Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +154 -0
- config.json +119 -0
- generation_config.json +12 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1034 -0
- preprocessor_config.json +21 -0
- tokenizer.json +3 -0
- tokenizer_config.json +305 -0
- trainer_state.json +1294 -0
- training_args.bin +3 -0
- video_preprocessor_config.json +21 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 248056,
|
| 6 |
+
"model_type": "qwen3_5_moe",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attn_output_gate": true,
|
| 11 |
+
"bos_token_id": 248044,
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": 248044,
|
| 14 |
+
"full_attention_interval": 4,
|
| 15 |
+
"head_dim": 256,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 2048,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"layer_types": [
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"full_attention"
|
| 60 |
+
],
|
| 61 |
+
"linear_conv_kernel_dim": 4,
|
| 62 |
+
"linear_key_head_dim": 128,
|
| 63 |
+
"linear_num_key_heads": 16,
|
| 64 |
+
"linear_num_value_heads": 32,
|
| 65 |
+
"linear_value_head_dim": 128,
|
| 66 |
+
"mamba_ssm_dtype": "float32",
|
| 67 |
+
"max_position_embeddings": 262144,
|
| 68 |
+
"model_type": "qwen3_5_moe_text",
|
| 69 |
+
"moe_intermediate_size": 512,
|
| 70 |
+
"mtp_num_hidden_layers": 1,
|
| 71 |
+
"mtp_use_dedicated_embeddings": false,
|
| 72 |
+
"num_attention_heads": 16,
|
| 73 |
+
"num_experts": 256,
|
| 74 |
+
"num_experts_per_tok": 8,
|
| 75 |
+
"num_hidden_layers": 40,
|
| 76 |
+
"num_key_value_heads": 2,
|
| 77 |
+
"output_router_logits": false,
|
| 78 |
+
"pad_token_id": null,
|
| 79 |
+
"partial_rotary_factor": 0.25,
|
| 80 |
+
"rms_norm_eps": 1e-06,
|
| 81 |
+
"rope_parameters": {
|
| 82 |
+
"mrope_interleaved": true,
|
| 83 |
+
"mrope_section": [
|
| 84 |
+
11,
|
| 85 |
+
11,
|
| 86 |
+
10
|
| 87 |
+
],
|
| 88 |
+
"partial_rotary_factor": 0.25,
|
| 89 |
+
"rope_theta": 10000000,
|
| 90 |
+
"rope_type": "default"
|
| 91 |
+
},
|
| 92 |
+
"router_aux_loss_coef": 0.001,
|
| 93 |
+
"shared_expert_intermediate_size": 512,
|
| 94 |
+
"tie_word_embeddings": false,
|
| 95 |
+
"use_cache": true,
|
| 96 |
+
"vocab_size": 248320
|
| 97 |
+
},
|
| 98 |
+
"tie_word_embeddings": false,
|
| 99 |
+
"transformers_version": "4.57.1",
|
| 100 |
+
"video_token_id": 248057,
|
| 101 |
+
"vision_config": {
|
| 102 |
+
"deepstack_visual_indexes": [],
|
| 103 |
+
"depth": 27,
|
| 104 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 105 |
+
"hidden_size": 1152,
|
| 106 |
+
"in_channels": 3,
|
| 107 |
+
"initializer_range": 0.02,
|
| 108 |
+
"intermediate_size": 4304,
|
| 109 |
+
"model_type": "qwen3_5_moe",
|
| 110 |
+
"num_heads": 16,
|
| 111 |
+
"num_position_embeddings": 2304,
|
| 112 |
+
"out_hidden_size": 2048,
|
| 113 |
+
"patch_size": 16,
|
| 114 |
+
"spatial_merge_size": 2,
|
| 115 |
+
"temporal_patch_size": 2
|
| 116 |
+
},
|
| 117 |
+
"vision_end_token_id": 248054,
|
| 118 |
+
"vision_start_token_id": 248053
|
| 119 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95
|
| 12 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39f425f2bb6001c727291cc4735790f1c99a68deff2c643773a7af724d1a6711
|
| 3 |
+
size 49739502312
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a486260cc562716934a788410173703755da0a282d875ac11c2652492119aa67
|
| 3 |
+
size 20474993632
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1034 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8776795484,
|
| 4 |
+
"total_size": 70214363872
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.10.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.10.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.11.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.11.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.12.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.12.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.13.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.13.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.14.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.14.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.15.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.15.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.16.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.16.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.17.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.17.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.18.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.18.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.19.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.19.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.2.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.20.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.20.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.21.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.21.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.22.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.22.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.23.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.23.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.24.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.24.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.25.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.25.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.26.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.26.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.27.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.27.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.28.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.28.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.29.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.29.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.3.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.language_model.layers.30.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.language_model.layers.30.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.language_model.layers.31.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.language_model.layers.31.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.language_model.layers.32.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.language_model.layers.32.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.language_model.layers.32.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.language_model.layers.32.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.language_model.layers.32.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.language_model.layers.32.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.language_model.layers.32.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.language_model.layers.33.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.language_model.layers.33.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.language_model.layers.33.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.language_model.layers.33.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.language_model.layers.33.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.language_model.layers.33.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.language_model.layers.33.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.language_model.layers.34.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.language_model.layers.34.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.language_model.layers.34.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.language_model.layers.34.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.language_model.layers.34.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.language_model.layers.34.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.language_model.layers.34.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.language_model.layers.35.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.language_model.layers.35.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.language_model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.language_model.layers.36.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.language_model.layers.36.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.language_model.layers.36.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.language_model.layers.36.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.language_model.layers.36.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.language_model.layers.36.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.language_model.layers.36.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.language_model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.language_model.layers.37.