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": 0.25,
+  "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:b7965023fb90058fbcca08a10a8e9e39d8cf72c5b9f3d0eb2b25bc715dfb7185
+size 893438545

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abd226a9e0cc358d3b07162345d74dc2fab3322999fae6a6de0ab8221263680
+size 449471589

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8217c6a790474956dac035c8fd3d42f3d276f02a592aa421e5eed682cc08b9be
+size 15523

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46171f332d1e5155156d4999fec5406fc9f03857ff686d0152b9c4ca38519697
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611657e4e82b38f099b149471e6aaaa5a577926bec8385cc0f6dd743ea4cfd9b
+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": 0.55,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010075885246660077,
+      "loss": 0.5027,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00010073086073069567,
+      "loss": 0.4909,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001006916819700645,
+      "loss": 0.4828,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00010064132585148025,
+      "loss": 0.4791,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00010057980479956167,
+      "loss": 0.475,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010050713399370776,
+      "loss": 0.4706,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00010042333136435246,
+      "loss": 0.4686,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001003284175885406,
+      "loss": 0.4662,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00010022241608482616,
+      "loss": 0.4639,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.4434024393558502,
+      "eval_runtime": 58.4628,
+      "eval_samples_per_second": 85.524,
+      "eval_steps_per_second": 1.351,
+      "step": 5000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010010535300749402,
+      "loss": 0.4617,
+      "step": 5500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.997725724010688e-05,
+      "loss": 0.4605,
+      "step": 6000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.983816038837858e-05,
+      "loss": 0.4601,
+      "step": 6500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.968809677237595e-05,
+      "loss": 0.4567,
+      "step": 7000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.952710341805077e-05,
+      "loss": 0.4573,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.935522004810426e-05,
+      "loss": 0.4558,
+      "step": 8000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.91728653305258e-05,
+      "loss": 0.4534,
+      "step": 8500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.897935339304003e-05,
+      "loss": 0.4529,
+      "step": 9000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.87750865890554e-05,
+      "loss": 0.4511,
+      "step": 9500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.856055590913237e-05,
+      "loss": 0.45,
+      "step": 10000
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.42864668369293213,
+      "eval_runtime": 74.102,
+      "eval_samples_per_second": 67.475,
+      "eval_steps_per_second": 1.066,
+      "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 sha256:5338e8a2c0a904652b6d8f7e355dcea8351d2f08d02d32f0f504d2e3f53f6aa5
+size 5551

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abd226a9e0cc358d3b07162345d74dc2fab3322999fae6a6de0ab8221263680
+size 449471589

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5338e8a2c0a904652b6d8f7e355dcea8351d2f08d02d32f0f504d2e3f53f6aa5
+size 5551