初始化项目，由ModelHub XC社区提供模型
Model: boradorish/qwen2.5-3b-sft Source: Original Platform
This commit is contained in:
ModelHub XC
24
checkpoint-92/added_tokens.json
Normal file
24
checkpoint-92/added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
54
checkpoint-92/chat_template.jinja
Normal file
54
checkpoint-92/chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
67
checkpoint-92/config.json
Normal file
67
checkpoint-92/config.json
Normal file
@@ -0,0 +1,67 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
9
checkpoint-92/generation_config.json
Normal file
9
checkpoint-92/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
151388
checkpoint-92/merges.txt
Normal file
151388
checkpoint-92/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-92/model-00001-of-00002.safetensors
Normal file
3
checkpoint-92/model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:da2895b584c90ab1e6528ac22c23180037122a9a6b12a3d675078c83224a26ed
|
||||
size 4957560304
|
||||
3
checkpoint-92/model-00002-of-00002.safetensors
Normal file
3
checkpoint-92/model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7478bd0d1978077f6efea10a4da0d5eacde2ba5d789fe31c2972d3b568f8401f
|
||||
size 1836696752
|
||||
443
checkpoint-92/model.safetensors.index.json
Normal file
443
checkpoint-92/model.safetensors.index.json
Normal file
@@ -0,0 +1,443 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3085938688,
|
||||
"total_size": 6794207232
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
checkpoint-92/special_tokens_map.json
Normal file
31
checkpoint-92/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
checkpoint-92/tokenizer.json
Normal file
3
checkpoint-92/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
checkpoint-92/tokenizer_config.json
Normal file
208
checkpoint-92/tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
678
checkpoint-92/trainer_state.json
Normal file
678
checkpoint-92/trainer_state.json
Normal file
@@ -0,0 +1,678 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.3546987951807229,
|
||||
"eval_steps": 500,
|
||||
"global_step": 92,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0038554216867469878,
|
||||
"grad_norm": 0.6997007131576538,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.0405,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.0077108433734939755,
|
||||
"grad_norm": 0.6004841327667236,
|
||||
"learning_rate": 5.128205128205128e-07,
|
||||
"loss": 0.0413,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.011566265060240964,
|
||||
"grad_norm": 0.6796688437461853,
|
||||
"learning_rate": 1.0256410256410257e-06,
|
||||
"loss": 0.049,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.015421686746987951,
|
||||
"grad_norm": 0.6812688708305359,
|
||||
"learning_rate": 1.5384615384615387e-06,
|
||||
"loss": 0.0486,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.01927710843373494,
|
||||
"grad_norm": 0.6957109570503235,
|
||||
"learning_rate": 2.0512820512820513e-06,
|
||||
"loss": 0.033,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.02313253012048193,
|
||||
"grad_norm": 0.6179328560829163,
|
||||
"learning_rate": 2.564102564102564e-06,
|
||||
"loss": 0.0505,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.026987951807228915,
|
||||
"grad_norm": 0.5707671046257019,
|
||||
"learning_rate": 3.0769230769230774e-06,
|
||||
"loss": 0.0409,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.030843373493975902,
|
||||
"grad_norm": 0.41436561942100525,
|
||||
"learning_rate": 3.58974358974359e-06,
|
||||
"loss": 0.0433,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.03469879518072289,
|
||||
"grad_norm": 0.3194092810153961,
|
||||
"learning_rate": 4.102564102564103e-06,
|
||||
"loss": 0.032,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.03855421686746988,
|
||||
"grad_norm": 0.3646799325942993,
|
||||
"learning_rate": 4.615384615384616e-06,
|
||||
"loss": 0.0326,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.042409638554216866,
|
||||
"grad_norm": 0.3623705804347992,
|
||||
"learning_rate": 5.128205128205128e-06,
|
||||
"loss": 0.0415,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.04626506024096386,
|
||||
"grad_norm": 0.23459671437740326,
|
||||
"learning_rate": 5.641025641025641e-06,
|
||||
"loss": 0.0356,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 0.05012048192771084,
|
||||
"grad_norm": 0.27805373072624207,
|
||||
"learning_rate": 6.153846153846155e-06,
|
||||
