diff --git a/.gitattributes b/.gitattributes index 480f7474a13dff5f6a79136f05e5cb62d0d3d98f..36865112c0f3854526f2d1e5fbdba3d1680e369e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -82,3 +82,9 @@ models/Qwen2.5-Math-1.5B-Instruct-20250924_015412/mathevo-grpo-verl-concept-enha models/Qwen2.5-Math-1.5B-Instruct-20250924_015412/mathevo-grpo-verl-concept-enhanced/Qwen2.5-Math-1.5B-Instruct-20250924_015412/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-origin-10epochs-20250918_195851/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text models/deepmath-1.5b-grpo-origin-10epochs-20250918_195851/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_24_fa8e76fd376449198672ced79428c670.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_24_fa8e76fd376449198672ced79428c670.json new file mode 100644 index 0000000000000000000000000000000000000000..e0aeab551afbd90917615ee64aa8e026f36addce --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_24_fa8e76fd376449198672ced79428c670.json @@ -0,0 +1,28 @@ +{ + "null": [ + 0.25, + 0.5, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5 + ] +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_48_fe09a28a889c411c96fd86516ead1d0e.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_48_fe09a28a889c411c96fd86516ead1d0e.json new file mode 100644 index 0000000000000000000000000000000000000000..c571413e68d207fc6cab396ee9f78db92e95098f --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_48_fe09a28a889c411c96fd86516ead1d0e.json @@ -0,0 +1,52 @@ +{ + "null": [ + 0.25, + 0.5, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.25, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.25, + 0.25, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25 + ] +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_72_e634e8ab652d441ca03b53a7364caf18.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_72_e634e8ab652d441ca03b53a7364caf18.json new file mode 100644 index 0000000000000000000000000000000000000000..dcab429af2c257efea8e6c0d73aca24971340b6f --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_72_e634e8ab652d441ca03b53a7364caf18.json @@ -0,0 +1,76 @@ +{ + "null": [ + 0.25, + 0.5, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.5, + 0.25, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.5, + 0.25, + 0.25, + 0.25, + 0.5, + 0.5, + 0.25, + 0.5, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.5, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.5, + 0.5, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.25, + 0.5, + 0.5, + 0.5, + 0.5, + 0.25, + 0.25, + 0.5, + 0.25 + ] +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_24_d357672360bc4362a55fbbad2fa53885.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_24_d357672360bc4362a55fbbad2fa53885.json new file mode 100644 index 0000000000000000000000000000000000000000..9bcd50c21279dc1ce2fd1a427e477c940e7ea15f --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_24_d357672360bc4362a55fbbad2fa53885.json @@ -0,0 +1,28 @@ +{ + "null": { + "1": 0.25, + "2": 0.5, + "3": 0.5, + "4": 0.5, + "5": 0.25, + "6": 0.5, + "7": 0.5, + "8": 0.5, + "9": 0.5, + "10": 0.5, + "11": 0.5, + "12": 0.25, + "13": 0.5, + "14": 0.5, + "15": 0.25, + "16": 0.5, + "17": 0.25, + "18": 0.5, + "19": 0.5, + "20": 0.5, + "21": 0.5, + "22": 0.5, + "23": 0.5, + "24": 0.5 + } +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_48_b89a77750ae247119a175d40a0f96679.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_48_b89a77750ae247119a175d40a0f96679.json new file mode 100644 index 0000000000000000000000000000000000000000..ee79684832629f32ca47bdac1b6031c71b4b1da6 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_48_b89a77750ae247119a175d40a0f96679.json @@ -0,0 +1,52 @@ +{ + "null": { + "1": 0.25, + "2": 0.5, + "3": 0.5, + "4": 0.5, + "5": 0.25, + "6": 0.5, + "7": 0.5, + "8": 0.5, + "9": 0.5, + "10": 0.5, + "11": 0.5, + "12": 0.25, + "13": 0.5, + "14": 0.5, + "15": 0.25, + "16": 0.5, + "17": 0.25, + "18": 0.5, + "19": 0.5, + "20": 0.5, + "21": 0.5, + "22": 0.5, + "23": 0.5, + "24": 0.5, + "25": 0.5, + "26": 0.5, + "27": 0.25, + "28": 0.25, + "29": 0.5, + "30": 0.5, + "31": 0.25, + "32": 0.5, + "33": 0.5, + "34": 0.25, + "35": 0.25, + "36": 0.25, + "37": 0.5, + "38": 0.5, + "39": 0.25, + "40": 0.5, + "41": 0.25, + "42": 0.25, + "43": 0.25, + "44": 0.25, + "45": 0.25, + "46": 0.25, + "47": 0.25, + "48": 0.25 + } +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_72_0edebf091ebf48d0b712eb2c88dfd652.