test_ViT-Masked_4

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: test_ViT-Masked_4
+  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. -->
+
+# test_ViT-Masked_4
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the ppak10/Melt-Pool-Thermal-Images dataset.
+
+## 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: 1e-05
+- train_batch_size: 2048
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "ViTForMaskedImageModeling"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 8,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "image_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 1,
+  "num_hidden_layers": 12,
+  "patch_size": 8,
+  "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:a43adaced2939f3d15d7fe0393bbef9f2c97caa753575cfd13564ab423c9f892
+size 340849656

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2590,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.9305019305019306,
+      "grad_norm": 3.1227238178253174,
+      "learning_rate": 8.06949806949807e-06,
+      "loss": 0.0861,
+      "step": 500
+    },
+    {
+      "epoch": 1.9305019305019306,
+      "eval_runtime": 661.7783,
+      "eval_samples_per_second": 266.734,
+      "eval_steps_per_second": 16.672,
+      "step": 500
+    },
+    {
+      "epoch": 3.861003861003861,
+      "grad_norm": 4.147549152374268,
+      "learning_rate": 6.13899613899614e-06,
+      "loss": 0.0554,
+      "step": 1000
+    },
+    {
+      "epoch": 3.861003861003861,
+      "eval_runtime": 639.2021,
+      "eval_samples_per_second": 276.155,
+      "eval_steps_per_second": 17.261,
+      "step": 1000
+    },
+    {
+      "epoch": 5.7915057915057915,
+      "grad_norm": 4.684039115905762,
+      "learning_rate": 4.208494208494209e-06,
+      "loss": 0.0428,
+      "step": 1500
+    },
+    {
+      "epoch": 5.7915057915057915,
+      "eval_runtime": 638.2108,
+      "eval_samples_per_second": 276.584,
+      "eval_steps_per_second": 17.287,
+      "step": 1500
+    },
+    {
+      "epoch": 7.722007722007722,
+      "grad_norm": 3.6964356899261475,
+      "learning_rate": 2.2779922779922782e-06,
+      "loss": 0.0351,
+      "step": 2000
+    },
+    {
+      "epoch": 7.722007722007722,
+      "eval_runtime": 637.2615,
+      "eval_samples_per_second": 276.996,
+      "eval_steps_per_second": 17.313,
+      "step": 2000
+    },
+    {
+      "epoch": 9.652509652509652,
+      "grad_norm": 0.3747519552707672,
+      "learning_rate": 3.474903474903475e-07,
+      "loss": 0.0314,
+      "step": 2500
+    },
+    {
+      "epoch": 9.652509652509652,
+      "eval_runtime": 643.7118,
+      "eval_samples_per_second": 274.221,
+      "eval_steps_per_second": 17.14,
+      "step": 2500
+    },
+    {
+      "epoch": 10.0,
+      "step": 2590,
+      "total_flos": 1.1089078720895386e+19,
+      "train_loss": 0.04947091428469507,
+      "train_runtime": 17619.1199,
+      "train_samples_per_second": 300.557,
+      "train_steps_per_second": 0.147
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.1089078720895386e+19,
+  "train_batch_size": 2048,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06bd04dbd8729e94f967ee0cc3025883281f1257daa98f35a929899f79c84db
+size 4539