GenAI-ATX commited on
Commit
f387b3f
·
verified ·
1 Parent(s): 7f68da6

Upload fine-tuned TSDAE model

Browse files
Files changed (2) hide show
  1. README.md +156 -144
  2. model.safetensors +1 -1
README.md CHANGED
@@ -5,132 +5,140 @@ tags:
5
  - feature-extraction
6
  - dense
7
  - generated_from_trainer
8
- - dataset_size:24888
9
  - loss:DenoisingAutoEncoderLoss
10
  base_model: BAAI/bge-base-en-v1.5
11
  widget:
12
- - source_sentence: SUBSECTION] for services The must have a transfusion reviewed and
13
- responsible party) that the, transfer, and of blood.
 
 
 
 
 
 
14
  sentences:
15
- - '[SUBSECTION C] Encourage and promote use of enabling technologies for improving
16
- care coordination for beneficiaries. Enabling technologies may include one or
17
- more of the following: [CLAUSE 4] () Other electronic tools to engage beneficiaries
18
- in their care.'
19
- - '[SUBSECTION a] Arrangement for services.. The facility must have a transfusion
20
- service agreement reviewed and approved by the responsible party(ies) that govern
21
- the procurement, transfer, and availability of blood and blood products.'
22
- - '[SUBSECTION a] Resolution when noncompliance is indicated.. (1) If an investigation
23
- of a complaint pursuant to § 3.306 of this subpart or a compliance review pursuant
24
- to § 3.308 of this subpart indicates noncompliance, the Secretary may attempt
25
- to reach a resolution of the matter satisfactory to the Secretary by informal
26
- means. Informal means may include demonstrated compliance or a completed corrective
27
- action plan or other agreement. [CLAUSE 2] If the matter is resolved by informal
28
- means, the Secretary will so inform the respondent and, if the matter arose from
29
- a complaint, the complainant, in writing. [CLAUSE 3] If the matter is not resolved
30
- by informal means, the Secretary will— [ITEM i] So inform the respondent and provide
31
- the respondent an opportunity to submit written evidence of any mitigating factors.
32
- The respondent must submit any evidence to the Secretary within 30 days (computed
33
- in the same manner as prescribed under § 3.526 of this subpart) of receipt of
34
- such notification; and [ITEM ii] If, following action pursuant to paragraph (a)(3)(i)
35
- of this section, the Secretary decides that a civil money penalty should be imposed,
36
- inform the respondent of such finding in a notice of proposed determination in
37
- accordance with § 3.420 of this subpart.'
38
- - source_sentence: '[SUBSECTION e Continued, for after home [ITEM] and validly described
39
- ()) of this ITEM ii] subject and in with all the provisions of— [CLAUSE CMS may
40
- revoke a home infusion therapy enrollment of the: [i supplier accreditation described
41
- paragraph) 3) section . ITEM ii does not comply all of the provisions of—'
42
  sentences:
43
- - '[SUBSECTION e] Continued compliance, standards, and reasons for revocation..
44
- (1) Upon and after enrollment, a home infusion therapy supplier— [ITEM i] Must
45
- remain currently and validly accredited as described in paragraph (c)(3) of this
46
- section. [ITEM ii] Remains subject to, and must remain in full compliance with,
47
- all of the provisions of— [CLAUSE 2] CMS may revoke a home infusion therapy supplier''s
48
- enrollment on any of the following grounds: [ITEM i] The supplier does not meet
49
- the accreditation requirements as described in paragraph (c)(3) of this section.
50
- [ITEM ii] The supplier does not comply with all of the provisions of—'
51
- - '[SUBSECTION B] Activities falling under paragraph (2) of the definition of “health
52
- care operations” under 45 C.F.R. 164.501: Reviewing the competence or qualifications
53
- of health care professionals, evaluating practitioner and provider performance,
54
- health plan performance, conducting training programs in which students, trainees,
55
- or practitioners in areas of health care learn under supervision to practice or
56
- improve their skills as health care providers, training of non-health care professionals,
57
- accreditation, certification, licensing, or credentialing activities.'
58
- - '[SECTION HEADING] § 59.1 To what programs do these regulations apply? The regulations
59
- of this subpart are applicable to the award of grants under section 1001 of the
60
- Public Health Service Act (42 U.S.C. 300) to assist in the establishment and operation
61
- of voluntary family planning projects. These projects shall consist of the educational,
62
- comprehensive medical, and social services necessary to aid individuals to determine
63
- freely the number and spacing of their children.'
64
- - source_sentence: SUBSECTION] A outlines timing communications, and transition of
65
- these clinicians, groups subgroups Entities
 