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_72_0edebf091ebf48d0b712eb2c88dfd652.json new file mode 100644 index 0000000000000000000000000000000000000000..efcb49ea97b5d7ea1593ad94c82086af5d6237cb --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/acc_step_with_step_72_0edebf091ebf48d0b712eb2c88dfd652.json @@ -0,0 +1,76 @@ +{ + "null": { + "1": 0.25, + "2": 0.5, + "3": 0.5, + "4": 0.5, + "5": 0.25, + "6": 0.5, + "7": 0.5, + "8": 0.5, + "9": 0.5, + "10": 0.5, + "11": 0.5, + "12": 0.25, + "13": 0.5, + "14": 0.5, + "15": 0.25, + "16": 0.5, + "17": 0.25, + "18": 0.5, + "19": 0.5, + "20": 0.5, + "21": 0.5, + "22": 0.5, + "23": 0.5, + "24": 0.5, + "25": 0.5, + "26": 0.5, + "27": 0.25, + "28": 0.25, + "29": 0.5, + "30": 0.5, + "31": 0.25, + "32": 0.5, + "33": 0.5, + "34": 0.25, + "35": 0.25, + "36": 0.25, + "37": 0.5, + "38": 0.5, + "39": 0.25, + "40": 0.5, + "41": 0.25, + "42": 0.25, + "43": 0.25, + "44": 0.25, + "45": 0.25, + "46": 0.25, + "47": 0.25, + "48": 0.25, + "49": 0.5, + "50": 0.25, + "51": 0.25, + "52": 0.25, + "53": 0.25, + "54": 0.25, + "55": 0.25, + "56": 0.5, + "57": 0.5, + "58": 0.25, + "59": 0.25, + "60": 0.25, + "61": 0.25, + "62": 0.25, + "63": 0.25, + "64": 0.25, + "65": 0.5, + "66": 0.5, + "67": 0.5, + "68": 0.5, + "69": 0.25, + "70": 0.25, + "71": 0.5, + "72": 0.25 + } +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_24_0be5b91f00884cdb82d2516ed84d482b.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_24_0be5b91f00884cdb82d2516ed84d482b.json new file mode 100644 index 0000000000000000000000000000000000000000..36335802c1ec67666818d82c2f23110a1a83c6bc --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_24_0be5b91f00884cdb82d2516ed84d482b.json @@ -0,0 +1,7 @@ +{ + "math_mcq": { + "0": 0.5675675675675675, + "10": 0.5405405405405406, + "20": 0.5675675675675675 + } +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_48_5567b7ee3dd643aa97b75068195c0b80.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_48_5567b7ee3dd643aa97b75068195c0b80.json new file mode 100644 index 0000000000000000000000000000000000000000..09d37dcef2e4baeffdace3304247572c6dae6d8b --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_48_5567b7ee3dd643aa97b75068195c0b80.json @@ -0,0 +1,9 @@ +{ + "math_mcq": { + "0": 0.5675675675675675, + "10": 0.5405405405405406, + "20": 0.5675675675675675, + "30": 0.5855855855855856, + "40": 0.5675675675675675 + } +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_72_1d513f5e57284a1fabd90296dd488846.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_72_1d513f5e57284a1fabd90296dd488846.json new file mode 100644 index 0000000000000000000000000000000000000000..842b81bcefb0b2659e31a3ee79f5cd0c24bedeac --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/accuracy/val_acc_source_with_step_72_1d513f5e57284a1fabd90296dd488846.json @@ -0,0 +1,12 @@ +{ + "math_mcq": { + "0": 0.5675675675675675, + "10": 0.5405405405405406, + "20": 0.5675675675675675, + "30": 0.5855855855855856, + "40": 0.5675675675675675, + "50": 0.46846846846846846, + "60": 0.5045045045045045, + "70": 0.6306306306306306 + } +} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "embd_pdrop": 0.0, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/extra_state_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/extra_state_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..d36cbde7064f3590cf22434a01d438e98b36ec1a --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/extra_state_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce6bc1b9a54eecbd4cd45043e5da3564a856ec611d13a6262f266f4a136c4c5 +size 14632 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/extra_state_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/extra_state_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..27a1f506fada060c5bcb15780e6816c04085b8e8 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/extra_state_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb830797774a9ae24b80eea6c883bcc7cecca1731329b7b38fae8f902eb3bb1 +size 14632 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/generation_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "eos_token_id": 151643, + "pad_token_id": 151643, + "transformers_version": "4.55.4" +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "embd_pdrop": 0.0, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/huggingface/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model-00001-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..896b9ab13714ba0a6cbbac19bf3b3d470044c5a7 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c005d9c82278ec3c8ac3da1bcd5874c6a33a60c275c1142d0199e90eb90ae19 +size 4996670464 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model-00002-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2103812b5ad4aa4fe40d41317b6dc518f9b7ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0185f60f4416c10856cc401eb4edac2b109eef458dff5c19babfa913858c1e2 +size 2111719976 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model.safetensors.index.