Dataset Viewer
Auto-converted to Parquet Duplicate
state
listlengths
2
52
action
dict
next_obs
listlengths
2
2
state_len
int64
874
5.1k
temperature
float64
1
1
reward
float64
0.1
1
done
bool
2 classes
truncated
bool
1 class
timestep
int64
0
25
try_step
int64
0
0
batch_id
int64
99
99
unique_data_sample_id
int64
0
31
generation_id
int64
0
0
split
stringclasses
1 value
return_
float64
0.1
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
0.1
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 tables related to Tesla that might contain information about valuation allowances for deferred tax assets. First, I'll retrieve a list of possible table names for Tesla to identify which one might contain financial statements or tax-related data.\n\n<tool_call>\n{\"name\": \"get_descripti...
[ { "content": "[\"us_gaap_DebtInstrumentRedemptionTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"sla_ScheduleOfAccruedLiabilitiesAndOtherCurrentLiabilitiesTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredT...
891
1
1
false
false
0
0
99
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 most 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 va...
[ { "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\",\"...
1,497
1
1
false
false
1
0
99
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 identified that the \"valuation_allowance\" is a relevant column in the table. I will query the specific values for the valuation allowance and related deferred tax assets as of December 31, 2024, to assess its significance and understand management's view on future tax benefits.\n\n<tool_call>\n...
[ { "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...
1,351
1
0.558236
false
false
2
0
99
0
0
train_all
0.558236
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...
0.558236
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 understand the trend, I will check the valuation allowance and related metrics for the previous year (December 31, 2023). This will help determine whether the valuation allowance has increased or decreased over time, providing context for management's assessment of future tax benefits.\n\n<tool_call>...
[ { "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{\...
1,405
1
0.941125
false
false
3
0
99
0
0
train_all
0.941125
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...
0.941125
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. The values for December 31, 2024, are not directly available in the previous query, so I must first retrieve them to compute this percentage. I will now retrieve the Decemb...
[ { "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" } ]
1,542
1
0.148215
false
false
4
0
99
0
0
train_all
0.148215
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...
0.148215
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 calculate the percentage change in the valuation allowance from December 31, 2023 to December 31, 2024. This will provide insight into management's assessment of future tax benefits. The valuation allowance increased from $892 million to $1,224 million, so I will compute the percentage cha...
[ { "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" } ]
1,654
1
0.784228
false
false
5
0
99
0
0
train_all
0.784228
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...
0.784228
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 compute the valuation allowance as a percentage of total deferred tax assets for December 31, 2024. The total deferred tax assets for that date are $10,738 million. I will now calculate this percentage to determine how significant the valuation allowance is relative to the total deferred tax a...
[ { "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...
1,787
1
1
false
false
6
0
99
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 the necessary data: the valuation allowance amount, the total deferred tax assets, the percentage of the allowance relative to total assets, and the percentage change from the prior year. I can now summarize the findings to answer the user's question about the significance of the val...
[ { "content": "", "role": "assistant" }, { "content": "", "role": "assistant" } ]
1,899
1
0.108464
true
false
7
0
99
0
0
train_all
0.108464
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...
0.108464
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. The initial step is to get a list of table descriptions for Meta to understand what data is available regarding leasing or financial strategies.\n\n<tool_call>\n{\"name\": \"get_descriptions\", \"arguments\": {\"com...
[ { "content": "[\"srt_ContractualObligationFiscalYearMaturityScheduleTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredTaxAssetsAndLiabilitiesTableTextBlock\", \"us_gaap_ScheduleO...
884
1
1
false
false
0
0
99
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 information about Meta's lease obligations and their balance sheet impact, which would be essential to understanding their lease financing strategy. I need to check its structure to see what data it contains.\n\n<tool_cal...
[ { "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...
1,395
1
1
false
false
1
0
99
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 the structure of the table, so I will retrieve the actual data to analyze the evolution of Meta's lease financing strategy between 2022 and 2024. Since the data is in the table, I will query it directly to get the values for each item and lease type across the years.\n\n<tool_call>\n{\"name\"...
