Dataset Viewer
Auto-converted to Parquet Duplicate
state
listlengths
2
52
action
dict
next_obs
listlengths
2
2
state_len
int64
874
5.38k
temperature
float64
1
1
reward
float64
0.08
1
done
bool
2 classes
truncated
bool
1 class
timestep
int64
0
25
try_step
int64
0
0
batch_id
int64
80
80
unique_data_sample_id
int64
0
31
generation_id
int64
0
0
split
stringclasses
1 value
return_
float64
0.08
1
advantage
float64
0.08
1
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
0.08
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 first identify the relevant tables related to Tesla that might contain information about valuation allowances for deferred tax assets. The initial step is to get a list of table descriptions for Tesla to find one that specifically relates to financial statements or tax assets.\n\n<tool_call>\n...
[ { "content": "[\"us_gaap_DebtInstrumentRedemptionTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"sla_ScheduleOfAccruedLiabilitiesAndOtherCurrentLiabilitiesTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredT...
891
1
1
false
false
0
0
80
0
0
train_all
1
1
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 most likely to contain information about deferred tax assets and liabilities, including any valuation allowances. I need to retrieve the metadata of this table to understand its structure and identify columns related to val...
[ { "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\",\"...
1,500
1
1
false
false
1
0
80
0
0
train_all
1
1
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 identified that the table contains relevant information about deferred tax assets and valuation allowances. I will now query the specific rows related to the valuation allowance and net deferred tax assets to get the exact figures for December 31, 2024. This will allow me to assess the significan...
[ { "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...
1,352
1
0.592321
false
false
2
0
80
0
0
train_all
0.592321
0.592321
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...
0.592321
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 retrieved the valuation allowance and net deferred tax assets for December 31, 2024. To better understand the trend and management's assessment of future tax benefits, I should also check the corresponding figures from the previous year (December 31, 2023). This will help determine if the valuati...
[ { "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{\...
1,418
1
0.936567
false
false
3
0
80
0
0
train_all
0.936567
0.936567
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...
0.936567
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 significance of the valuation allowance as a percentage of total deferred tax assets for December 31, 2024. This will provide a clear metric to assess how substantial the valuation allowance is relative to the total deferred tax assets. The calculation is (valuation_allowance / t...
[ { "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" } ]
1,573
1
0.372084
false
false
4
0
80
0
0
train_all
0.372084
0.372084
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...
0.372084
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 change in the valuation allowance from December 31, 2023 to December 31, 2024. This will show whether the valuation allowance has increased or decreased, indicating management's changing assessment of future tax benefits. The formula is ((valuation_allowance_2024 - val...
[ { "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" } ]
1,668
1
0.581778
false
false
5
0
80
0
0
train_all
0.581778
0.581778
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...
0.581778
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 valuation allowance as a percentage of total deferred tax assets for December 31, 2023 to provide a historical context. This will allow me to compare the significance of the valuation allowance across years. The formula is (valuation_allowance / total_deferred_tax_assets) * 100.\...
[ { "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...
1,816
1
0.390865
false
false
6
0
80
0
0
train_all
0.390865
0.390865
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...
0.390865
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 collected all necessary data points: the valuation allowance and total deferred tax assets for both 2023 and 2024, calculated the percentages, and determined the percentage change. I now have a complete picture of the significance of the valuation allowance and its implications for management's v...
[ { "content": "", "role": "assistant" }, { "content": "", "role": "assistant" } ]
1,929
1
0.127795
true
false
7
0
80
0
0
train_all
0.127795
0.127795
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...
0.127795
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 identify the relevant tables related to Meta's lease financing strategy. By retrieving the descriptions of available texts (tables) for Meta, I can find which ones might contain information about leasing or financing activities over time, particularly from 2022 to 2024.\n\n<tool_call>\n{...
[ { "content": "[\"srt_ContractualObligationFiscalYearMaturityScheduleTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredTaxAssetsAndLiabilitiesTableTextBlock\", \"us_gaap_ScheduleO...
884
1
0.994065
false
false
0
0
80
1
0
train_all
0.994065
0.994065
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...
0.994065
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 data about Meta's lease liabilities and related financials over time. I should examine its structure to understand how lease financing has evolved, particularly in terms of balance sheet components such as lease liabi...
[ { "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...
1,413
1
0.976629
false
false
1
0
80
1
0
train_all
0.976629
0.976629
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...