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.language_model.layers.37.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.language_model.layers.37.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.language_model.layers.37.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.language_model.layers.37.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.language_model.layers.37.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.language_model.layers.37.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.language_model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.language_model.layers.38.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.language_model.layers.38.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.language_model.layers.38.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.language_model.layers.38.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.language_model.layers.38.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.language_model.layers.38.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.language_model.layers.38.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.language_model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.language_model.layers.39.mlp.experts.down_proj": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.language_model.layers.39.mlp.gate.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.language_model.layers.4.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.language_model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.language_model.layers.5.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.language_model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.language_model.layers.6.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.language_model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.language_model.layers.7.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.language_model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.language_model.layers.8.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.language_model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.language_model.layers.9.mlp.experts.down_proj": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.language_model.layers.9.mlp.gate.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 745 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 746 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 747 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 749 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 750 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 751 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 753 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 754 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 755 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 756 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 757 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 758 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 759 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 760 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 761 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 762 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 765 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 766 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 767 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 768 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 769 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 770 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 771 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 772 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 773 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 774 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 775 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 776 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 777 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 779 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 780 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 781 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 782 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 783 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 784 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 786 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 787 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 788 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 790 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 791 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 792 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 793 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 794 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 795 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 796 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 797 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 798 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 799 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 801 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 802 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 803 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 804 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 805 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 806 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 807 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 808 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 809 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 810 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 811 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 812 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 813 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 814 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 815 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 816 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 817 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 818 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 819 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 820 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 821 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 822 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 823 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 824 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 825 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 826 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 827 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 828 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 829 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 830 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 831 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 832 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 833 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 834 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 835 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 836 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 837 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 838 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 839 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 840 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 841 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 842 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 843 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 844 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 845 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 846 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 847 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 848 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 849 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 850 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 851 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 852 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 853 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 854 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 855 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 856 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 857 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 858 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 859 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 860 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 861 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 862 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 863 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 