 
66
  sentences:
67
- - '[SUBSECTION f] Prohibition on improper billing of premiums.. Part D plan sponsors
68
- shall not bill an enrollee for a premium payment period if the enrollee has had
69
- the premium for that period withheld from his or her Social Security, Railroad
70
- Retirement Board or Office of Personnel Management check. [CITATIONS]'
71
- - '[SUBSECTION D] A detailed timeline that outlines timing for communications, the
72
- start of the transition, and completion of the transition of these clinicians,
73
- groups, virtual groups, subgroups, or APM Entities.'
74
- - '[ITEM i] Ambulance service suppliers. [ITEM ii] Community mental health centers.
75
- [ITEM iii] Comprehensive outpatient rehabilitation facilities. [ITEM iv] Independent
76
- clinical laboratories. [ITEM v] Independent diagnostic testing facilities. [ITEM
77
- vi] Physical therapists enrolling as individuals or as group practices. [ITEM
78
- vii] Portable x-ray suppliers. [ITEM viii] Prospective (newly enrolling) and revalidating
79
- opioid treatment programs that have been fully and continuously certified by the
80
- Substance Abuse and Mental Health Services Administration (SAMHSA) since October
81
- 23, 2018. [ITEM ix] Revalidating opioid treatment programs that have not been
82
- fully and continuously certified by SAMHSA since October 23, 2018, revalidating
83
- DMEPOS suppliers, revalidating MDPP'
84
- - source_sentence: the the monthly provision mental health substance use treatment
85
- an IMD meet the requirements for lieu of services at (e 2) () through (iii . For
86
- of rate setting of enrollee this section health disorder the but utilization the
87
- the same through providers under . CITATIONS
 
 
 
 
 
 
 
 
88
  sentences:
89
- - more than 15 days during the period of the monthly capitation payment. The provision
90
- of inpatient mental health or substance use disorder treatment in an IMD must
91
- meet the requirements for in lieu of services at § 438.3(e)(2)(i) through (iii).
92
- For purposes of rate setting, the State may use the utilization of services provided
93
- to an enrollee under this section when developing the inpatient mental health
94
- or substance use disorder component of the capitation rate, but must price utilization
95
- at the cost of the same services through providers included under the State plan.
96
- [CITATIONS]
97
- - '[SUBSECTION b] The regulations in this part are applicable to and binding on
98
- the Office of Inspector General (OIG) in imposing and proposing exclusions, as
99
- well as to Administrative Law Judges (ALJs), the Departmental Appeals Board (DAB),
100
- and federal courts in reviewing the imposition of exclusions by the OIG (and,
101
- where applicable, in imposing exclusions proposed by the OIG). [CITATIONS]'
102
- - '[SUBSECTION c] Keep all loan accounts in good standing, provide timely documentation
103
- as needed, including payment verification, service verification, change of research,
104
- change of institution, etc. Failure to provide such documentation may result in
105
- early termination, and the individual may be subject to statutory financial penalties;
106
- and'
107
- - source_sentence: '[] the ALJ determines that the following [CLAUSE Sends a to parties
108
- and of number and deadline for record 2] of any submitted, and the letter described
109
- in (d (to contractor 3 CMS or to send a LCD record ALJ parties 30 of ALJ of complaint,
110
- extension'
 
 
 