0.976629
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 structure of the table, so I will retrieve the actual data to analyze how lease financing has evolved between 2022 and 2024. Specifically, I want to compare the weighted average remaining lease terms and discount rates for both finance and operating leases in 2023 and 2024.\n\n<tool_call>...
[ { "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...
1,268
1
0.730972
false
false
2
0
80
1
0
train_all
0.730972
0.730972
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...
0.730972
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 was rejected due to attempting to retrieve all data without filters. I now need to filter the data to focus on the specific item \"weighted_average_remaining_lease_term\" to understand changes in lease terms over time. This will allow me to analyze the evolution of Meta's lease financi...
[ { "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" }...
1,277
1
0.996918
false
false
3
0
80
1
0
train_all
0.996918
0.996918
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...
0.996918
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 fully understand Meta's capital allocation preferences, I need to examine the weighted average discount rates for both finance and operating leases in 2023 and 2024. This will provide insight into how the company values future lease obligations and whether their financing strategy reflects a preferen...
[ { "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{\"...
1,496
1
1
false
false
4
0
80
1
0
train_all
1
1
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 discount rates for finance leases have slightly increased from 3.4% in 2023 to 3.6% in 2024, and for operating leases from 3.7% to 3.9%. This suggests Meta is placing a slightly higher valuation on future lease cash flows, which could indicate a more conservative capital allocation strategy. However...
[ { "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...
1,647
1
0.96764
false
false
5
0
80
1
0
train_all
0.96764
0.96764
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...
0.96764
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 need to examine the cash payments related to lease liabilities to understand how Meta's financing strategy has evolved in terms of capital outflows. Specifically, I will focus on the cash payments for amounts included in the measurement of lease liabilities, which can provide insight into how the ...
[ { "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...
1,930
1
0.827972
false
false
6
0
80
1
0
train_all
0.827972
0.827972
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...
0.827972
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 results, possibly due to a mismatch in the line item naming. I will now check the operating cash flows for operating leases to determine if there are any changes in how Meta reports its operating lease cash flows over the years 2022, 2023, and 2024. This will help clari...
[ { "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...
1,971
1
0.771153
false
false
7
0
80
1
0
train_all
0.771153
0.771153
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...
0.771153
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 operating cash flows for operating leases have increased significantly from $1,654 in 2022 to $2,830 in 2024, indicating a growing emphasis on operating lease activities. To provide a complete picture, I should also check the finance lease cash flows to understand if there's a corresponding shift in...
[ { "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...
2,178
1
0.842657
false
false
8
0
80
1
0
train_all
0.842657
0.842657
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...
0.842657
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 finance leases, which are minimal. To understand the full picture of Meta's lease financing strategy, I need to examine the financing cash flows for finance leases as well. This will help determine if the company is actively using finance leases as a capital alloc...
[ { "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...
2,369
1
1
false
false
9
0
80
1
0
train_all
1
1
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 the financing cash flows for finance leases, which show a significant increase from $850 in 2022 to $1,969 in 2024. To complete the analysis, I will check the operating lease cash flows to ensure that the data is comprehensive and to understand if there's a clear shift in capital allocation p...
[ { "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...
2,579
1
0.799445
false
false
10
0
80
1
0
train_all
0.799445
0.799445
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...
0.799445
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 lease cash flows, which show a slight decrease from $4,370 in 2023 to $3,784 in 2024. To complete the analysis, I will check the financing cash flows for finance leases to ensure that all relevant data points are included. This will provide a comprehensive view of how Meta's lea...
[ { "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>", ...
2,773
1
0.92366
false
false
11
0
80
1
0
train_all
0.92366
0.92366
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...
0.92366
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 data on financing cash flows for finance leases shows a significant increase from $850 in 2022 to $1,969 in 2024, indicating a growing use of finance leases as a capital allocation tool. However, the operating lease cash flows have decreased slightly. To fully understand the implications of this shi...
[ { "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\",\...
2,976
1
1
false
false
12
0
80
1
0
train_all
1
1
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-gs=8-bs=8-lr=4e_05-ns=4-s=1-r=finqa_aprm_0
  • 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_0 --verbose --seed 1 --max_seq_len 4096
  • batch_idx: 80
  • split: train_all
  • trajectory_key: think_act_policy
  • num_trajectories: 508
  • num_episodes: 508
  • group_size: 8
  • batch_size: 8
Downloads last month
37