Upload v2 model and blimp results
Browse files- blimp_results +83 -0
- config.json +2 -1
- model.safetensors +1 -1
blimp_results
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Running loglikelihood requests: 100%|█████████████████████████████████████████████████████████████| 130186/130186 [1:01:21<00:00, 35.36it/s]
|
| 2 |
+
hf-mlm (pretrained=../../checkpoints/electra-tiny/,backend=mlm), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: 1
|
| 3 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 4 |
+
|---------------------------------------------------------------------|-------|------|-----:|------|-----:|---|-----:|
|
| 5 |
+
|blimp_supplement |N/A |none | 0|acc |0.4979|± |0.0068|
|
| 6 |
+
| - blimp_supplement_hypernym | 1|none | 0|acc |0.5238|± |0.0172|
|
| 7 |
+
| - blimp_supplement_qa_congruence_easy | 1|none | 0|acc |0.4531|± |0.0627|
|
| 8 |
+
| - blimp_supplement_qa_congruence_tricky | 1|none | 0|acc |0.5818|± |0.0385|
|
| 9 |
+
| - blimp_supplement_subject_aux_inversion | 1|none | 0|acc |0.3949|± |0.0079|
|
| 10 |
+
| - blimp_supplement_turn_taking | 1|none | 0|acc |0.5357|± |0.0299|
|
| 11 |
+
|blimp_filtered |N/A |none | 0|acc |0.5065|± |0.0019|
|
| 12 |
+
| - blimp_adjunct_island_filtered | 1|none | 0|acc |0.4321|± |0.0163|
|
| 13 |
+
| - blimp_anaphor_gender_agreement_filtered | 1|none | 0|acc |0.4830|± |0.0160|
|
| 14 |
+
| - blimp_anaphor_number_agreement_filtered | 1|none | 0|acc |0.6423|± |0.0157|
|
| 15 |
+
| - blimp_animate_subject_passive_filtered | 1|none | 0|acc |0.5140|± |0.0167|
|
| 16 |
+
| - blimp_animate_subject_trans_filtered | 1|none | 0|acc |0.1603|± |0.0121|
|
| 17 |
+
| - blimp_causative_filtered | 1|none | 0|acc |0.4315|± |0.0173|
|
| 18 |
+
| - blimp_complex_NP_island_filtered | 1|none | 0|acc |0.5130|± |0.0172|
|
| 19 |
+
| - blimp_coordinate_structure_constraint_complex_left_branch_filtered| 1|none | 0|acc |0.4570|± |0.0166|
|
| 20 |
+
| - blimp_coordinate_structure_constraint_object_extraction_filtered | 1|none | 0|acc |0.4826|± |0.0162|
|
| 21 |
+
| - blimp_determiner_noun_agreement_1_filtered | 1|none | 0|acc |0.4930|± |0.0164|
|
| 22 |
+
| - blimp_determiner_noun_agreement_2_filtered | 1|none | 0|acc |0.4952|± |0.0164|
|
| 23 |
+
| - blimp_determiner_noun_agreement_irregular_1_filtered | 1|none | 0|acc |0.5477|± |0.0191|
|
| 24 |
+
| - blimp_determiner_noun_agreement_irregular_2_filtered | 1|none | 0|acc |0.4878|± |0.0175|
|
| 25 |
+
| - blimp_determiner_noun_agreement_with_adj_2_filtered | 1|none | 0|acc |0.4708|± |0.0163|
|
| 26 |
+
| - blimp_determiner_noun_agreement_with_adj_irregular_1_filtered | 1|none | 0|acc |0.5432|± |0.0186|
|
| 27 |
+
| - blimp_determiner_noun_agreement_with_adj_irregular_2_filtered | 1|none | 0|acc |0.5976|± |0.0169|
|
| 28 |
+
| - blimp_determiner_noun_agreement_with_adjective_1_filtered | 1|none | 0|acc |0.4845|± |0.0164|
|
| 29 |
+