 
111
  sentences:
112
- - '[SUBSECTION d] Acceptable complaint.. If the ALJ determines that the complaint
113
- (or amended complaint) is acceptable, the ALJ does the following: [CLAUSE 1] Sends
114
- a letter to the aggrieved party (or parties) acknowledging the complaint and informing
115
- the aggrieved party (or parties) of the docket number and the deadline for the
116
- contractor to produce the LCD record. [CLAUSE 2] Forwards a copy of the complaint,
117
- any evidence submitted in the complaint, and the letter described in paragraph
118
- (d)(1) of this section to the applicable contractor and CMS. [CLAUSE 3] Requires
119
- CMS or the contractor to send a copy of the LCD record to the ALJ and all parties
120
- to the LCD review within 30 days of receiving the ALJ''s letter, the copy of the
121
- complaint, and any associated evidence, subject to extension for good cause shown.'
122
- - '[SUBSECTION d] Payment for drugs and biologicals.. Drugs and biologicals that
123
- are CORF services under § 410.100(j) of this chapter, are paid the lesser of 80
124
- percent of the following: [CLAUSE 1] The actual charge for the service provided
125
- that payment for such item is not included in the payment amount for other CORF
126
- services paid under paragraphs (a) or (c); or [ENUM drug] (2) The amount determined
127
- using the same methodology for drugs (as defined in § 414.704 of this chapter)
128
- described in section 1842(o)(1) of the Act provided that payment for such is not
129
- included in the payment amount for other CORF services paid under paragraphs (a)
130
- or (c).'
131
- - '[SUBSECTION a] Basis and purpose.. This section implements section 1902(a)(24)
132
- of the Act, which requires that the State plan provide for consultative services
133
- by State agencies to certain institutions furnishing Medicaid services.'
134
  pipeline_tag: sentence-similarity
135
  library_name: sentence-transformers
136
  ---
@@ -184,9 +192,9 @@ from sentence_transformers import SentenceTransformer
184
  model = SentenceTransformer("sentence_transformers_model_id")
185
  # Run inference
186
  sentences = [
187
- '[] the ALJ determines that the following [CLAUSE Sends a to parties and of number and deadline for record 2] of any submitted, and the letter described in (d (to contractor 3 CMS or to send a LCD record ALJ parties 30 of ALJ of complaint, extension',
188
- "[SUBSECTION d] Acceptable complaint.. If the ALJ determines that the complaint (or amended complaint) is acceptable, the ALJ does the following: [CLAUSE 1] Sends a letter to the aggrieved party (or parties) acknowledging the complaint and informing the aggrieved party (or parties) of the docket number and the deadline for the contractor to produce the LCD record. [CLAUSE 2] Forwards a copy of the complaint, any evidence submitted in the complaint, and the letter described in paragraph (d)(1) of this section to the applicable contractor and CMS. [CLAUSE 3] Requires CMS or the contractor to send a copy of the LCD record to the ALJ and all parties to the LCD review within 30 days of receiving the ALJ's letter, the copy of the complaint, and any associated evidence, subject to extension for good cause shown.",
189
- '[SUBSECTION a] Basis and purpose.. This section implements section 1902(a)(24) of the Act, which requires that the State plan provide for consultative services by State agencies to certain institutions furnishing Medicaid services.',
190
  ]
191
  embeddings = model.encode(sentences)
192
  print(embeddings.shape)
@@ -195,9 +203,9 @@ print(embeddings.shape)
195
  # Get the similarity scores for the embeddings
196
  similarities = model.similarity(embeddings, embeddings)
197
  print(similarities)
198
- # tensor([[1.0000, 0.9850, 0.8258],
199
- # [0.9850, 1.0000, 0.8203],
200
- # [0.8258, 0.8203, 1.0000]])
201
  ```
202
 
203
  <!--
@@ -242,27 +250,26 @@ You can finetune this model on your own dataset.
242
 
243
  #### Unnamed Dataset
244
 
245
- * Size: 24,888 training samples
246
  * Columns: <code>sentence_0</code> and <code>sentence_1</code>
247
  * Approximate statistics based on the first 1000 samples:
248
- | | sentence_0 | sentence_1 |
249
- |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