864 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 865 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 866 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 867 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 868 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 869 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 870 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 871 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 872 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 873 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 874 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 875 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 876 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 877 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 878 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 879 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 880 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 881 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 882 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 883 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 884 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 885 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 886 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 887 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 888 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 889 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 890 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 891 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 892 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 893 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 894 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 895 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 896 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 897 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 898 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 899 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 900 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 901 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 902 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 903 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 904 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 905 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 906 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 907 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 908 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 909 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 910 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 911 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 912 |
+
"model.visual.blocks.24.norm1.bias": "model-00002-of-00002.safetensors",
|
| 913 |
+
"model.visual.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
|
| 914 |
+
"model.visual.blocks.24.norm2.bias": "model-00002-of-00002.safetensors",
|
| 915 |
+
"model.visual.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
|
| 916 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 917 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 918 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 919 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 920 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 921 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 922 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 923 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 924 |
+
"model.visual.blocks.25.norm1.bias": "model-00002-of-00002.safetensors",
|
| 925 |
+
"model.visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
|
| 926 |
+
"model.visual.blocks.25.norm2.bias": "model-00002-of-00002.safetensors",
|
| 927 |
+
"model.visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
|
| 928 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 929 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 930 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 931 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 932 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 933 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 934 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 935 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 936 |
+
"model.visual.blocks.26.norm1.bias": "model-00002-of-00002.safetensors",
|
| 937 |
+
"model.visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors",
|
| 938 |
+
"model.visual.blocks.26.norm2.bias": "model-00002-of-00002.safetensors",
|
| 939 |
+
"model.visual.blocks.26.norm2.weight": "model-00002-of-00002.safetensors",
|
| 940 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 941 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 942 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 943 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 944 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 945 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 946 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 947 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 948 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 949 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 950 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 951 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 952 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 953 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 954 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 955 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 956 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 957 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 958 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 959 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 960 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 961 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 962 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 963 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 964 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 965 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 966 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 967 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 968 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 969 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 970 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 971 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 972 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 973 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 974 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 975 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 976 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 977 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 978 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 979 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 980 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 981 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 982 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 983 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 984 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 985 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 986 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 987 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 988 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 989 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 990 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 991 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 992 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 993 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 994 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 995 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 996 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 997 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 998 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 999 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 1000 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 1001 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 1002 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 1003 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 1004 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 1005 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 1006 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 1007 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 1008 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 1009 