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 sha256:84328ec4f3395a8a552b0898448b2fedff19ca78ff620af1951baa5452fc8603
+size 1711848436

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07476493eaabbc39825d32b58e9bda7d6a03c39a86244dcc1d54b9103a192f21
+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 sha256:99e9e0c817bb2bd5a0011cf67b4be3be86362fcb6a8e2004e21ba757c007f264
+size 623

checkpoint-500/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 1.0726110935211182,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e2l57-l/checkpoint-500",
+  "epoch": 0.09211495946941783,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09211495946941783,
+      "grad_norm": 2.838374137878418,
+      "learning_rate": 4.769712601326456e-07,
+      "loss": 0.2712,
+      "step": 500
+    },
+    {
+      "epoch": 0.09211495946941783,
+      "eval_loss": 1.0726110935211182,
+      "eval_runtime": 77.3241,
+      "eval_samples_per_second": 15.61,
+      "eval_steps_per_second": 1.953,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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 sha256:4cd5d7856a0d40c1aa83893e8a456fbbee3c7b8b2995fa667c213e700eef2e98
+size 4847