Upload folder using huggingface_hub (#6)

- Upload folder using huggingface_hub (bf42622586506ccf637a4095ecc1c9e858c19d08)

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 22.0,
+    "total_flos": 1.2615695909255578e+17,
+    "train_loss": 0.04397649819200689,
+    "train_runtime": 84.5517,
+    "train_samples_per_second": 19.254,
+    "train_steps_per_second": 1.301
+}

checkpoint-160/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "mold",
+    "1": "non-mold"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "mold": "0",
+    "non-mold": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1"
+}

checkpoint-160/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2dec449c03a6a4a335f6706b8121a11f67349c62f865dc61bebeab88fcc1f9d
+size 343223968

checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5058d92612251a9c59fb5caa74cdf04a9cf374e124467191f87f6175c4207b
+size 686568890

checkpoint-160/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86f749dc73bc16a2502fef2f98f5c00b4400cb2c67fbe62653b7ed104d13779
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec82b88d9fc1851330cce56bddf8838806450e0dcb4ecdc26493c05dc810338d
+size 1064

checkpoint-160/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.018665345385670662,
+  "best_model_checkpoint": "./vit-strawberries/checkpoint-120",
+  "epoch": 32.0,
+  "eval_steps": 40,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6030758023262024,
+      "learning_rate": 0.0001875,
+      "loss": 0.3813,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.19357694685459137,
+      "learning_rate": 0.000175,
+      "loss": 0.0627,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.09823369234800339,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 0.0166,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.06956500560045242,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0102,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.021412454545497894,
+      "eval_runtime": 0.4006,
+      "eval_samples_per_second": 64.901,
+      "eval_steps_per_second": 9.985,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.059710320085287094,
+      "learning_rate": 0.0001375,
+      "loss": 0.0078,
+      "step": 50
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.04971468821167946,
+      "learning_rate": 0.000125,
+      "loss": 0.0065,
+      "step": 60
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.044971030205488205,
+      "learning_rate": 0.00011250000000000001,
+      "loss": 0.0058,
+      "step": 70
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.04283370077610016,
+      "learning_rate": 0.0001,
+      "loss": 0.0052,
+      "step": 80
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.019078843295574188,
+      "eval_runtime": 0.4188,
+      "eval_samples_per_second": 62.087,
+      "eval_steps_per_second": 9.552,
+      "step": 80
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.03907443583011627,
+      "learning_rate": 8.75e-05,
+      "loss": 0.0048,
+      "step": 90
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.03701604902744293,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0045,
+      "step": 100
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.03528870269656181,
+      "learning_rate": 6.25e-05,
+      "loss": 0.0043,
+      "step": 110
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.033964332193136215,
+      "learning_rate": 5e-05,
+      "loss": 0.0041,
+      "step": 120
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.018665345385670662,
+      "eval_runtime": 0.4061,
+      "eval_samples_per_second": 64.02,
+      "eval_steps_per_second": 9.849,
+      "step": 120
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.03315058350563049,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.004,
+      "step": 130
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 0.031990278512239456,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0039,
+      "step": 140
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.031738851219415665,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0038,
+      "step": 150
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 0.03203798457980156,
+      "learning_rate": 0.0,
+      "loss": 0.0038,
+      "step": 160
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.01877218298614025,
+      "eval_runtime": 0.485,
+      "eval_samples_per_second": 53.611,
+      "eval_steps_per_second": 8.248,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 32,
+  "save_steps": 40,
+  "total_flos": 1.8350103140735386e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb496ae4ef9baef4da454a5aeb81107fc1c8c5186e0e0e4558b603478a5db94
+size 4984

checkpoint-40/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "mold",
+    "1": "non-mold"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "mold": "0",
+    "non-mold": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1"
+}

checkpoint-40/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb420995dc8be7c272dadcd477dedb06052fd58a346e130d03ff45f4c1c91771
+size 343223968

checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358f9b33732a7d412948bf0cf3da9233eb8df30982b22bc31c74407deeaf386e
+size 686568890

checkpoint-40/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+size 14244

checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc50aee520433cf5ed68f3911fe02fa94186318c9e0ea67084b2aceb7a1eaa20
+size 1064

checkpoint-40/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.08537869900465012,
+  "best_model_checkpoint": "./vit-strawberries/checkpoint-40",
+  "epoch": 8.0,
+  "eval_steps": 40,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6375295519828796,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.3845,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.1383754014968872,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.0393,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.08163678646087646,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.0128,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.06157604977488518,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.0087,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_loss": 0.08537869900465012,
+      "eval_runtime": 0.4612,
+      "eval_samples_per_second": 56.375,
+      "eval_steps_per_second": 8.673,
+      "step": 40
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 22,
+  "save_steps": 40,
+  "total_flos": 4.587525785183846e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab60cc9e62a612ea5adfddbcae3b3d445ad2a66cf5b8c39079230d5655ada3a
+size 4984

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "mold",
+    "1": "non-mold"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "mold": "0",
+    "non-mold": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb420995dc8be7c272dadcd477dedb06052fd58a346e130d03ff45f4c1c91771
+size 343223968

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 22.0,
+    "total_flos": 1.2615695909255578e+17,
+    "train_loss": 0.04397649819200689,
+    "train_runtime": 84.5517,
+    "train_samples_per_second": 19.254,
+    "train_steps_per_second": 1.301
+}

trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.08537869900465012,
+  "best_model_checkpoint": "./vit-strawberries/checkpoint-40",
+  "epoch": 22.0,
+  "eval_steps": 40,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6375295519828796,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.3845,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.1383754014968872,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.0393,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.08163678646087646,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.0128,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.06157604977488518,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.0087,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_loss": 0.08537869900465012,
+      "eval_runtime": 0.4612,
+      "eval_samples_per_second": 56.375,
+      "eval_steps_per_second": 8.673,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.05511847883462906,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.007,
+      "step": 50
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.047300320118665695,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.0061,
+      "step": 60
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.044113993644714355,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.0056,
+      "step": 70
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.043533895164728165,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.0052,
+      "step": 80
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_loss": 0.14537294209003448,
+      "eval_runtime": 0.4597,
+      "eval_samples_per_second": 56.556,
+      "eval_steps_per_second": 8.701,
+      "step": 80
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.040240347385406494,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.005,
+      "step": 90
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0400131419301033,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.0048,
+      "step": 100
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.039389099925756454,
+      "learning_rate": 0.0,
+      "loss": 0.0048,
+      "step": 110
+    },
+    {
+      "epoch": 22.0,
+      "step": 110,
+      "total_flos": 1.2615695909255578e+17,
+      "train_loss": 0.04397649819200689,
+      "train_runtime": 84.5517,
+      "train_samples_per_second": 19.254,
+      "train_steps_per_second": 1.301
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 22,
+  "save_steps": 40,
+  "total_flos": 1.2615695909255578e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab60cc9e62a612ea5adfddbcae3b3d445ad2a66cf5b8c39079230d5655ada3a
+size 4984