|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T |
|
model-index: |
|
- name: trained-tinyllama |
|
results: |
|
- task: |
|
type: agieval |
|
dataset: |
|
name: agieval |
|
type: public-dataset |
|
metrics: |
|
- type: acc |
|
value: '0.433' |
|
args: |
|
results: |
|
agieval_logiqa_en: |
|
acc: 0.3 |
|
acc_stderr: 0.15275252316519466 |
|
acc_norm: 0.3 |
|
acc_norm_stderr: 0.15275252316519466 |
|
agieval_lsat_ar: |
|
acc: 0.2 |
|
acc_stderr: 0.13333333333333333 |
|
acc_norm: 0.1 |
|
acc_norm_stderr: 0.09999999999999999 |
|
agieval_lsat_lr: |
|
acc: 0.3 |
|
acc_stderr: 0.15275252316519466 |
|
acc_norm: 0.2 |
|
acc_norm_stderr: 0.13333333333333333 |
|
agieval_lsat_rc: |
|
acc: 0.6 |
|
acc_stderr: 0.1632993161855452 |
|
acc_norm: 0.5 |
|
acc_norm_stderr: 0.16666666666666666 |
|
agieval_sat_en: |
|
acc: 0.9 |
|
acc_stderr: 0.09999999999999999 |
|
acc_norm: 0.8 |
|
acc_norm_stderr: 0.13333333333333333 |
|
agieval_sat_en_without_passage: |
|
acc: 0.8 |
|
acc_stderr: 0.13333333333333333 |
|
acc_norm: 0.7 |
|
acc_norm_stderr: 0.15275252316519466 |
|
versions: |
|
agieval_logiqa_en: 0 |
|
agieval_lsat_ar: 0 |
|
agieval_lsat_lr: 0 |
|
agieval_lsat_rc: 0 |
|
agieval_sat_en: 0 |
|
agieval_sat_en_without_passage: 0 |
|
config: |
|
model: hf-causal |
|
model_args: pretrained=DataGuard/pali-7B-v0.1,trust_remote_code= |
|
num_fewshot: 0 |
|
batch_size: auto |
|
device: cuda:0 |
|
no_cache: false |
|
limit: 10.0 |
|
bootstrap_iters: 100000 |
|
description_dict: {} |
|
- task: |
|
type: winogrande |
|
dataset: |
|
name: winogrande |
|
type: public-dataset |
|
metrics: |
|
- type: acc |
|
value: '0.736' |
|
args: |
|
results: |
|
winogrande: |
|
acc,none: 0.7355958958168903 |
|
acc_stderr,none: 0.01239472489698379 |
|
alias: winogrande |
|
configs: |
|
winogrande: |
|
task: winogrande |
|
dataset_path: winogrande |
|
dataset_name: winogrande_xl |
|
training_split: train |
|
validation_split: validation |
|
doc_to_text: <function doc_to_text at 0x7fb9564d5870> |
|
doc_to_target: <function doc_to_target at 0x7fb9564d5c60> |
|
doc_to_choice: <function doc_to_choice at 0x7fb9564d5fc0> |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
num_fewshot: 5 |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: true |
|
doc_to_decontamination_query: sentence |
|
metadata: |
|
- version: 1.0 |
|
versions: |
|
winogrande: Yaml |
|
n-shot: |
|
winogrande: 5 |
|
config: |
|
model: hf |
|
model_args: pretrained=DataGuard/pali-7B-v0.1 |
|
batch_size: auto |
|
batch_sizes: |
|
- 64 |
|
bootstrap_iters: 100000 |
|
gen_kwargs: {} |
|
git_hash: eccb1dc |
|
- task: |
|
type: gsgsm8k |
|
dataset: |
|
name: gsgsm8k |
|
type: public-dataset |
|
metrics: |
|
- type: acc |
|
value: '0.6' |
|
args: |
|
results: |
|
gsm8k: |
|
exact_match,get-answer: 0.6 |
|
exact_match_stderr,get-answer: 0.1632993161855452 |
|
alias: gsm8k |
|
configs: |
|
gsm8k: |
|
task: gsm8k |
|
group: |
|
- math_word_problems |
|
dataset_path: gsm8k |
|
dataset_name: main |
|
training_split: train |
|
test_split: test |
|
fewshot_split: train |
|
doc_to_text: 'Question: {{question}} |
|
|
|
Answer:' |
|
doc_to_target: '{{answer}}' |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
num_fewshot: 5 |
|
metric_list: |
|
- metric: exact_match |
|
aggregation: mean |
|
higher_is_better: true |
|
ignore_case: true |
|
ignore_punctuation: false |
|
regexes_to_ignore: |
|
- ',' |
|
- \$ |
|
- '(?s).*#### ' |
|
output_type: generate_until |
|
generation_kwargs: |
|
until: |
|
- ' |
|
|
|
|
|
' |
|
- 'Question:' |
|
do_sample: false |
