初始化项目，由ModelHub XC社区提供模型
Model: Jihyung803/Qwen3-8B-SOCIALIQA-DPO Source: Original Platform
This commit is contained in:
ModelHub XC
28
checkpoint-400/added_tokens.json
Normal file
28
checkpoint-400/added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
89
checkpoint-400/chat_template.jinja
Normal file
89
checkpoint-400/chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
checkpoint-400/config.json
Normal file
68
checkpoint-400/config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"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",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
checkpoint-400/generation_config.json
Normal file
12
checkpoint-400/generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
checkpoint-400/merges.txt
Normal file
151388
checkpoint-400/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-400/model-00001-of-00004.safetensors
Normal file
3
checkpoint-400/model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fe48ba4546232baf1ab54f67e9b3e99cc0a7872cde23c678a675217eb84646a
|
||||
size 4902257696
|
||||
3
checkpoint-400/model-00002-of-00004.safetensors
Normal file
3
checkpoint-400/model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ce90c5862ce03dc9096b4096850b697b1fc1aa0188506a93fa8ea2f288e70a48
|
||||
size 4915960368
|
||||
3
checkpoint-400/model-00003-of-00004.safetensors
Normal file
3
checkpoint-400/model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42d7a88beb574df1e939a36884bc0603b4afe1486ccaf5aea0a7d880f6e1ee2d
|
||||
size 4983068496
|
||||
3
checkpoint-400/model-00004-of-00004.safetensors
Normal file
3
checkpoint-400/model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13f92316beff9a11f33dab85e510a23a33375c6735614aaa015ac55380beadad
|
||||
size 1580230264
|
||||
407
checkpoint-400/model.safetensors.index.json
Normal file
407
checkpoint-400/model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8190735360,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
checkpoint-400/optimizer.pt
Normal file
3
checkpoint-400/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:061060811136fa2d8599ffe83d562d41bae32e2180282805fc940b99694ae92d
|
||||
size 12049845371
|
||||
3
checkpoint-400/rng_state.pth
Normal file
3
checkpoint-400/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
|
||||
size 14645
|
||||
3
checkpoint-400/scheduler.pt
Normal file
3
checkpoint-400/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:84ae6a10bd78366a08bd66e628bf1ff3adc4b383c2aacf4eec4e03bb420c0ab0
|
||||
size 1465
|
||||
31
checkpoint-400/special_tokens_map.json
Normal file
31
checkpoint-400/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
checkpoint-400/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoint-400/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
checkpoint-400/tokenizer_config.json
Normal file
239
checkpoint-400/tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"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": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"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
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
698
checkpoint-400/trainer_state.json
Normal file
698
checkpoint-400/trainer_state.json
Normal file
@@ -0,0 +1,698 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.8065532451165721,
|
||||
"eval_steps": 100,
|
||||
"global_step": 400,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.020163831127914304,
|
||||
"grad_norm": 15.5,
|
||||
"learning_rate": 3e-08,