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_parameters": 888544000, + "total_size": 7108352000 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f7c1a8c41429886bd9f1be7931d889ffe2f6487 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40bdf5690d7eb2221f2e4dbce34eb7f741c06b60ddee83517a7cbcc164a369c +size 3554364602 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3471630a2dd92a0497cb8ac30817a542ab91a6d --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/model_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3eb20c7c844d0b12d1d6d786734359adc99e77ba0b4cb37a5c738c14f24b6e1 +size 3554364602 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/optim_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/optim_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..64fc6593d266498649126a6553632ce95a25991f --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/optim_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80517ee77ca8e3e0e5474c152d3e6de1693f187533fdc77231f0ac6e51bce3d +size 7108378739 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/optim_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/optim_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbd61213cb1cb54a2fbe846c326e72678b6b26de --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/optim_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741cf52a376c6a510dfa96a85206e422bd4d8fb915f95198dcda67ddb5d47cce +size 7108378739 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/actor/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/data.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb9ef95e3602226ac6663f33fec9357d9c1ec722 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3adc30950e92556e672d48265a0c6e030a3867af92c61c493906822e2b379c +size 6948493 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/training_state.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/training_state.json new file mode 100644 index 0000000000000000000000000000000000000000..418f9655752e16299d164484e92213692e04dfbc --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_24/training_state.json @@ -0,0 +1 @@ +{"history_accuracy": {"null": [0.25, 0.5, 0.5, 0.5, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.25, 0.5, 0.5, 0.25, 0.5, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5]}, "history_accuracy_with_step": {"null": {"1": 0.25, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.25, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.25, "13": 0.5, "14": 0.5, "15": 0.25, "16": 0.5, "17": 0.25, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.5, "23": 0.5, "24": 0.5}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5675675675675675, "10": 0.5405405405405406, "20": 0.5675675675675675}}} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "embd_pdrop": 0.0, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/extra_state_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/extra_state_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..28f11ca1dacd10e1ce5844a9dcb93d386f95469a --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/extra_state_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d98874d507c60b111626e74011ef2120528e92e6f5145af01c9a8099dab2e07 +size 14632 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/extra_state_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/extra_state_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb2ad48e49689e6e172269ee70942b6ba6313364 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/extra_state_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a38afc6779225e1702ffb506b7139dbdcbc3722cd8987ce466c6f3945ae7ac +size 14632 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/generation_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "eos_token_id": 151643, + "pad_token_id": 151643, + "transformers_version": "4.55.4" +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "embd_pdrop": 0.0, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/huggingface/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model-00001-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..612e86772918eea16faea64aaaf5ff76b5a52320 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be67d68f63914d249a5c7745d5be0a1eb0f551d7c8f4168dd8c8faa1bf3c7b0 +size 4996670464 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model-00002-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c4ab1b429394a91cedd6953f2b5216d17d47d9c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca6d45441ea9fa849debcde3a2b99c07a9c23995166aeec3957491e5ac3da30 +size 2111719976 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model.safetensors.index.