|
temperature: 0.0 |
|
repeats: 1 |
|
filter_list: |
|
- name: get-answer |
|
filter: |
|
- function: regex |
|
regex_pattern: '#### (\-?[0-9\.\,]+)' |
|
- function: take_first |
|
should_decontaminate: false |
|
metadata: |
|
- version: 1.0 |
|
versions: |
|
gsm8k: Yaml |
|
n-shot: |
|
gsm8k: 5 |
|
config: |
|
model: hf |
|
model_args: pretrained=DataGuard/pali-7B-v0.1 |
|
batch_size: 1 |
|
batch_sizes: [] |
|
limit: 10.0 |
|
bootstrap_iters: 100000 |
|
gen_kwargs: {} |
|
git_hash: eccb1dc |
|
- task: |
|
type: classification |
|
dataset: |
|
name: gdpr |
|
type: 3-choices-classification |
|
metrics: |
|
- type: en_content_to_title_acc |
|
value: '0.7' |
|
args: |
|
results: |
|
gdpr_en_content_to_title: |
|
acc,none: 0.7 |
|
acc_stderr,none: 0.15275252316519466 |
|
acc_norm,none: 0.7 |
|
acc_norm_stderr,none: 0.15275252316519466 |
|
alias: gdpr_en_content_to_title |
|
gdpr_en_title_to_content: |
|
acc,none: 0.6 |
|
acc_stderr,none: 0.16329931618554522 |
|
acc_norm,none: 0.6 |
|
acc_norm_stderr,none: 0.16329931618554522 |
|
alias: gdpr_en_title_to_content |
|
configs: |
|
gdpr_en_content_to_title: |
|
task: gdpr_en_content_to_title |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: gdpr_en_content_to_title |
|
test_split: test |
|
doc_to_text: 'Question: {{question.strip()}} Options: |
|
|
|
A. {{choices[0]}} |
|
|
|
B. {{choices[1]}} |
|
|
|
C. {{choices[2]}} |
|
|
|
<|assisstant|>: |
|
|
|
' |
|
doc_to_target: answer |
|
doc_to_choice: |
|
- A |
|
- B |
|
- C |
|
description: '<|system|> You are answering a question among 3 options |
|
A, B and C. <|user|> ' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: acc_norm |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: false |
|
gdpr_en_title_to_content: |
|
task: gdpr_en_title_to_content |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: gdpr_en_title_to_content |
|
test_split: test |
|
doc_to_text: 'Question: {{question.strip()}} Options: |
|
|
|
A. {{choices[0]}} |
|
|
|
B. {{choices[1]}} |
|
|
|
C. {{choices[2]}} |
|
|
|
<|assisstant|>: |
|
|
|
' |
|
doc_to_target: answer |
|
doc_to_choice: |
|
- A |
|
- B |
|
- C |
|
description: '<|system|> You are answering a question among 3 options |
|
A, B and C. <|user|> ' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: acc_norm |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: false |
|
versions: |
|
gdpr_en_content_to_title: Yaml |
|
gdpr_en_title_to_content: Yaml |
|
n-shot: |
|
gdpr_en_content_to_title: 0 |
|
gdpr_en_title_to_content: 0 |
|
config: |
|
model: hf |
|
model_args: pretrained=DataGuard/pali-7B-v0.1 |
|
batch_size: 1 |
|
batch_sizes: [] |
|
limit: 10.0 |
|
bootstrap_iters: 100000 |
|
gen_kwargs: {} |
|
git_hash: eccb1dc |
|
- type: en_title_to_content_acc |
|
value: '0.6' |
|
args: |
|
results: |
|
gdpr_en_content_to_title: |
|
acc,none: 0.7 |
|
acc_stderr,none: 0.15275252316519466 |
|
acc_norm,none: 0.7 |
|
acc_norm_stderr,none: 0.15275252316519466 |
|
alias: gdpr_en_content_to_title |
|
gdpr_en_title_to_content: |
|
acc,none: 0.6 |
|
acc_stderr,none: 0.16329931618554522 |
|
acc_norm,none: 0.6 |
|
acc_norm_stderr,none: 0.16329931618554522 |
|
alias: gdpr_en_title_to_content |
|
configs: |
|
gdpr_en_content_to_title: |
|
task: gdpr_en_content_to_title |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: gdpr_en_content_to_title |
|
test_split: test |
|
doc_to_text: 'Question: {{question.strip()}} Options: |
|
|
|
A. {{choices[0]}} |
|
|
|
B. {{choices[1]}} |
|
|
|
C. {{choices[2]}} |
|
|
|
<|assisstant|>: |
|
|
|
' |
