Training in progress, step 4000, checkpoint

checkpoint-4000/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-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd6b8f2b0e94dfe260a1dd8a49b317198033c4155d6d15e067bbad16ecbc290
+size 1711848436

checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6194ce851679c69cccd1917b3eba2c3b2c9df0696f497da3cbb1251ad8fb2686
+size 3424043887

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0289613f9abb782023ce231f34f2dee59b6b952ce76bf1fa3bd8f2e3b35b3825
+size 14503

checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba266763f45c5a92f9dd3e089490f6840349f485cd776d10d2de75265bed452
+size 623

checkpoint-4000/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 1.0176074504852295,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-4000",
+  "epoch": 0.42662116040955633,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "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
+    },
+    {
+      "epoch": 0.10665529010238908,
+      "grad_norm": 72.11767578125,
+      "learning_rate": 9.64448236632537e-08,
+      "loss": 0.414,
+      "step": 1000
+    },
+    {
+      "epoch": 0.10665529010238908,
+      "eval_loss": 1.284197211265564,
+      "eval_runtime": 62.7418,
+      "eval_samples_per_second": 15.731,
+      "eval_steps_per_second": 1.976,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1599829351535836,
+      "grad_norm": 812.2269287109375,
+      "learning_rate": 9.466723549488054e-08,
+      "loss": 0.3279,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1599829351535836,
+      "eval_loss": 1.2100127935409546,
+      "eval_runtime": 62.6215,
+      "eval_samples_per_second": 15.761,
+      "eval_steps_per_second": 1.98,
+      "step": 1500
+    },
+    {
+      "epoch": 0.21331058020477817,
+      "grad_norm": 4.459943771362305,
+      "learning_rate": 9.288964732650739e-08,
+      "loss": 0.2912,
+      "step": 2000
+    },
+    {
+      "epoch": 0.21331058020477817,
+      "eval_loss": 1.1584910154342651,
+      "eval_runtime": 64.0453,
+      "eval_samples_per_second": 15.411,
+      "eval_steps_per_second": 1.936,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2666382252559727,
+      "grad_norm": 328.06475830078125,
+      "learning_rate": 9.111205915813424e-08,
+      "loss": 0.3056,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2666382252559727,
+      "eval_loss": 1.1090214252471924,
+      "eval_runtime": 63.2171,
+      "eval_samples_per_second": 15.613,
+      "eval_steps_per_second": 1.961,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3199658703071672,
+      "grad_norm": 0.00026008329587057233,
+      "learning_rate": 8.933447098976109e-08,
+      "loss": 0.2453,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3199658703071672,
+      "eval_loss": 1.0675184726715088,
+      "eval_runtime": 63.9757,
+      "eval_samples_per_second": 15.428,
+      "eval_steps_per_second": 1.938,
+      "step": 3000
+    },
+    {
+      "epoch": 0.37329351535836175,
+      "grad_norm": 7.824947834014893,
+      "learning_rate": 8.755688282138793e-08,
+      "loss": 0.2721,
+      "step": 3500
+    },
+    {
+      "epoch": 0.37329351535836175,
+      "eval_loss": 1.0416266918182373,
+      "eval_runtime": 63.8858,
+      "eval_samples_per_second": 15.449,
+      "eval_steps_per_second": 1.941,
+      "step": 3500
+    },
+    {
+      "epoch": 0.42662116040955633,
+      "grad_norm": 4.335076332092285,
+      "learning_rate": 8.57792946530148e-08,
+      "loss": 0.1925,
+      "step": 4000
+    },
+    {
+      "epoch": 0.42662116040955633,
+      "eval_loss": 1.0176074504852295,
+      "eval_runtime": 64.023,
+      "eval_samples_per_second": 15.416,
+      "eval_steps_per_second": 1.937,
+      "step": 4000
+    }
+  ],
+  "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": 1439752921742520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4000/training_args.bin

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