initial commit

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

best_eval.json

@@ -0,0 +1 @@
+{"eval_loss": 0.040195662528276443, "eval_rmse": 0.20048855245113373, "eval_runtime": 9.092, "eval_samples_per_second": 345.139, "eval_steps_per_second": 28.817, "epoch": 3.0}

config.json

@@ -0,0 +1,871 @@
+{
+  "_name_or_path": "sileod/deberta-v3-base-tasksource-nli",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifiers_size": [
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    1,
+    3,
+    3,
+    2,
+    2,
+    3,
+    2,
+    2,
+    2,
+    6,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    47,
+    23,
+    9,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    20,
+    50,
+    3,
+    3,
+    4,
+    2,
+    8,
+    20,
+    4,
+    2,
+    2,
+    3,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    174,
+    2,
+    3,
+    2,
+    2,
+    2,
+    2,
+    41,
+    51,
+    2,
+    8,
+    2,
+    16,
+    18,
+    2,
+    2,
+    17,
+    2,
+    3,
+    2,
+    3,
+    12,
+    42,
+    3,
+    7,
+    11,
+    7,
+    4,
+    3,
+    100,
+    13,
+    100,
+    8,
+    1,
+    20,
+    2,
+    2,
+    4,
+    5,
+    3,
+    4,
+    14,
+    2,
+    6,
+    4,
+    2,
+    1,
+    3,
+    10,
+    77,
+    3,
+    10,
+    4,
+    2,
+    7,
+    6,
+    28,
+    3,
+    6,
+    5,
+    7,
+    4,
+    3,
+    6,
+    20,
+    2,
+    2,
+    2,
+    6,
+    2,
+    2,
+    2,
+    7,
+    3,
+    13,
+    9,
+    4,
+    2,
+    2,
+    2,
+    3,
+    4,
+    2,
+    2,
+    2,
+    2,
+    4,
+    1,
+    2,
+    1,
+    13,
+    3,
+    5,
+    11,
+    37,
+    2,
+    49,
+    12,
+    40,
+    10,
+    4,
+    1,
+    2,
+    2,
+    1,
+    5,
+    3,
+    2,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    2,
+    2,
+    12,
+    3,
+    3,
+    2,
+    19,
+    3,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    2,
+    1,
+    1,
+    2,
+    3,
+    2,
+    1,
+    4,
+    4,
+    1,
+    1,
+    1,
+    2,
+    3,
+    2,
+    3,
+    1,
+    1,
+    2,
+    1,
+    3,
+    2,
+    2,
+    2,
+    2,
+    3,
+    2,
+    2,
+    2,
+    1,
+    3,
+    2,
+    2,
+    1,
+    1,
+    1,
+    1,
+    2,
+    1,
+    1,
+    1,
+    1,
+    4,
+    1,
+    1,
+    1,
+    3,
+    1,
+    2,
+    3,
+    3,
+    3,
+    1,
+    1
+  ],
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tasks": [
+    "glue/mnli",
+    "glue/qnli",
+    "glue/rte",
+    "glue/wnli",
+    "glue/mrpc",
+    "glue/qqp",
+    "glue/stsb",
+    "super_glue/boolq",
+    "super_glue/cb",
+    "super_glue/multirc",
+    "super_glue/wic",
+    "super_glue/axg",
+    "anli/a1",
+    "anli/a2",
+    "anli/a3",
+    "sick/label",
+    "sick/relatedness",
+    "sick/entailment_AB",
+    "snli",
+    "scitail/snli_format",
+    "hans",
+    "WANLI",
+    "recast/recast_factuality",
+    "recast/recast_verbcorner",
+    "recast/recast_puns",
+    "recast/recast_kg_relations",
+    "recast/recast_ner",
+    "recast/recast_sentiment",
+    "recast/recast_megaveridicality",
+    "recast/recast_verbnet",
+    "probability_words_nli/usnli",
+    "probability_words_nli/reasoning_2hop",
+    "probability_words_nli/reasoning_1hop",
+    "nan-nli/joey234--nan-nli",
+    "nli_fever",
+    "breaking_nli",
+    "conj_nli",
+    "fracas",
+    "dialogue_nli",
+    "mpe",
+    "dnc",
+    "gpt3_nli",
+    "recast_white/fnplus",
+    "recast_white/sprl",
+    "recast_white/dpr",
+    "joci",
+    "contrast_nli",
+    "robust_nli/IS_CS",
+    "robust_nli/LI_LI",
+    "robust_nli/ST_WO",
+    "robust_nli/PI_SP",
+    "robust_nli/PI_CD",
