Dataset Viewer
Auto-converted to Parquet Duplicate
state
listlengths
2
52
action
dict
next_obs
listlengths
2
2
state_len
int64
874
5.05k
temperature
float64
1
1
reward
float64
0.07
1
done
bool
2 classes
truncated
bool
1 class
timestep
int64
0
25
try_step
int64
0
0
batch_id
int64
40
40
unique_data_sample_id
int64
0
31
generation_id
int64
0
0
split
stringclasses
1 value
return_
float64
0.07
1
advantage
float64
0
0
return_is_computed
bool
1 class
advantage_is_computed
bool
1 class
constant_reward_group
bool
1 class
tools
listlengths
5
5
action_prob
float64
0.07
1
system_prompt
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I need to find the relevant table that contains information about Tesla's valuation allowance for deferred tax assets. First, I'll get a list of available tables for Tesla to identify which one might contain financial or tax-related data.\n\n<tool_call>\n{\"name\": \"get_descriptions\", \"arguments\": {...
[ { "content": "[\"us_gaap_DebtInstrumentRedemptionTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"sla_ScheduleOfAccruedLiabilitiesAndOtherCurrentLiabilitiesTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredT...
891
1
1
false
false
0
0
40
0
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "The table \"us_gaap_ScheduleOfDeferredTaxAssetsAndLiabilitiesTableTextBlock\" is likely to contain information about deferred tax assets and liabilities, including any valuation allowance. I will retrieve the metadata for this table to understand its structure and see if it includes a column for valuati...
[ { "content": "{\"description\": \"deferred_tax_assets_liabilities_as_of_december_31_2024_and_2023_consisted_of_the_following_in_millions\",\"column_names\": [\"item\",\"december_31_2024\",\"december_31_2023\"],\"unique_vals_per_col\": {\"item\": [\"deferred_tax_assets:\",\"net_operating_loss_carry_forwards\",\"...
1,495
1
1
false
false
1
0
40
0
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "The query is now fetching specific items related to deferred tax assets and the valuation allowance from the table. This will provide the necessary data to determine the size of the valuation allowance and its impact on the net deferred tax assets.\n\n<tool_call>\n{\"name\": \"sql_query\", \"arguments\"...
[ { "content": "[{\"item\":\"total_deferred_tax_assets\",\"december_31_2024\":\"$11,962\"},{\"item\":\"valuation_allowance\",\"december_31_2024\":\"($1,224)\"},{\"item\":\"deferred_tax_assets_net_of_valuation_allowance\",\"december_31_2024\":\"$10,738\"},{\"item\":\"deferred_tax_assets_liabilities_net_of_valuatio...
1,348
1
0.577199
false
false
2
0
40
0
0
train_all
0.577199
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.577199
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "To better understand the significance of the valuation allowance, I need to compare the 2024 figures with those from 2023. This will help determine if the valuation allowance has changed and what this might suggest about management's assessment of future tax benefits. I will retrieve the historical data...
[ { "content": "[{\"item\":\"total_deferred_tax_assets\",\"december_31_2023\":\"$10,774\"},{\"item\":\"valuation_allowance\",\"december_31_2023\":\"($892)\"},{\"item\":\"deferred_tax_assets_net_of_valuation_allowance\",\"december_31_2023\":\"$9,882\"}]", "role": "tool" }, { "content": "<tool_call>\n{\...
1,386
1
0.927518
false
false
3
0
40
0
0
train_all
0.927518
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.927518
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I need to calculate the percentage of the valuation allowance relative to total deferred tax assets for 2024 to assess its significance. However, I don't have the 2024 values yet. I will first retrieve the 2024 data to complete this calculation.\n\n<tool_call>\n{\"name\": \"calculator\", \"arguments\": ...