| - blimp_distractor_agreement_relational_noun_filtered | 1|none | 0|acc |0.5127|± |0.0178|
|
| 30 |
+
| - blimp_distractor_agreement_relative_clause_filtered | 1|none | 0|acc |0.4914|± |0.0169|
|
| 31 |
+
| - blimp_drop_argument_filtered | 1|none | 0|acc |0.5109|± |0.0165|
|
| 32 |
+
| - blimp_ellipsis_n_bar_1_filtered | 1|none | 0|acc |0.4539|± |0.0176|
|
| 33 |
+
| - blimp_ellipsis_n_bar_2_filtered | 1|none | 0|acc |0.3986|± |0.0170|
|
| 34 |
+
| - blimp_existential_there_object_raising_filtered | 1|none | 0|acc |0.5456|± |0.0175|
|
| 35 |
+
| - blimp_existential_there_quantifiers_1_filtered | 1|none | 0|acc |0.4140|± |0.0162|
|
| 36 |
+
| - blimp_existential_there_quantifiers_2_filtered | 1|none | 0|acc |0.4643|± |0.0165|
|
| 37 |
+
| - blimp_existential_there_subject_raising_filtered | 1|none | 0|acc |0.5855|± |0.0162|
|
| 38 |
+
| - blimp_expletive_it_object_raising_filtered | 1|none | 0|acc |0.4822|± |0.0181|
|
| 39 |
+
| - blimp_inchoative_filtered | 1|none | 0|acc |0.5287|± |0.0171|
|
| 40 |
+
| - blimp_intransitive_filtered | 1|none | 0|acc |0.4689|± |0.0169|
|
| 41 |
+
| - blimp_irregular_past_participle_adjectives_filtered | 1|none | 0|acc |0.2799|± |0.0145|
|
| 42 |
+
| - blimp_irregular_past_participle_verbs_filtered | 1|none | 0|acc |0.5255|± |0.0163|
|
| 43 |
+
| - blimp_irregular_plural_subject_verb_agreement_1_filtered | 1|none | 0|acc |0.5100|± |0.0176|
|
| 44 |
+
| - blimp_irregular_plural_subject_verb_agreement_2_filtered | 1|none | 0|acc |0.5415|± |0.0167|
|
| 45 |
+
| - blimp_left_branch_island_echo_question_filtered | 1|none | 0|acc |0.3939|± |0.0159|
|
| 46 |
+
| - blimp_left_branch_island_simple_question_filtered | 1|none | 0|acc |0.5037|± |0.0162|
|
| 47 |
+
| - blimp_matrix_question_npi_licensor_present_filtered | 1|none | 0|acc |0.0000|± |0.0000|
|
| 48 |
+
| - blimp_npi_present_1_filtered | 1|none | 0|acc |0.4356|± |0.0165|
|
| 49 |
+
| - blimp_npi_present_2_filtered | 1|none | 0|acc |0.3950|± |0.0162|
|
| 50 |
+
| - blimp_only_npi_licensor_present_filtered | 1|none | 0|acc |0.4739|± |0.0168|
|
| 51 |
+
| - blimp_only_npi_scope_filtered | 1|none | 0|acc |0.1493|± |0.0123|
|
| 52 |
+
| - blimp_passive_1_filtered | 1|none | 0|acc |0.5024|± |0.0173|
|
| 53 |
+
| - blimp_passive_2_filtered | 1|none | 0|acc |0.5017|± |0.0166|
|
| 54 |
+
| - blimp_principle_A_c_command_filtered | 1|none | 0|acc |0.3446|± |0.0155|
|
| 55 |
+
| - blimp_principle_A_case_1_filtered | 1|none | 0|acc |0.3827|± |0.0161|
|
| 56 |
+
| - blimp_principle_A_case_2_filtered | 1|none | 0|acc |0.5148|± |0.0165|
|
| 57 |
+
| - blimp_principle_A_domain_1_filtered | 1|none | 0|acc |0.3698|± |0.0160|
|
| 58 |
+
| - blimp_principle_A_domain_2_filtered | 1|none | 0|acc |0.5213|± |0.0165|
|
| 59 |
+
| - blimp_principle_A_domain_3_filtered | 1|none | 0|acc |0.4899|± |0.0163|
|
| 60 |
+
| - blimp_principle_A_reconstruction_filtered | 1|none | 0|acc |0.3909|± |0.0157|
|
