Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.3333333333333333,
+    "eval_loss": 0.6925444602966309,
+    "eval_runtime": 0.4804,
+    "eval_samples_per_second": 6.245,
+    "eval_steps_per_second": 2.082,
+    "total_flos": 349570801336320.0,
+    "train_loss": 0.668668270111084,
+    "train_runtime": 49.9671,
+    "train_samples_per_second": 1.201,
+    "train_steps_per_second": 0.1
+}

checkpoint-1/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Anoa",
+    "1": "Kerbau"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Anoa": 0,
+    "Kerbau": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3"
+}

checkpoint-1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af63baef92f78f5c0ab9713b1d04bdabb0297fb74fa31dbbabd0d3359b071e02
+size 19851560

checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0535de8faf9bc6c7a4e8b9b5c4109d8f3fe501877dca17650594bbfa97e81a
+size 39713530

checkpoint-1/preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}

checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30bf26c2c7590b2e63c6c2907406745c658919a91b180d36b7329198dffe3f3c
+size 13990

checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e3bf5f5b48923fff34716541354d4e7a796b08fd31ef67518ffbadf93e0a7a
+size 1064

checkpoint-1/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_global_step": 1,
+  "best_metric": 0.25,
+  "best_model_checkpoint": "mobilevit-small-custom-classifier/checkpoint-1",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.703833281993866,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 1.639,
+      "step": 1
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 69914160267264.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c4c8b91e93df31166eeab2284d193936d8fc951d549d79ae4264174d4b0972
+size 5304

checkpoint-2/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Anoa",
+    "1": "Kerbau"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Anoa": 0,
+    "Kerbau": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3"
+}

checkpoint-2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc791843e7147b98c35e161f4920f0364a23499c03759fbee479b462e662b8c
+size 19851560

checkpoint-2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839e08aba2811cd5dd88f55acb0c9519ec14d4fe5983d3a4f8b517af0ed87133
+size 39713530

checkpoint-2/preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}

checkpoint-2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6d8058bd13e850e48a0ca4df78973a507fff3502b12e5a684df109f166e171
+size 13990

checkpoint-2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b651bc4149658a6da631b87808cf9b99990105ee57a4afb648cdae24c114d817
+size 1064

checkpoint-2/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_global_step": 1,
+  "best_metric": 0.25,
+  "best_model_checkpoint": "mobilevit-small-custom-classifier/checkpoint-1",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.703833281993866,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 1.639,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.7048182487487793,
+      "eval_runtime": 0.5506,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 1.816,
+      "step": 2
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 139828320534528.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c4c8b91e93df31166eeab2284d193936d8fc951d549d79ae4264174d4b0972
+size 5304

checkpoint-3/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Anoa",
+    "1": "Kerbau"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Anoa": 0,
+    "Kerbau": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3"
+}

checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a92c78883131906aaef4bbdc772eef0783419199345d541ee7ef4bef0301fbd
+size 19851560

checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0a4f5bc5849b38f9620b1f4fb10c25b07089d1f79a7a830040a5562480ae41
+size 39713530

checkpoint-3/preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}

checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31d6afad5e3e8a020d10830e7192e96c1cefecc9d434406fa55604bfdc9b81a
+size 13990

checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22a8c335a9de0ca2a4c0e701e17a73b4d4af7bec6085d00edb0674e4213d34a
+size 1064

checkpoint-3/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.5,
+  "best_model_checkpoint": "mobilevit-small-custom-classifier/checkpoint-3",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.703833281993866,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 1.639,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.7048182487487793,
+      "eval_runtime": 0.5506,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 1.816,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7065370082855225,
+      "eval_runtime": 0.8353,
+      "eval_samples_per_second": 4.789,
+      "eval_steps_per_second": 1.197,
+      "step": 3
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 209742480801792.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c4c8b91e93df31166eeab2284d193936d8fc951d549d79ae4264174d4b0972
+size 5304

checkpoint-4/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Anoa",
+    "1": "Kerbau"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Anoa": 0,
+    "Kerbau": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3"
+}

checkpoint-4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94bb888314b3489473b4a4e364f83fb979bf0fb437622b6064e8be0eff7b400
+size 19851560

checkpoint-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bd923e92e9187269720618e76be9073ace4e778fe4bc5ef90f1ff95770fc09
+size 39713530