|
||||
"logits/chosen": -0.4867519736289978,
|
||||
"logits/rejected": 0.7175194621086121,
|
||||
"logps/chosen": -30.936298370361328,
|
||||
"logps/rejected": -33.71613311767578,
|
||||
"loss": 0.6928,
|
||||
"rewards/accuracies": 0.4234375059604645,
|
||||
"rewards/chosen": 0.0013589367736130953,
|
||||
"rewards/margins": 0.0008156307740136981,
|
||||
"rewards/rejected": 0.0005433057667687535,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04032766225582861,
|
||||
"grad_norm": 14.75,
|
||||
"learning_rate": 6.333333333333333e-08,
|
||||
"logits/chosen": -0.42843765020370483,
|
||||
"logits/rejected": 0.7893258929252625,
|
||||
"logps/chosen": -30.931198120117188,
|
||||
"logps/rejected": -33.70547866821289,
|
||||
"loss": 0.6923,
|
||||
"rewards/accuracies": 0.546875,
|
||||
"rewards/chosen": 0.0024414127692580223,
|
||||
"rewards/margins": 0.0018455162644386292,
|
||||
"rewards/rejected": 0.0005958965630270541,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06049149338374291,
|
||||
"grad_norm": 13.5,
|
||||
"learning_rate": 9.666666666666666e-08,
|
||||
"logits/chosen": -0.4219973087310791,
|
||||
"logits/rejected": 0.6850587725639343,
|
||||
"logps/chosen": -30.893016815185547,
|
||||
"logps/rejected": -33.663429260253906,
|
||||
"loss": 0.6918,
|
||||
"rewards/accuracies": 0.5453125238418579,
|
||||
"rewards/chosen": 0.004747429862618446,
|
||||
"rewards/margins": 0.0027347125578671694,
|
||||
"rewards/rejected": 0.0020127175375819206,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.08065532451165722,
|
||||
"grad_norm": 15.125,
|
||||
"learning_rate": 1.3e-07,
|
||||
"logits/chosen": -0.46360141038894653,
|
||||
"logits/rejected": 0.7466679215431213,
|
||||
"logps/chosen": -30.849849700927734,
|
||||
"logps/rejected": -33.69337463378906,
|
||||
"loss": 0.6893,
|
||||
"rewards/accuracies": 0.6812499761581421,
|
||||
"rewards/chosen": 0.009496917016804218,
|
||||
"rewards/margins": 0.007778028957545757,
|
||||
"rewards/rejected": 0.001718888757750392,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10081915563957151,
|
||||
"grad_norm": 14.3125,
|
||||
"learning_rate": 1.6333333333333331e-07,
|
||||
"logits/chosen": -0.5125963091850281,
|
||||
"logits/rejected": 0.7158086895942688,
|
||||
"logps/chosen": -30.67547607421875,
|
||||
"logps/rejected": -33.68535232543945,
|
||||
"loss": 0.6864,
|
||||
"rewards/accuracies": 0.75,
|
||||
"rewards/chosen": 0.015847254544496536,
|
||||
"rewards/margins": 0.013664955273270607,
|
||||
"rewards/rejected": 0.002182298805564642,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.12098298676748583,
|
||||
"grad_norm": 15.25,
|
||||
"learning_rate": 1.9666666666666665e-07,
|
||||
"logits/chosen": -0.5598157644271851,
|
||||
"logits/rejected": 0.6922208070755005,
|
||||
"logps/chosen": -30.706085205078125,
|
||||
"logps/rejected": -33.59804153442383,
|
||||
"loss": 0.6824,
|
||||
"rewards/accuracies": 0.824999988079071,
|
||||
"rewards/chosen": 0.02341878041625023,
|
||||
"rewards/margins": 0.02176792547106743,
|
||||
"rewards/rejected": 0.0016508543631061912,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.14114681789540012,
|
||||
"grad_norm": 13.5625,
|
||||
"learning_rate": 2.3e-07,
|
||||
"logits/chosen": -0.5082000494003296,
|
||||
"logits/rejected": 0.6696754693984985,
|
||||
"logps/chosen": -30.65346908569336,
|
||||
"logps/rejected": -33.60075378417969,
|
||||
"loss": 0.6784,
|
||||
"rewards/accuracies": 0.84375,
|
||||