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 1010 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 1011 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 1012 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 1013 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 1014 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 1015 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 1016 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 1017 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 1018 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 1019 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 1020 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 1021 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 1022 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 1023 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 1024 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 1025 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 1026 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 1027 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 1028 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 1029 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 1030 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 1031 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 1032 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 1033 |
+
}
|
| 1034 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
|
| 3 |
+
size 12807982
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"248044": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"248045": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"248046": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"248047": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"248048": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"248049": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"248050": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"248051": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"248052": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"248053": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"248054": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"248055": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"248056": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"248057": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"248058": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"248059": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"248060": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"248061": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"248062": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"248063": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"248064": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"248065": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"248066": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"248067": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"248068": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"248069": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"248070": {
|
| 213 |
+
"content": "<|audio_start|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"248071": {
|
| 221 |
+
"content": "<|audio_end|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"248072": {
|
| 229 |
+
"content": "<tts_pad>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"248073": {
|
| 237 |
+
"content": "<tts_text_bos>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"248074": {
|
| 245 |
+
"content": "<tts_text_eod>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"248075": {
|
| 253 |
+
"content": "<tts_text_bos_single>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"248076": {
|
| 261 |
+
"content": "<|audio_pad|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"additional_special_tokens": [
|
| 270 |
+
"<|im_start|>",
|
| 271 |
+
"<|im_end|>",
|
| 272 |
+
"<|object_ref_start|>",
|
| 273 |
+
"<|object_ref_end|>",
|
| 274 |
+
"<|box_start|>",
|
| 275 |
+
"<|box_end|>",
|
| 276 |
+
"<|quad_start|>",
|
| 277 |
+
"<|quad_end|>",
|
| 278 |
+
"<|vision_start|>",
|
| 279 |
+
"<|vision_end|>",
|
| 280 |
+
"<|vision_pad|>",
|
| 281 |
+
"<|image_pad|>",
|
| 282 |
+
"<|video_pad|>"
|
| 283 |
+
],
|
| 284 |
+
"bos_token": null,
|
| 285 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 286 |
+
"clean_up_tokenization_spaces": false,
|
| 287 |
+
"eos_token": "<|im_end|>",
|
| 288 |
+
"errors": "replace",
|
| 289 |
+
"model_max_length": 262144,
|
| 290 |
+
"pad_token": "<|endoftext|>",
|
| 291 |
+
"split_special_tokens": false,
|
| 292 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 293 |
+
"unk_token": null,
|
| 294 |
+
"add_bos_token": false,
|
| 295 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 296 |
+
"extra_special_tokens": {
|
| 297 |
+
"audio_bos_token": "<|audio_start|>",
|
| 298 |
+
"audio_eos_token": "<|audio_end|>",
|
| 299 |
+
"audio_token": "<|audio_pad|>",
|
| 300 |
+
"image_token": "<|image_pad|>",
|
| 301 |
+
"video_token": "<|video_pad|>",
|
| 302 |
+
"vision_bos_token": "<|vision_start|>",
|
| 303 |
+
"vision_eos_token": "<|vision_end|>"
|
| 304 |
+
}
|
| 305 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0843373493975903,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 180,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006024096385542169,
|
| 14 |
+
"grad_norm": 11.142176628112793,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.428902804851532,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012048192771084338,
|
| 21 |
+
"grad_norm": 11.034109115600586,
|
| 22 |
+
"learning_rate": 5.555555555555555e-07,
|
| 23 |
+
"loss": 0.42792809009552,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018072289156626505,
|
| 28 |
+
"grad_norm": 8.74612045288086,
|
| 29 |
+
"learning_rate": 1.111111111111111e-06,
|
| 30 |
+
"loss": 0.3810642957687378,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.024096385542168676,
|
| 35 |
+
"grad_norm": 9.825540542602539,
|
| 36 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 37 |
+
"loss": 0.4792688190937042,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.030120481927710843,
|
| 42 |
+
"grad_norm": 9.189689636230469,
|
| 43 |
+
"learning_rate": 2.222222222222222e-06,
|
| 44 |
+
"loss": 0.40543031692504883,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03614457831325301,
|
| 49 |
+
"grad_norm": 7.393019199371338,
|
| 50 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 51 |
+
"loss": 0.4046850800514221,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.04216867469879518,
|
| 56 |
+
"grad_norm": 5.906346797943115,
|
| 57 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 58 |
+
"loss": 0.3256700038909912,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04819277108433735,
|
| 63 |
+
"grad_norm": 4.1642632484436035,
|
| 64 |
+
"learning_rate": 3.88888888888889e-06,
|
| 65 |
+
"loss": 0.2622697651386261,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.05421686746987952,
|
| 70 |
+
"grad_norm": 4.239490032196045,
|
| 71 |
+
"learning_rate": 4.444444444444444e-06,
|
| 72 |
+
"loss": 0.31185054779052734,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.060240963855421686,
|
| 77 |
+
"grad_norm": 2.696002721786499,
|
| 78 |
+
"learning_rate": 5e-06,
|
| 79 |
+
"loss": 0.26603323221206665,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06626506024096386,
|
| 84 |
+
"grad_norm": 2.6713006496429443,
|
| 85 |
+
"learning_rate": 4.999881749961716e-06,
|
| 86 |
+
"loss": 0.29827162623405457,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07228915662650602,
|
| 91 |
+
"grad_norm": 2.532520294189453,
|
| 92 |
+
"learning_rate": 4.999527011033321e-06,
|
| 93 |
+
"loss": 0.2619355022907257,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0783132530120482,
|
| 98 |
+
"grad_norm": 2.390526533126831,
|
| 99 |
+
"learning_rate": 4.9989358167731285e-06,
|
| 100 |
+
"loss": 0.2530556321144104,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.08433734939759036,
|
| 105 |
+
"grad_norm": 2.513714551925659,
|
| 106 |
+
"learning_rate": 4.998108223108133e-06,
|
| 107 |
+
"loss": 0.2906743884086609,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.09036144578313253,
|
| 112 |
+
"grad_norm": 2.0978147983551025,
|
| 113 |
+
"learning_rate": 4.9970443083287224e-06,
|
| 114 |
+
"loss": 0.23413600027561188,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0963855421686747,
|
| 119 |
+
"grad_norm": 2.065729856491089,
|
| 120 |
+
"learning_rate": 4.995744173081265e-06,
|
| 121 |
+
"loss": 0.24827918410301208,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.10240963855421686,
|
| 126 |
+
"grad_norm": 1.884876012802124,
|
| 127 |
+
"learning_rate": 4.994207940358597e-06,