"loss": 0.0265,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.05397590361445783,
|
||||
"grad_norm": 0.2236052304506302,
|
||||
"learning_rate": 6.666666666666667e-06,
|
||||
"loss": 0.0237,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.05783132530120482,
|
||||
"grad_norm": 0.2813984453678131,
|
||||
"learning_rate": 7.17948717948718e-06,
|
||||
"loss": 0.0271,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.061686746987951804,
|
||||
"grad_norm": 0.24619753658771515,
|
||||
"learning_rate": 7.692307692307694e-06,
|
||||
"loss": 0.0237,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 0.0655421686746988,
|
||||
"grad_norm": 0.2730517089366913,
|
||||
"learning_rate": 8.205128205128205e-06,
|
||||
"loss": 0.0227,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 0.06939759036144579,
|
||||
"grad_norm": 0.2350538820028305,
|
||||
"learning_rate": 8.717948717948719e-06,
|
||||
"loss": 0.0245,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 0.07325301204819278,
|
||||
"grad_norm": 0.18193207681179047,
|
||||
"learning_rate": 9.230769230769232e-06,
|
||||
"loss": 0.0168,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 0.07710843373493977,
|
||||
"grad_norm": 0.18165752291679382,
|
||||
"learning_rate": 9.743589743589744e-06,
|
||||
"loss": 0.0159,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.08096385542168674,
|
||||
"grad_norm": 0.27797478437423706,
|
||||
"learning_rate": 1.0256410256410256e-05,
|
||||
"loss": 0.0301,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 0.08481927710843373,
|
||||
"grad_norm": 0.26159757375717163,
|
||||
"learning_rate": 1.076923076923077e-05,
|
||||
"loss": 0.0279,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 0.08867469879518072,
|
||||
"grad_norm": 0.20290671288967133,
|
||||
"learning_rate": 1.1282051282051283e-05,
|
||||
"loss": 0.0215,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 0.09253012048192771,
|
||||
"grad_norm": 0.3016839921474457,
|
||||
"learning_rate": 1.1794871794871796e-05,
|
||||
"loss": 0.0239,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 0.0963855421686747,
|
||||
"grad_norm": 0.23746410012245178,
|
||||
"learning_rate": 1.230769230769231e-05,
|
||||
"loss": 0.0287,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.10024096385542168,
|
||||
"grad_norm": 0.20524649322032928,
|
||||
"learning_rate": 1.2820512820512823e-05,
|
||||
"loss": 0.0233,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 0.10409638554216867,
|
||||
"grad_norm": 0.23074588179588318,
|
||||
"learning_rate": 1.3333333333333333e-05,
|
||||
"loss": 0.0227,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 0.10795180722891566,
|
||||
"grad_norm": 0.17793533205986023,
|
||||
"learning_rate": 1.3846153846153847e-05,
|
||||
"loss": 0.0206,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 0.11180722891566265,
|
||||
"grad_norm": 0.19907526671886444,
|
||||
"learning_rate": 1.435897435897436e-05,
|
||||
"loss": 0.0291,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 0.11566265060240964,
|
||||
"grad_norm": 0.22600896656513214,
|
||||
"learning_rate": 1.4871794871794874e-05,
|
||||
"loss": 0.0277,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.11951807228915663,
|
||||
"grad_norm": 0.2135571539402008,
|
||||
"learning_rate": 1.5384615384615387e-05,
|
||||
"loss": 0.0157,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 0.12337349397590361,
|
||||
"grad_norm": 0.17844079434871674,
|
||||
"learning_rate": 1.5897435897435897e-05,
|
||||
"loss": 0.0207,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 0.1272289156626506,
|
||||
"grad_norm": 0.21249860525131226,
|
||||
"learning_rate": 1.641025641025641e-05,
|
||||
"loss": 0.0258,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 0.1310843373493976,
|
||||
"grad_norm": 0.18014496564865112,
|
||||
"learning_rate": 1.6923076923076924e-05,
|
||||
"loss": 0.0187,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 0.13493975903614458,
|
||||
"grad_norm": 0.1790035516023636,
|
||||
"learning_rate": 1.7435897435897438e-05,
|
||||
"loss": 0.0141,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.13879518072289157,
|
||||
"grad_norm": 0.18319612741470337,
|
||||
"learning_rate": 1.794871794871795e-05,
|
||||
"loss": 0.0153,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 0.14265060240963856,
|
||||
"grad_norm": 0.16664963960647583,
|
||||
"learning_rate": 1.8461538461538465e-05,
|
||||