[ { "content": "[10.23240260825949, \"Calculated: (1224/11962) * 100 = 10.23240260825949\"]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"calculator\", \"arguments\": {\"expression\": \"((1224-892)/892) * 100\"}}\n</tool_call>", "role": "assistant" } ]
1,532
1
0.151622
false
false
4
0
40
0
0
train_all
0.151622
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.151622
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "Now that I have the 2024 valuation allowance and total deferred tax assets, I will calculate the percentage change in the valuation allowance from 2023 to 2024. This will provide insight into whether management's assessment of future tax benefits has become more or less conservative.\n\n<tool_call>\n{\"...
[ { "content": "[37.219730941704036, \"Calculated: ((1224-892)/892) * 100 = 37.219730941704036\"]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"calculator\", \"arguments\": {\"expression\": \"(1224/10738) * 100\"}}\n</tool_call>", "role": "assistant" } ]
1,612
1
0.583801
false
false
5
0
40
0
0
train_all
0.583801
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.583801
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I need to calculate the percentage of the valuation allowance relative to total deferred tax assets for 2024. I have the valuation allowance value (1224) but need the total deferred tax assets value for 2024. Based on the previous query, I see that the total deferred tax assets for 2024 are 10,738. I wi...
[ { "content": "[11.398770720804619, \"Calculated: (1224/10738) * 100 = 11.398770720804619\"]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"respond_user\", \"arguments\": {\"text\": \"As of December 31, 2024 Tesla reported total deferred tax assets of $11,962 million and a valuation allo...
1,727
1
1
false
false
6
0
40
0
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I have gathered all necessary data: the valuation allowance amount, total deferred tax assets, and historical comparisons. I've calculated the percentage of the valuation allowance relative to total deferred tax assets and the year-over-year change. Now I will provide a comprehensive and clear response ...
[ { "content": "", "role": "assistant" }, { "content": "", "role": "assistant" } ]
1,867
1
0.110315
true
false
7
0
40
0
0
train_all
0.110315
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.110315
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I need to first get a list of available tables for the company \"meta\" to understand what data is available about their lease financing strategy. This will help identify relevant tables that might contain information about lease financing over time, such as financial statements or capital allocation da...
[ { "content": "[\"srt_ContractualObligationFiscalYearMaturityScheduleTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredTaxAssetsAndLiabilitiesTableTextBlock\", \"us_gaap_ScheduleO...
884
1
1
false
false
0
0
40
1
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "The table \"meta_LeaseBalanceSheetInformationTableTextBlock\" is likely to contain key information about lease liabilities and assets, which directly relates to lease financing. I will retrieve its metadata to understand the columns and data types, to see if it includes data for the years 2022 and 2024....
[ { "content": "{\"description\": \"supplemental_balance_sheet_information_related_to_lease_liabilities\",\"column_names\": [\"item\",\"lease_type\",\"2024\",\"2023\"],\"unique_vals_per_col\": {\"item\": [\"weighted_average_remaining_lease_term\",\"weighted_average_discount_rate\"],\"lease_type\": [\"finance_leas...
1,421
1
1
false
false
1
0
40
1
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I have gathered metadata about the table and now need to retrieve the actual data for lease financing information across the years 2023 and 2024. This will allow me to analyze how lease financing has evolved, particularly in terms of weighted average remaining lease terms and discount rates for finance ...
[ { "content": "Error: You are trying to query without any kind of filters, which is not allowed!", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"sql_query\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"meta_LeaseBalanceSheetInformationTableTextBlock\", \"query\": \"SELEC...
1,267
1
0.740036
false
false
2
0
40
1
0
train_all
0.740036
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.740036
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "The initial query failed because it was attempting to retrieve data without filters, which is not allowed. I now need to add a filter to query only the relevant item, \"weighted_average_remaining_lease_term\", to get specific data about lease terms for finance and operating leases in 2023 and 2024. This...
[ { "content": "[{\"item\":\"weighted_average_remaining_lease_term\",\"lease_type\":\"finance_leases\",\"2024\":\"13.7 years\",\"2023\":\"14.0 years\"},{\"item\":\"weighted_average_remaining_lease_term\",\"lease_type\":\"operating_leases\",\"2024\":\"11.5 years\",\"2023\":\"11.6 years\"}]", "role": "tool" }...