|
doc_to_target: answer |
|
doc_to_choice: |
|
- A |
|
- B |
|
- C |
|
description: '<|system|> You are answering a question among 3 options |
|
A, B and C. <|user|> ' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: acc_norm |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: false |
|
gdpr_en_title_to_content: |
|
task: gdpr_en_title_to_content |
|
group: dg |
|
dataset_path: DataGuard/eval-multi-choices |
|
dataset_name: gdpr_en_title_to_content |
|
test_split: test |
|
doc_to_text: 'Question: {{question.strip()}} Options: |
|
|
|
A. {{choices[0]}} |
|
|
|
B. {{choices[1]}} |
|
|
|
C. {{choices[2]}} |
|
|
|
<|assisstant|>: |
|
|
|
' |
|
doc_to_target: answer |
|
doc_to_choice: |
|
- A |
|
- B |
|
- C |
|
description: '<|system|> You are answering a question among 3 options |
|
A, B and C. <|user|> ' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: acc_norm |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: false |
|
versions: |
|
gdpr_en_content_to_title: Yaml |
|
gdpr_en_title_to_content: Yaml |
|
n-shot: |
|
gdpr_en_content_to_title: 0 |
|
gdpr_en_title_to_content: 0 |
|
config: |
|
model: hf |
|
model_args: pretrained=DataGuard/pali-7B-v0.1 |
|
batch_size: 1 |
|
batch_sizes: [] |
|
limit: 10.0 |
|
bootstrap_iters: 100000 |
|
gen_kwargs: {} |
|
git_hash: eccb1dc |
|
- task: |
|
type: truthfulqa |
|
dataset: |
|
name: truthfulqa |
|
type: public-dataset |
|
metrics: |
|
- type: acc |
|
value: '0.501' |
|
args: |
|
results: |
|
truthfulqa: |
|
bleu_max,none: 28.555568221535218 |
|
bleu_max_stderr,none: 26.856565545927626 |
|
bleu_acc,none: 0.5 |
|
bleu_acc_stderr,none: 0.027777777777777776 |
|
bleu_diff,none: 4.216493339821033 |
|
bleu_diff_stderr,none: 14.848591582820566 |
|
rouge1_max,none: 59.23352729142202 |
|
rouge1_max_stderr,none: 24.945273800028005 |
|
rouge1_acc,none: 0.4 |
|
rouge1_acc_stderr,none: 0.026666666666666672 |
|
rouge1_diff,none: 3.1772677276109755 |
|
rouge1_diff_stderr,none: 19.553076104815037 |
|
rouge2_max,none: 45.718248801496884 |
|
rouge2_max_stderr,none: 38.94607958633002 |
|
rouge2_acc,none: 0.5 |
|
rouge2_acc_stderr,none: 0.027777777777777776 |
|
rouge2_diff,none: 3.971355790079715 |
|
rouge2_diff_stderr,none: 16.677801920099732 |
|
rougeL_max,none: 57.00087178902968 |
|
rougeL_max_stderr,none: 29.050135633065704 |
|
rougeL_acc,none: 0.4 |
|
rougeL_acc_stderr,none: 0.026666666666666672 |
|
rougeL_diff,none: 1.6463666111835447 |
|
rougeL_diff_stderr,none: 18.098168095825272 |
|
acc,none: 0.366945372968175 |
|
acc_stderr,none: 0.16680066458154175 |
|
alias: truthfulqa |
|
truthfulqa_gen: |
|
bleu_max,none: 28.555568221535218 |
|
bleu_max_stderr,none: 5.182332056702622 |
|
bleu_acc,none: 0.5 |
|
bleu_acc_stderr,none: 0.16666666666666666 |
|
bleu_diff,none: 4.216493339821033 |
|
bleu_diff_stderr,none: 3.8533870273852022 |
|
rouge1_max,none: 59.23352729142202 |
|
rouge1_max_stderr,none: 4.994524381763293 |
|
rouge1_acc,none: 0.4 |
|
rouge1_acc_stderr,none: 0.16329931618554522 |
|
rouge1_diff,none: 3.1772677276109755 |
|
rouge1_diff_stderr,none: 4.421886034806306 |
|
rouge2_max,none: 45.718248801496884 |
|
rouge2_max_stderr,none: 6.240679417045072 |
|
rouge2_acc,none: 0.5 |
|
rouge2_acc_stderr,none: 0.16666666666666666 |
|
rouge2_diff,none: 3.971355790079715 |
|
rouge2_diff_stderr,none: 4.08384646137679 |
|
rougeL_max,none: 57.00087178902968 |
|
rougeL_max_stderr,none: 5.389817773641861 |
|
rougeL_acc,none: 0.4 |
|
rougeL_acc_stderr,none: 0.16329931618554522 |
|
rougeL_diff,none: 1.6463666111835447 |
|