250
- | type | string | string |
251
- | details | <ul><li>min: 11 tokens</li><li>mean: 45.55 tokens</li><li>max: 132 tokens</li></ul> | <ul><li>min: 37 tokens</li><li>mean: 111.1 tokens</li><li>max: 291 tokens</li></ul> |
252
  * Samples:
253
- | sentence_0 | sentence_1 |
254
- |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
255
- | <code>SUBSECTION b qualifying MA organization qualifying MA an equivalent under of this part CLAUSE MA must 2 months of the of annual to services that be covered as professional B received EP for enrollees plans of MA [] the MA organization for each qualifying EP an amount of the (() of the under o (1 () of.</code> | <code>[SUBSECTION b] Amount payable to qualifying MA organization for qualifying MA EPs.. (1) CMS substitutes an amount determined to be equivalent to the amount computed under § 495.102 of this part. [CLAUSE 2] The qualifying MA organization must report to CMS within 2 months of the close of the calendar year, the aggregate annual amount of revenue attributable to providing services that would otherwise be covered as professional services under Part B received by each qualifying MA EP for enrollees in MA plans of the MA organization in the payment year. [CLAUSE 3] CMS calculates the incentive amount for the MA organization for each qualifying MA EP as an amount equal to 75 percent of the reported annual revenue specified in paragraph (b)(2) of this section, up to the maximum amounts specified under section 1848(o)(1)(B) of the Act.</code> |
256
- | <code>(assurance that the, protects underutilization,, including measurable appropriate; [CLAUSE 5) Protection from other than and and [CLAUSE 6 Federal care program beneficiaries than other because of their Federal care program beneficiaries [() than 10 Medicare beneficiaries, not for whom a Federal program is the secondary payer</code> | <code>[CLAUSE 3] () A quality assurance program that promotes the coordination of care, protects against underutilization, and specifies patient goals, including measurable outcomes where appropriate; [CLAUSE 5] () Protection of enrollees from incurring financial liability other than copayments and deductibles; and [CLAUSE 6] () Treatment for Federal health care program beneficiaries that is not different than treatment for other enrollees because of their status as Federal health care program beneficiaries; and [CLAUSE 1] () No more than 10 percent are Medicare beneficiaries, not including persons for whom a Federal health care program is the secondary payer; or</code> |
257
- | <code>is Prescription Plan] A brief the iii] A about the can be .] program participation payment received the, amount last and of by participant . balance from prior including any missed payments . vii] Itemized by for the being billed [viii The from</code> | <code>[ITEM i] A statement that the bill is for the Medicare Prescription Payment Plan. [ITEM ii] A brief description of the program. [ITEM iii] A reference to where additional information about the program can be found. [ITEM iv] The effective date of program participation. [ITEM v] The last payment received, showing the date, amount of the last payment, and the means of payment made by the participant. [ITEM vi] Any balance carried over from the prior month, including any missed payments. [ITEM vii] Itemized out-of-pocket costs by prescription for the month being billed. [ITEM viii] The amount due from the</code> |
258
  * Loss: [<code>DenoisingAutoEncoderLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#denoisingautoencoderloss)
259
 
260
  ### Training Hyperparameters
261
  #### Non-Default Hyperparameters
262
 
263
- - `per_device_train_batch_size`: 24
264
- - `per_device_eval_batch_size`: 24
265
- - `num_train_epochs`: 2
266
  - `multi_dataset_batch_sampler`: round_robin
267
 
268
  #### All Hyperparameters
@@ -272,8 +279,8 @@ You can finetune this model on your own dataset.
272
  - `do_predict`: False
273
  - `eval_strategy`: no
274
  - `prediction_loss_only`: True
275
- - `per_device_train_batch_size`: 24
276
- - `per_device_eval_batch_size`: 24
277
  - `per_gpu_train_batch_size`: None
278
  - `per_gpu_eval_batch_size`: None
279