+    "robust_nli/ST_SE",
+    "robust_nli/ST_NE",
+    "robust_nli/ST_LM",
+    "robust_nli_is_sd",
+    "robust_nli_li_ts",
+    "add_one_rte",
+    "imppres/implicature_quantifiers/log",
+    "imppres/implicature_numerals_2_3/log",
+    "imppres/implicature_numerals_10_100/log",
+    "imppres/implicature_modals/log",
+    "imppres/implicature_gradable_verb/log",
+    "imppres/implicature_gradable_adjective/log",
+    "imppres/implicature_connectives/log",
+    "glue_diagnostics/diagnostics",
+    "hlgd",
+    "paws/labeled_final",
+    "paws/labeled_swap",
+    "quora",
+    "medical_questions_pairs",
+    "conll2003/pos_tags",
+    "conll2003/chunk_tags",
+    "conll2003/ner_tags",
+    "hh-rlhf",
+    "model-written-evals",
+    "truthful_qa/multiple_choice",
+    "fig-qa",
+    "bigbench/similarities_abstraction",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/dyck_languages",
+    "bigbench/cause_and_effect",
+    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/logical_deduction",
+    "bigbench/movie_recommendation",
+    "bigbench/hhh_alignment",
+    "bigbench/checkmate_in_one",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/identify_odd_metaphor",
+    "bigbench/entailed_polarity",
+    "bigbench/novel_concepts",
+    "bigbench/nonsense_words_grammar",
+    "bigbench/goal_step_wikihow",
+    "bigbench/sports_understanding",
+    "bigbench/moral_permissibility",
+    "bigbench/code_line_description",
+    "bigbench/odd_one_out",
+    "bigbench/empirical_judgments",
+    "bigbench/gre_reading_comprehension",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/identify_math_theorems",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/date_understanding",
+    "bigbench/play_dialog_same_or_different",
+    "bigbench/real_or_fake_text",
+    "bigbench/crass_ai",
+    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/ruin_names",
+    "bigbench/sentence_ambiguity",
+    "bigbench/intent_recognition",
+    "bigbench/analytic_entailment",
+    "bigbench/conceptual_combinations",
+    "bigbench/implicit_relations",
+    "bigbench/emojis_emotion_prediction",
+    "bigbench/hindu_knowledge",
+    "bigbench/elementary_math_qa",
+    "bigbench/mathematical_induction",
+    "bigbench/irony_identification",
+    "bigbench/authorship_verification",
+    "bigbench/disambiguation_qa",
+    "bigbench/general_knowledge",
+    "bigbench/known_unknowns",
+    "bigbench/metaphor_boolean",
+    "bigbench/logical_args",
+    "bigbench/metaphor_understanding",
+    "bigbench/arithmetic",
+    "bigbench/salient_translation_error_detection",
+    "bigbench/human_organs_senses",
+    "bigbench/formal_fallacies_syllogisms_negation",
+    "bigbench/fantasy_reasoning",
+    "bigbench/fact_checker",
+    "bigbench/unit_interpretation",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/cifar10_classification",
+    "bigbench/social_iqa",
+    "bigbench/emoji_movie",
+    "bigbench/dark_humor_detection",
+    "bigbench/understanding_fables",
+    "bigbench/symbol_interpretation",
+    "bigbench/social_support",
+    "bigbench/logical_fallacy_detection",
+    "bigbench/causal_judgment",
+    "bigbench/strategyqa",
+    "bigbench/epistemic_reasoning",
+    "bigbench/anachronisms",
+    "bigbench/mnist_ascii",
+    "bigbench/crash_blossom",
+    "bigbench/english_proverbs",
+    "bigbench/cs_algorithms",
+    "bigbench/simple_ethical_questions",
+    "bigbench/hyperbaton",
+    "bigbench/key_value_maps",
+    "bigbench/physics",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/undo_permutation",
+    "bigbench/timedial",