"rewards/chosen": 0.03311777114868164,
|
||||
"rewards/margins": 0.02995235286653042,
|
||||
"rewards/rejected": 0.003165417117998004,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.16131064902331443,
|
||||
"grad_norm": 16.125,
|
||||
"learning_rate": 2.633333333333333e-07,
|
||||
"logits/chosen": -0.48689335584640503,
|
||||
"logits/rejected": 0.7162936925888062,
|
||||
"logps/chosen": -30.42413330078125,
|
||||
"logps/rejected": -33.7276611328125,
|
||||
"loss": 0.6722,
|
||||
"rewards/accuracies": 0.871874988079071,
|
||||
"rewards/chosen": 0.042802099138498306,
|
||||
"rewards/margins": 0.04268326610326767,
|
||||
"rewards/rejected": 0.0001188320602523163,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.18147448015122875,
|
||||
"grad_norm": 15.0625,
|
||||
"learning_rate": 2.966666666666667e-07,
|
||||
"logits/chosen": -0.6490235328674316,
|
||||
"logits/rejected": 0.663810670375824,
|
||||
"logps/chosen": -30.447296142578125,
|
||||
"logps/rejected": -33.84953689575195,
|
||||
"loss": 0.6663,
|
||||
"rewards/accuracies": 0.8843749761581421,
|
||||
"rewards/chosen": 0.05355549976229668,
|
||||
"rewards/margins": 0.05490420013666153,
|
||||
"rewards/rejected": -0.0013486887328326702,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.20163831127914303,
|
||||
"grad_norm": 14.6875,
|
||||
"learning_rate": 3.3e-07,
|
||||
"logits/chosen": -0.6071578860282898,
|
||||
"logits/rejected": 0.6672302484512329,
|
||||
"logps/chosen": -30.24630355834961,
|
||||
"logps/rejected": -33.704193115234375,
|
||||
"loss": 0.6589,
|
||||
"rewards/accuracies": 0.8812500238418579,
|
||||
"rewards/chosen": 0.06409426033496857,
|
||||
"rewards/margins": 0.07057920843362808,
|
||||
"rewards/rejected": -0.006484942976385355,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20163831127914303,
|
||||
"eval_logits/chosen": -0.8155572414398193,
|
||||
"eval_logits/rejected": 0.4097934663295746,
|
||||
"eval_logps/chosen": -30.2824764251709,
|
||||
"eval_logps/rejected": -33.65603256225586,
|
||||
"eval_loss": 0.656726062297821,
|
||||
"eval_rewards/accuracies": 0.8702152967453003,
|
||||
"eval_rewards/chosen": 0.06777840107679367,
|
||||
"eval_rewards/margins": 0.0754016563296318,
|
||||
"eval_rewards/rejected": -0.007623251993209124,
|
||||
"eval_runtime": 44.5266,
|
||||
"eval_samples_per_second": 37.506,
|
||||
"eval_steps_per_second": 9.388,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.22180214240705734,
|
||||
"grad_norm": 15.5,
|
||||
"learning_rate": 3.6333333333333333e-07,
|
||||
"logits/chosen": -0.6406155824661255,
|
||||
"logits/rejected": 0.6143032312393188,
|
||||
"logps/chosen": -30.176578521728516,
|
||||
"logps/rejected": -33.91298294067383,
|
||||
"loss": 0.6486,
|
||||
"rewards/accuracies": 0.8999999761581421,
|
||||
"rewards/chosen": 0.07676664739847183,
|
||||
"rewards/margins": 0.09246878325939178,
|
||||
"rewards/rejected": -0.0157021377235651,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.24196597353497165,
|
||||
"grad_norm": 16.5,
|
||||
"learning_rate": 3.9666666666666665e-07,
|
||||
"logits/chosen": -0.6949701905250549,
|
||||
"logits/rejected": 0.5297445058822632,
|
||||
"logps/chosen": -30.219324111938477,
|
||||
"logps/rejected": -33.860145568847656,
|
||||
"loss": 0.639,
|
||||
"rewards/accuracies": 0.871874988079071,
|
||||
"rewards/chosen": 0.0840606540441513,
|
||||
"rewards/margins": 0.11379051208496094,
|
||||
"rewards/rejected": -0.02972986176609993,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.26212980466288593,
