Add files using upload-large-folder tool

checkpoint-1656/config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "SFW",
+    "1": "NSFW"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "NSFW": 1,
+    "SFW": 0
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "pad_token_id": 1,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-1656/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2929794660fa5ecce24e09e184967b5dcc0eb79eeaf4fd393d26f1c269081d
+size 86690920

checkpoint-1656/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dddc528dd4e529722356fa8c0a36f692cebcb886b283f40e69a448d62651c2e
+size 173498123

checkpoint-1656/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-1656/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28084d42c87bbada89e294ecf25b2845eb7ec8ea4a2670824c66be70cb1719a3
+size 14645

checkpoint-1656/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe832b07084f2c7df03d6102ca9410d5d3719dfa5b4997b9b76d95904031cc5e
+size 1465

checkpoint-1656/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_global_step": 1656,
+  "best_metric": 0.40332305431365967,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-1656",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1656,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6038647342995169,
+      "grad_norm": 10.075688362121582,
+      "learning_rate": 0.00017247087676272227,
+      "loss": 0.6110287475585937,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7589396971642186,
+      "eval_loss": 0.4971259534358978,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 329.8093,
+      "eval_samples_per_second": 80.298,
+      "eval_steps_per_second": 10.039,
+      "step": 828
+    },
+    {
+      "epoch": 1.2077294685990339,
+      "grad_norm": 3.758291721343994,
+      "learning_rate": 0.00014181483752299202,
+      "loss": 0.5085984802246094,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 8.271088600158691,
+      "learning_rate": 0.00011115879828326181,
+      "loss": 0.4401962585449219,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8178076501906884,
+      "eval_loss": 0.40332305431365967,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 330.4601,
+      "eval_samples_per_second": 80.14,
+      "eval_steps_per_second": 10.019,
+      "step": 1656
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.032861037377577e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1656/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddbaf8fc28bf5b8af4e972e6227e3b18cd5d54090fc40ee776e5477e89bce37
+size 5201

checkpoint-2484/config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "SFW",
+    "1": "NSFW"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "NSFW": 1,
+    "SFW": 0
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "pad_token_id": 1,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-2484/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37387b087135b6507b052f5ffc4c69d9967616046cb0a1ea27caabc51e5b2cb
+size 86690920

checkpoint-2484/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f236718382f390fd3b2c1ca615c82bd3c5d703f87a778150f41b081b34104f
+size 173498123

checkpoint-2484/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-2484/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33ee76f763942463e21d381009e61f5b2de5891def23619d96beadf3f79235f
+size 14645

checkpoint-2484/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1bf925656d7c590ef87de6874a77500252d5d5c15b1c8066244db657c28095
+size 1465

checkpoint-2484/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_global_step": 2484,
+  "best_metric": 0.30450552701950073,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-2484",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2484,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6038647342995169,
+      "grad_norm": 10.075688362121582,
+      "learning_rate": 0.00017247087676272227,
+      "loss": 0.6110287475585937,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7589396971642186,
+      "eval_loss": 0.4971259534358978,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 329.8093,
+      "eval_samples_per_second": 80.298,
+      "eval_steps_per_second": 10.039,
+      "step": 828
+    },
+    {
+      "epoch": 1.2077294685990339,
+      "grad_norm": 3.758291721343994,
+      "learning_rate": 0.00014181483752299202,
+      "loss": 0.5085984802246094,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 8.271088600158691,
+      "learning_rate": 0.00011115879828326181,
+      "loss": 0.4401962585449219,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8178076501906884,
+      "eval_loss": 0.40332305431365967,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 330.4601,
+      "eval_samples_per_second": 80.14,
+      "eval_steps_per_second": 10.019,
+      "step": 1656
+    },
+    {
+      "epoch": 2.4154589371980677,
+      "grad_norm": 3.3510007858276367,
+      "learning_rate": 8.050275904353158e-05,
+      "loss": 0.37929122924804687,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8700298304572744,
+      "eval_loss": 0.30450552701950073,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 338.3909,
+      "eval_samples_per_second": 78.262,
+      "eval_steps_per_second": 9.785,
+      "step": 2484
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.5492915560663654e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2484/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddbaf8fc28bf5b8af4e972e6227e3b18cd5d54090fc40ee776e5477e89bce37
+size 5201

checkpoint-3312/config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "SFW",
+    "1": "NSFW"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "NSFW": 1,
+    "SFW": 0
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "pad_token_id": 1,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-3312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08a34c4e4cee97a9c995c6d5c51fd12423325194c0837e3c7ebed0a4e777e5a
+size 86690920