1,270
1
0.998458
false
false
3
0
40
1
0
train_all
0.998458
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.998458
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "Now that I have the weighted average remaining lease terms, I need to examine the weighted average discount rates for both finance and operating leases in 2023 and 2024. This will provide insight into the company's cost of capital and financing preferences, which helps determine their capital allocation...
[ { "content": "[{\"item\":\"weighted_average_discount_rate\",\"lease_type\":\"finance_leases\",\"2024\":\"3.6%\",\"2023\":\"3.4%\"},{\"item\":\"weighted_average_discount_rate\",\"lease_type\":\"operating_leases\",\"2024\":\"3.9%\",\"2023\":\"3.7%\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"...
1,506
1
1
false
false
4
0
40
1
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I now have information about the discount rates for finance and operating leases, but to fully understand the evolution of Meta's lease financing strategy, I should also examine the cash flow information. The \"meta_LeaseCashFlowsInformationTableTextBlock\" table may contain details about lease cash flo...
[ { "content": "{\"description\": \"supplemental_cash_flow_information_related_to_leases_is_as_follows_(in_millions):\",\"column_names\": [\"line_item\",\"2024\",\"2023\",\"2022\"],\"unique_vals_per_col\": {\"line_item\": [\"cash_paid_for_amounts_included_in_the_measurement_of_lease_liabilities:\",\"operating_cas...
1,653
1
0.862408
false
false
5
0
40
1
0
train_all
0.862408
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.862408
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I need to extract the specific cash payments related to lease liabilities for the years 2022, 2023, and 2024. This data will help quantify the actual outflows associated with lease financing, which is essential to understanding the company's capital allocation strategy. The query is now focused on the l...
[ { "content": "[{\"line_item\":\"cash_paid_for_amounts_included_in_the_measurement_of_lease_liabilities:\",\"2024\":\"\",\"2023\":\"\",\"2022\":\"\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"sql_query\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"meta_LeaseCashF...
1,876
1
0.846122
false
false
6
0
40
1
0
train_all
0.846122
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.846122
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "The previous query returned empty values, which suggests that the cash flow data for lease liabilities might not be available in the expected format. To further investigate, I will query the operating cash flows for operating leases for the years 2022, 2023, and 2024. This will help determine if there a...
[ { "content": "[{\"line_item\":\"operating_cash_flows_for_operating_leases(1)\",\"2024\":\"$2,830\",\"2023\":\"$2,233\",\"2022\":\"$1,654\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"sql_query\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"meta_LeaseCashFlowsInfor...
1,930
1
0.797466
false
false
7
0
40
1
0
train_all
0.797466
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.797466
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I now have the operating cash flows for operating leases across the years 2022, 2023, and 2024. To get a complete picture of Meta's lease financing strategy, I need to also retrieve the operating cash flows for finance leases. This will allow me to compare the cash flows associated with finance and oper...
[ { "content": "[{\"line_item\":\"operating_cash_flows_for_finance_leases\",\"2024\":\"$23\",\"2023\":\"$20\",\"2022\":\"$16\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"sql_query\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"meta_LeaseCashFlowsInformationTableTex...
2,145
1
0.912988
false
false
8
0
40
1
0
train_all
0.912988
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.912988
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "Now that I have the operating cash flows for finance leases, I need to retrieve the financing cash flows specifically for finance leases. This data will provide insight into how Meta is managing its financing activities, which is crucial for understanding their capital allocation strategy. This will com...
[ { "content": "[{\"line_item\":\"financing_cash_flows_for_finance_leases\",\"2024\":\"$1,969\",\"2023\":\"$1,058\",\"2022\":\"$850\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"sql_query\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"meta_LeaseCashFlowsInformationT...