checkpoint-4/preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}

checkpoint-4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef88e9e82c3db55d48c417ecdd583933a3ed3c6d77f2902882cf634aedf0f39
+size 13990

checkpoint-4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097d7390e2ea6e2dc7b13ed52d618b4b09bb1445c1d3cd28d2ba5b19709a290a
+size 1064

checkpoint-4/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.5,
+  "best_model_checkpoint": "mobilevit-small-custom-classifier/checkpoint-3",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.703833281993866,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 1.639,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.7048182487487793,
+      "eval_runtime": 0.5506,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 1.816,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7065370082855225,
+      "eval_runtime": 0.8353,
+      "eval_samples_per_second": 4.789,
+      "eval_steps_per_second": 1.197,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7078632116317749,
+      "eval_runtime": 0.5684,
+      "eval_samples_per_second": 7.037,
+      "eval_steps_per_second": 1.759,
+      "step": 4
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 279656641069056.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c4c8b91e93df31166eeab2284d193936d8fc951d549d79ae4264174d4b0972
+size 5304

checkpoint-5/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Anoa",
+    "1": "Kerbau"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Anoa": 0,
+    "Kerbau": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3"
+}

checkpoint-5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cb013cf2b05e501551d542157e88caac296c63ce497a7882c232c14ff39433
+size 19851560

checkpoint-5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733b9461bc75cda02c507c96df53aa69de4f6a44c44d6de4ae457cb91499a29b
+size 39713530

checkpoint-5/preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}

checkpoint-5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e9ed59d65719ca75221e245800cec6eb2565ef03680c2d408e6efad799991a
+size 13990

checkpoint-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c7cc88724873ebe7646569a370a20622e5bc45bf31d6c9df8c11adca8e41e8
+size 1064

checkpoint-5/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.5,
+  "best_model_checkpoint": "mobilevit-small-custom-classifier/checkpoint-3",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.703833281993866,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 1.639,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.7048182487487793,
+      "eval_runtime": 0.5506,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 1.816,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7065370082855225,
+      "eval_runtime": 0.8353,
+      "eval_samples_per_second": 4.789,
+      "eval_steps_per_second": 1.197,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7078632116317749,
+      "eval_runtime": 0.5684,
+      "eval_samples_per_second": 7.037,
+      "eval_steps_per_second": 1.759,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.708530604839325,
+      "eval_runtime": 0.5344,
+      "eval_samples_per_second": 7.485,
+      "eval_steps_per_second": 1.871,
+      "step": 5
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 349570801336320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c4c8b91e93df31166eeab2284d193936d8fc951d549d79ae4264174d4b0972
+size 5304

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Anoa",
+    "1": "Kerbau"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Anoa": 0,
+    "Kerbau": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.3333333333333333,
+    "eval_loss": 0.6925444602966309,
+    "eval_runtime": 0.4804,
+    "eval_samples_per_second": 6.245,
+    "eval_steps_per_second": 2.082
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a92c78883131906aaef4bbdc772eef0783419199345d541ee7ef4bef0301fbd
+size 19851560

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 349570801336320.0,
+    "train_loss": 0.668668270111084,
+    "train_runtime": 49.9671,
+    "train_samples_per_second": 1.201,
+    "train_steps_per_second": 0.1
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.5,
+  "best_model_checkpoint": "mobilevit-small-custom-classifier/checkpoint-3",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.703833281993866,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 6.557,
+      "eval_steps_per_second": 1.639,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.7048182487487793,
+      "eval_runtime": 0.5506,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 1.816,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7065370082855225,
+      "eval_runtime": 0.8353,
+      "eval_samples_per_second": 4.789,
+      "eval_steps_per_second": 1.197,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7078632116317749,
+      "eval_runtime": 0.5684,
+      "eval_samples_per_second": 7.037,
+      "eval_steps_per_second": 1.759,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.708530604839325,
+      "eval_runtime": 0.5344,
+      "eval_samples_per_second": 7.485,
+      "eval_steps_per_second": 1.871,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "step": 5,
+      "total_flos": 349570801336320.0,
+      "train_loss": 0.668668270111084,
+      "train_runtime": 49.9671,
+      "train_samples_per_second": 1.201,
+      "train_steps_per_second": 0.1
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 349570801336320.0,
+  "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:e2c4c8b91e93df31166eeab2284d193936d8fc951d549d79ae4264174d4b0972
+size 5304