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": 0.25,
+  "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",
+  "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 sha256:07f4c191169bdefbf903ed26706aa4d7421568132260ed3c336a7bb1e9b346b7
+size 893438545

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec70d2781e97f4d329ba4c23b171ff2d9e095d57e1d6f397b53ab37773b559f
+size 449471589

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89bfe126fed4c4ad4dd5e48270f02e29322c35de34e86277f87fea6ea6285c49
+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:a01f1f0436989f1373566c8148c19011dd0ac4c035b4f3ba4538506b2eac4732
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.00810142990237777,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "eval_runtime": 4.2859,
+      "eval_samples_per_second": 11.666,
+      "eval_steps_per_second": 0.467,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "eval_runtime": 6.7254,
+      "eval_samples_per_second": 7.435,
+      "eval_steps_per_second": 0.297,
+      "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "eval_runtime": 4.4562,
+      "eval_samples_per_second": 11.22,
+      "eval_steps_per_second": 0.449,
+      "step": 300
+    },
+    {
+      "epoch": 0.01,
+      "eval_runtime": 4.3116,
+      "eval_samples_per_second": 11.597,
+      "eval_steps_per_second": 0.464,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 0.535,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "eval_runtime": 4.3937,
+      "eval_samples_per_second": 11.38,
+      "eval_steps_per_second": 0.455,
+      "step": 500
+    }
+  ],
+  "max_steps": 1000000,
+  "num_train_epochs": 17,
+  "total_flos": 4.38126636957696e+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:d6270bc289a88f0f959604cd35e12f62592ad82a5a0194af541981581f153ae0
+size 5551

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec70d2781e97f4d329ba4c23b171ff2d9e095d57e1d6f397b53ab37773b559f
+size 449471589

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6270bc289a88f0f959604cd35e12f62592ad82a5a0194af541981581f153ae0
+size 5551