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 sha256:4986a544e8254a7bcbed3736ad8c80f3ef1d2e844ddacd63bfdf16e0f9249bbf
+size 1711848436

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123b83688a3ef9bf6bf650b585649d382ca46a52ced87ab5795b66a0547b6b2e
+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:a5912b32026fa010990d2716c9308951d8a6e307fbff9d6533e5a2eaf8193deb
+size 623

checkpoint-3500/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 1.4432125091552734,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l59-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": 20.952665328979492,
+      "learning_rate": 4.884856300663228e-09,
+      "loss": 0.3952,
+      "step": 500
+    },
+    {
+      "epoch": 0.09211495946941783,
+      "eval_loss": 1.4940427541732788,
+      "eval_runtime": 73.9282,
+      "eval_samples_per_second": 16.327,
+      "eval_steps_per_second": 2.043,
+      "step": 500
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "grad_norm": 59.28666687011719,
+      "learning_rate": 4.769712601326456e-09,
+      "loss": 0.4562,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "eval_loss": 1.4853259325027466,
+      "eval_runtime": 74.6533,
+      "eval_samples_per_second": 16.168,
+      "eval_steps_per_second": 2.023,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "grad_norm": 1.179814338684082,
+      "learning_rate": 4.654568901989683e-09,
+      "loss": 0.5131,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "eval_loss": 1.4757832288742065,
+      "eval_runtime": 76.2866,
+      "eval_samples_per_second": 15.822,
+      "eval_steps_per_second": 1.979,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "grad_norm": 0.900991678237915,
+      "learning_rate": 4.5394252026529105e-09,
+      "loss": 0.4481,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "eval_loss": 1.4675536155700684,
+      "eval_runtime": 75.9348,
+      "eval_samples_per_second": 15.895,
+      "eval_steps_per_second": 1.989,
+      "step": 2000
+    },
+    {
+      "epoch": 0.46057479734708917,
+      "grad_norm": 346.93853759765625,
+      "learning_rate": 4.424281503316139e-09,
+      "loss": 0.4839,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46057479734708917,
+      "eval_loss": 1.4585391283035278,
+      "eval_runtime": 76.7708,
+      "eval_samples_per_second": 15.722,
+      "eval_steps_per_second": 1.967,
+      "step": 2500
+    },
+    {
+      "epoch": 0.552689756816507,
+      "grad_norm": 318.47515869140625,
+      "learning_rate": 4.3091378039793666e-09,
+      "loss": 0.4377,
+      "step": 3000
+    },
+    {
+      "epoch": 0.552689756816507,
+      "eval_loss": 1.4507631063461304,
+      "eval_runtime": 76.5424,
+      "eval_samples_per_second": 15.769,
+      "eval_steps_per_second": 1.973,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6448047162859248,
+      "grad_norm": 112.41814422607422,
+      "learning_rate": 4.193994104642594e-09,
+      "loss": 0.4231,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6448047162859248,
+      "eval_loss": 1.4432125091552734,
+      "eval_runtime": 76.4812,
+      "eval_samples_per_second": 15.782,
+      "eval_steps_per_second": 1.974,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 21712,
+  "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": 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 sha256:17dd82d53ab261b7081e3e93503b374d907fea92ca3e505d0ff1319c5765d331
+size 4847