|
||||
"grad_norm": 15.875,
|
||||
"learning_rate": 4.2999999999999996e-07,
|
||||
"logits/chosen": -0.8164470791816711,
|
||||
"logits/rejected": 0.4915032386779785,
|
||||
"logps/chosen": -29.9921817779541,
|
||||
"logps/rejected": -34.11717224121094,
|
||||
"loss": 0.6243,
|
||||
"rewards/accuracies": 0.871874988079071,
|
||||
"rewards/chosen": 0.09985624253749847,
|
||||
"rewards/margins": 0.14640672504901886,
|
||||
"rewards/rejected": -0.04655047133564949,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.28229363579080025,
|
||||
"grad_norm": 17.25,
|
||||
"learning_rate": 4.633333333333333e-07,
|
||||
"logits/chosen": -0.8576955795288086,
|
||||
"logits/rejected": 0.475827693939209,
|
||||
"logps/chosen": -29.987823486328125,
|
||||
"logps/rejected": -34.64146041870117,
|
||||
"loss": 0.606,
|
||||
"rewards/accuracies": 0.8687499761581421,
|
||||
"rewards/chosen": 0.10108546912670135,
|
||||
"rewards/margins": 0.1895439326763153,
|
||||
"rewards/rejected": -0.08845846354961395,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.30245746691871456,
|
||||
"grad_norm": 15.75,
|
||||
"learning_rate": 4.966666666666666e-07,
|
||||
"logits/chosen": -0.9962993860244751,
|
||||
"logits/rejected": 0.2535431385040283,
|
||||
"logps/chosen": -30.001697540283203,
|
||||
"logps/rejected": -34.91169357299805,
|
||||
"loss": 0.5907,
|
||||
"rewards/accuracies": 0.8609374761581421,
|
||||
"rewards/chosen": 0.0953492671251297,
|
||||
"rewards/margins": 0.23015904426574707,
|
||||
"rewards/rejected": -0.13480977714061737,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.32262129804662887,
|
||||
"grad_norm": 19.5,
|
||||
"learning_rate": 4.869942196531791e-07,
|
||||
"logits/chosen": -1.1013362407684326,
|
||||
"logits/rejected": 0.16825838387012482,
|
||||
"logps/chosen": -30.271495819091797,
|
||||
"logps/rejected": -35.96307373046875,
|
||||
"loss": 0.558,
|
||||
"rewards/accuracies": 0.8812500238418579,
|
||||
"rewards/chosen": 0.07991272956132889,
|
||||
"rewards/margins": 0.3163560628890991,
|
||||
"rewards/rejected": -0.23644332587718964,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3427851291745432,
|
||||
"grad_norm": 20.0,
|
||||
"learning_rate": 4.7254335260115607e-07,
|
||||
"logits/chosen": -1.3539522886276245,
|
||||
"logits/rejected": -0.050642382353544235,
|
||||
"logps/chosen": -30.70322608947754,
|
||||
"logps/rejected": -36.963932037353516,
|
||||
"loss": 0.5439,
|
||||
"rewards/accuracies": 0.854687511920929,
|
||||
"rewards/chosen": 0.04025987908244133,
|
||||
"rewards/margins": 0.3653072416782379,
|
||||
"rewards/rejected": -0.3250473737716675,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.3629489603024575,
|
||||
"grad_norm": 19.375,
|
||||
"learning_rate": 4.5809248554913295e-07,
|
||||
"logits/chosen": -1.5499536991119385,
|
||||
"logits/rejected": -0.12814846634864807,
|
||||
"logps/chosen": -30.65024185180664,
|
||||
"logps/rejected": -38.008567810058594,
|
||||
"loss": 0.5077,
|
||||
"rewards/accuracies": 0.878125011920929,
|
||||
"rewards/chosen": 0.030102571472525597,
|
||||
"rewards/margins": 0.46569380164146423,
|
||||
"rewards/rejected": -0.4355912208557129,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.38311279143037175,
|
||||
"grad_norm": 21.75,
|
||||
"learning_rate": 4.436416184971098e-07,
|
||||
"logits/chosen": -1.6617387533187866,
|
||||
"logits/rejected": -0.32283174991607666,
|
||||
"logps/chosen": -30.94146156311035,
