Training in progress, step 2000, checkpoint

checkpoint-2000/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-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48998e529a8c390fa678ec56819e64346605db4478af8b5a6d8471049af38b18
+size 1711848436

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e431ef2704994761cc34d264c65229edc555b161a1e6d247046100fa0fdc0c8
+size 3424043887

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d41fa6662602ededfc4b7984d27ddf54962906079944f4a744895f11dfd2c3
+size 14503

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a70a2ce58c4af59edfa3e6fce364b63916ec83e257c0bdde48550aa3d780ff
+size 623

checkpoint-2000/trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": 1.3193777799606323,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l56-l/checkpoint-2000",
+  "epoch": 0.36845983787767134,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09211495946941783,
+      "grad_norm": 18.028329849243164,
+      "learning_rate": 4.846475067550971e-06,
+      "loss": 0.2253,
+      "step": 500
+    },
+    {
+      "epoch": 0.09211495946941783,
+      "eval_loss": 1.4693936109542847,
+      "eval_runtime": 74.2802,
+      "eval_samples_per_second": 16.249,
+      "eval_steps_per_second": 2.033,
+      "step": 500
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "grad_norm": 0.4609026312828064,
+      "learning_rate": 4.692950135101941e-06,
+      "loss": 0.2544,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18422991893883567,
+      "eval_loss": 1.5420819520950317,
+      "eval_runtime": 74.0766,
+      "eval_samples_per_second": 16.294,
+      "eval_steps_per_second": 2.038,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "grad_norm": 71.96737670898438,
+      "learning_rate": 4.5394252026529115e-06,
+      "loss": 0.3236,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2763448784082535,
+      "eval_loss": 1.4642689228057861,
+      "eval_runtime": 74.2336,
+      "eval_samples_per_second": 16.259,
+      "eval_steps_per_second": 2.034,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "grad_norm": 6.366127069945549e-10,
+      "learning_rate": 4.385900270203882e-06,
+      "loss": 0.1888,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36845983787767134,
+      "eval_loss": 1.3193777799606323,
+      "eval_runtime": 76.1214,
+      "eval_samples_per_second": 15.856,
+      "eval_steps_per_second": 1.984,
+      "step": 2000
+    }
+  ],
+  "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": 720236219222520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46089b82f4ed355b4512be05866138fa1fe20f53cc2bb3deace890abfba0e5f2
+size 4847