Training in progress, step 220000

backup-290000/GoNotoCurrent.ttf

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

backup-290000/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "PIXELForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cache_dir": null,
+  "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": [
+    16,
+    8464
+  ],
+  "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,
+  "revision": "main",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_auth_token": false
+}

backup-290000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9dcbb20629922bf85067e22faf5d25195f8e035f7d57e5f526ba804954689c
+size 449474626

backup-290000/text_renderer_config.json

@@ -0,0 +1,168 @@
+{
+  "background_color": "white",
+  "dpi": 120,
+  "font_color": "black",
+  "font_file": "GoNotoCurrent.ttf",
+  "font_size": 8,
+  "fonts_list": [
+    "Abyssinica SIL",
+    "Ani",
+    "AnjaliOldLipi",
+    "Bitstream Vera Sans",
+    "Bitstream Vera Sans Mono",
+    "Bitstream Vera Serif",
+    "C059",
+    "Chandas",
+    "Chilanka",
+    "D050000L",
+    "DejaVu Math TeX Gyre",
+    "DejaVu Sans",
+    "DejaVu Sans Mono",
+    "DejaVu Serif",
+    "Droid Sans Fallback",
+    "Dyuthi",
+    "FreeMono",
+    "FreeSans",
+    "FreeSerif",
+    "Gargi",
+    "Garuda",
+    "Gayathri",
+    "Go Noto Current",
+    "Gubbi",
+    "Inconsolata",
+    "Jamrul",
+    "KacstArt",
+    "KacstBook",
+    "KacstDecorative",
+    "KacstDigital",
+    "KacstFarsi",
+    "KacstLetter",
+    "KacstNaskh",
+    "KacstOffice",
+    "KacstOne",
+    "KacstPen",
+    "KacstPoster",
+    "KacstQurn",
+    "KacstScreen",
+    "KacstTitle",
+    "KacstTitleL",
+    "Kalapi",
+    "Kalimati",
+    "Karumbi",
+    "Keraleeyam",
+    "Khmer OS",
+    "Khmer OS System",
+    "Kinnari",
+    "LKLUG",
+    "Laksaman",
+    "Liberation Mono",
+    "Liberation Sans",
+    "Liberation Sans Narrow",
+    "Liberation Serif",
+    "Likhan",
+    "Lohit Assamese",
+    "Lohit Bengali",
+    "Lohit Devanagari",
+    "Lohit Gujarati",
+    "Lohit Gurmukhi",
+    "Lohit Kannada",
+    "Lohit Malayalam",
+    "Lohit Odia",
+    "Lohit Tamil",
+    "Lohit Tamil Classical",
+    "Lohit Telugu",
+    "Loma",
+    "Manjari",
+    "Meera",
+    "Mitra Mono",
+    "Monospace",
+    "Mukti Narrow",
+    "Nakula",
+    "Navilu",
+    "Nimbus Mono PS",
+    "Nimbus Roman",
+    "Nimbus Sans",
+    "Nimbus Sans Narrow",
+    "Norasi",
+    "Noto Color Emoji",
+    "Noto Mono",
+    "Noto Sans CJK HK",
+    "Noto Sans CJK JP",
+    "Noto Sans CJK KR",
+    "Noto Sans CJK SC",
+    "Noto Sans CJK TC",
+    "Noto Sans Mono CJK HK",
+    "Noto Sans Mono CJK JP",
+    "Noto Sans Mono CJK KR",
+    "Noto Sans Mono CJK SC",
+    "Noto Sans Mono CJK TC",
+    "Noto Serif CJK JP",
+    "Noto Serif CJK KR",
+    "Noto Serif CJK SC",
+    "Noto Serif CJK TC",
+    "OpenSymbol",
+    "P052",
+    "Padauk",
+    "Padauk Book",
+    "Pagul",
+    "Phetsarath OT",
+    "Pothana2000",
+    "Purisa",
+    "Rachana",
+    "RaghuMalayalamSans",
+    "Rasa",
+    "Rekha",
+    "Saab",
+    "Sahadeva",
+    "Samanata",
+    "Samyak Devanagari",
+    "Samyak Gujarati",
+    "Samyak Malayalam",
+    "Samyak Tamil",
+    "Sans",
+    "Sarai",
+    "Sawasdee",
+    "Serif",
+    "Source Code Pro",
+    "Standard Symbols PS",
+    "Suruma",
+    "System-ui",
+    "Tibetan Machine Uni",
+    "Tlwg Mono",
+    "Tlwg Typewriter",
+    "Tlwg Typist",
+    "Tlwg Typo",
+    "URW Bookman",
+    "URW Gothic",
+    "Ubuntu",
+    "Ubuntu Condensed",
+    "Ubuntu Mono",
+    "Umpush",
+    "Uroob",
+    "Vemana2000",
+    "Waree",
+    "Yrsa",
+    "Z003",
+    "aakar",
+    "cmex10",
+    "cmmi10",
+    "cmr10",
+    "cmsy10",
+    "esint10",
+    "eufm10",
+    "mry_KacstQurn",
+    "msam10",
+    "msbm10",
+    "ori1Uni",
+    "padmaa",
+    "padmaa-Bold.1.1",
+    "rsfs10",
+    "stmary10",
+    "wasy10"
+  ],
+  "max_seq_length": 529,
+  "pad_size": 3,
+  "pixels_per_patch": 16,
+  "rgb": false,
+  "text_renderer_type": "PangoCairoTextRenderer"
+}