|
||||
"logps/rejected": -39.50160598754883,
|
||||
"loss": 0.4704,
|
||||
"rewards/accuracies": 0.895312488079071,
|
||||
"rewards/chosen": 0.004333639983087778,
|
||||
"rewards/margins": 0.5781550407409668,
|
||||
"rewards/rejected": -0.5738214254379272,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.40327662255828606,
|
||||
"grad_norm": 14.6875,
|
||||
"learning_rate": 4.291907514450867e-07,
|
||||
"logits/chosen": -1.791582703590393,
|
||||
"logits/rejected": -0.44964680075645447,
|
||||
"logps/chosen": -31.526784896850586,
|
||||
"logps/rejected": -39.81529998779297,
|
||||
"loss": 0.4811,
|
||||
"rewards/accuracies": 0.864062488079071,
|
||||
"rewards/chosen": -0.03861772269010544,
|
||||
"rewards/margins": 0.56865394115448,
|
||||
"rewards/rejected": -0.607271671295166,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.40327662255828606,
|
||||
"eval_logits/chosen": -1.988352656364441,
|
||||
"eval_logits/rejected": -0.7473806738853455,
|
||||
"eval_logps/chosen": -31.514951705932617,
|
||||
"eval_logps/rejected": -40.30702209472656,
|
||||
"eval_loss": 0.4655759632587433,
|
||||
"eval_rewards/accuracies": 0.8690191507339478,
|
||||
"eval_rewards/chosen": -0.05546921119093895,
|
||||
"eval_rewards/margins": 0.6172530651092529,
|
||||
"eval_rewards/rejected": -0.6727222204208374,
|
||||
"eval_runtime": 44.074,
|
||||
"eval_samples_per_second": 37.891,
|
||||
"eval_steps_per_second": 9.484,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.42344045368620037,
|
||||
"grad_norm": 17.875,
|
||||
"learning_rate": 4.1473988439306354e-07,
|
||||
"logits/chosen": -1.9743998050689697,
|
||||
"logits/rejected": -0.7126643061637878,
|
||||
"logps/chosen": -31.816967010498047,
|
||||
"logps/rejected": -40.79069519042969,
|
||||
"loss": 0.4591,
|
||||
"rewards/accuracies": 0.879687488079071,
|
||||
"rewards/chosen": -0.06654059141874313,
|
||||
"rewards/margins": 0.6414004564285278,
|
||||
"rewards/rejected": -0.7079410552978516,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.4436042848141147,
|
||||
"grad_norm": 15.875,
|
||||
"learning_rate": 4.002890173410404e-07,
|
||||
"logits/chosen": -1.9798154830932617,
|
||||
"logits/rejected": -0.7139844298362732,
|
||||
"logps/chosen": -32.13506317138672,
|
||||
"logps/rejected": -41.47466278076172,
|
||||
"loss": 0.4525,
|
||||
"rewards/accuracies": 0.8656250238418579,
|
||||
"rewards/chosen": -0.0931621789932251,
|
||||
"rewards/margins": 0.6879409551620483,
|
||||
"rewards/rejected": -0.7811031341552734,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.463768115942029,
|
||||
"grad_norm": 20.0,
|
||||
"learning_rate": 3.8583815028901736e-07,
|
||||
"logits/chosen": -2.0034127235412598,
|
||||
"logits/rejected": -0.7428504228591919,
|
||||
"logps/chosen": -31.648120880126953,
|
||||
"logps/rejected": -42.38803482055664,
|
||||
"loss": 0.4149,
|
||||
"rewards/accuracies": 0.893750011920929,
|
||||
"rewards/chosen": -0.07446546852588654,
|
||||
"rewards/margins": 0.8017433285713196,
|
||||
"rewards/rejected": -0.8762086629867554,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.4839319470699433,
|
||||
"grad_norm": 18.25,
|
||||
"learning_rate": 3.713872832369942e-07,
|
||||
"logits/chosen": -2.0142064094543457,
|
||||
"logits/rejected": -0.9079702496528625,
|
||||
"logps/chosen": -32.108821868896484,
|
||||
"logps/rejected": -43.06040954589844,
|
||||
"loss": 0.4058,
|
||||
"rewards/accuracies": 0.8890625238418579,
|
||||
"rewards/chosen": -0.10588344186544418,