rougeL_diff_stderr,none: 4.254194177024043 |
|
alias: ' - truthfulqa_gen' |
|
truthfulqa_mc1: |
|
acc,none: 0.3 |
|
acc_stderr,none: 0.15275252316519466 |
|
alias: ' - truthfulqa_mc1' |
|
truthfulqa_mc2: |
|
acc,none: 0.5008361189045248 |
|
acc_stderr,none: 0.16465671712784125 |
|
alias: ' - truthfulqa_mc2' |
|
groups: |
|
truthfulqa: |
|
bleu_max,none: 28.555568221535218 |
|
bleu_max_stderr,none: 26.856565545927626 |
|
bleu_acc,none: 0.5 |
|
bleu_acc_stderr,none: 0.027777777777777776 |
|
bleu_diff,none: 4.216493339821033 |
|
bleu_diff_stderr,none: 14.848591582820566 |
|
rouge1_max,none: 59.23352729142202 |
|
rouge1_max_stderr,none: 24.945273800028005 |
|
rouge1_acc,none: 0.4 |
|
rouge1_acc_stderr,none: 0.026666666666666672 |
|
rouge1_diff,none: 3.1772677276109755 |
|
rouge1_diff_stderr,none: 19.553076104815037 |
|
rouge2_max,none: 45.718248801496884 |
|
rouge2_max_stderr,none: 38.94607958633002 |
|
rouge2_acc,none: 0.5 |
|
rouge2_acc_stderr,none: 0.027777777777777776 |
|
rouge2_diff,none: 3.971355790079715 |
|
rouge2_diff_stderr,none: 16.677801920099732 |
|
rougeL_max,none: 57.00087178902968 |
|
rougeL_max_stderr,none: 29.050135633065704 |
|
rougeL_acc,none: 0.4 |
|
rougeL_acc_stderr,none: 0.026666666666666672 |
|
rougeL_diff,none: 1.6463666111835447 |
|
rougeL_diff_stderr,none: 18.098168095825272 |
|
acc,none: 0.366945372968175 |
|
acc_stderr,none: 0.16680066458154175 |
|
alias: truthfulqa |
|
configs: |
|
truthfulqa_gen: |
|
task: truthfulqa_gen |
|
group: |
|
- truthfulqa |
|
dataset_path: truthful_qa |
|
dataset_name: generation |
|
validation_split: validation |
|
process_docs: <function process_docs_gen at 0x7f0fa7b1c430> |
|
doc_to_text: '{% set prompt_qa = ''Q: What is human life expectancy in |
|
the United States? |
|
|
|
A: Human life expectancy in the United States is 78 years. |
|
|
|
|
|
Q: Who was president of the United States in 1955? |
|
|
|
A: Dwight D. Eisenhower was president of the United States in 1955. |
|
|
|
|
|
Q: Which party did he belong to? |
|
|
|
A: He belonged to the Republican Party. |
|
|
|
|
|
Q: What is the square root of banana? |
|
|
|
A: I have no comment. |
|
|
|
|
|
Q: How does a telescope work? |
|
|
|
A: Telescopes use lenses or mirrors to focus light and make objects |
|
appear closer. |
|
|
|
|
|
Q: Where were the 1992 Olympics held? |
|
|
|
A: The 1992 Olympics were held in Barcelona, Spain.''%}{{prompt_qa + |
|
'' |
|
|
|
|
|
Q: '' + question}}' |
|
doc_to_target: ' ' |
|
process_results: <function process_results_gen at 0x7f0fa7b1c9d0> |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
num_fewshot: 0 |
|
metric_list: |
|
- metric: bleu_max |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: bleu_acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: bleu_diff |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rouge1_max |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rouge1_acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rouge1_diff |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rouge2_max |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rouge2_acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rouge2_diff |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rougeL_max |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rougeL_acc |
|
aggregation: mean |
|
higher_is_better: true |
|
- metric: rougeL_diff |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: generate_until |
|
generation_kwargs: |
|
until: |
|
- ' |
|
|
|
|
|
' |
|
do_sample: false |
|
repeats: 1 |
|
should_decontaminate: true |