  - `gradient_accumulation_steps`: 1
@@ -285,7 +292,7 @@ You can finetune this model on your own dataset.
285
  - `adam_beta2`: 0.999
286
  - `adam_epsilon`: 1e-08
287
  - `max_grad_norm`: 1
288
- - `num_train_epochs`: 2
289
  - `max_steps`: -1
290
  - `lr_scheduler_type`: linear
291
  - `lr_scheduler_kwargs`: {}
@@ -392,10 +399,15 @@ You can finetune this model on your own dataset.
392
  ### Training Logs
393
  | Epoch | Step | Training Loss |
394
  |:------:|:----:|:-------------:|
395
- | 0.4822 | 500 | 5.8369 |
396
- | 0.9643 | 1000 | 4.2938 |
397
- | 1.4465 | 1500 | 3.7972 |
398
- | 1.9286 | 2000 | 3.5272 |
 
 
 
 
 
399
 
400
 
401
  ### Framework Versions
 
5
  - feature-extraction
6
  - dense
7
  - generated_from_trainer
8
+ - dataset_size:24880
9
  - loss:DenoisingAutoEncoderLoss
10
  base_model: BAAI/bge-base-en-v1.5
11
  widget:
12
+ - source_sentence: '[MASK] blood and blood components from previous donations in inventory.
13
+ [ITEM i] If the blood collecting establishment notifies the hospital that the
14
+ result of the supplemental (additional, more specific) test or other follow-up
15
+ testing required by FDA is negative, absent other informative test results, the
16
+ hospital may release the blood and blood components from quarantine. [ITEM ii]
17
+ If the blood collecting establishment notifies the hospital that the result of
18
+ the supplemental, (additional, more specific) test or other follow-up testing
19
+ required by FDA is positive, the hospital must—'
20
  sentences:
21
+ - '[SUBSECTION b] Space rental.. As used in section 1128B of the Act, “remuneration”
22
+ does not include any payment made by a lessee to a lessor for the use of premises,
23
+ as long as all of the following six standards are met— [CLAUSE 1] The lease agreement
24
+ is set out in writing and signed by the parties. [CLAUSE 2] The lease covers all
25
+ of the premises leased between the parties for the term of the lease and specifies
26
+ the premises covered by the lease. [CLAUSE 3] If the lease is intended to provide
27
+ the lessee with access to the premises for periodic intervals of time, rather
28
+ than on a full-time basis for the term of the lease, the lease specifies exactly
29
+ the schedule of such intervals, their precise length, and the exact rent for such
30
+ intervals.'
31
+ - of the blood or blood product and quarantine all blood and blood components from
32
+ previous donations in inventory. [ITEM i] If the blood collecting establishment
33
+ notifies the hospital that the result of the supplemental (additional, more specific)
34
+ test or other follow-up testing required by FDA is negative, absent other informative
35
+ test results, the hospital may release the blood and blood components from quarantine.
36
+ [ITEM ii] If the blood collecting establishment notifies the hospital that the
37
+ result of the supplemental, (additional, more specific) test or other follow-up
38
+ testing required by FDA is positive, the hospital must—
39
+ - '[SUBSECTION d] Each application shall contain a statement that the respirator
40
+ has been pretested by the applicant as prescribed in § 84.64, and shall include
41
+ the results of such tests.'
42
+ - source_sentence: '[SUBSECTION b] Security.. A school must require security or endorsement
43
+ if the borrower is a [MASK] the applicable State law, the note signed by him or
44
+ her would not create a binding obligation. The school may not require security
45
+ or endorsement in any other circumstances.'
 
 
46
  sentences:
47
+ - '[SUBSECTION b] Security.. A school must require security or endorsement if the
48
+ borrower is a minor and if, under the applicable State law, the note signed by
49
+ him or her would not create a binding obligation. The school may not require security
50
+ or endorsement in any other circumstances.'
51
+ - '[SUBSECTION b] The minimum flow of air required to maintain a positive pressure
52
+ in the respiratory-inlet covering throughout the entire breathing cycle will be
53
+ supplied to the wearer, provided however, that airflow shall not be less than
54
+ 115 liters per minute for tight-fitting and not less than 170 liters per minute
55
+ for loose-fitting respiratory inlet-coverings.'
