Training in progress, epoch 1

config.json

@@ -0,0 +1,124 @@
+{
+  "architectures": [
+    "SamModel"
+  ],
+  "dtype": "float32",
+  "initializer_range": 0.02,
+  "mask_decoder_config": {
+    "add_cross_attention": false,
+    "attention_downsample_rate": 2,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "hidden_act": "relu",
+    "hidden_size": 256,
+    "iou_head_depth": 3,
+    "iou_head_hidden_dim": 256,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 2048,
+    "model_type": "",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 2,
+    "num_multimask_outputs": 3,
+    "pad_token_id": null,
+    "prefix": null,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false
+  },
+  "model_type": "sam",
+  "prompt_encoder_config": {
+    "add_cross_attention": false,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_size": 256,
+    "image_embedding_size": 64,
+    "image_size": 1024,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-06,
+    "mask_input_channels": 16,
+    "model_type": "",
+    "num_point_embeddings": 4,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "vision_config": {
+    "add_cross_attention": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "global_attn_indexes": [
+      2,
+      5,
+      8,
+      11
+    ],
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "image_size": 1024,
+    "initializer_factor": 1.0,
+    "initializer_range": 1e-10,
+    "intermediate_size": 6144,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 3072,
+    "mlp_ratio": 4.0,
+    "model_type": "sam_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_pos_feats": 128,
+    "output_channels": 256,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "scale": 384,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_abs_pos": true,
+    "use_bfloat16": false,
+    "use_rel_pos": true,
+    "window_size": 14
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c334e6c474820e928a74e072a14221b63e1ed51a48b9275d20408c2d866bb2af
+size 374979376

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48086ad1f805a849029cc80a418725b7ebc2afd5a18501f053faecc415fd87c6
+size 5393