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_parameters": 888544000, + "total_size": 7108352000 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6ab4e301c74b1e776669b75ff6ef0bb4d6bace3 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba78c856f8c7ac822e04d20d233fbb63a0c1d78c89f86847a58cb7b87c2d6f8 +size 3554364602 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c9e58c0b35997da43b50348ac010593bfd787c8 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/model_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9659b27cdc41aa96d65a114ca7ce1f6f6eb5bec15242fb78387da674e2fcb62d +size 3554364602 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/optim_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/optim_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f6b42810d573eb72e72c541e2e5096b817dc888 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/optim_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0615f6f0f4d374e5776d772c4cef2172e00efd17f99fc07e5860d3839466083b +size 7108378739 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/optim_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/optim_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3cb3e8af5f719850e642c19e0544aa504b3e103 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/optim_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837f1c1afb4bd333ccd9667588a4fae8396f36b6177edf9f7d26d5e0cff8c75c +size 7108378739 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/actor/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/data.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..2060d758febf404fab718a76d303b839c5b0c003 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deadada4e14cffeb8fa749641d20a3652f4e8bbc2bd6fa40c3032047c9c74d70 +size 6948493 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/training_state.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/training_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ec07339419ae0444a6df69c73ac65b7be341582c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_48/training_state.json @@ -0,0 +1 @@ +{"history_accuracy": {"null": [0.25, 0.5, 0.5, 0.5, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.25, 0.5, 0.5, 0.25, 0.5, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.25, 0.25, 0.5, 0.5, 0.25, 0.5, 0.5, 0.25, 0.25, 0.25, 0.5, 0.5, 0.25, 0.5, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25]}, "history_accuracy_with_step": {"null": {"1": 0.25, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.25, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.25, "13": 0.5, "14": 0.5, "15": 0.25, "16": 0.5, "17": 0.25, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.5, "23": 0.5, "24": 0.5, "25": 0.5, "26": 0.5, "27": 0.25, "28": 0.25, "29": 0.5, "30": 0.5, "31": 0.25, "32": 0.5, "33": 0.5, "34": 0.25, "35": 0.25, "36": 0.25, "37": 0.5, "38": 0.5, "39": 0.25, "40": 0.5, "41": 0.25, "42": 0.25, "43": 0.25, "44": 0.25, "45": 0.25, "46": 0.25, "47": 0.25, "48": 0.25}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5675675675675675, "10": 0.5405405405405406, "20": 0.5675675675675675, "30": 0.5855855855855856, "40": 0.5675675675675675}}} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "embd_pdrop": 0.0, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/extra_state_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/extra_state_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..84f65fed68ef4d5344dce2548a5c333097c71206 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/extra_state_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59c247eabd522902cd30ac4ea1d396d91d49a9fa897a4b22a0e4f9bae155609 +size 14632 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/extra_state_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/extra_state_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb5ad950a7f4d46e8ad6ef591ee5b1c10a2d2d0b --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/extra_state_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6c69af1c879140b789bece187f5353cb38e3f698e5e64b70bb8b758ee81706 +size 14632 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/generation_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "eos_token_id": 151643, + "pad_token_id": 151643, + "transformers_version": "4.55.4" +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "embd_pdrop": 0.0, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.55.4", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/huggingface/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model-00001-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3afbaf52f4348cd1461915b2f12949b859383191 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2da10ff14a5bf91396f38b7267fd18aa66e66b1cfd3440f2239f67224294e8 +size 4996670464 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model-00002-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0495780805c3bf2627526693212441115337359d --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b78db500c7ba253c504cf3180c4364a846d592f59b9c4fd9de14cf34828a689 +size 2111719976 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model.safetensors.index.