|
||||
"rewards/margins": 0.8354071378707886,
|
||||
"rewards/rejected": -0.941290557384491,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.5040957781978576,
|
||||
"grad_norm": 16.5,
|
||||
"learning_rate": 3.5693641618497107e-07,
|
||||
"logits/chosen": -2.275698184967041,
|
||||
"logits/rejected": -1.122511863708496,
|
||||
"logps/chosen": -32.408470153808594,
|
||||
"logps/rejected": -43.69465255737305,
|
||||
"loss": 0.4089,
|
||||
"rewards/accuracies": 0.875,
|
||||
"rewards/chosen": -0.13990476727485657,
|
||||
"rewards/margins": 0.8530368804931641,
|
||||
"rewards/rejected": -0.992941677570343,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.5242596093257719,
|
||||
"grad_norm": 13.9375,
|
||||
"learning_rate": 3.4248554913294795e-07,
|
||||
"logits/chosen": -2.2892613410949707,
|
||||
"logits/rejected": -1.177565336227417,
|
||||
"logps/chosen": -32.277252197265625,
|
||||
"logps/rejected": -44.352439880371094,
|
||||
"loss": 0.3905,
|
||||
"rewards/accuracies": 0.8687499761581421,
|
||||
"rewards/chosen": -0.13188917934894562,
|
||||
"rewards/margins": 0.9304295778274536,
|
||||
"rewards/rejected": -1.0623188018798828,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.5444234404536862,
|
||||
"grad_norm": 16.875,
|
||||
"learning_rate": 3.2803468208092484e-07,
|
||||
"logits/chosen": -2.309782028198242,
|
||||
"logits/rejected": -1.1110422611236572,
|
||||
"logps/chosen": -32.4368896484375,
|
||||
"logps/rejected": -44.47226333618164,
|
||||
"loss": 0.3876,
|
||||
"rewards/accuracies": 0.8734375238418579,
|
||||
"rewards/chosen": -0.14435531198978424,
|
||||
"rewards/margins": 0.945163369178772,
|
||||
"rewards/rejected": -1.0895185470581055,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.5645872715816005,
|
||||
"grad_norm": 20.0,
|
||||
"learning_rate": 3.135838150289017e-07,
|
||||
"logits/chosen": -2.4775633811950684,
|
||||
"logits/rejected": -1.2171634435653687,
|
||||
"logps/chosen": -31.85956382751465,
|
||||
"logps/rejected": -44.78974151611328,
|
||||
"loss": 0.3722,
|
||||
"rewards/accuracies": 0.893750011920929,
|
||||
"rewards/chosen": -0.10046832263469696,
|
||||
"rewards/margins": 1.0068700313568115,
|
||||
"rewards/rejected": -1.107338309288025,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5847511027095148,
|
||||
"grad_norm": 15.3125,
|
||||
"learning_rate": 2.991329479768786e-07,
|
||||
"logits/chosen": -2.3516058921813965,
|
||||
"logits/rejected": -1.2547065019607544,
|
||||
"logps/chosen": -32.33803939819336,
|
||||
"logps/rejected": -44.54314422607422,
|
||||
"loss": 0.3877,
|
||||
"rewards/accuracies": 0.8734375238418579,
|
||||
"rewards/chosen": -0.1320447474718094,
|
||||
"rewards/margins": 0.960769534111023,
|
||||
"rewards/rejected": -1.0928142070770264,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.6049149338374291,
|
||||
"grad_norm": 14.3125,
|
||||
"learning_rate": 2.846820809248555e-07,
|
||||
"logits/chosen": -2.5609071254730225,
|
||||
"logits/rejected": -1.3568521738052368,
|
||||
"logps/chosen": -31.781259536743164,
|
||||
"logps/rejected": -45.361305236816406,
|
||||
"loss": 0.3534,
|
||||
"rewards/accuracies": 0.8968750238418579,
|
||||
"rewards/chosen": -0.0874972864985466,
|
||||
"rewards/margins": 1.0803875923156738,
|
||||
"rewards/rejected": -1.1678849458694458,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.6049149338374291,
|
||||
"eval_logits/chosen": -2.652808666229248,
|
||||
"eval_logits/rejected": -1.5094201564788818,