|
| 128 |
+
"loss": 0.26246076822280884,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.10843373493975904,
|
| 133 |
+
"grad_norm": 2.5683226585388184,
|
| 134 |
+
"learning_rate": 4.99243575548838e-06,
|
| 135 |
+
"loss": 0.3206707835197449,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.1144578313253012,
|
| 140 |
+
"grad_norm": 1.6468095779418945,
|
| 141 |
+
"learning_rate": 4.9904277861193574e-06,
|
| 142 |
+
"loss": 0.20793572068214417,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.12048192771084337,
|
| 147 |
+
"grad_norm": 2.026458263397217,
|
| 148 |
+
"learning_rate": 4.988184222205492e-06,
|
| 149 |
+
"loss": 0.23015552759170532,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.12650602409638553,
|
| 154 |
+
"grad_norm": 1.8717762231826782,
|
| 155 |
+
"learning_rate": 4.9857052759880006e-06,
|
| 156 |
+
"loss": 0.25441068410873413,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.13253012048192772,
|
| 161 |
+
"grad_norm": 2.0290212631225586,
|
| 162 |
+
"learning_rate": 4.98299118197527e-06,
|
| 163 |
+
"loss": 0.22494634985923767,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.13855421686746988,
|
| 168 |
+
"grad_norm": 2.214284658432007,
|
| 169 |
+
"learning_rate": 4.980042196920677e-06,
|
| 170 |
+
"loss": 0.26744288206100464,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14457831325301204,
|
| 175 |
+
"grad_norm": 2.1135001182556152,
|
| 176 |
+
"learning_rate": 4.976858599798299e-06,
|
| 177 |
+
"loss": 0.27789992094039917,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.15060240963855423,
|
| 182 |
+
"grad_norm": 1.9528898000717163,
|
| 183 |
+
"learning_rate": 4.97344069177652e-06,
|
| 184 |
+
"loss": 0.2466088980436325,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1566265060240964,
|
| 189 |
+
"grad_norm": 2.101134777069092,
|
| 190 |
+
"learning_rate": 4.969788796189544e-06,
|
| 191 |
+
"loss": 0.2756834030151367,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.16265060240963855,
|
| 196 |
+
"grad_norm": 2.343674421310425,
|
| 197 |
+
"learning_rate": 4.965903258506806e-06,
|
| 198 |
+
"loss": 0.28239595890045166,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1686746987951807,
|
| 203 |
+
"grad_norm": 2.253816843032837,
|
| 204 |
+
"learning_rate": 4.9617844463002895e-06,
|
| 205 |
+
"loss": 0.2833530306816101,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1746987951807229,
|
| 210 |
+
"grad_norm": 2.0298430919647217,
|
| 211 |
+
"learning_rate": 4.957432749209755e-06,
|
| 212 |
+
"loss": 0.25803640484809875,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.18072289156626506,
|
| 217 |
+
"grad_norm": 1.9530489444732666,
|
| 218 |
+
"learning_rate": 4.952848578905881e-06,
|
| 219 |
+
"loss": 0.2215431183576584,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.18674698795180722,
|
| 224 |
+
"grad_norm": 1.940727949142456,
|
| 225 |
+
"learning_rate": 4.948032369051317e-06,
|
| 226 |
+
"loss": 0.21956567466259003,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.1927710843373494,
|
| 231 |
+
"grad_norm": 1.7422584295272827,
|
| 232 |
+
"learning_rate": 4.942984575259666e-06,
|
| 233 |
+
"loss": 0.20336072146892548,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.19879518072289157,
|
| 238 |
+
"grad_norm": 1.7944018840789795,
|
| 239 |
+
"learning_rate": 4.937705675052373e-06,
|
| 240 |
+
"loss": 0.2340494990348816,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.20481927710843373,
|
| 245 |
+
"grad_norm": 1.9949196577072144,
|
| 246 |
+
"learning_rate": 4.932196167813559e-06,
|
| 247 |
+
"loss": 0.30935412645339966,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.21084337349397592,
|
| 252 |
+
"grad_norm": 1.9301334619522095,
|
| 253 |
+
"learning_rate": 4.926456574742778e-06,
|
| 254 |
+
"loss": 0.24893832206726074,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.21686746987951808,
|
| 259 |
+
"grad_norm": 1.830209493637085,
|
| 260 |
+
"learning_rate": 4.920487438805711e-06,
|
| 261 |
+
"loss": 0.24357952177524567,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.22289156626506024,
|
| 266 |
+
"grad_norm": 1.988722324371338,
|
| 267 |
+
"learning_rate": 4.9142893246828e-06,
|
| 268 |
+
"loss": 0.22917479276657104,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2289156626506024,
|
| 273 |
+
"grad_norm": 1.8187060356140137,
|
| 274 |
+
"learning_rate": 4.907862818715831e-06,
|
| 275 |
+
"loss": 0.27028727531433105,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.23493975903614459,
|
| 280 |
+
"grad_norm": 2.018294095993042,
|
| 281 |
+
"learning_rate": 4.901208528852465e-06,
|
| 282 |
+
"loss": 0.2310202419757843,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.24096385542168675,
|
| 287 |
+
"grad_norm": 2.0524044036865234,
|
| 288 |
+
"learning_rate": 4.894327084588727e-06,
|
| 289 |
+
"loss": 0.2731711268424988,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.2469879518072289,
|
| 294 |
+
"grad_norm": 1.8044854402542114,
|
| 295 |
+
"learning_rate": 4.887219136909455e-06,
|
| 296 |
+
"loss": 0.21416833996772766,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.25301204819277107,
|
| 301 |
+
"grad_norm": 1.7802573442459106,
|
| 302 |
+
"learning_rate": 4.879885358226718e-06,
|
| 303 |
+
"loss": 0.19698399305343628,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.25903614457831325,
|
| 308 |
+
"grad_norm": 2.2974190711975098,
|
| 309 |
+
"learning_rate": 4.872326442316203e-06,
|
| 310 |
+
"loss": 0.27448707818984985,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.26506024096385544,
|
| 315 |
+
"grad_norm": 2.2874867916107178,
|
| 316 |
+
"learning_rate": 4.864543104251587e-06,
|
| 317 |
+
"loss": 0.25334182381629944,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.2710843373493976,
|
| 322 |
+
"grad_norm": 1.9537646770477295,
|
| 323 |
+
"learning_rate": 4.856536080336889e-06,
|
| 324 |
+
"loss": 0.23862236738204956,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.27710843373493976,
|
| 329 |
+
"grad_norm": 2.0207152366638184,
|
| 330 |
+
"learning_rate": 4.848306128036817e-06,
|
| 331 |
+
"loss": 0.21768009662628174,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.28313253012048195,
|
| 336 |
+
"grad_norm": 1.8584778308868408,
|
| 337 |
+
"learning_rate": 4.839854025905111e-06,
|
| 338 |
+
"loss": 0.22923576831817627,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2891566265060241,
|
| 343 |
+
"grad_norm": 1.950571060180664,
|
| 344 |
+
"learning_rate": 4.83118057351089e-06,
|
| 345 |
+
"loss": 0.24856369197368622,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.29518072289156627,
|
| 350 |
+
"grad_norm": 1.9584742784500122,
|
| 351 |
+
"learning_rate": 4.822286591363018e-06,
|
| 352 |
+
"loss": 0.22143439948558807,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.30120481927710846,
|
| 357 |
+
"grad_norm": 1.7273216247558594,
|
| 358 |
+
"learning_rate": 4.813172920832477e-06,
|
| 359 |
+
"loss": 0.21043998003005981,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3072289156626506,
|
| 364 |
+
"grad_norm": 1.895005702972412,
|
| 365 |
+
"learning_rate": 4.8038404240727785e-06,
|
| 366 |
+
"loss": 0.2245764136314392,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3132530120481928,
|
| 371 |
+
"grad_norm": 2.0731658935546875,
|
| 372 |
+
"learning_rate": 4.794289983938403e-06,
|
| 373 |
+
"loss": 0.22999663650989532,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3192771084337349,
|
| 378 |
+
"grad_norm": 1.8308407068252563,
|
| 379 |
+
"learning_rate": 4.784522503901279e-06,
|
| 380 |
+
"loss": 0.195350781083107,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3253012048192771,
|
| 385 |
+
"grad_norm": 1.843331217765808,
|
| 386 |
+
"learning_rate": 4.774538907965318e-06,
|
| 387 |
+
"loss": 0.2074728161096573,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3313253012048193,
|
| 392 |
+
"grad_norm": 1.7621232271194458,
|
| 393 |
+
"learning_rate": 4.764340140578999e-06,
|
| 394 |
+
"loss": 0.2011730819940567,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3373493975903614,
|
| 399 |
+
"grad_norm": 2.133352518081665,
|
| 400 |
+
"learning_rate": 4.753927166546032e-06,
|
| 401 |
+
"loss": 0.2272721230983734,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3433734939759036,
|
| 406 |
+
"grad_norm": 1.7030085325241089,
|
| 407 |
+
"learning_rate": 4.743300970934077e-06,
|
| 408 |
+
"loss": 0.21829667687416077,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.3493975903614458,
|
| 413 |
+
"grad_norm": 1.9551599025726318,
|
| 414 |
+
"learning_rate": 4.732462558981566e-06,
|
| 415 |
+
"loss": 0.27412763237953186,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.35542168674698793,
|
| 420 |
+
"grad_norm": 1.7485458850860596,
|
| 421 |
+
"learning_rate": 4.7214129560026015e-06,
