Training in progress, step 3500, checkpoint

checkpoint-3500/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14-336",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566fd5b1cea7df67ae242c96e37f4afb5fa97a0e4f99dd8ef1298b463cc70c0e
+size 1711848436

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa740bb243c96c9697f0c972ba42ba87c330af9d74a8812333ca22799e4297b
+size 3424043887

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6545428b68c90b341f7066f45a8dc9f93c35ad0b51fda8ce46148a7fa136e1a0
+size 14503

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9233cb0bba958a77fdb1c6b7d9bee0340b217e653dfb7039b5c9f521e3361168
+size 623

checkpoint-3500/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.7048410177230835,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-3500",
+  "epoch": 0.6448047162859248,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09211495946941783,
+      "grad_norm": 3.083087682723999,
+      "learning_rate": 4.84647506755097e-07,
+      "loss": 0.2708,
+      "step": 500
+    },
+    {
+      "epoch": 0.09211495946941783,
+      "eval_loss": 1.0631108283996582,
+      "eval_runtime": 74.1964,
+      "eval_samples_per_second": 16.268,
+      "eval_steps_per_second": 2.035,
+      "step": 500
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "grad_norm": 7.726487159729004,
+      "learning_rate": 4.69295013510194e-07,
+      "loss": 0.251,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "eval_loss": 0.942773699760437,
+      "eval_runtime": 74.6047,
+      "eval_samples_per_second": 16.179,
+      "eval_steps_per_second": 2.024,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "grad_norm": 0.02718021161854267,
+      "learning_rate": 4.5394252026529107e-07,
+      "loss": 0.235,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "eval_loss": 0.8716810345649719,
+      "eval_runtime": 75.03,
+      "eval_samples_per_second": 16.087,
+      "eval_steps_per_second": 2.013,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "grad_norm": 0.0001215290030813776,
+      "learning_rate": 4.385900270203881e-07,
+      "loss": 0.1529,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "eval_loss": 0.8318113088607788,
+      "eval_runtime": 76.6917,
+      "eval_samples_per_second": 15.738,
+      "eval_steps_per_second": 1.969,
+      "step": 2000
+    },
+    {
+      "epoch": 0.46057479734708917,
+      "grad_norm": 419.545166015625,
+      "learning_rate": 4.232375337754851e-07,
+      "loss": 0.1781,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46057479734708917,
+      "eval_loss": 0.7549223303794861,
+      "eval_runtime": 75.2036,
+      "eval_samples_per_second": 16.05,
+      "eval_steps_per_second": 2.008,
+      "step": 2500
+    },
+    {
+      "epoch": 0.552689756816507,
+      "grad_norm": 368.7484436035156,
+      "learning_rate": 4.0788504053058217e-07,
+      "loss": 0.1681,
+      "step": 3000
+    },
+    {
+      "epoch": 0.552689756816507,
+      "eval_loss": 0.7217888236045837,
+      "eval_runtime": 76.0606,
+      "eval_samples_per_second": 15.869,
+      "eval_steps_per_second": 1.985,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6448047162859248,
+      "grad_norm": 20.03949737548828,
+      "learning_rate": 3.925325472856792e-07,
+      "loss": 0.1064,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6448047162859248,
+      "eval_loss": 0.7048410177230835,
+      "eval_runtime": 76.0578,
+      "eval_samples_per_second": 15.87,
+      "eval_steps_per_second": 1.985,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1259873746112520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9589d95f7287a546fe28eed1162f0176f1b95b18274e91ad5fc36f7db12aeb
+size 4847