backup-290000/trainer_state.json

@@ -0,0 +1,305 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 111.9194180190263,
+  "global_step": 200000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 11.19,
+      "learning_rate": 1.8749999999999998e-06,
+      "loss": 0.8164,
+      "step": 10000
+    },
+    {
+      "epoch": 11.19,
+      "eval_loss": 0.7568955421447754,
+      "eval_runtime": 301.8174,
+      "eval_samples_per_second": 25.618,
+      "eval_steps_per_second": 1.604,
+      "step": 10000
+    },
+    {
+      "epoch": 22.37,
+      "learning_rate": 3.7499999999999997e-06,
+      "loss": 0.7702,
+      "step": 20000
+    },
+    {
+      "epoch": 22.37,
+      "eval_loss": 0.7498099207878113,
+      "eval_runtime": 249.204,
+      "eval_samples_per_second": 31.027,
+      "eval_steps_per_second": 1.942,
+      "step": 20000
+    },
+    {
+      "epoch": 33.56,
+      "learning_rate": 5.6249999999999995e-06,
+      "loss": 0.7668,
+      "step": 30000
+    },
+    {
+      "epoch": 33.56,
+      "eval_loss": 0.7477062344551086,
+      "eval_runtime": 189.0409,
+      "eval_samples_per_second": 40.901,
+      "eval_steps_per_second": 2.56,
+      "step": 30000
+    },
+    {
+      "epoch": 44.74,
+      "learning_rate": 7.499999999999999e-06,
+      "loss": 0.7655,
+      "step": 40000
+    },
+    {
+      "epoch": 44.74,
+      "eval_loss": 0.7450574040412903,
+      "eval_runtime": 66.2284,
+      "eval_samples_per_second": 116.748,
+      "eval_steps_per_second": 7.308,
+      "step": 40000
+    },
+    {
+      "epoch": 27.98,
+      "learning_rate": 9.375e-06,
+      "loss": 0.7653,
+      "step": 50000
+    },
+    {
+      "epoch": 27.98,
+      "eval_loss": 0.7478589415550232,
+      "eval_runtime": 76.5001,
+      "eval_samples_per_second": 101.072,
+      "eval_steps_per_second": 12.641,
+      "step": 50000
+    },
+    {
+      "epoch": 33.58,
+      "learning_rate": 1.1249999999999999e-05,
+      "loss": 0.7648,
+      "step": 60000
+    },
+    {
+      "epoch": 33.58,
+      "eval_loss": 0.7447686195373535,
+      "eval_runtime": 76.3539,
+      "eval_samples_per_second": 101.265,
+      "eval_steps_per_second": 12.665,
+      "step": 60000
+    },
+    {
+      "epoch": 39.17,
+      "learning_rate": 1.3124999999999999e-05,
+      "loss": 0.7645,
+      "step": 70000
+    },
+    {
+      "epoch": 39.17,
+      "eval_loss": 0.7464274764060974,
+      "eval_runtime": 76.7958,
+      "eval_samples_per_second": 100.683,
+      "eval_steps_per_second": 12.592,
+      "step": 70000
+    },
+    {
+      "epoch": 44.77,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.7642,
+      "step": 80000
+    },
+    {
+      "epoch": 44.77,
+      "eval_loss": 0.7449608445167542,
+      "eval_runtime": 122.9116,
+      "eval_samples_per_second": 62.907,
+      "eval_steps_per_second": 7.867,
+      "step": 80000
+    },
+    {
+      "epoch": 50.36,
+      "learning_rate": 1.6875e-05,
+      "loss": 0.7636,
+      "step": 90000
+    },
+    {
+      "epoch": 50.36,
+      "eval_loss": 0.7427342534065247,
+      "eval_runtime": 76.4172,
+      "eval_samples_per_second": 101.181,
+      "eval_steps_per_second": 12.654,
+      "step": 90000
+    },
+    {
+      "epoch": 55.96,
+      "learning_rate": 2e-05,
+      "loss": 0.7602,
+      "step": 100000
+    },
+    {
+      "epoch": 55.96,
+      "eval_loss": 0.726163387298584,
+      "eval_runtime": 76.3938,
+      "eval_samples_per_second": 101.212,
+      "eval_steps_per_second": 12.658,
+      "step": 100000
+    },
+    {
+      "epoch": 61.56,
+      "learning_rate": 2e-05,
+      "loss": 0.7279,
+      "step": 110000
+    },
+    {
+      "epoch": 61.56,
+      "eval_loss": 0.6971690654754639,
+      "eval_runtime": 76.7625,
+      "eval_samples_per_second": 100.726,
+      "eval_steps_per_second": 12.597,
+      "step": 110000
+    },
+    {
+      "epoch": 67.15,
