Training in progress, step 10000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Nadav/PretrainedPHD-v2",
+  "architectures": [
+    "PIXELForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "decoder_hidden_size": 512,
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 16,
+  "decoder_num_hidden_layers": 8,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "image_size": [
+    368,
+    368
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "mask_ratio": 0.25,
+  "model_type": "pixel",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0"
+}

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Nadav/PretrainedPHD-v2",
+  "architectures": [
+    "PIXELForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "decoder_hidden_size": 512,
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 16,
+  "decoder_num_hidden_layers": 8,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "image_size": [
+    368,
+    368
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "mask_ratio": 0.25,
+  "model_type": "pixel",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6efcea1f718e992622738eebec6655b308d8abaef61a2f7a2af6fa93b0ce7b9
+size 893438545

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d606552814a4ba7950abd9e209968958ecfd2f24d817fd26ef28c35737c8054d
+size 449471589

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c1cdccf174ece9de604197435ede54ec32a3b78eb6226070a07ab576a5585d
+size 15523

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4ea5b486ac1940989e451ce41280116176be849f45b93fb6c79bbd63b9b878
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d524b4cb1391ef7e50966a3eef7ac714ecb6ed976eedf165d99a07d29c73b99
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.870852564660803,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00010077565027123787,
+      "loss": 0.4732,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010075885246660077,
+      "loss": 0.4445,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00010073086073069567,
+      "loss": 0.4329,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001006916819700645,
+      "loss": 0.4256,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001006414377109213,
+      "loss": 0.421,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00010057993897463803,
+      "loss": 0.4167,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010050729045131372,
+      "loss": 0.4132,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00010042351006588448,
+      "loss": 0.4107,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00010032861848990674,
+      "loss": 0.4091,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001002228621438404,
+      "loss": 0.4067,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.3877949118614197,
+      "eval_runtime": 108.0468,
+      "eval_samples_per_second": 46.276,
+      "eval_steps_per_second": 0.731,
+      "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010010584325708389,
+      "loss": 0.4038,
+      "step": 5500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.997779155931062e-05,
+      "loss": 0.402,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.983873864536092e-05,
+      "loss": 0.401,
+      "step": 6500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.968871882446063e-05,
+      "loss": 0.4001,
+      "step": 7000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.952776911175577e-05,
+      "loss": 0.3987,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.935592921917959e-05,
+      "loss": 0.3974,
+      "step": 8000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.917361771757108e-05,
+      "loss": 0.3954,
+      "step": 8500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.898014889719868e-05,
+      "loss": 0.3945,
+      "step": 9000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.877592501404869e-05,
+      "loss": 0.394,
+      "step": 9500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.856099645730841e-05,
+      "loss": 0.3926,
+      "step": 10000
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.37431180477142334,
+      "eval_runtime": 106.4392,
+      "eval_samples_per_second": 46.975,
+      "eval_steps_per_second": 0.742,
+      "step": 10000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 9,
+  "total_flos": 4.709861347295232e+20,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd49a349d77c455473f49543bf6e96561e293025b2e65d9b3c90c0be2504db32
+size 5615

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d606552814a4ba7950abd9e209968958ecfd2f24d817fd26ef28c35737c8054d
+size 449471589

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd49a349d77c455473f49543bf6e96561e293025b2e65d9b3c90c0be2504db32
+size 5615