56
+ - '[SUBSECTION a] The following intermediate sanctions may be imposed and will continue
57
+ in effect until CMS is satisfied that the deficiencies that are the basis for
58
+ the sanction determination have been corrected and are not likely to recur: [CLAUSE
59
+ 2] Suspension of payment to the MA organization for Medicare beneficiaries enrolled
60
+ after the date CMS notifies the organization of the intermediate sanction. [CLAUSE
61
+ 3] Suspension of communication activities to Medicare beneficiaries by an MA organization,
62
+ as defined by CMS.'
63
+ - source_sentence: '[SUBSECTION c] Procedures the State uses to accomplish coordination
64
+ of CHIP with other public and private health insurance programs, sources of health
65
+ benefits coverage for children, and relevant child health programs, such as title
66
+ V, that provide health care services for low-income children. Such procedures
67
+ include those designed to— [CLAUSE 2] Assist in the enrollment in CHIP of children
68
+ determined ineligible for Medicaid; and [CLAUSE 3] Ensure coordination with other
69
+ insurance affordability programs in the [MASK] eligible individuals are enrolled
70
+ in the appropriate program, including through use of the procedures described
71
+ in § § 457.305, 457.348 and 457.350 of this part. [CITATIONS]'
72
  sentences:
73
+ - '[SUBSECTION d] Changes in hospitals'' status.. For purposes of exclusion from
74
+ the prospective payment systems under this subpart, the status of each currently
75
+ participating hospital (excluded or not excluded) is determined at the beginning
76
+ of each cost reporting period and is effective for the entire cost reporting period.
77
+ Any changes in the status of the hospital are made only at the start of a cost
78
+ reporting period.'
79
+ - '[SUBSECTION c] Procedures the State uses to accomplish coordination of CHIP with
80
+ other public and private health insurance programs, sources of health benefits
81
+ coverage for children, and relevant child health programs, such as title V, that
82
+ provide health care services for low-income children. Such procedures include
83
+ those designed to— [CLAUSE 2] Assist in the enrollment in CHIP of children determined
84
+ ineligible for Medicaid; and [CLAUSE 3] Ensure coordination with other insurance
85
+ affordability programs in the determination of eligibility and enrollment in coverage
86
+ to ensure that all eligible individuals are enrolled in the appropriate program,
87
+ including through use of the procedures described in § § 457.305, 457.348 and
88
+ 457.350 of this part. [CITATIONS]'
89
+ - '[SECTION HEADING] § 71.41 General provisions. Carriers arriving at a U.S. port
90
+ from a foreign area shall be subject to a sanitary inspection to determine whether
91
+ there exists rodent, insect, or other vermin infestation, contaminated food or
92
+ water, or other insanitary conditions requiring measures for the prevention of
93
+ the introduction, transmission, or spread of communicable disease.'
94
+ - source_sentence: '[SUBSECTION c] Adjustment for cost reporting period.. (1) If a
95
+ facility has a cost reporting [MASK] the contractor increases the labor-related
96
+ and nonlabor-related portions of the prospective payment rate that would otherwise
97
+ apply to the SNF by an adjustment factor. Each factor represents the projected
98
+ increase in the market basket index for a specific 12-month period. The factors
99
+ are used to account for inflation in costs for cost reporting periods beginning
100
+ after October 1. Adjustment factors are published in the annual notice of prospectively
101
+ determined payment rates described in § 413.320.'
102
  sentences:
103
+ - '[SUBSECTION c] Adjustment for cost reporting period.. (1) If a facility has a
104
+ cost reporting period beginning after the beginning of the Federal fiscal year,
105
+ the contractor increases the labor-related and nonlabor-related portions of the
106
+ prospective payment rate that would otherwise apply to the SNF by an adjustment
107
+ factor. Each factor represents the projected increase in the market basket index
108
+ for a specific 12-month period. The factors are used to account for inflation