2,322
1
1
false
false
9
0
40
1
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I have now retrieved the financing cash flows for finance leases. To complete the analysis, I need to obtain the operating lease cash flows, which will provide a full view of Meta's lease-related cash outflows. This data is essential to compare operating and finance lease activities and understand their...
[ { "content": "[{\"line_item\":\"operating_leases\",\"2024\":\"$3,784\",\"2023\":\"$4,370\",\"2022\":\"$4,366\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"sql_query\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"meta_LeaseCashFlowsInformationTableTextBlock\", \"qu...
2,496
1
0.81233
false
false
10
0
40
1
0
train_all
0.81233
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.81233
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "I have obtained the operating lease cash flows for the years 2022, 2023, and 2024. To complete the analysis, I now need to retrieve the cash flows specifically for finance leases. This data will allow me to compare the total lease-related cash outflows between operating and finance leases, providing a c...
[ { "content": "[{\"line_item\":\"finance_leases\",\"2024\":\"$181\",\"2023\":\"$588\",\"2022\":\"$223\"}]", "role": "tool" }, { "content": "<tool_call>\n{\"name\": \"get_table_info\", \"arguments\": {\"company_name\": \"meta\", \"table_name\": \"us_gaap_LeaseCostTableTextBlock\"}}\n</tool_call>", ...
2,652
1
0.978183
false
false
11
0
40
1
0
train_all
0.978183
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
0.978183
null
[ { "content": "Only execute one tool call at a time. Think and reason step by step. Feel free to iteratively gather data as much as you need to answer the question. Although there is a limit of 30 turns, you can still gather data as much as you need to answer the question. When you have gathered all the data, an...
{ "content": "The query for finance lease cash flows returned data, but I still need to ensure that all aspects of Meta's lease financing strategy are covered. I will now check the \"us_gaap_LeaseCostTableTextBlock\" table to see if it contains additional cost-related information that could help explain capital alloc...
[ { "content": "{\"description\": \"the_components_of_lease_costs_are_as_follows_(in_millions):\",\"column_names\": [\"component\",\"2024\",\"2023\",\"2022\"],\"unique_vals_per_col\": {\"component\": [\"amortization_of_right_of_use_assets\",\"interest\",\"operating_lease_cost\",\"variable_lease_cost_and_other\",\...
2,827
1
1
false
false
12
0
40
1
0
train_all
1
0
true
true
false
[ { "description": "Get a list of possible texts to look up for. Each text contains a singular table that is described by its complete name.", "name": "get_descriptions", "parameters": { "properties": { "company_name": { "description": "The name of the company to get the table name...
1
null
End of preview. Expand in Data Studio

Act-PRM Rollout Dataset

Run Metadata

  • run_name: act-prm-v2-ia=0-rr=0-ec=act_prm_finqa_reasoning_gpt5m-gc=aprm_qwen3_ap-tc=aprm_for_sft100-rbc=default-msl=4096-mc=hf_qwen3_4b_inst_2507-lc=r8_a16_qkvo-nf=0-ao=1-ho=1-eec=finqa_reasoning-mc=1-gs=8-bs=8-lr=4e_05-ns=4-s=1-r=finqa_aprm_1_mc
  • run_cmd: main_pytorch.py --env_config act_prm/finqa_reasoning_gpt5m --eval_env_config finqa/reasoning --model_config hf_qwen3_4b_inst_2507 --lora_config r8_a16_qkvo --generator_config aprm_qwen3_ap --trainer_config aprm_for_sft100 --replay_buffer_config default --log_path ./logs --actions_only --hide_observations --batch_size 8 --group_size 8 --learning_rate 4e-5 --num_substeps 4 --seed 0 --replicate finqa_aprm_1_mc --verbose --seed 1 --max_seq_len 4096 --mean_center
  • batch_idx: 40
  • split: train_all
  • trajectory_key: think_act_policy
  • num_trajectories: 508
  • num_episodes: 508
  • group_size: 8
  • batch_size: 8
Downloads last month
21