checkpoint-3312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3dfa067512b9f765fe6d0858ee8f3a7214f47416ea829ad9bba85b3be55175f
+size 173498123

checkpoint-3312/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-3312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa650eaf5f28bb150e12307b561d61ce6ce87d145ddf52a5eb9665f34eab375
+size 14645

checkpoint-3312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0bb21237f97eca32a2c098f63d123dccc7572edc12ac4d2e9f8327ca8fd5cd
+size 1465

checkpoint-3312/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_global_step": 3312,
+  "best_metric": 0.26380330324172974,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-3312",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 3312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6038647342995169,
+      "grad_norm": 10.075688362121582,
+      "learning_rate": 0.00017247087676272227,
+      "loss": 0.6110287475585937,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7589396971642186,
+      "eval_loss": 0.4971259534358978,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 329.8093,
+      "eval_samples_per_second": 80.298,
+      "eval_steps_per_second": 10.039,
+      "step": 828
+    },
+    {
+      "epoch": 1.2077294685990339,
+      "grad_norm": 3.758291721343994,
+      "learning_rate": 0.00014181483752299202,
+      "loss": 0.5085984802246094,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 8.271088600158691,
+      "learning_rate": 0.00011115879828326181,
+      "loss": 0.4401962585449219,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8178076501906884,
+      "eval_loss": 0.40332305431365967,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 330.4601,
+      "eval_samples_per_second": 80.14,
+      "eval_steps_per_second": 10.019,
+      "step": 1656
+    },
+    {
+      "epoch": 2.4154589371980677,
+      "grad_norm": 3.3510007858276367,
+      "learning_rate": 8.050275904353158e-05,
+      "loss": 0.37929122924804687,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8700298304572744,
+      "eval_loss": 0.30450552701950073,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 338.3909,
+      "eval_samples_per_second": 78.262,
+      "eval_steps_per_second": 9.785,
+      "step": 2484
+    },
+    {
+      "epoch": 3.0193236714975846,
+      "grad_norm": 3.468003273010254,
+      "learning_rate": 4.984671980380135e-05,
+      "loss": 0.35336199951171876,
+      "step": 2500
+    },
+    {
+      "epoch": 3.6231884057971016,
+      "grad_norm": 3.735905885696411,
+      "learning_rate": 1.9190680564071123e-05,
+      "loss": 0.3137332763671875,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8917796322168938,
+      "eval_loss": 0.26380330324172974,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 323.8225,
+      "eval_samples_per_second": 81.782,
+      "eval_steps_per_second": 10.225,
+      "step": 3312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 2.065722074755154e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddbaf8fc28bf5b8af4e972e6227e3b18cd5d54090fc40ee776e5477e89bce37
+size 5201

checkpoint-828/config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "SFW",
+    "1": "NSFW"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "NSFW": 1,
+    "SFW": 0
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "pad_token_id": 1,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-828/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3afbdd32ffa5af50bbf6d23e7d96790c6118553a56715f7ebff578be2bfc7e
+size 86690920

checkpoint-828/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb8df33c8fee0b1529c1ba761e11016f4ba2976017bc7b4ea246825db327346
+size 173498123

checkpoint-828/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-828/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9551607da6e674b84fd1c1eb8b415048048d4961bd83bd3a47ff0baecabdb8
+size 14645

checkpoint-828/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67993d55bcde151768c99c8b1e64d49a4387d2f7f2b94142d4e67143fa9707ab
+size 1465

checkpoint-828/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_global_step": 828,
+  "best_metric": 0.4971259534358978,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-828",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 828,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6038647342995169,
+      "grad_norm": 10.075688362121582,
+      "learning_rate": 0.00017247087676272227,
+      "loss": 0.6110287475585937,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7589396971642186,
+      "eval_loss": 0.4971259534358978,
+      "eval_model_preparation_time": 0.0022,
+      "eval_runtime": 329.8093,
+      "eval_samples_per_second": 80.298,
+      "eval_steps_per_second": 10.039,
+      "step": 828
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 5.164305186887885e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-828/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddbaf8fc28bf5b8af4e972e6227e3b18cd5d54090fc40ee776e5477e89bce37
+size 5201

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "SFW",
+    "1": "NSFW"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "NSFW": 1,
+    "SFW": 0
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "pad_token_id": 1,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08a34c4e4cee97a9c995c6d5c51fd12423325194c0837e3c7ebed0a4e777e5a
+size 86690920

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddbaf8fc28bf5b8af4e972e6227e3b18cd5d54090fc40ee776e5477e89bce37
+size 5201