|
| 422 |
+
"loss": 0.2115289866924286,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3614457831325301,
|
| 427 |
+
"grad_norm": 2.274949789047241,
|
| 428 |
+
"learning_rate": 4.710153207289963e-06,
|
| 429 |
+
"loss": 0.2607116997241974,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.3674698795180723,
|
| 434 |
+
"grad_norm": 1.6567832231521606,
|
| 435 |
+
"learning_rate": 4.698684378016223e-06,
|
| 436 |
+
"loss": 0.2039959728717804,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.37349397590361444,
|
| 441 |
+
"grad_norm": 2.048426866531372,
|
| 442 |
+
"learning_rate": 4.687007553132984e-06,
|
| 443 |
+
"loss": 0.2799915075302124,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3795180722891566,
|
| 448 |
+
"grad_norm": 1.7995165586471558,
|
| 449 |
+
"learning_rate": 4.675123837268235e-06,
|
| 450 |
+
"loss": 0.21062196791172028,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3855421686746988,
|
| 455 |
+
"grad_norm": 1.8946254253387451,
|
| 456 |
+
"learning_rate": 4.663034354621864e-06,
|
| 457 |
+
"loss": 0.20754952728748322,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.39156626506024095,
|
| 462 |
+
"grad_norm": 1.7134093046188354,
|
| 463 |
+
"learning_rate": 4.650740248859297e-06,
|
| 464 |
+
"loss": 0.21463951468467712,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.39759036144578314,
|
| 469 |
+
"grad_norm": 1.9219496250152588,
|
| 470 |
+
"learning_rate": 4.638242683003317e-06,
|
| 471 |
+
"loss": 0.26067647337913513,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.4036144578313253,
|
| 476 |
+
"grad_norm": 1.7691570520401,
|
| 477 |
+
"learning_rate": 4.625542839324036e-06,
|
| 478 |
+
"loss": 0.23639249801635742,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.40963855421686746,
|
| 483 |
+
"grad_norm": 1.9222103357315063,
|
| 484 |
+
"learning_rate": 4.6126419192270555e-06,
|
| 485 |
+
"loss": 0.2021777331829071,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.41566265060240964,
|
| 490 |
+
"grad_norm": 1.7899214029312134,
|
| 491 |
+
"learning_rate": 4.599541143139811e-06,
|
| 492 |
+
"loss": 0.24930432438850403,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.42168674698795183,
|
| 497 |
+
"grad_norm": 2.099332094192505,
|
| 498 |
+
"learning_rate": 4.586241750396123e-06,
|
| 499 |
+
"loss": 0.22903309762477875,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.42771084337349397,
|
| 504 |
+
"grad_norm": 1.7237921953201294,
|
| 505 |
+
"learning_rate": 4.572744999118951e-06,
|
| 506 |
+
"loss": 0.21340343356132507,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.43373493975903615,
|
| 511 |
+
"grad_norm": 2.0501701831817627,
|
| 512 |
+
"learning_rate": 4.55905216610138e-06,
|
| 513 |
+
"loss": 0.2957020699977875,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.4397590361445783,
|
| 518 |
+
"grad_norm": 1.9058964252471924,
|
| 519 |
+
"learning_rate": 4.545164546685833e-06,
|
| 520 |
+
"loss": 0.1939191371202469,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4457831325301205,
|
| 525 |
+
"grad_norm": 1.6917678117752075,
|
| 526 |
+
"learning_rate": 4.531083454641531e-06,
|
| 527 |
+
"loss": 0.17142519354820251,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.45180722891566266,
|
| 532 |
+
"grad_norm": 1.7717102766036987,
|
| 533 |
+
"learning_rate": 4.5168102220402134e-06,
|
| 534 |
+
"loss": 0.2252553552389145,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4578313253012048,
|
| 539 |
+
"grad_norm": 1.658211588859558,
|
| 540 |
+
"learning_rate": 4.502346199130122e-06,
|
| 541 |
+
"loss": 0.23183956742286682,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.463855421686747,
|
| 546 |
+
"grad_norm": 1.8013274669647217,
|
| 547 |
+
"learning_rate": 4.487692754208266e-06,
|
| 548 |
+
"loss": 0.22619429230690002,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.46987951807228917,
|
| 553 |
+
"grad_norm": 1.7795627117156982,
|
| 554 |
+
"learning_rate": 4.472851273490985e-06,
|
| 555 |
+
"loss": 0.2013862431049347,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4759036144578313,
|
| 560 |
+
"grad_norm": 1.939047932624817,
|
| 561 |
+
"learning_rate": 4.457823160982807e-06,
|
| 562 |
+
"loss": 0.24375547468662262,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4819277108433735,
|
| 567 |
+
"grad_norm": 2.0435917377471924,
|
| 568 |
+
"learning_rate": 4.442609838343639e-06,
|
| 569 |
+
"loss": 0.2810860276222229,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4879518072289157,
|
| 574 |
+
"grad_norm": 1.6849004030227661,
|
| 575 |
+
"learning_rate": 4.427212744754265e-06,
|
| 576 |
+
"loss": 0.20575395226478577,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.4939759036144578,
|
| 581 |
+
"grad_norm": 1.7432836294174194,
|
| 582 |
+
"learning_rate": 4.411633336780213e-06,
|
| 583 |
+
"loss": 0.24015243351459503,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5,
|
| 588 |
+
"grad_norm": 2.005021810531616,
|
| 589 |
+
"learning_rate": 4.395873088233954e-06,
|
| 590 |
+
"loss": 0.2686704397201538,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5060240963855421,
|
| 595 |
+
"grad_norm": 1.9157148599624634,
|
| 596 |
+
"learning_rate": 4.379933490035482e-06,
|
| 597 |
+
"loss": 0.2602766752243042,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.5120481927710844,
|
| 602 |
+
"grad_norm": 1.8026031255722046,
|
| 603 |
+
"learning_rate": 4.363816050071275e-06,
|
| 604 |
+
"loss": 0.2138879895210266,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.5180722891566265,
|
| 609 |
+
"grad_norm": 1.8697198629379272,
|
| 610 |
+
"learning_rate": 4.3475222930516484e-06,
|
| 611 |
+
"loss": 0.24326106905937195,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5240963855421686,
|
| 616 |
+
"grad_norm": 1.840242624282837,
|
| 617 |
+
"learning_rate": 4.331053760366514e-06,
|
| 618 |
+
"loss": 0.23169377446174622,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5301204819277109,
|
| 623 |
+
"grad_norm": 1.9570574760437012,
|
| 624 |
+
"learning_rate": 4.314412009939568e-06,
|
| 625 |
+
"loss": 0.21268793940544128,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.536144578313253,
|
| 630 |
+
"grad_norm": 6.490395545959473,
|
| 631 |
+
"learning_rate": 4.297598616080912e-06,
|
| 632 |
+
"loss": 0.23041915893554688,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.5421686746987951,
|
| 637 |
+
"grad_norm": 1.701446294784546,
|
| 638 |
+
"learning_rate": 4.28061516933812e-06,
|
| 639 |
+
"loss": 0.19419308006763458,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.5481927710843374,
|
| 644 |
+
"grad_norm": 1.8265910148620605,
|
| 645 |
+
"learning_rate": 4.2634632763457725e-06,
|
| 646 |
+
"loss": 0.21390798687934875,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.5542168674698795,
|
| 651 |
+
"grad_norm": 1.8848633766174316,
|
| 652 |
+
"learning_rate": 4.246144559673472e-06,
|
| 653 |
+
"loss": 0.234243705868721,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5602409638554217,
|
| 658 |
+
"grad_norm": 1.739385724067688,
|
| 659 |
+
"learning_rate": 4.228660657672347e-06,
|
| 660 |
+
"loss": 0.197153240442276,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5662650602409639,
|
| 665 |
+
"grad_norm": 1.7461135387420654,
|
| 666 |
+
"learning_rate": 4.211013224320062e-06,
|
| 667 |
+
"loss": 0.19059306383132935,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.572289156626506,
|
| 672 |
+
"grad_norm": 1.9738885164260864,
|
| 673 |
+
"learning_rate": 4.1932039290643534e-06,
|
| 674 |
+
"loss": 0.21974927186965942,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5783132530120482,
|
| 679 |
+
"grad_norm": 1.7048437595367432,
|
| 680 |
+
"learning_rate": 4.175234456665096e-06,
|
| 681 |
+
"loss": 0.1835278868675232,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5843373493975904,
|
| 686 |
+
"grad_norm": 1.8517098426818848,
|
| 687 |
+
"learning_rate": 4.15710650703493e-06,
|
| 688 |
+
"loss": 0.2452908456325531,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5903614457831325,
|
| 693 |
+
"grad_norm": 1.8890876770019531,
|
| 694 |
+
"learning_rate": 4.138821795078447e-06,
|
| 695 |
+
"loss": 0.2501678466796875,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5963855421686747,
|
| 700 |
+
"grad_norm": 1.751680850982666,
|
| 701 |
+
"learning_rate": 4.120382050529957e-06,
|
| 702 |
+
"loss": 0.21254503726959229,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6024096385542169,
|
| 707 |
+
"grad_norm": 1.9866863489151,
|
| 708 |
+
"learning_rate": 4.101789017789858e-06,
|
| 709 |
+
"loss": 0.26266080141067505,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.608433734939759,
|
| 714 |
+
"grad_norm": 2.1752734184265137,
|
| 715 |
+
"learning_rate": 4.083044455759618e-06,
|
| 716 |
+