|
||||
"eval_logps/chosen": -32.167049407958984,
|
||||
"eval_logps/rejected": -45.16587829589844,
|
||||
"eval_loss": 0.37229523062705994,
|
||||
"eval_rewards/accuracies": 0.8755980730056763,
|
||||
"eval_rewards/chosen": -0.12067891657352448,
|
||||
"eval_rewards/margins": 1.0379289388656616,
|
||||
"eval_rewards/rejected": -1.158607840538025,
|
||||
"eval_runtime": 44.3186,
|
||||
"eval_samples_per_second": 37.682,
|
||||
"eval_steps_per_second": 9.432,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.6250787649653434,
|
||||
"grad_norm": 12.125,
|
||||
"learning_rate": 2.7023121387283236e-07,
|
||||
"logits/chosen": -2.574951410293579,
|
||||
"logits/rejected": -1.4039162397384644,
|
||||
"logps/chosen": -32.359107971191406,
|
||||
"logps/rejected": -45.18638229370117,
|
||||
"loss": 0.3833,
|
||||
"rewards/accuracies": 0.870312511920929,
|
||||
"rewards/chosen": -0.12439367920160294,
|
||||
"rewards/margins": 1.0330053567886353,
|
||||
"rewards/rejected": -1.1573989391326904,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.6452425960932577,
|
||||
"grad_norm": 16.125,
|
||||
"learning_rate": 2.5578034682080925e-07,
|
||||
"logits/chosen": -2.5044591426849365,
|
||||
"logits/rejected": -1.4151450395584106,
|
||||
"logps/chosen": -32.13268280029297,
|
||||
"logps/rejected": -45.22514343261719,
|
||||
"loss": 0.3719,
|
||||
"rewards/accuracies": 0.875,
|
||||
"rewards/chosen": -0.11237072944641113,
|
||||
"rewards/margins": 1.047181487083435,
|
||||
"rewards/rejected": -1.1595523357391357,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.665406427221172,
|
||||
"grad_norm": 15.0,
|
||||
"learning_rate": 2.4132947976878613e-07,
|
||||
"logits/chosen": -2.631962776184082,
|
||||
"logits/rejected": -1.3861881494522095,
|
||||
"logps/chosen": -31.74435043334961,
|
||||
"logps/rejected": -45.44641876220703,
|
||||
"loss": 0.3586,
|
||||
"rewards/accuracies": 0.885937511920929,
|
||||
"rewards/chosen": -0.074491485953331,
|
||||
"rewards/margins": 1.1014248132705688,
|
||||
"rewards/rejected": -1.1759161949157715,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.6855702583490864,
|
||||
"grad_norm": 16.0,
|
||||
"learning_rate": 2.26878612716763e-07,
|
||||
"logits/chosen": -2.5997676849365234,
|
||||
"logits/rejected": -1.4487764835357666,
|
||||
"logps/chosen": -31.48516845703125,
|
||||
"logps/rejected": -45.57600021362305,
|
||||
"loss": 0.3413,
|
||||
"rewards/accuracies": 0.903124988079071,
|
||||
"rewards/chosen": -0.054619044065475464,
|
||||
"rewards/margins": 1.1495531797409058,
|
||||
"rewards/rejected": -1.2041722536087036,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.7057340894770007,
|
||||
"grad_norm": 12.9375,
|
||||
"learning_rate": 2.1242774566473987e-07,
|
||||
"logits/chosen": -2.581223726272583,
|
||||
"logits/rejected": -1.451586127281189,
|
||||
"logps/chosen": -31.826080322265625,
|
||||
"logps/rejected": -45.72737503051758,
|
||||
"loss": 0.3609,
|
||||
"rewards/accuracies": 0.879687488079071,
|
||||
"rewards/chosen": -0.08685452491044998,
|
||||
"rewards/margins": 1.1219041347503662,
|
||||
"rewards/rejected": -1.2087585926055908,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.725897920604915,
|
||||
"grad_norm": 14.125,
|
||||
"learning_rate": 1.9797687861271675e-07,
|
||||
"logits/chosen": -2.6039886474609375,
|
||||
"logits/rejected": -1.593008279800415,
|
||||
"logps/chosen": -32.02338790893555,
|
||||
"logps/rejected": -45.7207145690918,
