Dataset Viewer
Auto-converted to Parquet Duplicate
state
listlengths
2
52
action
dict
next_obs
listlengths
2
2
state_len
int64
874
5.02k
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
99
99
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 find relevant 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 data on tax assets or valuation allowances.\n\n<tool_call>\n{\"na...
[ { "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
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 any valuation allowances. I will retrieve the metadata for this table to understand its structure, including column names and data types, to determine if it i...
[ { "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
99
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 query retrieves specific items related to deferred tax assets and valuation allowances for December 31, 2024. This will provide the necessary data to assess the significance of the valuation allowance and understand its implications for future tax benefits.\n\n<tool_call>\n{\"name\": \"sql_query\", ...
[ { "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...
1,358
1
0.607839
false
false
2
0
99
0
0
train_all
0.607839
0.607839
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...
0.607839
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 and significance of the valuation allowance, I need to compare the valuation allowance for December 31, 2024, with the previous year (2023). This will help determine if the allowance has changed and what that suggests about management's assessment of future tax benefits.\n\n<tool...
[ { "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{\...
1,400
1
0.932032
false
false
3
0
99
0
0
train_all
0.932032
0.932032
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...
0.932032
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 2024. However, I don't have the 2024 values yet. I need to retrieve the 2024 data to perform this calculation.\n\n<tool_call>\n{\"name\": \"calculator\", \"arguments\": {\"expression\": \"(12...
[ { "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" } ]
1,543
1
0.135849
false
false
4
0
99
0
0
train_all
0.135849
0.135849
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...
0.135849
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 I need to calculate the percentage change in the valuation allowance from 2023 to 2024 to understand the trend. This will provide insight into management's assessment of future tax benefits.\n\n<tool_call>\n{\"name\": \"calculator\", \"arguments\": {\"expression\": \"((1224-892)/892) * 100\"}}\n</to...
[ { "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" } ]
1,621
1
0.583801
false
false
5
0
99
0
0
train_all
0.583801
0.583801
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 valuation allowance as a percentage of total deferred tax assets in 2024 to assess its significance. I have the valuation allowance value (1224) and the total deferred tax assets (10738) for 2024. This will give the exact percentage.\n\n<tool_call>\n{\"name\": \"calculator\", \"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...
1,717
1
1
false
false
6
0
99
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 gathered all necessary data: the valuation allowance amount, total deferred tax assets, and changes over time. I have calculated the percentage of the valuation allowance relative to total deferred tax assets and the percentage change from 2023 to 2024. I now have a complete and accurate response...
[ { "content": "", "role": "assistant" }, { "content": "", "role": "assistant" } ]
1,827
1
0.109746
true
false
7
0
99
0
0
train_all
0.109746
0.109746
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...
0.109746
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 financial data, particularly those that might contain information about lease financing and capital allocation. The get_descriptions function will help me find the available tables.\n\n<tool_call>\n{\"name\": \"get_descriptions\", \"argument...
[ { "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
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 \"meta_LeaseBalanceSheetInformationTableTextBlock\" seems most relevant to lease financing strategy as it likely contains balance sheet information about leases. I'll retrieve its metadata to understand the structure of the data, particularly focusing on time-based metrics that might show changes fr...
[ { "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
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 metadata showing that the table contains lease-related data for 2023 and 2024, including weighted average remaining lease terms and discount rates. I'll execute a query to extract the actual data for both years to analyze the evolution of Meta's lease financing strategy.\n\n<tool_call>\n{...
[ { "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...
1,240
1
0.713175
false
false
2
0
99
1
0
train_all
0.713175
0.713175
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...
0.713175
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 because it tried to fetch all data without filters. I now refine the query to specifically target the weighted average remaining lease term, which is a key metric for understanding lease financing strategy. This will allow me to compare the term between 2023 and 2024.\n\n<...
[ { "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" }...
1,239
1
0.827112
false
false
3
0
99
1
0
train_all
0.827112
0.827112
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...
0.827112
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 years to understand if there are changes in financing costs or capital structure preferences. This will provide a more complete picture of Meta's lease financing strategy evolution....
[ { "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{\"...
1,458
1
1
false
false
4
0
99
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 discount rate data for both finance and operating leases. To provide a more comprehensive analysis of Meta's capital allocation, I should also examine cash flow information from the lease cash flows table, which might reveal trends in leasing activity or financial commitments over time. T...
[ { "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...
1,595
1
0.766096
false
false
5
0
99
1
0
train_all
0.766096
0.766096
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...
0.766096
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 cash flow information related to lease liabilities. Specifically, I need to extract the data for \"cash paid for amounts included in the measurement of lease liabilities\" to understand the actual financial outflows related to lease financing. This will provide insight into how Meta's cap...
[ { "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...
1,818
1
0.809179
false
false
6
0
99
1
0
train_all
0.809179
0.809179
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...
0.809179
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 cash payments related to lease liabilities returned empty results. I will now check operating cash flows for operating leases to see if there are any changes in operating lease cash flows that might indicate shifts in capital allocation preferences. This will provide additional context abo...
[ { "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...
1,866
1
0.777777
false
false
7
0
99
1
0
train_all
0.777777
0.777777
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...
0.777777
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 for all three years. To complete the analysis, I need to check the operating cash flows for finance leases to understand if there are any significant changes in finance lease-related cash flows, which would indicate shifts in capital allocation pr...
[ { "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...
2,047
1
0.916717
false
false
8
0
99
1
0
train_all
0.916717
0.916717
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...
0.916717
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. To complete the analysis, I need to check the financing cash flows for finance leases to understand the actual financing activities related to lease liabilities. This will provide a comprehensive view of Meta's capital allocation preferences over t...
[ { "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...
2,197
1
1
false
false
9
0
99
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. To complete the analysis, I need to check the operating leases cash flows to understand the overall lease-related operating activities. This will provide a comprehensive view of Meta's capital allocation preferences over time.\n\n<tool_call>\n{\"na...
[ { "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...
2,363
1
0.814695
false
false
10
0
99
1
0
train_all
0.814695
0.814695
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...
0.814695
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 leases cash flows. To complete the analysis, I need to check the finance leases cash flows to understand the actual financing activities related to lease liabilities. This will provide a comprehensive view of Meta's capital allocation preferences over time.\n\n<tool_call>\n{\"na...
[ { "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>", ...
2,508
1
0.991215
false
false
11
0
99
1
0
train_all
0.991215
0.991215
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...
0.991215
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 finance leases cash flows data shows a significant decrease from $588 in 2023 to $181 in 2024. However, to provide a more complete picture of Meta's capital allocation preferences, I should also examine the lease cost data from the us_gaap_LeaseCostTableTextBlock to understand the actual lease costs...
[ { "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\",\...
2,649
1
1
false
false
12
0
99
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 lease cost components for all years. This will allow me to analyze how the composition of lease costs has changed over time, providing deeper insight into Meta's capital allocation preferences. I will now synthesize all the gathered data to provide a comprehensive answer to the user's que...
[ { "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, \\\...
2,861
1
0.996716
false
false
13
0
99
1
0
train_all
0.996716
0.996716
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...
0.996716
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: 99
  • split: train_all
  • trajectory_key: think_act_policy
  • num_trajectories: 508
  • num_episodes: 508
  • group_size: 8
  • batch_size: 8
Downloads last month
33