init

.gitattributes

@@ -33,3 +33,6 @@ 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
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58

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

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- parallel-pt-nl-pl
+model-index:
+- name: allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400
+
+This model is a fine-tuned version of [zxh4546/allnli_wikispan_unsup_ensemble_last](https://huggingface.co/zxh4546/allnli_wikispan_unsup_ensemble_last) on the PARALLEL-PT-NL-PL dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 128
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 9400
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.11.0
+- Datasets 2.14.6
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 8.931647637549867,
+    "train_runtime": 5062.6195,
+    "train_samples": 1201407,
+    "train_samples_per_second": 237.664,
+    "train_steps_per_second": 1.857
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "zxh4546/allnli_wikispan_unsup_ensemble_last",
+  "architectures": [
+    "PIXELForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "decoder_hidden_size": 512,
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 16,
+  "decoder_num_hidden_layers": 8,
+  "finetuning_task": "parallel-pt-nl-pl",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Entailment",
+    "1": "Neutral",
+    "2": "Contradiction"
+  },
+  "image_size": [
+    16,
+    1024
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "interpolate_pos_encoding": false,
+  "label2id": {
+    "Contradiction": 2,
+    "Entailment": 0,
+    "Neutral": 1
+  },
+  "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"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b967736f6cbc69dba1819c0eb486d659782a6322ce214677f8f203af9f7f1a
+size 345238445

text_renderer_config.json

@@ -0,0 +1,175 @@
+{
+  "background_color": "white",
+  "dpi": 120,
+  "font_color": "black",
+  "font_file": "763e176b60c0e797d0388f0145df643d884c8574fa9925151d3a1d53c46d29c8.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
+  "font_size": 8,
+  "fonts_list": [
+    "Abyssinica SIL",
+    "Ani",
+    "AnjaliOldLipi",
+    "C059",
+    "Chandas",
+    "Chilanka",
+    "D050000L",
+    "DejaVu Math TeX Gyre",
+    "DejaVu Sans",
+    "DejaVu Sans Mono",
+    "DejaVu Serif",
+    "Dhurjati",
+    "Droid Sans Fallback",
+    "Dyuthi",
+    "FreeMono",
+    "FreeSans",
+    "FreeSerif",
+    "Gargi",
+    "Garuda",
+    "Gayathri",
+    "Gidugu",
+    "Go Noto Current",
+    "Gubbi",
+    "Gurajada",
+    "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",
+    "LakkiReddy",
+    "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",
+    "Mallanna",
+    "Mandali",
+    "Manjari",
+    "Meera",
+    "Mitra Mono",
+    "Monospace",
+    "Mukti Narrow",
+    "NATS",
+    "NTR",
+    "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",
+    "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",
+    "Peddana",
+    "Phetsarath OT",
+    "Ponnala",
+    "Pothana2000",
+    "Potti Sreeramulu",
+    "Purisa",
+    "Rachana",
+    "RaghuMalayalamSans",
+    "Ramabhadra",
+    "Ramaraja",
+    "Rasa",
+    "RaviPrakash",
+    "Rekha",
+    "Saab",
+    "Sahadeva",
+    "Samanata",
+    "Samyak Devanagari",
+    "Samyak Gujarati",
+    "Samyak Malayalam",
+    "Samyak Tamil",
+    "Sans",
+    "Sarai",
+    "Sawasdee",
+    "Serif",
+    "Source Code Pro",
+    "Sree Krushnadevaraya",
+    "Standard Symbols PS",
+    "Suranna",
+    "Suravaram",
+    "Suruma",
+    "Syamala Ramana",
+    "System-ui",
+    "TenaliRamakrishna",
+    "Tibetan Machine Uni",
+    "Timmana",
+    "Tlwg Mono",
+    "Tlwg Typewriter",
+    "Tlwg Typist",
+    "Tlwg Typo",
+    "URW Bookman",
+    "URW Gothic",
+    "Ubuntu",
+    "Ubuntu Condensed",
+    "Ubuntu Mono",
+    "Umpush",
+    "Uroob",
+    "Vemana2000",
+    "Waree",
+    "Yrsa",
+    "Z003",
+    "aakar",
+    "mry_KacstQurn",
+    "ori1Uni",
+    "padmaa",
+    "padmaa-Bold.1.1"
+  ],
+  "max_seq_length": 64,
+  "pad_size": 3,
+  "pixels_per_patch": 16,
+  "rgb": false,
+  "text_renderer_type": "PangoCairoTextRenderer"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 8.931647637549867,
+    "train_runtime": 5062.6195,
+    "train_samples": 1201407,
+    "train_samples_per_second": 237.664,
+    "train_steps_per_second": 1.857
+}

