Dataset Viewer
Auto-converted to Parquet Duplicate
state
listlengths
2
52
action
dict
next_obs
listlengths
2
2
state_len
int64
874
5.12k
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
90
90
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 first find out which tables are available for Tesla to look for information about valuation allowance for deferred tax assets. The question specifically mentions \"valuation allowance for deferred tax assets\" and \"management's assessment of future tax benefits,\" which are financial metrics ...
[ { "content": "[\"us_gaap_DebtInstrumentRedemptionTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"sla_ScheduleOfAccruedLiabilitiesAndOtherCurrentLiabilitiesTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredT...
891
1
0.852919
false
false
0
0
90
0
0
train_all
0.852919
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...
0.852919
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 valuation allowances. I will retrieve its metadata to understand the columns and data types, which will help in identifying whether there is a valuation allow...
[ { "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\",\"...
1,507
1
1
false
false
1
0
90
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 need to extract specific values related to deferred tax assets and the valuation allowance as of December 31, 2024. The query targets rows with items that include \"valuation_allowance,\" \"total_deferred_tax_assets,\" and related net values to understand the magnitude of the valuation allowance and i...
[ { "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...
1,365
1
0.601973
false
false
2
0
90
0
0
train_all
0.601973
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...
0.601973
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 assess the significance of the valuation allowance and understand management's assessment of future tax benefits, I need to compare the valuation allowance and related deferred tax assets from December 31, 2024, with the prior year (December 31, 2023). This comparison will reveal trends and provide c...
[ { "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{\...
1,429
1
0.924148
false
false
3
0
90
0
0
train_all
0.924148
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...
0.924148
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 as of December 31, 2024. This will quantify the significance of the valuation allowance. I have the values for 2024 from the previous query, but I need to compute the percentage to provide a clear metric....
[ { "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" } ]
1,592
1
0.273773
false
false
4
0
90
0
0
train_all
0.273773
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...
0.273773
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 help determine whether management has become more or less optimistic about future tax benefits. The change is (1224 - 892) divided by the 2023 valuation allowance (892), then multi...
[ { "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" } ]
1,681
1
0.615013
false
false
5
0
90
0
0
train_all
0.615013
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...
0.615013
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 as of December 31, 2023 to provide a historical context for the valuation allowance's significance. This will allow me to compare the 2024 valuation allowance to the 2023 baseline.\n\n<tool_call>\n{\"name...
[ { "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...
1,827
1
0.535261
false
false
6
0
90
0
0
train_all
0.535261
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...
0.535261
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, total deferred tax assets, and changes over time. I have calculated the percentages and the percentage change, which show the significance and trend of the valuation allowance. I now have a complete answer that includes the magnitude, percenta...
[ { "content": "", "role": "assistant" }, { "content": "", "role": "assistant" } ]
1,935
1
0.124154
true
false
7
0
90
0
0
train_all
0.124154
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...
0.124154
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 out what tables are available for Meta to understand their lease financing strategy. Once I have the relevant tables, I can explore the data to determine how their lease financing has changed between 2022 and 2024.\n\n<tool_call>\n{\"name\": \"get_descriptions\", \"arguments\": {\"company...
[ { "content": "[\"srt_ContractualObligationFiscalYearMaturityScheduleTableTextBlock\", \"us_gaap_ScheduleOfComponentsOfIncomeTaxExpenseBenefitTableTextBlock\", \"us_gaap_LesseeOperatingLeaseLiabilityMaturityTableTextBlock\", \"us_gaap_ScheduleOfDeferredTaxAssetsAndLiabilitiesTableTextBlock\", \"us_gaap_ScheduleO...
884
1
0.959189
false
false
0
0
90
1
0
train_all
0.959189
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...
0.959189
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 understanding lease financing strategy. I'll retrieve its structure to see what data it contains, particularly around lease liabilities and cash flows over time.\n\n<tool_call>\n{\"name\": \"get_table_info\", \"arguments\": {...
