Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Nadav/PretrainedPHD-v2-all-fonts",
+  "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-v2-all-fonts",
+  "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:eb45938d953a9e02a93e023c6a0b6bfb85db281d7688bb4637b08cc92108582c
+size 893438545

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3c27dbd3634486f44b515b1ac2f607480d0607442e74b1007f80c67dee71ed
+size 449471589

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7b0cc71c51ef5f7a78f816541ca99e7efff8df2315723a0c94e1b16e8f0771
+size 15459

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5552ea5d95da782f44b70f8a22ae167ba18f71e31f49d66221dac13c0bd1155
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681eed174af016a0d856f771b729ad32b51485c9166d03117b81f6f3901e0509
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4352746583093932,
+  "global_step": 5000,
+  "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": 0.5268,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010075885246660077,
+      "loss": 0.5021,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00010073086073069567,
+      "loss": 0.4927,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001006916819700645,
+      "loss": 0.4854,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00010064132585148025,
+      "loss": 0.4834,
+      "step": 2500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00010057980479956167,
+      "loss": 0.4781,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010050713399370776,
+      "loss": 0.4752,
+      "step": 3500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00010042333136435246,
+      "loss": 0.4725,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00010032881934692084,
+      "loss": 0.4705,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001002228621438404,
+      "loss": 0.4686,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.45014095306396484,
+      "eval_runtime": 54.4029,
+      "eval_samples_per_second": 91.907,
+      "eval_steps_per_second": 1.452,
+      "step": 5000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 9,
+  "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 sha256:30c25b619285837a9cbe79c92a5e0fc44806703a40caa54c45909f86e5afdcbb
+size 5679

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3c27dbd3634486f44b515b1ac2f607480d0607442e74b1007f80c67dee71ed
+size 449471589

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c25b619285837a9cbe79c92a5e0fc44806703a40caa54c45909f86e5afdcbb
+size 5679