Training in progress, step 500, checkpoint

checkpoint-500/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-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c72ad550f3491c0388a3ae2ca626d8f49a81eb079b23b84ae43ded59c6e90c4
+size 1711848436

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc96f333524234cbbb711884da5cca4fbbda263cd689e48741c878e140f6412
+size 3424043887

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cddbf207acff68da0d051345656b78fe58e07a53e2d0a8f4d9ea5c8255f66ff
+size 14503

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b34ef632336b8c9174847c53fb5a71e6753b132bc0cc00b3074f98bbd0d2db2
+size 623

checkpoint-500/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 1.38526451587677,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-500",
+  "epoch": 0.05332764505119454,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05332764505119454,
+      "grad_norm": 247.07174682617188,
+      "learning_rate": 9.822241183162683e-08,
+      "loss": 0.4515,
+      "step": 500
+    },
+    {
+      "epoch": 0.05332764505119454,
+      "eval_loss": 1.38526451587677,
+      "eval_runtime": 63.6956,
+      "eval_samples_per_second": 15.496,
+      "eval_steps_per_second": 1.947,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28128,
+  "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": 180598692332520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52c451dc1fefed1a64b0a23a69d323685c58d3023f0abb7cb18bc82e1be68c7
+size 4847