+    "bigbench/geometric_shapes",
+    "bigbench/analogical_similarity",
+    "bigbench/color",
+    "bigbench/question_selection",
+    "bigbench/evaluating_information_essentiality",
+    "bigbench/phrase_relatedness",
+    "bigbench/logic_grid_puzzle",
+    "bigbench/misconceptions",
+    "bigbench/winowhy",
+    "bigbench/snarks",
+    "bigbench/temporal_sequences",
+    "bigbench/riddle_sense",
+    "bigbench/implicatures",
+    "bigbench/logical_sequence",
+    "bigbench/suicide_risk",
+    "bigbench/physical_intuition",
+    "bigbench/movie_dialog_same_or_different",
+    "bigbench/navigate",
+    "bigbench/penguins_in_a_table",
+    "bigbench/strange_stories",
+    "bigbench/bbq_lite_json",
+    "cos_e/v1.0",
+    "cosmos_qa",
+    "dream",
+    "openbookqa",
+    "qasc",
+    "quartz",
+    "quail",
+    "head_qa/en",
+    "sciq",
+    "social_i_qa",
+    "wiki_hop",
+    "wiqa",
+    "piqa",
+    "hellaswag",
+    "super_glue/copa",
+    "balanced-copa",
+    "e-CARE",
+    "art",
+    "winogrande/winogrande_xl",
+    "codah/codah",
+    "ai2_arc/ARC-Easy/challenge",
+    "ai2_arc/ARC-Challenge/challenge",
+    "definite_pronoun_resolution",
+    "swag",
+    "math_qa",
+    "glue/cola",
+    "glue/sst2",
+    "utilitarianism",
+    "amazon_counterfactual/en",
+    "insincere-questions",
+    "toxic_conversations",
+    "TuringBench",
+    "trec",
+    "vitaminc/tals--vitaminc",
+    "hope_edi/english",
+    "rumoureval_2019/RumourEval2019",
+    "ethos/binary",
+    "ethos/multilabel",
+    "tweet_eval/emoji",
+    "tweet_eval/emotion",
+    "tweet_eval/hate",
+    "tweet_eval/offensive",
+    "tweet_eval/sentiment",
+    "tweet_eval/irony",
+    "tweet_eval/stance_atheism",
+    "tweet_eval/stance_climate",
+    "tweet_eval/stance_hillary",
+    "tweet_eval/stance_feminist",
+    "tweet_eval/stance_abortion",
+    "discovery/discovery",
+    "pragmeval/squinky-informativeness",
+    "pragmeval/verifiability",
+    "pragmeval/squinky-formality",
+    "pragmeval/squinky-implicature",
+    "pragmeval/emobank-dominance",
+    "pragmeval/emobank-arousal",
+    "pragmeval/switchboard",
+    "pragmeval/mrda",
+    "pragmeval/emobank-valence",
+    "pragmeval/persuasiveness-premisetype",
+    "pragmeval/persuasiveness-relevance",
+    "pragmeval/pdtb",
+    "pragmeval/stac",
+    "pragmeval/persuasiveness-strength",
+    "pragmeval/sarcasm",
+    "pragmeval/gum",
+    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/persuasiveness-claimtype",
+    "pragmeval/persuasiveness-specificity",
+    "pragmeval/emergent",
+    "silicone/maptask",
+    "silicone/oasis",
+    "silicone/meld_s",
+    "silicone/meld_e",
+    "silicone/iemocap",
+    "silicone/dyda_e",
+    "silicone/dyda_da",
+    "silicone/sem",
+    "lex_glue/eurlex",
+    "lex_glue/scotus",
+    "lex_glue/ledgar",
+    "lex_glue/unfair_tos",
+    "lex_glue/case_hold",
+    "language-identification",
+    "imdb",
+    "rotten_tomatoes",
+    "ag_news",
+    "yelp_review_full/yelp_review_full",
+    "financial_phrasebank/sentences_allagree",
+    "poem_sentiment",
+    "dbpedia_14/dbpedia_14",
+    "amazon_polarity/amazon_polarity",
+    "app_reviews",
+    "hate_speech18",
+    "sms_spam",
+    "humicroedit/subtask-1",
+    "humicroedit/subtask-2",
+    "snips_built_in_intents",
+    "banking77",
+    "hate_speech_offensive",
+    "yahoo_answers_topics",
+    "stackoverflow-questions",
+    "hyperpartisan_news",
+    "sciie",
+    "citation_intent",
+    "go_emotions/simplified",
+    "scicite",
+    "liar",
+    "lexical_relation_classification/CogALexV",
+    "lexical_relation_classification/EVALution",