109
+ in costs for cost reporting periods beginning after October 1. Adjustment factors
110
+ are published in the annual notice of prospectively determined payment rates described
111
+ in § 413.320.'
112
+ - '[SUBSECTION B] QCDR measure considerations for approval include, but are not
113
+ limited to: [CLAUSE 1] () Measures that are outcome-based rather than clinical
114
+ process measures. [CLAUSE 3] () Measures that identify appropriate use of diagnosis
115
+ and therapeutics. [CLAUSE 5] () Measures that address the domain for patient and
116
+ caregiver experience. [CLAUSE 7] () Beginning with the CY 2021 performance period/2023
117
+ MIPS payment year - [ITEM i] () That QCDRs link their QCDR measures as feasible
118
+ to at least one cost measure, improvement activity, or an MVP at the time of self-nomination.
119
+ [ITEM ii] () In cases where a QCDR measure does not have a clear link to a cost
120
+ measure, improvement activity, or an MVP, CMS would consider exceptions if the
121
+ potential QCDR measure otherwise meets the QCDR measure requirements and considerations.'
122
+ - this section may be considered evidence that the MPPP supplier standards have
123
+ not been met. This information must be kept at each administrative location and
124
+ made available to CMS or its contractors upon request.
125
+ - source_sentence: '[SECTION HEADING] § 24.6 Performance appraisal system. The members
126
+ of the Service shall be subject to a performance appraisal system that is designed
127
+ to encourage excellence in performance and shall provide for periodic and systematic
128
+ assessment of the performance of members.'
129
  sentences:
130
+ - '[SECTION HEADING] § 24.6 Performance appraisal system. The members of the Service
131
+ shall be subject to a performance appraisal system that is designed to encourage
132
+ excellence in performance and shall provide for periodic and systematic assessment
133
+ of the performance of members.'
134
+ - '[SUBSECTION g] Under the terms of the contract, the approved CAP vendor must
135
+ provide assistance to beneficiaries experiencing financial difficulty in paying
136
+ their cost-sharing amounts through any one or all of the following:'
137
+ - '[SUBSECTION a] General rules.. (1) An HMO or CMP that has an APCRP (as determined
138
+ under § 417.590) greater than its ACR (as determined under § 417.594) must elect
139
+ one of the options specified in paragraph (b) of this section. [CLAUSE 2] The
140
+ dollar value of the elected option must, over the course of a contract period,
141
+ be at least equal to the difference between the APCRP and the proposed ACR.'
 
 
 
 
 
 
 
 
 
 
142
  pipeline_tag: sentence-similarity
143
  library_name: sentence-transformers
144
  ---
 
192
  model = SentenceTransformer("sentence_transformers_model_id")
193
  # Run inference
194
  sentences = [
195
+ '[SECTION HEADING] § 24.6 Performance appraisal system. The members of the Service shall be subject to a performance appraisal system that is designed to encourage excellence in performance and shall provide for periodic and systematic assessment of the performance of members.',
196
+ '[SECTION HEADING] § 24.6 Performance appraisal system. The members of the Service shall be subject to a performance appraisal system that is designed to encourage excellence in performance and shall provide for periodic and systematic assessment of the performance of members.',
197
+ '[SUBSECTION a] General rules.. (1) An HMO or CMP that has an APCRP (as determined under § 417.590) greater than its ACR (as determined under § 417.594) must elect one of the options specified in paragraph (b) of this section. [CLAUSE 2] The dollar value of the elected option must, over the course of a contract period, be at least equal to the difference between the APCRP and the proposed ACR.',
198
  ]
199
  embeddings = model.encode(sentences)
200
  print(embeddings.shape)
 
203
  # Get the similarity scores for the embeddings
204
  similarities = model.similarity(embeddings, embeddings)
205
  print(similarities)
206
+ # tensor([[1.0000, 1.0000, 0.6782],
207
+ # [1.0000, 1.0000, 0.6782],
208
+ # [0.6782, 0.6782, 1.0000]])
209
  ```
210
 