|
||||
"loss": 0.3591,
|
||||
"rewards/accuracies": 0.8812500238418579,
|
||||
"rewards/chosen": -0.09107818454504013,
|
||||
"rewards/margins": 1.1208597421646118,
|
||||
"rewards/rejected": -1.2119379043579102,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.7460617517328293,
|
||||
"grad_norm": 14.3125,
|
||||
"learning_rate": 1.8352601156069363e-07,
|
||||
"logits/chosen": -2.6979289054870605,
|
||||
"logits/rejected": -1.5796029567718506,
|
||||
"logps/chosen": -31.300853729248047,
|
||||
"logps/rejected": -45.72681427001953,
|
||||
"loss": 0.3522,
|
||||
"rewards/accuracies": 0.878125011920929,
|
||||
"rewards/chosen": -0.03190985321998596,
|
||||
"rewards/margins": 1.1756919622421265,
|
||||
"rewards/rejected": -1.20760178565979,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.7662255828607435,
|
||||
"grad_norm": 10.875,
|
||||
"learning_rate": 1.690751445086705e-07,
|
||||
"logits/chosen": -2.669769525527954,
|
||||
"logits/rejected": -1.4769527912139893,
|
||||
"logps/chosen": -30.98702049255371,
|
||||
"logps/rejected": -46.33720779418945,
|
||||
"loss": 0.3226,
|
||||
"rewards/accuracies": 0.90625,
|
||||
"rewards/chosen": -0.009888170287013054,
|
||||
"rewards/margins": 1.2525317668914795,
|
||||
"rewards/rejected": -1.2624199390411377,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.7863894139886578,
|
||||
"grad_norm": 12.5,
|
||||
"learning_rate": 1.546242774566474e-07,
|
||||
"logits/chosen": -2.6219515800476074,
|
||||
"logits/rejected": -1.4883930683135986,
|
||||
"logps/chosen": -31.58437156677246,
|
||||
"logps/rejected": -46.32578659057617,
|
||||
"loss": 0.348,
|
||||
"rewards/accuracies": 0.875,
|
||||
"rewards/chosen": -0.05657508969306946,
|
||||
"rewards/margins": 1.205727458000183,
|
||||
"rewards/rejected": -1.2623026371002197,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.8065532451165721,
|
||||
"grad_norm": 13.4375,
|
||||
"learning_rate": 1.4017341040462428e-07,
|
||||
"logits/chosen": -2.6918234825134277,
|
||||
"logits/rejected": -1.4419605731964111,
|
||||
"logps/chosen": -31.05796241760254,
|
||||
"logps/rejected": -45.93518829345703,
|
||||
"loss": 0.3322,
|
||||
"rewards/accuracies": 0.8890625238418579,
|
||||
"rewards/chosen": -0.011668933555483818,
|
||||
"rewards/margins": 1.2215235233306885,
|
||||
"rewards/rejected": -1.2331925630569458,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.8065532451165721,
|
||||
"eval_logits/chosen": -2.7881991863250732,
|
||||
"eval_logits/rejected": -1.6745110750198364,
|
||||
"eval_logps/chosen": -31.51004981994629,
|
||||
"eval_logps/rejected": -45.77407455444336,
|
||||
"eval_loss": 0.3527255356311798,
|
||||
"eval_rewards/accuracies": 0.8761961460113525,
|
||||
"eval_rewards/chosen": -0.05497899651527405,
|
||||
"eval_rewards/margins": 1.164448618888855,
|
||||
"eval_rewards/rejected": -1.219427466392517,
|
||||
"eval_runtime": 43.521,
|
||||
"eval_samples_per_second": 38.372,
|
||||
"eval_steps_per_second": 9.605,
|
||||
"step": 400
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 496,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 100,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-400/training_args.bin
Normal file
3
checkpoint-400/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:692c0137546b29ea74e61694d9a4044c44abed927ae8ed2b420027636ef57b56
|
||||
size 6865
|
||||
1
checkpoint-400/vocab.json
Normal file
1
checkpoint-400/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user