+    "lexical_relation_classification/K&H+N",
+    "lexical_relation_classification/ROOT09",
+    "lexical_relation_classification/BLESS",
+    "linguisticprobing/top_constituents",
+    "linguisticprobing/bigram_shift",
+    "linguisticprobing/odd_man_out",
+    "linguisticprobing/coordination_inversion",
+    "linguisticprobing/sentence_length",
+    "linguisticprobing/past_present",
+    "linguisticprobing/obj_number",
+    "linguisticprobing/subj_number",
+    "linguisticprobing/tree_depth",
+    "crowdflower/economic-news",
+    "crowdflower/text_emotion",
+    "crowdflower/political-media-message",
+    "crowdflower/sentiment_nuclear_power",
+    "crowdflower/political-media-bias",
+    "crowdflower/political-media-audience",
+    "crowdflower/tweet_global_warming",
+    "crowdflower/airline-sentiment",
+    "crowdflower/corporate-messaging",
+    "ethics/commonsense",
+    "ethics/deontology",
+    "ethics/justice",
+    "ethics/virtue",
+    "emo/emo2019",
+    "google_wellformed_query",
+    "tweets_hate_speech_detection",
+    "has_part",
+    "wnut_17/wnut_17",
+    "ncbi_disease/ncbi_disease",
+    "acronym_identification",
+    "jnlpba/jnlpba",
+    "ontonotes_english/SpeedOfMagic--ontonotes_english",
+    "blog_authorship_corpus/gender",
+    "blog_authorship_corpus/age",
+    "blog_authorship_corpus/horoscope",
+    "blog_authorship_corpus/job",
+    "open_question_type",
+    "health_fact",
+    "commonsense_qa",
+    "mc_taco",
+    "ade_corpus_v2/Ade_corpus_v2_classification",
+    "discosense",
+    "circa",
+    "EffectiveFeedbackStudentWriting",
+    "promptSentiment",
+    "promptNLI",
+    "promptSpoke",
+    "promptProficiency",
+    "promptGrammar",
+    "promptCoherence",
+    "phrase_similarity",
+    "scientific-exaggeration-detection",
+    "quarel",
+    "fever-evidence-related/mwong--fever-related",
+    "numer_sense",
+    "dynasent/dynabench.dynasent.r1.all/r1",
+    "dynasent/dynabench.dynasent.r2.all/r2",
+    "Sarcasm_News_Headline",
+    "sem_eval_2010_task_8",
+    "auditor_review/demo-org--auditor_review",
+    "medmcqa",
+    "aqua_rat/tokenized",
+    "Dynasent_Disagreement",
+    "Politeness_Disagreement",
+    "SBIC_Disagreement",
+    "SChem_Disagreement",
+    "Dilemmas_Disagreement",
+    "logiqa",
+    "wiki_qa",
+    "cycic_classification",
+    "cycic_multiplechoice",
+    "sts-companion",
+    "commonsense_qa_2.0",
+    "lingnli",
+    "monotonicity-entailment",
+    "arct",
+    "scinli",
+    "naturallogic",
+    "onestop_qa",
+    "moral_stories/full",
+    "prost",
+    "dynahate",
+    "syntactic-augmentation-nli",
+    "autotnli",
+    "CONDAQA",
+    "webgpt_comparisons",
+    "synthetic-instruct-gptj-pairwise",
+    "scruples",
+    "wouldyourather",
+    "attempto-nli",
+    "defeasible-nli/atomic",
+    "defeasible-nli/snli",
+    "nli-veridicality-transitivity",
+    "natural-language-satisfiability",
+    "lonli",
+    "dadc-limit-nli",
+    "FLUTE",
+    "strategy-qa",
+    "summarize_from_feedback/comparisons",
+    "folio",
+    "tomi-nli",
+    "avicenna",
+    "SHP",
+    "MedQA-USMLE-4-options-hf",
+    "wikimedqa/medwiki",
+    "cicero",
+    "CREAK",
+    "mutual",
+    "NeQA",
+    "quote-repetition",
+    "redefine-math",
+    "puzzte",
+    "implicatures",
+    "race/high",
+    "race/middle",
+    "spartqa-yn",
+    "spartqa-mchoice",
+    "babi_nli",
+    "gen_debiased_nli",
+    "imppres/presupposition",
+    "/prag",
+    "blimp-2",
+    "mmlu-4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f31eceff5a1264f3a1ae519cb45e624fa9b337d255f869f44f5b6120b433c7
+size 1475500377