211
  <!--
 
250
 
251
  #### Unnamed Dataset
252
 
253
+ * Size: 24,880 training samples
254
  * Columns: <code>sentence_0</code> and <code>sentence_1</code>
255
  * Approximate statistics based on the first 1000 samples:
256
+ | | sentence_0 | sentence_1 |
257
+ |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
258
+ | type | string | string |
259
+ | details | <ul><li>min: 35 tokens</li><li>mean: 105.52 tokens</li><li>max: 335 tokens</li></ul> | <ul><li>min: 37 tokens</li><li>mean: 112.72 tokens</li><li>max: 335 tokens</li></ul> |
260
  * Samples:
261
+ | sentence_0 | sentence_1 |
262
+ |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
263
+ | <code>[ITEM i] The name and TIN of the CJR collaborator and the name, TIN, and NPI of the collaboration agent. [ITEM ii] The start date and, if applicable, end date, for the distribution arrangement between the CJR collaborator and the collaboration agent. [ENUM Downstream collaboration agents.] (3) For each physician, nonphysician practitioner, or therapist who is a downstream collaboration agent during the period of the CJR performance year specified by CMS— [ITEM i] The name and TIN of the CJR collaborator and the [MASK] TIN, and NPI of the downstream collaboration</code> | <code>[ITEM i] The name and TIN of the CJR collaborator and the name, TIN, and NPI of the collaboration agent. [ITEM ii] The start date and, if applicable, end date, for the distribution arrangement between the CJR collaborator and the collaboration agent. [ENUM Downstream collaboration agents.] (3) For each physician, nonphysician practitioner, or therapist who is a downstream collaboration agent during the period of the CJR performance year specified by CMS— [ITEM i] The name and TIN of the CJR collaborator and the name and TIN of the collaboration agent and the name, TIN, and NPI of the downstream collaboration</code> |
264
+ | <code>[SUBSECTION a] Termination of agreements.. (1) CMS may terminate any approved agreement if it finds, after the procedures described in this paragraph are followed that the State system does not satisfactorily meet the requirements of section 1886(c) of the Act or the regulations in this subpart. A termination must be effective on the last day of a calendar quarter. [CLAUSE 2] CMS will give the State reasonable notice of the proposed termination of an agreement [MASK] days before the effective date of the termination. [CLAUSE 3] CMS will give the State the opportunity to present evidence to refute the finding.</code> | <code>[SUBSECTION a] Termination of agreements.. (1) CMS may terminate any approved agreement if it finds, after the procedures described in this paragraph are followed that the State system does not satisfactorily meet the requirements of section 1886(c) of the Act or the regulations in this subpart. A termination must be effective on the last day of a calendar quarter. [CLAUSE 2] CMS will give the State reasonable notice of the proposed termination of an agreement and of the reasons for the termination at least 90 days before the effective date of the termination. [CLAUSE 3] CMS will give the State the opportunity to present evidence to refute the finding.</code> |
265
+ | <code>[CLAUSE 4] The amount of the post-TDAPA add-on payment adjustment is equal to 65 percent of the amount calculated in paragraph (g)(2) of this section, multiplied by the reduction factor specified in paragraph (g)(3) of this section, and multiplied by the latest available forecast of annual growth in the ESRD bundled market basket composite price proxy for pharmaceuticals. [CLAUSE 5] The post-TDAPA [MASK] ESRD PPS claim is adjsuted by any applicable patient-level case-mix adjustments under § 413.235. [CITATIONS]</code> | <code>[CLAUSE 4] The amount of the post-TDAPA add-on payment adjustment is equal to 65 percent of the amount calculated in paragraph (g)(2) of this section, multiplied by the reduction factor specified in paragraph (g)(3) of this section, and multiplied by the latest available forecast of annual growth in the ESRD bundled market basket composite price proxy for pharmaceuticals. [CLAUSE 5] The post-TDAPA add-on payment adjustment that is applied to an ESRD PPS claim is adjsuted by any applicable patient-level case-mix adjustments under § 413.235. [CITATIONS]</code> |
266
  * Loss: [<code>DenoisingAutoEncoderLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#denoisingautoencoderloss)
267
 
268
  ### Training Hyperparameters
269
  #### Non-Default Hyperparameters
270
 
271
+ - `per_device_train_batch_size`: 16
272
+ - `per_device_eval_batch_size`: 16
 
273
  - `multi_dataset_batch_sampler`: round_robin
274
 
275
  #### All Hyperparameters
 
279
  - `do_predict`: False
280
  - `eval_strategy`: no
281
  - `prediction_loss_only`: True
282
+ - `per_device_train_batch_size`: 16
283
+ - `per_device_eval_batch_size`: 16
284
  - `per_gpu_train_batch_size`: None
285
  - `per_gpu_eval_batch_size`: None
286
  - `gradient_accumulation_steps`: 1
 
292
  - `adam_beta2`: 0.999
293
  - `adam_epsilon`: 1e-08
294
  - `max_grad_norm`: 1
295
+ - `num_train_epochs`: 3
296
  - `max_steps`: -1
297
  - `lr_scheduler_type`: linear
298
  - `lr_scheduler_kwargs`: {}
 
399
  ### Training Logs
400
  | Epoch | Step | Training Loss |
401
  |:------:|:----:|:-------------:|
402
+ | 0.3215 | 500 | 5.7169 |
403
+ | 0.6431 | 1000 | 4.3196 |
404
+ | 0.9646 | 1500 | 3.8613 |
405
+ | 1.2862 | 2000 | 3.5443 |
406
+ | 1.6077 | 2500 | 3.357 |
407
+ | 1.9293 | 3000 | 3.2075 |
408
+ | 2.2508 | 3500 | 3.0466 |
409
+ | 2.5723 | 4000 | 2.9261 |
410
+ | 2.8939 | 4500 | 2.8525 |
411
 
412
 
413
  ### Framework Versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:671ffbf4f6f6d7a90128b2a446bbd37102ea2bed4d3beb454887da86e5eceae3
3
  size 437951328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ec979ed0a5f997c093a4486ae7cb95684d851792e427c26d525954b520a966
3
  size 437951328