Training in progress, step 500

.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:c177d67649d7f75b030bd418cddf6480e5eee4eaeae0bb4328b091286c890856
+size 893438545

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16152db69174268dbe07d778850689e6c5ed4790cd775f2f1ed4652d4acd62ad
+size 449471589

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5c838e275078f37af9b6c8757b7465b5c9e75013d9cd72620d4baca15a3525
+size 15523

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa4c7be44c959599b8b43bb9bc3371e9e4e5bbc5758b3ab5afcccfda3e72e67
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf2de0112530414421e243bcec4058cb8653784c2ee9714acd33b6f07a1c191
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.8696136490103726e-05,
+      "loss": 0.7321,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8535872258791296e-05,
+      "loss": 0.6501,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6644620299339294,
+      "eval_runtime": 1.6316,
+      "eval_samples_per_second": 9.806,
+      "eval_steps_per_second": 0.613,
+      "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8273153543324108e-05,
+      "loss": 0.645,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.791444935039039e-05,
+      "loss": 0.6326,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.651160478591919,
+      "eval_runtime": 1.5553,
+      "eval_samples_per_second": 10.288,
+      "eval_steps_per_second": 0.643,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7468592167691143e-05,
+      "loss": 0.6383,
+      "step": 250
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6946560478779568e-05,
+      "loss": 0.6232,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.63567054271698,
+      "eval_runtime": 1.56,
+      "eval_samples_per_second": 10.256,
+      "eval_steps_per_second": 0.641,
+      "step": 300
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6361208436360516e-05,
+      "loss": 0.636,
+      "step": 350
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.5726949350390392e-05,
+      "loss": 0.6299,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.6344127655029297,
+      "eval_runtime": 1.7227,
+      "eval_samples_per_second": 9.288,
+      "eval_steps_per_second": 0.58,
+      "step": 400
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.505940078455101e-05,
+      "loss": 0.5992,
+      "step": 450
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.4375e-05,
+      "loss": 0.6041,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6284211874008179,
+      "eval_runtime": 1.5568,
+      "eval_samples_per_second": 10.277,
+      "eval_steps_per_second": 0.642,
+      "step": 500
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.19063318478848e+18,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f94f3c16f943b3ec1bd2078d69d2f71c340cad97b31d2dd85408a857e23494
+size 5487

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16152db69174268dbe07d778850689e6c5ed4790cd775f2f1ed4652d4acd62ad
+size 449471589

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f94f3c16f943b3ec1bd2078d69d2f71c340cad97b31d2dd85408a857e23494
+size 5487