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad7971503ec0bfaba6ea736cde306c3d20580f65d7fd4394289f447af4325ef
+size 737763883

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f53af8e60397d65f15e0262cc02ccdfa323733a41cd7094d7b1c36dd8183c3
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc29663715b73806415359a4b738935ad8cc9de5cbb6a59316fa6c2d5de4e6c
+size 623

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "sileod/deberta-v3-base-tasksource-nli",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.04146179184317589,
+  "best_model_checkpoint": "./models/deberta-v3-base-nli-v1/checkpoint-811",
+  "epoch": 3.0,
+  "global_step": 2433,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.56144677353062e-06,
+      "loss": 0.064,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.04146179184317589,
+      "eval_rmse": 0.20362168550491333,
+      "eval_runtime": 4.397,
+      "eval_samples_per_second": 348.191,
+      "eval_steps_per_second": 29.111,
+      "step": 811
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 4.122893547061241e-06,
+      "loss": 0.0441,
+      "step": 1000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.684340320591862e-06,
+      "loss": 0.0347,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.04254383593797684,
+      "eval_rmse": 0.20626157522201538,
+      "eval_runtime": 4.3965,
+      "eval_samples_per_second": 348.229,
+      "eval_steps_per_second": 29.114,
+      "step": 1622
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.2457870941224826e-06,
+      "loss": 0.0292,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.04311966523528099,
+      "eval_rmse": 0.207652747631073,
+      "eval_runtime": 4.4067,
+      "eval_samples_per_second": 347.422,
+      "eval_steps_per_second": 29.046,
+      "step": 2433
+    }
+  ],
+  "max_steps": 2433,
+  "num_train_epochs": 3,
+  "total_flos": 1826338023730968.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a86da052435c2a8d3e0ff7fc10883ac90a6762590ac1ba8ad30aafd2a1831c
+size 3439

training_cfg.json

@@ -0,0 +1,9 @@
+{
+  "model_name": "sileod/deberta-v3-base-tasksource-nli",
+  "lr": 7e-06,
+  "epochs": 3,
+  "weight_decay": 0.01,
+  "train_bs": 12,
+  "eval_bs": 12,
+  "dataset_path": "./data/model_training_data"
+}