"loss": 0.2721603214740753,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.6144578313253012,
|
| 721 |
+
"grad_norm": 1.7891639471054077,
|
| 722 |
+
"learning_rate": 4.064150137675378e-06,
|
| 723 |
+
"loss": 0.21918655931949615,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.6204819277108434,
|
| 728 |
+
"grad_norm": 1.7796125411987305,
|
| 729 |
+
"learning_rate": 4.045107850940209e-06,
|
| 730 |
+
"loss": 0.28184622526168823,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.6265060240963856,
|
| 735 |
+
"grad_norm": 1.5150421857833862,
|
| 736 |
+
"learning_rate": 4.025919396955019e-06,
|
| 737 |
+
"loss": 0.1914132535457611,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.6325301204819277,
|
| 742 |
+
"grad_norm": 1.752693772315979,
|
| 743 |
+
"learning_rate": 4.006586590948141e-06,
|
| 744 |
+
"loss": 0.23128381371498108,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.6385542168674698,
|
| 749 |
+
"grad_norm": 1.8561952114105225,
|
| 750 |
+
"learning_rate": 3.987111261803618e-06,
|
| 751 |
+
"loss": 0.22575634717941284,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.6445783132530121,
|
| 756 |
+
"grad_norm": 1.6240315437316895,
|
| 757 |
+
"learning_rate": 3.967495251888181e-06,
|
| 758 |
+
"loss": 0.20704583823680878,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.6506024096385542,
|
| 763 |
+
"grad_norm": 1.8144125938415527,
|
| 764 |
+
"learning_rate": 3.947740416876971e-06,
|
| 765 |
+
"loss": 0.20163677632808685,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.6566265060240963,
|
| 770 |
+
"grad_norm": 1.8921997547149658,
|
| 771 |
+
"learning_rate": 3.9278486255779835e-06,
|
| 772 |
+
"loss": 0.21554049849510193,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.6626506024096386,
|
| 777 |
+
"grad_norm": 1.804047703742981,
|
| 778 |
+
"learning_rate": 3.907821759755286e-06,
|
| 779 |
+
"loss": 0.23601463437080383,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.6686746987951807,
|
| 784 |
+
"grad_norm": 1.6722337007522583,
|
| 785 |
+
"learning_rate": 3.8876617139509965e-06,
|
| 786 |
+
"loss": 0.25775057077407837,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.6746987951807228,
|
| 791 |
+
"grad_norm": 2.067570686340332,
|
| 792 |
+
"learning_rate": 3.8673703953060685e-06,
|
| 793 |
+
"loss": 0.23134759068489075,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6807228915662651,
|
| 798 |
+
"grad_norm": 1.8785966634750366,
|
| 799 |
+
"learning_rate": 3.846949723379863e-06,
|
| 800 |
+
"loss": 0.23591741919517517,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6867469879518072,
|
| 805 |
+
"grad_norm": 2.127025604248047,
|
| 806 |
+
"learning_rate": 3.826401629968575e-06,
|
| 807 |
+
"loss": 0.23402580618858337,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.6927710843373494,
|
| 812 |
+
"grad_norm": 1.544934868812561,
|
| 813 |
+
"learning_rate": 3.805728058922467e-06,
|
| 814 |
+
"loss": 0.1696513295173645,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6987951807228916,
|
| 819 |
+
"grad_norm": 1.9435012340545654,
|
| 820 |
+
"learning_rate": 3.7849309659619943e-06,
|
| 821 |
+
"loss": 0.224832683801651,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.7048192771084337,
|
| 826 |
+
"grad_norm": 1.7729871273040771,
|
| 827 |
+
"learning_rate": 3.7640123184927876e-06,
|
| 828 |
+
"loss": 0.21986815333366394,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.7108433734939759,
|
| 833 |
+
"grad_norm": 1.636151671409607,
|
| 834 |
+
"learning_rate": 3.742974095419538e-06,
|
| 835 |
+
"loss": 0.19982966780662537,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.7168674698795181,
|
| 840 |
+
"grad_norm": 1.822206735610962,
|
| 841 |
+
"learning_rate": 3.7218182869587923e-06,
|
| 842 |
+
"loss": 0.25640130043029785,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.7228915662650602,
|
| 847 |
+
"grad_norm": 1.7592462301254272,
|
| 848 |
+
"learning_rate": 3.70054689445068e-06,
|
| 849 |
+
"loss": 0.24146384000778198,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.7289156626506024,
|
| 854 |
+
"grad_norm": 2.0406506061553955,
|
| 855 |
+
"learning_rate": 3.6791619301695824e-06,
|
| 856 |
+
"loss": 0.24204370379447937,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7349397590361446,
|
| 861 |
+
"grad_norm": 1.798247218132019,
|
| 862 |
+
"learning_rate": 3.6576654171337765e-06,
|
| 863 |
+
"loss": 0.19507844746112823,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.7409638554216867,
|
| 868 |
+
"grad_norm": 1.9995570182800293,
|
| 869 |
+
"learning_rate": 3.6360593889140543e-06,
|
| 870 |
+
"loss": 0.20422318577766418,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.7469879518072289,
|
| 875 |
+
"grad_norm": 2.01058030128479,
|
| 876 |
+
"learning_rate": 3.6143458894413463e-06,
|
| 877 |
+
"loss": 0.24596446752548218,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.7530120481927711,
|
| 882 |
+
"grad_norm": 1.6475582122802734,
|
| 883 |
+
"learning_rate": 3.592526972813367e-06,
|
| 884 |
+
"loss": 0.20919951796531677,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.7590361445783133,
|
| 889 |
+
"grad_norm": 1.663503646850586,
|
| 890 |
+
"learning_rate": 3.5706047031002993e-06,
|
| 891 |
+
"loss": 0.21953055262565613,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.7650602409638554,
|
| 896 |
+
"grad_norm": 1.7317630052566528,
|
| 897 |
+
"learning_rate": 3.5485811541495274e-06,
|
| 898 |
+
"loss": 0.2076019048690796,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.7710843373493976,
|
| 903 |
+
"grad_norm": 1.492385983467102,
|
| 904 |
+
"learning_rate": 3.526458409389459e-06,
|
| 905 |
+
"loss": 0.17310795187950134,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7771084337349398,
|
| 910 |
+
"grad_norm": 1.6732460260391235,
|
| 911 |
+
"learning_rate": 3.5042385616324243e-06,
|
| 912 |
+
"loss": 0.1909010410308838,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.7831325301204819,
|
| 917 |
+
"grad_norm": 1.8162691593170166,
|
| 918 |
+
"learning_rate": 3.4819237128767012e-06,
|
| 919 |
+
"loss": 0.22556881606578827,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.7891566265060241,
|
| 924 |
+
"grad_norm": 1.8092666864395142,
|
| 925 |
+
"learning_rate": 3.4595159741076674e-06,
|
| 926 |
+
"loss": 0.22908125817775726,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.7951807228915663,
|
| 931 |
+
"grad_norm": 1.759559154510498,
|
| 932 |
+
"learning_rate": 3.4370174650980953e-06,
|
| 933 |
+
"loss": 0.22184421122074127,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.8012048192771084,
|
| 938 |
+
"grad_norm": 1.816255807876587,
|
| 939 |
+
"learning_rate": 3.4144303142076268e-06,
|
| 940 |
+
"loss": 0.20111408829689026,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.8072289156626506,
|
| 945 |
+
"grad_norm": 1.6726490259170532,
|
| 946 |
+
"learning_rate": 3.3917566581814277e-06,
|
| 947 |
+
"loss": 0.20235317945480347,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.8132530120481928,
|
| 952 |
+
"grad_norm": 1.8278712034225464,
|
| 953 |
+
"learning_rate": 3.368998641948052e-06,
|
| 954 |
+
"loss": 0.25044453144073486,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.8192771084337349,
|
| 959 |
+
"grad_norm": 1.8829212188720703,
|
| 960 |
+
"learning_rate": 3.346158418416533e-06,
|
| 961 |
+
"loss": 0.24094229936599731,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.8253012048192772,
|
| 966 |
+
"grad_norm": 1.904211401939392,
|
| 967 |
+
"learning_rate": 3.323238148272717e-06,
|
| 968 |
+
"loss": 0.22016692161560059,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.8313253012048193,
|
| 973 |
+
"grad_norm": 1.8119757175445557,
|
| 974 |
+
"learning_rate": 3.3002399997748604e-06,
|
| 975 |
+
"loss": 0.2539440989494324,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.8373493975903614,
|
| 980 |
+
"grad_norm": 1.6660523414611816,
|
| 981 |
+
"learning_rate": 3.277166148548516e-06,
|
| 982 |
+
"loss": 0.21818749606609344,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8433734939759037,
|
| 987 |
+
"grad_norm": 1.9667959213256836,
|
| 988 |
+
"learning_rate": 3.2540187773807162e-06,
|
| 989 |
+
"loss": 0.21603018045425415,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8493975903614458,
|
| 994 |
+
"grad_norm": 1.7938474416732788,
|
| 995 |
+
"learning_rate": 3.230800076013483e-06,
|
| 996 |
+
"loss": 0.20440860092639923,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.8554216867469879,
|
| 1001 |
+
"grad_norm": 1.7303977012634277,
|
| 1002 |
+
"learning_rate": 3.207512240936676e-06,
|
| 1003 |
+
"loss": 0.2181878238916397,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.8614457831325302,
|
| 1008 |
+
"grad_norm": 1.7015107870101929,
|
| 1009 |
+
"learning_rate": 3.184157475180208e-06,
|
| 1010 |
+
