Training in progress, step 5000

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 filter=lfs diff=lfs merge=lfs -text

.gitignore

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

49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
+size 15645492

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "PIXELForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "decoder_hidden_size": 264,
+  "decoder_intermediate_size": 1056,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "image_size": [
+    16,
+    8464
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "mask_ratio": 0.25,
+  "model_type": "pixel",
+  "norm_pix_input": true,
+  "norm_pix_loss": true,
+  "num_attention_heads": 6,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0"
+}

last-checkpoint/49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
+size 15645492

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "PIXELForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "decoder_hidden_size": 264,
+  "decoder_intermediate_size": 1056,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "image_size": [
+    16,
+    8464
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "mask_ratio": 0.25,
+  "model_type": "pixel",
+  "norm_pix_input": true,
+  "norm_pix_loss": true,
+  "num_attention_heads": 6,
+  "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 sha256:5c1615dfe102dab2a138602271d02396c2a0543d78d5c84432b37b7135c321f6
+size 202193937

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1073eb1928fc8408104ce2bf932850768861af32dde26a1b7ddb75456b5aa2b
+size 102501541

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb26b59330b615a98e78d6fa6f00cb6141e029593d57c287ed1c46236d2e017
+size 14503

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb26b59330b615a98e78d6fa6f00cb6141e029593d57c287ed1c46236d2e017
+size 14503

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb26b59330b615a98e78d6fa6f00cb6141e029593d57c287ed1c46236d2e017
+size 14503

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb26b59330b615a98e78d6fa6f00cb6141e029593d57c287ed1c46236d2e017
+size 14503

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c11dd53838f08d583b09590e96c554aabe7ed9ae5fb5c669bfc6beb9fddacbd
+size 623

last-checkpoint/text_renderer_config.json

@@ -0,0 +1,11 @@
+{
+  "background_color": "white",
+  "dpi": 120,
+  "font_color": "black",
+  "font_file": "49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
+  "font_size": 8,
+  "max_seq_length": 529,
+  "pad_size": 3,
+  "pixels_per_patch": 16,
+  "text_renderer_type": "PyGameTextRenderer"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07659607062157711,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 0.7239,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 0.2594,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 0.0798,
+      "step": 1500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 0.0611,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.0603,
+      "step": 2500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 0.06,
+      "step": 3000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.1e-05,
+      "loss": 0.0597,
+      "step": 3500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 0.0596,
+      "step": 4000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 0.0595,
+      "step": 4500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.0594,
+      "step": 5000
+    }
+  ],
+  "max_steps": 500000,
+  "num_train_epochs": 8,
+  "total_flos": 7.9871784693625e+19,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fc0c551198ca4907e70bb4b0044b0f6f08d72a20ab8c2f1ed25d998371c8a9
+size 3247

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1073eb1928fc8408104ce2bf932850768861af32dde26a1b7ddb75456b5aa2b
+size 102501541

text_renderer_config.json

@@ -0,0 +1,11 @@
+{
+  "background_color": "white",
+  "dpi": 120,
+  "font_color": "black",
+  "font_file": "49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
+  "font_size": 8,
+  "max_seq_length": 529,
+  "pad_size": 3,
+  "pixels_per_patch": 16,
+  "text_renderer_type": "PyGameTextRenderer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fc0c551198ca4907e70bb4b0044b0f6f08d72a20ab8c2f1ed25d998371c8a9
+size 3247