trainer_state.json

@@ -0,0 +1,307 @@
+{
+  "best_metric": 0.7769453778278917,
+  "best_model_checkpoint": "2-parallel-pt-nl-pl-**zxh4546/allnli_wikispan_unsup_ensemble_last**-64-128-3e-5-9400/checkpoint-9200",
+  "epoch": 1.0014915832090348,
+  "global_step": 9400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 6e-06,
+      "loss": 68.9386,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.2e-05,
+      "loss": 29.743,
+      "step": 400
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8e-05,
+      "loss": 22.6828,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4e-05,
+      "loss": 18.3538,
+      "step": 800
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3e-05,
+      "loss": 16.8795,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9285714285714284e-05,
+      "loss": 15.0949,
+      "step": 1200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 13.1123,
+      "step": 1400
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 11.6076,
+      "step": 1600
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.7142857142857144e-05,
+      "loss": 11.0653,
+      "step": 1800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6428571428571428e-05,
+      "loss": 10.2023,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 9.4697,
+      "step": 2200
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.5e-05,
+      "loss": 9.073,
+      "step": 2400
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 8.2219,
+      "step": 2600
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 8.1709,
+      "step": 2800
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 7.6007,
+      "step": 3000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.2142857142857145e-05,
+      "loss": 7.3222,
+      "step": 3200
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 6.8397,
+      "step": 3400
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.0714285714285715e-05,
+      "loss": 6.7136,
+      "step": 3600
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 6.4772,
+      "step": 3800
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 6.136,
+      "step": 4000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 6.3031,
+      "step": 4200
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 5.8973,
+      "step": 4400
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 5.849,
+      "step": 4600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.6428571428571432e-05,
+      "loss": 5.7724,
+      "step": 4800
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 5.5508,
+      "step": 5000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.5e-05,
+      "loss": 5.1375,
+      "step": 5200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 5.3564,
+      "step": 5400
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.3571428571428572e-05,
+      "loss": 5.173,
+      "step": 5600
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 4.8572,
+      "step": 5800
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.2142857142857144e-05,
+      "loss": 5.0517,
+      "step": 6000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 4.8886,
+      "step": 6200
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 4.7235,
+      "step": 6400
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 4.4131,
+      "step": 6600
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.285714285714286e-06,
+      "loss": 4.6411,
+      "step": 6800
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 4.3489,
+      "step": 7000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.857142857142858e-06,
+      "loss": 4.4199,
+      "step": 7200
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 4.2557,
+      "step": 7400
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 3.9598,
+      "step": 7600
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 4.1423,
+      "step": 7800
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 3.9408,
+      "step": 8000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 4.1499,
+      "step": 8200
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 4.0065,
+      "step": 8400
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 3.7546,
+      "step": 8600
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 3.8722,
+      "step": 8800
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 3.7097,
+      "step": 9000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 4.0694,
+      "step": 9200
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 3.8382,
+      "step": 9400
+    },
+    {
+      "epoch": 1.0,
+      "step": 9400,
+      "total_flos": 622939976497152.0,
+      "train_loss": 8.931647637549867,
+      "train_runtime": 5062.6195,
+      "train_samples_per_second": 237.664,
+      "train_steps_per_second": 1.857
+    }
+  ],
+  "max_steps": 9400,
+  "num_train_epochs": 2,
+  "total_flos": 622939976497152.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862ebe7e2ca11c0caed3b20966cc710bcee68f4e444ab132f69bf4d348128a61
+size 3311