Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 250001,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/infoxlm-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 0.027912303786724806
+mae = 0.1337405837457627
+pearson_corr = 0.6614688004509174
+spearman_corr = 0.6385996345996346

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "best_model_dir": "temp/outputs/best_model", "cache_dir": "temp/cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 900, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 900, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "microsoft/infoxlm-large", "model_type": "auto", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3, "optimizer": "AdamW", "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 14, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 900, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 1519, "weight_decay": 0, "model_class": "MonoTransQuestModel", "labels_list": [0], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": true, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998f4b2fe23c34386e92581840ad4fcf6b11fa7fd649a2cb4510e1c53f06d71a
+size 2239701425

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19232daba569c004c5fbe45f373ccaf2ee505055da00969f78a99e5754db8f25
+size 17082688

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f3fd9545ac37a23e47f6ebf0adaf5e787cbdc1f9d8cedc4760858c221ad768
+size 3131

training_progress_scores.csv

@@ -0,0 +1,30 @@
+global_step,train_loss,eval_loss,pearson_corr,spearman_corr,mae
+900,0.010972382500767708,0.023622597827499647,0.8095263919274487,0.7477709458577968,0.10836906881953279
+1800,0.024250676855444908,0.01965948116423479,0.852999659637736,0.7921037572475905,0.09408535485888521
+2700,0.0777399092912674,0.016465272444403614,0.8634203622580631,0.8140271415200131,0.09269004237577319
+3600,0.019647672772407532,0.01733681273470168,0.8655721241308866,0.8168274679240014,0.08867474158331752
+4500,0.004889407195150852,0.01752337293402388,0.8517099940769709,0.8102333628098319,0.09533902626261115
+5400,0.006191556807607412,0.014645925749265558,0.874763219728429,0.8287448843591987,0.08384718116844694
+6300,0.010350584983825684,0.015890496995621253,0.8733738402839469,0.8270801883222405,0.08521010853076974
+7200,0.008930422365665436,0.01746654192447168,0.8618049046447056,0.8191550757871159,0.08742531948710482
+8100,0.008716677315533161,0.014988660523635663,0.8733847828895496,0.8303749946161613,0.08297336158044637
+8438,0.006874650251120329,0.014495847345109402,0.8771138184877546,0.8293322584308879,0.08428333136960864
+9000,0.0027079477440565825,0.017132625416063193,0.8610594627907026,0.8140230009371195,0.08540235457643866
+9900,0.025045502930879593,0.014366308314741146,0.8765501210906305,0.8336736006566232,0.08066835181042552
+10800,0.0005104829906485975,0.014980095981827268,0.8787209962850588,0.8358185429253102,0.07955874591637403
+11700,0.019913285970687866,0.014589658029893014,0.8754119402856617,0.8328415525607632,0.07959132467309633
+12600,0.01404587458819151,0.014833916258879814,0.8781519330321061,0.834841852531428,0.07909681311969956
+13500,0.002813139231875539,0.01435592326473123,0.8785480767124942,0.8374481465615233,0.07993123553072413
+14400,0.027911338955163956,0.013652427638667438,0.883746284016827,0.8403473138164992,0.07734708464170496
+15300,0.010912811383605003,0.01387389815395831,0.881266285851631,0.8379662713187247,0.07899580380742749
+16200,0.0026525966823101044,0.01392610707442025,0.8830646047869838,0.8427597860131076,0.07691527850305041
+16876,0.008507627062499523,0.014063196564984342,0.8819925492789804,0.8404219596063984,0.07975475781783462
+17100,0.03084692172706127,0.026583898738066335,0.8709676663475687,0.8330950018418924,0.11143418893441558
+18000,0.0017649661749601364,0.013820967025977167,0.8822864558798611,0.8410843965793222,0.07751031193062663
+18900,0.005625757854431868,0.013956047197580953,0.8823450157442638,0.8419570211899576,0.07775558447167277
+19800,0.0023463282268494368,0.013920765790057235,0.8812456562922729,0.8391186521687765,0.07864128595469519
+20700,0.0019751680083572865,0.013957940639423103,0.8813369760968356,0.8408679050553961,0.07956283309981227
+21600,0.0035954818595200777,0.014042881537049608,0.8818791547246982,0.841236316599913,0.07719836699391405
+22500,0.0012073402758687735,0.014842115464741424,0.8807377958685363,0.8403218215959766,0.07886135330622394
+23400,0.013370152562856674,0.014173355137862052,0.8820753487778998,0.841039618234482,0.0775727372162044
+24300,0.0019900635816156864,0.01388849318120579,0.8829944732507771,0.840658225133702,0.0772534340493381