Training in progress, epoch 0

README.md

@@ -0,0 +1,64 @@
+---
+base_model: MBZUAI/swiftformer-xs
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: swiftformer-xs-dmae-va-U-SF
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# swiftformer-xs-dmae-va-U-SF
+
+This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3463
+- Accuracy: 0.3486
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.9   | 7    | 1.4376          | 0.2477   |
+| 1.4126        | 1.94  | 15   | 1.3582          | 0.3211   |
+| 1.359         | 2.71  | 21   | 1.3463          | 0.3486   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.71,
+    "total_flos": 7291673091440640.0,
+    "train_loss": 1.383760514713469,
+    "train_runtime": 25.3309,
+    "train_samples_per_second": 115.827,
+    "train_steps_per_second": 0.829
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "MBZUAI/swiftformer-xs",
+  "architectures": [
+    "SwiftFormerForImageClassification"
+  ],
+  "batch_norm_eps": 1e-05,
+  "depths": [
+    3,
+    3,
+    6,
+    4
+  ],
+  "down_pad": 1,
+  "down_patch_size": 3,
+  "down_stride": 2,
+  "downsamples": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "drop_path_rate": 0.0,
+  "embed_dims": [
+    48,
+    56,
+    112,
+    220
+  ],
+  "hidden_act": "gelu",
+  "id2label": {
+    "0": "avanzada",
+    "1": "leve",
+    "2": "moderada",
+    "3": "no dmae"
+  },
+  "label2id": {
+    "avanzada": 0,
+    "leve": 1,
+    "moderada": 2,
+    "no dmae": 3
+  },
+  "layer_scale_init_value": 1e-05,
+  "mlp_ratio": 4,
+  "model_type": "swiftformer",
+  "num_channels": 3,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_layer_scale": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fc19e5fc303179709ddd7d9ca36c88e396786ebdd24a788f35298d1dd84ee5
+size 12203648

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jan28_16-55-46_4890d88f69da/events.out.tfevents.1706460975.4890d88f69da.226.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48d584069fce30bea4a3b14d090cc2e3a87f5763b71744e25e734b69d4075a6
+size 6025

runs/Jan28_17-01-40_4890d88f69da/events.out.tfevents.1706461319.4890d88f69da.2289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c184e59e5526f39e37a7c16a3a5508f182685a578b0cb318cf76a56d146fc317
+size 4736

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.71,
+    "total_flos": 7291673091440640.0,
+    "train_loss": 1.383760514713469,
+    "train_runtime": 25.3309,
+    "train_samples_per_second": 115.827,
+    "train_steps_per_second": 0.829
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.3486238532110092,
+  "best_model_checkpoint": "swiftformer-xs-dmae-va-U-SF/checkpoint-21",
+  "epoch": 2.709677419354839,
+  "eval_steps": 500,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.24770642201834864,
+      "eval_loss": 1.4376270771026611,
+      "eval_runtime": 0.5029,
+      "eval_samples_per_second": 216.756,
+      "eval_steps_per_second": 7.954,
+      "step": 7
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 1.4126,
+      "step": 10
+    },
+    {
+      "epoch": 1.94,
+      "eval_accuracy": 0.3211009174311927,
+      "eval_loss": 1.3581504821777344,
+      "eval_runtime": 0.4287,
+      "eval_samples_per_second": 254.235,
+      "eval_steps_per_second": 9.33,
+      "step": 15
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 1.359,
+      "step": 20
+    },
+    {
+      "epoch": 2.71,
+      "eval_accuracy": 0.3486238532110092,
+      "eval_loss": 1.3463064432144165,
+      "eval_runtime": 0.4247,
+      "eval_samples_per_second": 256.633,
+      "eval_steps_per_second": 9.418,
+      "step": 21
+    },
+    {
+      "epoch": 2.71,
+      "step": 21,
+      "total_flos": 7291673091440640.0,
+      "train_loss": 1.383760514713469,
+      "train_runtime": 25.3309,
+      "train_samples_per_second": 115.827,
+      "train_steps_per_second": 0.829
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 21,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7291673091440640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d4f1e9018d58313ce26e8b1f1e66fa850f71f6f03cf86d06dd15cf73c1c1e1
+size 4600