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:ed8c0643963453d9fb906c91e412f6325314f81fe5ff15b417ead54309575950
+size 1711848436

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947171e6da8b230295cbfffccac225ed5d84b293718d3ff13a1c7cfbf9cb5119
+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 sha256:930b433ac6e86f0faf6276e8d08a34bab7f251e66c9c08f6f0bb7c446960b849
+size 623

checkpoint-3500/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 1.5010316371917725,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e5l510-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": 21.660480499267578,
+      "learning_rate": 4.907885040530583e-10,
+      "loss": 0.3974,
+      "step": 500
+    },
+    {
+      "epoch": 0.09211495946941783,
+      "eval_loss": 1.5028706789016724,
+      "eval_runtime": 74.0662,
+      "eval_samples_per_second": 16.296,
+      "eval_steps_per_second": 2.039,
+      "step": 500
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "grad_norm": 60.26338577270508,
+      "learning_rate": 4.815770081061165e-10,
+      "loss": 0.462,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "eval_loss": 1.5025668144226074,
+      "eval_runtime": 75.1835,
+      "eval_samples_per_second": 16.054,
+      "eval_steps_per_second": 2.008,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "grad_norm": 1.4199143648147583,
+      "learning_rate": 4.723655121591747e-10,
+      "loss": 0.5249,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "eval_loss": 1.5022265911102295,
+      "eval_runtime": 76.3442,
+      "eval_samples_per_second": 15.81,
+      "eval_steps_per_second": 1.978,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "grad_norm": 1.2705016136169434,
+      "learning_rate": 4.6315401621223287e-10,
+      "loss": 0.4642,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "eval_loss": 1.5019283294677734,
+      "eval_runtime": 77.0512,
+      "eval_samples_per_second": 15.665,
+      "eval_steps_per_second": 1.96,
+      "step": 2000
+    },
+    {
+      "epoch": 0.46057479734708917,
+      "grad_norm": 335.6837463378906,
+      "learning_rate": 4.5394252026529114e-10,
+      "loss": 0.5056,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46057479734708917,
+      "eval_loss": 1.5015931129455566,
+      "eval_runtime": 76.8527,
+      "eval_samples_per_second": 15.705,
+      "eval_steps_per_second": 1.965,
+      "step": 2500
+    },
+    {
+      "epoch": 0.552689756816507,
+      "grad_norm": 402.1738586425781,
+      "learning_rate": 4.4473102431834935e-10,
+      "loss": 0.4604,
+      "step": 3000
+    },
+    {
+      "epoch": 0.552689756816507,
+      "eval_loss": 1.501311182975769,
+      "eval_runtime": 76.7728,
+      "eval_samples_per_second": 15.722,
+      "eval_steps_per_second": 1.967,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6448047162859248,
+      "grad_norm": 120.70919799804688,
+      "learning_rate": 4.3551952837140756e-10,
+      "loss": 0.4508,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6448047162859248,
+      "eval_loss": 1.5010316371917725,
+      "eval_runtime": 77.0074,
+      "eval_samples_per_second": 15.674,
+      "eval_steps_per_second": 1.961,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 27140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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 sha256:4216477e635a737e95915c1d07b3b9cd2ee3a4f3b4c352bfa7225c18c894aa58
+size 4847