285714285714283e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.342857142857143e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5576923076923077,
+      "eval_loss": NaN,
+      "eval_runtime": 3.5767,
+      "eval_samples_per_second": 43.616,
+      "eval_steps_per_second": 5.592,
+      "step": 78
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.0571428571428572e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 7.714285714285714e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.857142857142858e-06,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2e-06,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5576923076923077,
+      "eval_loss": NaN,
+      "eval_runtime": 3.4388,
+      "eval_samples_per_second": 45.365,
+      "eval_steps_per_second": 5.816,
+      "step": 117
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.466646131344343e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e433e9974b55e701ad7a67bbb39c2088d473f0802548c64adfac07842753b9
+size 4283

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d20d881dbedada2a4d5ecb43d89e437b64f0c4e74de9a748505d26141b92af5
+oid sha256:a62fc0b0d717fa837857cfd143c9072eb823fa60e0275dcabbb1447a5ad9eeee
 size 4283