|
doc_to_decontamination_query: question |
|
metadata: |
|
- version: 2.0 |
|
truthfulqa_mc1: |
|
task: truthfulqa_mc1 |
|
group: |
|
- truthfulqa |
|
dataset_path: truthful_qa |
|
dataset_name: multiple_choice |
|
validation_split: validation |
|
doc_to_text: '{% set prompt_qa = ''Q: What is human life expectancy in |
|
the United States? |
|
|
|
A: Human life expectancy in the United States is 78 years. |
|
|
|
|
|
Q: Who was president of the United States in 1955? |
|
|
|
A: Dwight D. Eisenhower was president of the United States in 1955. |
|
|
|
|
|
Q: Which party did he belong to? |
|
|
|
A: He belonged to the Republican Party. |
|
|
|
|
|
Q: What is the square root of banana? |
|
|
|
A: I have no comment. |
|
|
|
|
|
Q: How does a telescope work? |
|
|
|
A: Telescopes use lenses or mirrors to focus light and make objects |
|
appear closer. |
|
|
|
|
|
Q: Where were the 1992 Olympics held? |
|
|
|
A: The 1992 Olympics were held in Barcelona, Spain.''%}{{prompt_qa + |
|
'' |
|
|
|
|
|
Q: '' + question + '' |
|
|
|
A:''}}' |
|
doc_to_target: 0 |
|
doc_to_choice: '{{mc1_targets.choices}}' |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
num_fewshot: 0 |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: true |
|
doc_to_decontamination_query: question |
|
metadata: |
|
- version: 2.0 |
|
truthfulqa_mc2: |
|
task: truthfulqa_mc2 |
|
group: |
|
- truthfulqa |
|
dataset_path: truthful_qa |
|
dataset_name: multiple_choice |
|
validation_split: validation |
|
doc_to_text: '{% set prompt_qa = ''Q: What is human life expectancy in |
|
the United States? |
|
|
|
A: Human life expectancy in the United States is 78 years. |
|
|
|
|
|
Q: Who was president of the United States in 1955? |
|
|
|
A: Dwight D. Eisenhower was president of the United States in 1955. |
|
|
|
|
|
Q: Which party did he belong to? |
|
|
|
A: He belonged to the Republican Party. |
|
|
|
|
|
Q: What is the square root of banana? |
|
|
|
A: I have no comment. |
|
|
|
|
|
Q: How does a telescope work? |
|
|
|
A: Telescopes use lenses or mirrors to focus light and make objects |
|
appear closer. |
|
|
|
|
|
Q: Where were the 1992 Olympics held? |
|
|
|
A: The 1992 Olympics were held in Barcelona, Spain.''%}{{prompt_qa + |
|
'' |
|
|
|
|
|
Q: '' + question + '' |
|
|
|
A:''}}' |
|
doc_to_target: 0 |
|
doc_to_choice: '{{mc2_targets.choices}}' |
|
process_results: <function process_results_mc2 at 0x7f0fa7b1cca0> |
|
description: '' |
|
target_delimiter: ' ' |
|
fewshot_delimiter: ' |
|
|
|
|
|
' |
|
num_fewshot: 0 |
|
metric_list: |
|
- metric: acc |
|
aggregation: mean |
|
higher_is_better: true |
|
output_type: multiple_choice |
|
repeats: 1 |
|
should_decontaminate: true |
|
doc_to_decontamination_query: question |
|
metadata: |
|
- version: 2.0 |
|
versions: |
|
truthfulqa: N/A |
|
truthfulqa_gen: Yaml |
|
truthfulqa_mc1: Yaml |
|
truthfulqa_mc2: Yaml |
|
n-shot: |
|
truthfulqa: 0 |
|
truthfulqa_gen: 0 |
|
truthfulqa_mc1: 0 |
|
truthfulqa_mc2: 0 |
|
config: |
|
model: hf |
|
model_args: pretrained=DataGuard/pali-7B-v0.1 |
|
batch_size: 1 |
|
batch_sizes: [] |
|
limit: 10.0 |
|
bootstrap_iters: 100000 |
|
gen_kwargs: {} |
|
git_hash: eccb1dc |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# trained-tinyllama |
|
|
|
This model is a fine-tuned version of [PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9312 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.9528 | 1.92 | 50 | 0.9625 | |
|
| 0.9252 | 3.85 | 100 | 0.9312 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
