Training in progress, step 10000

.gitignore

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Nadav/PretrainedPHD",
+  "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": 0.29,
+  "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",
+  "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": 0.29,
+  "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 sha256:153be8a536485c83aa6dfda3ccd31cbb49591a8b1d3add03c304c0ca882f4f80
+size 893438545

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c20144a4b9e27b7911ada8d36376e0bfc98e3a7b006c69a1edf0cab2408ed8
+size 449471589

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c5109bb7103f67386e48a9ef9b3e5c761f186216810c95f00eb2eff9d2a4ec
+size 15523

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70032c0133ae8be4d57f5bc088df5e80deb90ddcc920990a92103ea496b93a7d
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42e0bd380ddae36480c7e1c1943e2b9fbad63e7f4fc190b9b9f25706bedbf28
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010077985004622052,
+      "loss": 0.5551,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010077565027123787,
+      "loss": 0.5087,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010076865093411392,
+      "loss": 0.5035,
+      "step": 1500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010075885246660077,
+      "loss": 0.5002,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010074625547311406,
+      "loss": 0.4973,
+      "step": 2500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010073086073069567,
+      "loss": 0.4936,
+      "step": 3000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010071266918896582,
+      "loss": 0.4953,
+      "step": 3500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001006916819700645,
+      "loss": 0.4924,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00010066790036858225,
+      "loss": 0.4905,
+      "step": 4500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010064132585148025,
+      "loss": 0.4899,
+      "step": 5000
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.4648222029209137,
+      "eval_runtime": 559.9664,
+      "eval_samples_per_second": 114.293,
+      "eval_steps_per_second": 1.786,
+      "step": 5000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001006119600579999,
+      "loss": 0.4887,
+      "step": 5500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010057980479956167,
+      "loss": 0.4881,
+      "step": 6000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010054493472563566,
+      "loss": 0.487,
+      "step": 6500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00010050721222807678,
+      "loss": 0.4854,
+      "step": 7000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00010046670672689959,
+      "loss": 0.4851,
+      "step": 7500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00010042342072067417,
+      "loss": 0.4832,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00010037735687948529,
+      "loss": 0.4838,
+      "step": 8500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001003287189239578,
+      "loss": 0.4837,
+      "step": 9000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010027711919001668,
+      "loss": 0.4828,
+      "step": 9500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00010022275064567964,
+      "loss": 0.4826,
+      "step": 10000
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.456764280796051,
+      "eval_runtime": 528.1623,
+      "eval_samples_per_second": 121.175,
+      "eval_steps_per_second": 1.893,
+      "step": 10000
+    }
+  ],
+  "max_steps": 200000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.354930673647616e+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:ca762f1acf9a6f6d964307929433968af3e08f4803fb33705fe0dbbd68e4da76
+size 5551

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c20144a4b9e27b7911ada8d36376e0bfc98e3a7b006c69a1edf0cab2408ed8
+size 449471589

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca762f1acf9a6f6d964307929433968af3e08f4803fb33705fe0dbbd68e4da76
+size 5551