"loss": 0.23690566420555115,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.8674698795180723,
|
| 1015 |
+
"grad_norm": 1.7471257448196411,
|
| 1016 |
+
"learning_rate": 3.1607379881056333e-06,
|
| 1017 |
+
"loss": 0.22546926140785217,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.8734939759036144,
|
| 1022 |
+
"grad_norm": 1.7830501794815063,
|
| 1023 |
+
"learning_rate": 3.137255995197147e-06,
|
| 1024 |
+
"loss": 0.19030848145484924,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.8795180722891566,
|
| 1029 |
+
"grad_norm": 1.5704936981201172,
|
| 1030 |
+
"learning_rate": 3.1137137178519983e-06,
|
| 1031 |
+
"loss": 0.21496745944023132,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.8855421686746988,
|
| 1036 |
+
"grad_norm": 1.9630683660507202,
|
| 1037 |
+
"learning_rate": 3.090113383170344e-06,
|
| 1038 |
+
"loss": 0.2366226762533188,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.891566265060241,
|
| 1043 |
+
"grad_norm": 1.7654658555984497,
|
| 1044 |
+
"learning_rate": 3.0664572237445684e-06,
|
| 1045 |
+
"loss": 0.26164698600769043,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.8975903614457831,
|
| 1050 |
+
"grad_norm": 1.6233384609222412,
|
| 1051 |
+
"learning_rate": 3.042747477448078e-06,
|
| 1052 |
+
"loss": 0.17893335223197937,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.9036144578313253,
|
| 1057 |
+
"grad_norm": 1.801803708076477,
|
| 1058 |
+
"learning_rate": 3.018986387223597e-06,
|
| 1059 |
+
"loss": 0.22494494915008545,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.9096385542168675,
|
| 1064 |
+
"grad_norm": 1.7251133918762207,
|
| 1065 |
+
"learning_rate": 0.0,
|
| 1066 |
+
"loss": 0.21339407563209534,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.9156626506024096,
|
| 1071 |
+
"grad_norm": 1.9012843370437622,
|
| 1072 |
+
"learning_rate": 5.555555555555555e-07,
|
| 1073 |
+
"loss": 0.24071244895458221,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.9216867469879518,
|
| 1078 |
+
"grad_norm": 1.6273796558380127,
|
| 1079 |
+
"learning_rate": 1.111111111111111e-06,
|
| 1080 |
+
"loss": 0.19139668345451355,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.927710843373494,
|
| 1085 |
+
"grad_norm": 1.7698148488998413,
|
| 1086 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 1087 |
+
"loss": 0.22368842363357544,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.9337349397590361,
|
| 1092 |
+
"grad_norm": 1.7884771823883057,
|
| 1093 |
+
"learning_rate": 2.222222222222222e-06,
|
| 1094 |
+
"loss": 0.16862092912197113,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.9397590361445783,
|
| 1099 |
+
"grad_norm": 1.6387245655059814,
|
| 1100 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 1101 |
+
"loss": 0.24389740824699402,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.9457831325301205,
|
| 1106 |
+
"grad_norm": 1.9914135932922363,
|
| 1107 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1108 |
+
"loss": 0.22333872318267822,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.9518072289156626,
|
| 1113 |
+
"grad_norm": 1.6643177270889282,
|
| 1114 |
+
"learning_rate": 3.88888888888889e-06,
|
| 1115 |
+
"loss": 0.20086194574832916,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.9578313253012049,
|
| 1120 |
+
"grad_norm": 1.6900769472122192,
|
| 1121 |
+
"learning_rate": 4.444444444444444e-06,
|
| 1122 |
+
"loss": 0.20764178037643433,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.963855421686747,
|
| 1127 |
+
"grad_norm": 1.817714810371399,
|
| 1128 |
+
"learning_rate": 5e-06,
|
| 1129 |
+
"loss": 0.24200844764709473,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.9698795180722891,
|
| 1134 |
+
"grad_norm": 1.7363492250442505,
|
| 1135 |
+
"learning_rate": 4.999881749961716e-06,
|
| 1136 |
+
"loss": 0.207527294754982,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.9759036144578314,
|
| 1141 |
+
"grad_norm": 1.7865567207336426,
|
| 1142 |
+
"learning_rate": 4.999527011033321e-06,
|
| 1143 |
+
"loss": 0.21617457270622253,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.9819277108433735,
|
| 1148 |
+
"grad_norm": 1.9564707279205322,
|
| 1149 |
+
"learning_rate": 4.9989358167731285e-06,
|
| 1150 |
+
"loss": 0.2597506642341614,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.9879518072289156,
|
| 1155 |
+
"grad_norm": 1.88765549659729,
|
| 1156 |
+
"learning_rate": 4.998108223108133e-06,
|
| 1157 |
+
"loss": 0.2530207931995392,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.9939759036144579,
|
| 1162 |
+
"grad_norm": 1.703033685684204,
|
| 1163 |
+
"learning_rate": 4.9970443083287224e-06,
|
| 1164 |
+
"loss": 0.18831050395965576,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.0,
|
| 1169 |
+
"grad_norm": 1.7099109888076782,
|
| 1170 |
+
"learning_rate": 4.995744173081265e-06,
|
| 1171 |
+
"loss": 0.21984407305717468,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.0060240963855422,
|
| 1176 |
+
"grad_norm": 1.407286524772644,
|
| 1177 |
+
"learning_rate": 4.994207940358597e-06,
|
| 1178 |
+
"loss": 0.09358582645654678,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.0120481927710843,
|
| 1183 |
+
"grad_norm": 1.4928256273269653,
|
| 1184 |
+
"learning_rate": 4.99243575548838e-06,
|
| 1185 |
+
"loss": 0.10626605153083801,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.0180722891566265,
|
| 1190 |
+
"grad_norm": 1.4833334684371948,
|
| 1191 |
+
"learning_rate": 4.9904277861193574e-06,
|
| 1192 |
+
"loss": 0.12156569212675095,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.0240963855421688,
|
| 1197 |
+
"grad_norm": 1.4212719202041626,
|
| 1198 |
+
"learning_rate": 4.988184222205492e-06,
|
| 1199 |
+
"loss": 0.10794398933649063,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.0301204819277108,
|
| 1204 |
+
"grad_norm": 1.5113886594772339,
|
| 1205 |
+
"learning_rate": 4.9857052759880006e-06,
|
| 1206 |
+
"loss": 0.12738291919231415,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.036144578313253,
|
| 1211 |
+
"grad_norm": 1.4146442413330078,
|
| 1212 |
+
"learning_rate": 4.98299118197527e-06,
|
| 1213 |
+
"loss": 0.09423454105854034,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.0421686746987953,
|
| 1218 |
+
"grad_norm": 1.4581801891326904,
|
| 1219 |
+
"learning_rate": 4.980042196920677e-06,
|
| 1220 |
+
"loss": 0.0916857123374939,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.0481927710843373,
|
| 1225 |
+
"grad_norm": 1.7278649806976318,
|
| 1226 |
+
"learning_rate": 4.976858599798299e-06,
|
| 1227 |
+
"loss": 0.1625499427318573,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.0542168674698795,
|
| 1232 |
+
"grad_norm": 1.7814223766326904,
|
| 1233 |
+
"learning_rate": 4.97344069177652e-06,
|
| 1234 |
+
"loss": 0.09106528013944626,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.0602409638554218,
|
| 1239 |
+
"grad_norm": 1.7452236413955688,
|
| 1240 |
+
"learning_rate": 4.969788796189544e-06,
|
| 1241 |
+
"loss": 0.09855592250823975,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.0662650602409638,
|
| 1246 |
+
"grad_norm": 1.877186894416809,
|
| 1247 |
+
"learning_rate": 4.965903258506806e-06,
|
| 1248 |
+
"loss": 0.11333008855581284,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.072289156626506,
|
| 1253 |
+
"grad_norm": 1.9699362516403198,
|
| 1254 |
+
"learning_rate": 4.9617844463002895e-06,
|
| 1255 |
+
"loss": 0.10632774233818054,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.0783132530120483,
|
| 1260 |
+
"grad_norm": 1.8559452295303345,
|
| 1261 |
+
"learning_rate": 4.957432749209755e-06,
|
| 1262 |
+
"loss": 0.09790239483118057,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.0843373493975903,
|
| 1267 |
+
"grad_norm": 2.022092342376709,
|
| 1268 |
+
"learning_rate": 4.952848578905881e-06,
|
| 1269 |
+
"loss": 0.13124418258666992,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
}
|
| 1272 |
+
],
|
| 1273 |
+
"logging_steps": 1,
|
| 1274 |
+
"max_steps": 332,
|
| 1275 |
+
"num_input_tokens_seen": 0,
|
| 1276 |
+
"num_train_epochs": 2,
|
| 1277 |
+
"save_steps": 30,
|
| 1278 |
+
"stateful_callbacks": {
|
| 1279 |
+
"TrainerControl": {
|
| 1280 |
+
"args": {
|
| 1281 |
+
"should_epoch_stop": false,
|
| 1282 |
+
"should_evaluate": false,
|
| 1283 |
+
"should_log": false,
|
| 1284 |
+
"should_save": true,
|
| 1285 |
+
"should_training_stop": false
|
| 1286 |
+
},
|
| 1287 |
+
"attributes": {}
|
| 1288 |
+
}
|
| 1289 |
+
},
|
| 1290 |
+
"total_flos": 1.0321363888305603e+18,
|
| 1291 |
+
"train_batch_size": 1,
|
| 1292 |
+
"trial_name": null,
|
| 1293 |
+
"trial_params": null
|
| 1294 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcfd2dd9ae457d308ab173b4b81faee099dcff4c740efc35965241603210fa0c
|
| 3 |
+
size 5777
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|