[ { "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...
1,405
1
1
false
false
1
0
90
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 relevant table. I will execute a query to get the actual data on lease liabilities and their changes between 2023 and 2024, specifically focusing on the weighted average remaining lease term and discount rate for finance and operating leases.\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
0.750533
false
false
2
0
90
1
0
train_all
0.750533
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...
0.750533
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 all data without filters was rejected. I need to narrow down the query to a specific item (weighted average remaining lease term) to get relevant data for 2023 and 2024. This will allow me to analyze how the lease financing strategy has evolved over time.\n\n<tool_call>\n{\"name\":...
[ { "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" }...
1,224
1
0.870325
false
false
3
0
90
1
0
train_all
0.870325
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...
0.870325
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 the weighted average remaining lease term for both finance and operating leases. To fully understand the evolution of Meta's lease financing strategy, I also need to examine the weighted average discount rate for finance leases in 2023 and 2024. This will provide insight into their ca...
[ { "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{\"...
1,443
1
0.998419
false
false
4
0
90
1
0
train_all
0.998419
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...
0.998419
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 the weighted average discount rates for both finance and operating leases. To get a more comprehensive understanding of Meta's lease financing strategy, I should also examine their lease cash flows. I'll retrieve the structure of the \"meta_LeaseCashFlowsInformationTableTextBlock\" ta...
[ { "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...
1,594
1
1
false
false
5
0
90
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 lease cash flows table. I will query specifically for the cash paid for amounts included in the measurement of lease liabilities, as this directly relates to capital allocation in lease financing. This will help me understand how Meta's capital allocation preferences have...
[ { "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...
1,828
1
0.804035
false
false
6
0
90
1
0
train_all
0.804035
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...
0.804035
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 paid for lease liabilities didn't return data, which might indicate that this specific information is not available or is not structured as expected. Instead, I will examine operating cash flows for operating leases, which might provide insight into their capital allocation preference...
[ { "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...
1,872
1
0.808029
false
false
7
0
90
1
0
train_all
0.808029
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...
0.808029
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 operating cash flows for operating leases, which show a clear upward trend from $1,654 in 2022 to $2,830 in 2024. To provide a complete picture of Meta's capital allocation preferences, I should also examine operating cash flows for finance leases, which would give insight into their financin...
[ { "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...
2,065
1
0.914229
false
false
8
0
90
1
0
train_all
0.914229
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...
0.914229
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 operating cash flows for finance leases, which show a very small amount over the years. To complete the analysis, I need to get the financing cash flows for finance leases, which will provide insight into how Meta is allocating capital through lease financing. This will allow me to understand...
[ { "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...
2,239
1
1
false
false
9
0
90
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 financing cash flows for finance leases, which show a clear increase from $850 in 2022 to $1,969 in 2024. This indicates a growing reliance on lease financing. To complete the analysis, I need to examine operating leases data to understand the overall capital allocation strategy. This wil...
[ { "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...
2,415
1
0.841167
false
false
10
0
90
1
0
train_all
0.841167
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...
0.841167
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 data, which shows a slight decrease from $4,366 in 2022 to $3,784 in 2024. This indicates a shift in capital allocation. To complete the analysis, I need to get the financing cash flows for finance leases, which will provide a complete picture of Meta's capital allocation...
[ { "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>", ...
2,595
1
0.891628
false
false
11
0
90
1
0
train_all
0.891628
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...
0.891628
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 gathered all the necessary data points regarding Meta's lease financing strategy between 2022 and 2024. However, to ensure a comprehensive understanding of their capital allocation preferences, I should also examine the lease cost data from the \"us_gaap_LeaseCostTableTextBlock\" to see how l...
[ { "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\",\...
2,791
1
1
false
false
12
0
90
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: 90
  • split: train_all
  • trajectory_key: think_act_policy
  • num_trajectories: 508
  • num_episodes: 508
  • group_size: 8
  • batch_size: 8
Downloads last month
29