| 61 |
+
| - blimp_regular_plural_subject_verb_agreement_1_filtered | 1|none | 0|acc |0.5180|± |0.0168|
|
| 62 |
+
| - blimp_regular_plural_subject_verb_agreement_2_filtered | 1|none | 0|acc |0.5196|± |0.0163|
|
| 63 |
+
| - blimp_sentential_negation_npi_licensor_present_filtered | 1|none | 0|acc |1.0000|± |0.0000|
|
| 64 |
+
| - blimp_sentential_negation_npi_scope_filtered | 1|none | 0|acc |0.5281|± |0.0169|
|
| 65 |
+
| - blimp_sentential_subject_island_filtered | 1|none | 0|acc |0.4755|± |0.0161|
|
| 66 |
+
| - blimp_superlative_quantifiers_1_filtered | 1|none | 0|acc |0.6016|± |0.0157|
|
| 67 |
+
| - blimp_superlative_quantifiers_2_filtered | 1|none | 0|acc |0.5213|± |0.0159|
|
| 68 |
+
| - blimp_tough_vs_raising_1_filtered | 1|none | 0|acc |0.4757|± |0.0162|
|
| 69 |
+
| - blimp_tough_vs_raising_2_filtered | 1|none | 0|acc |0.4913|± |0.0165|
|
| 70 |
+
| - blimp_transitive_filtered | 1|none | 0|acc |0.5253|± |0.0170|
|
| 71 |
+
| - blimp_wh_island_filtered | 1|none | 0|acc |0.4896|± |0.0161|
|
| 72 |
+
| - blimp_wh_questions_object_gap_filtered | 1|none | 0|acc |0.9569|± |0.0069|
|
| 73 |
+
| - blimp_wh_questions_subject_gap_filtered | 1|none | 0|acc |0.9944|± |0.0025|
|
| 74 |
+
| - blimp_wh_questions_subject_gap_long_distance_filtered | 1|none | 0|acc |0.9673|± |0.0061|
|
| 75 |
+
| - blimp_wh_vs_that_no_gap_filtered | 1|none | 0|acc |1.0000|± |0.0000|
|
| 76 |
+
| - blimp_wh_vs_that_no_gap_long_distance_filtered | 1|none | 0|acc |0.9954|± |0.0023|
|
| 77 |
+
| - blimp_wh_vs_that_with_gap_filtered | 1|none | 0|acc |0.5484|± |0.0164|
|
| 78 |
+
| - blimp_wh_vs_that_with_gap_long_distance_filtered | 1|none | 0|acc |0.0088|± |0.0031|
|
| 79 |
+
|
| 80 |
+
| Groups |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 81 |
+
|----------------|-------|------|-----:|------|-----:|---|-----:|
|
| 82 |
+
|blimp_supplement|N/A |none | 0|acc |0.4979|± |0.0068|
|
| 83 |
+
|blimp_filtered |N/A |none | 0|acc |0.5065|± |0.0019|
|
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"ElectraForMaskedLM"
|
| 4 |
],
|
|
@@ -22,7 +23,7 @@
|
|
| 22 |
"summary_type": "first",
|
| 23 |
"summary_use_proj": true,
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"type_vocab_size": 2,
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 30522
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "electra_owt_full_b256_hs196_ah4_is128_l18_es64_vs30522_pytorch",
|
| 3 |
"architectures": [
|
| 4 |
"ElectraForMaskedLM"
|
| 5 |
],
|
|
|
|
| 23 |
"summary_type": "first",
|
| 24 |
"summary_use_proj": true,
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.49.0",
|
| 27 |
"type_vocab_size": 2,
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 30522
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 23017856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0036421435c9a3a0521d95269e4a14d3591c1bc7228b181e18ecc7bc3b49c4f
|
| 3 |
size 23017856
|