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_parameters": 888544000, + "total_size": 7108352000 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a18ca42989cc9fad72a8522d01206eb25c80baf --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207b126b80b1f64605779058578a1eca02ae47e8ff45272c198619d495e0cd06 +size 3554364602 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..371dfbfa47adadaa5e57e166f54fd36127d3f9a8 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/model_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde0bf2f631d601f83f59b16a28770068758f9f96a6b8b8ee0038ed110635d2b +size 3554364602 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/optim_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/optim_world_size_2_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..81fc2cf7b9c12052c24ba4a13d78d601d27f4d57 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/optim_world_size_2_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5db4996d8ca3aecbc2a3e3579900dea92cccef7b26d862be731dba49403f742 +size 7108378739 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/optim_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/optim_world_size_2_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..037776562dd65b75b1ece0d35d8c6160e0894800 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/optim_world_size_2_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d84a26fed1d1485b8efb1b35e8b6077c62c6b22ec4cf1db58b8b60e5966fb0 +size 7108378739 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/data.pt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..828b12f4ddd5fdbd37b9594b0bb54a524a09cc55 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f772a46c4ad13212c319576680a8d025aff7420153dd57a0fb259c3e801f08 +size 6948493 diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/training_state.json b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/training_state.json new file mode 100644 index 0000000000000000000000000000000000000000..471ba4c2d27c27a51207636f9ab4e1cc49fe9154 --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/training_state.json @@ -0,0 +1 @@ +{"history_accuracy": {"null": [0.25, 0.5, 0.5, 0.5, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.25, 0.5, 0.5, 0.25, 0.5, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.25, 0.25, 0.5, 0.5, 0.25, 0.5, 0.5, 0.25, 0.25, 0.25, 0.5, 0.5, 0.25, 0.5, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.5, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.5, 0.5, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.5, 0.5, 0.5, 0.5, 0.25, 0.25, 0.5, 0.25]}, "history_accuracy_with_step": {"null": {"1": 0.25, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.25, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.25, "13": 0.5, "14": 0.5, "15": 0.25, "16": 0.5, "17": 0.25, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.5, "23": 0.5, "24": 0.5, "25": 0.5, "26": 0.5, "27": 0.25, "28": 0.25, "29": 0.5, "30": 0.5, "31": 0.25, "32": 0.5, "33": 0.5, "34": 0.25, "35": 0.25, "36": 0.25, "37": 0.5, "38": 0.5, "39": 0.25, "40": 0.5, "41": 0.25, "42": 0.25, "43": 0.25, "44": 0.25, "45": 0.25, "46": 0.25, "47": 0.25, "48": 0.25, "49": 0.5, "50": 0.25, "51": 0.25, "52": 0.25, "53": 0.25, "54": 0.25, "55": 0.25, "56": 0.5, "57": 0.5, "58": 0.25, "59": 0.25, "60": 0.25, "61": 0.25, "62": 0.25, "63": 0.25, "64": 0.25, "65": 0.5, "66": 0.5, "67": 0.5, "68": 0.5, "69": 0.25, "70": 0.25, "71": 0.5, "72": 0.25}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5675675675675675, "10": 0.5405405405405406, "20": 0.5675675675675675, "30": 0.5855855855855856, "40": 0.5675675675675675, "50": 0.46846846846846846, "60": 0.5045045045045045, "70": 0.6306306306306306}}} \ No newline at end of file diff --git a/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/latest_checkpointed_iteration.txt b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..9cd72aa941214d4cb8522dda34eb12cf878e3e8b --- /dev/null +++ b/models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +72 \ No newline at end of file