+      "learning_rate": 2e-05,
+      "loss": 0.6981,
+      "step": 120000
+    },
+    {
+      "epoch": 67.15,
+      "eval_loss": 0.6809367537498474,
+      "eval_runtime": 76.4831,
+      "eval_samples_per_second": 101.094,
+      "eval_steps_per_second": 12.643,
+      "step": 120000
+    },
+    {
+      "epoch": 72.75,
+      "learning_rate": 2e-05,
+      "loss": 0.6781,
+      "step": 130000
+    },
+    {
+      "epoch": 72.75,
+      "eval_loss": 0.6643149852752686,
+      "eval_runtime": 76.5075,
+      "eval_samples_per_second": 101.062,
+      "eval_steps_per_second": 12.639,
+      "step": 130000
+    },
+    {
+      "epoch": 78.34,
+      "learning_rate": 2e-05,
+      "loss": 0.6612,
+      "step": 140000
+    },
+    {
+      "epoch": 78.34,
+      "eval_loss": 0.653438150882721,
+      "eval_runtime": 76.7069,
+      "eval_samples_per_second": 100.799,
+      "eval_steps_per_second": 12.606,
+      "step": 140000
+    },
+    {
+      "epoch": 83.94,
+      "learning_rate": 2e-05,
+      "loss": 0.6483,
+      "step": 150000
+    },
+    {
+      "epoch": 83.94,
+      "eval_loss": 0.6426078081130981,
+      "eval_runtime": 76.587,
+      "eval_samples_per_second": 100.957,
+      "eval_steps_per_second": 12.626,
+      "step": 150000
+    },
+    {
+      "epoch": 89.54,
+      "learning_rate": 2e-05,
+      "loss": 0.6389,
+      "step": 160000
+    },
+    {
+      "epoch": 89.54,
+      "eval_loss": 0.6356751918792725,
+      "eval_runtime": 76.2962,
+      "eval_samples_per_second": 101.342,
+      "eval_steps_per_second": 12.674,
+      "step": 160000
+    },
+    {
+      "epoch": 95.13,
+      "learning_rate": 2e-05,
+      "loss": 0.6318,
+      "step": 170000
+    },
+    {
+      "epoch": 95.13,
+      "eval_loss": 0.6319578289985657,
+      "eval_runtime": 134.8378,
+      "eval_samples_per_second": 57.343,
+      "eval_steps_per_second": 7.172,
+      "step": 170000
+    },
+    {
+      "epoch": 100.73,
+      "learning_rate": 2e-05,
+      "loss": 0.6261,
+      "step": 180000
+    },
+    {
+      "epoch": 100.73,
+      "eval_loss": 0.6279829740524292,
+      "eval_runtime": 76.2996,
+      "eval_samples_per_second": 101.337,
+      "eval_steps_per_second": 12.674,
+      "step": 180000
+    },
+    {
+      "epoch": 106.32,
+      "learning_rate": 2e-05,
+      "loss": 0.6214,
+      "step": 190000
+    },
+    {
+      "epoch": 106.32,
+      "eval_loss": 0.6199918389320374,
+      "eval_runtime": 76.2832,
+      "eval_samples_per_second": 101.359,
+      "eval_steps_per_second": 12.676,
+      "step": 190000
+    },
+    {
+      "epoch": 111.92,
+      "learning_rate": 2e-05,
+      "loss": 0.6177,
+      "step": 200000
+    },
+    {
+      "epoch": 111.92,
+      "eval_loss": 0.6199995875358582,
+      "eval_runtime": 76.4051,
+      "eval_samples_per_second": 101.197,
+      "eval_steps_per_second": 12.656,
+      "step": 200000
+    },
+    {
+      "epoch": 111.92,
+      "step": 200000,
+      "total_flos": 1.0512018951481177e+21,
+      "train_loss": 0.5566074145507812,
+      "train_runtime": 84698.4102,
+      "train_samples_per_second": 37.781,
+      "train_steps_per_second": 2.361
+    }
+  ],
+  "max_steps": 200000,
+  "num_train_epochs": 112,
+  "total_flos": 1.0512018951481177e+21,
+  "trial_name": null,
+  "trial_params": null
+}

backup-290000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038e617dff220000f31c4466086e928ab769fb3dea37924e2293e04e7cc1b50e
+size 3512

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa9f45bcfe7ade94da8070fb641dadb99c295d78f116fbcf194f0b4b3efe7f5
+oid sha256:8fe03a0ad7b9683981e4caf01b17bfe2cf452df3b7b9c3116d8e49a92a0dd2a3
 size 449474626

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eef506434d84b6048bd48859e91edb3cf72837ea07cb9913ed23969f5d79423
-size 3576
+oid sha256:22ae2c800e5a18cc08d55905c495c8e84c79de6592e8c823e6150aa5b70f4654
+size 3640