[ { "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...
1,228
1
0.76252
false
false
2
0
99
1
0
train_all
0.76252
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...
0.76252
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 to retrieve the entire table was rejected due to inefficiency. I will now narrow the scope by focusing on a specific item, \"weighted_average_remaining_lease_term,\" which might provide insight into the company's lease financing strategy over time. This targeted query should return relevant da...
[ { "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" }...
1,233
1
0.998458
false
false
3
0
99
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": "To gain a more comprehensive understanding of Meta's lease financing strategy, I should also examine the weighted average discount rate, which influences the financial impact of lease obligations. This will help determine if changes in financing strategy are driven by shifts in discount rates or other f...
[ { "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{\"...
1,459
1
1
false
false
4
0
99
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 previous data on discount rates is useful, but to fully understand the evolution of Meta's lease financing strategy, I should also look into cash flow information. I will now retrieve the structure of the \"meta_LeaseCashFlowsInformationTableTextBlock\" to see what data it contains regarding lease-r...
[ { "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...
1,597
1
1
false
false
5
0
99
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 the structure of the cash flow table and will extract specific line items related to cash paid for lease liabilities. This information will help clarify how Meta's lease financing strategy has evolved in terms of actual cash outflows over the years, providing a more complete picture of their ...
[ { "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...
1,826
1
0.874653
false
false
6
0
99
1
0
train_all
0.874653
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...
0.874653
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 specific cash flow line item for operating cash flows related to operating leases is not providing data. I need to check if there are other relevant line items that could provide insight into Meta's lease financing strategy. I will query for a different, more specific line item that might contain us...
[ { "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...
1,862
1
0.719681
false
false
7
0
99
1
0
train_all
0.719681
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...
0.719681
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 data on operating cash flows for operating leases, which shows an increase from $1,654 in 2022 to $2,830 in 2024. To fully understand Meta's capital allocation preferences, I need to also examine cash flows related to finance leases. This will provide a more complete picture of how Meta's lea...
[ { "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...
2,051
1
0.91051
false
false
8
0
99
1
0
train_all
0.91051
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...
0.91051
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 finance leases are minimal, so I need to check if there are any significant financing cash flows related to finance leases. This will help determine if Meta's capital allocation is shifting toward long-term financing or operational leasing. I will query for the specific line...
[ { "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...
2,229
1
1
false
false
9
0
99
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 data on financing cash flows for finance leases shows a positive trend, increasing from $850 in 2022 to $1,969 in 2024. However, to get a complete picture of Meta's lease financing strategy, I need to also examine the overall operating lease cash flows. This will help understand the balance between ...
[ { "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...
2,406
1
0.837507
false
false
10
0
99
1
0
train_all
0.837507
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...
0.837507
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 lease cash flows have shown a slight decrease from 2023 to 2024, which might indicate a shift in operational leasing activities. To fully understand the evolution of Meta's lease financing strategy, I need to examine the cash flows specifically for finance leases. This will provide insight...
[ { "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>", ...
2,592
1
0.983954
false
false
11
0
99
1
0
train_all
0.983954
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...
0.983954
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 finance lease cash flows shows a significant decrease from 2023 to 2024, which might indicate a shift in strategy. However, to provide a more comprehensive answer, I should also check if there are other relevant tables, such as the \"us_gaap_LeaseCostTableTextBlock,\" which might contain add...
[ { "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\",\...
2,768
1
1
false
false
12
0
99
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 access to the detailed components of lease costs, which will provide a more granular view of Meta's lease financing strategy. By examining the amortization, interest, and other cost components, I can determine if changes in financing are driven by shifts in operational costs or interest expen...
[ { "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\": \"us_gaap_LeaseCostTableTextBlock\", \"query\": \"SELECT component, \\\...
2,993
1
0.993443
false
false
13
0
99
1
0
train_all
0.993443
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...
0.993443
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: 99
  • split: train_all
  • trajectory_key: think_act_policy
  • num_trajectories: 508
  • num_episodes: 508
  • group_size: 8
  • batch_size: 8
Downloads last month
13