"loss": 0.0146,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 0.14650602409638555,
|
||||
"grad_norm": 0.17741602659225464,
|
||||
"learning_rate": 1.8974358974358975e-05,
|
||||
"loss": 0.0138,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 0.15036144578313254,
|
||||
"grad_norm": 0.16826853156089783,
|
||||
"learning_rate": 1.9487179487179488e-05,
|
||||
"loss": 0.0149,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 0.15421686746987953,
|
||||
"grad_norm": 0.17632468044757843,
|
||||
"learning_rate": 2e-05,
|
||||
"loss": 0.0315,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.1580722891566265,
|
||||
"grad_norm": 0.21154020726680756,
|
||||
"learning_rate": 2.0512820512820512e-05,
|
||||
"loss": 0.0313,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 0.16192771084337348,
|
||||
"grad_norm": 0.17007827758789062,
|
||||
"learning_rate": 2.102564102564103e-05,
|
||||
"loss": 0.0283,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 0.16578313253012048,
|
||||
"grad_norm": 0.20888379216194153,
|
||||
"learning_rate": 2.153846153846154e-05,
|
||||
"loss": 0.0173,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 0.16963855421686747,
|
||||
"grad_norm": 0.17302851378917694,
|
||||
"learning_rate": 2.2051282051282056e-05,
|
||||
"loss": 0.023,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 0.17349397590361446,
|
||||
"grad_norm": 0.28571709990501404,
|
||||
"learning_rate": 2.2564102564102566e-05,
|
||||
"loss": 0.0528,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.17734939759036145,
|
||||
"grad_norm": 0.2224675714969635,
|
||||
"learning_rate": 2.3076923076923076e-05,
|
||||
"loss": 0.0326,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 0.18120481927710844,
|
||||
"grad_norm": 0.16989563405513763,
|
||||
"learning_rate": 2.3589743589743593e-05,
|
||||
"loss": 0.0106,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 0.18506024096385543,
|
||||
"grad_norm": 0.17279551923274994,
|
||||
"learning_rate": 2.4102564102564103e-05,
|
||||
"loss": 0.0143,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 0.18891566265060242,
|
||||
"grad_norm": 0.1571756899356842,
|
||||
"learning_rate": 2.461538461538462e-05,
|
||||
"loss": 0.0112,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 0.1927710843373494,
|
||||
"grad_norm": 0.21857869625091553,
|
||||
"learning_rate": 2.512820512820513e-05,
|
||||
"loss": 0.0149,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.1966265060240964,
|
||||
"grad_norm": 0.21509476006031036,
|
||||
"learning_rate": 2.5641025641025646e-05,
|
||||
"loss": 0.0248,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 0.20048192771084336,
|
||||
"grad_norm": 0.15649166703224182,
|
||||
"learning_rate": 2.6153846153846157e-05,
|
||||
"loss": 0.0101,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 0.20433734939759035,
|
||||
"grad_norm": 0.17392459511756897,
|
||||
"learning_rate": 2.6666666666666667e-05,
|
||||
"loss": 0.0115,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 0.20819277108433734,
|
||||
"grad_norm": 0.13562685251235962,
|
||||
"learning_rate": 2.7179487179487183e-05,
|
||||
"loss": 0.0102,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 0.21204819277108433,
|
||||
"grad_norm": 0.22402575612068176,
|
||||
"learning_rate": 2.7692307692307694e-05,
|
||||
"loss": 0.0164,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.21590361445783132,
|
||||
"grad_norm": 0.1317652314901352,
|
||||
"learning_rate": 2.820512820512821e-05,
|
||||
"loss": 0.0091,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 0.2197590361445783,
|
||||
"grad_norm": 0.11563073843717575,
|
||||
"learning_rate": 2.871794871794872e-05,
|
||||
"loss": 0.009,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 0.2236144578313253,
|
||||
"grad_norm": 0.12244722992181778,
|
||||
"learning_rate": 2.923076923076923e-05,
|
||||
"loss": 0.0077,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 0.2274698795180723,
|
||||
"grad_norm": 0.18595360219478607,
|
||||
"learning_rate": 2.9743589743589747e-05,
|
||||
"loss": 0.0118,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 0.23132530120481928,
|
||||
"grad_norm": 0.16396519541740417,
|
||||
"learning_rate": 3.0256410256410257e-05,
|
||||
"loss": 0.0113,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.23518072289156627,
|
||||
"grad_norm": 0.16600239276885986,
|
||||
"learning_rate": 3.0769230769230774e-05,
|
||||
"loss": 0.0273,
|
||||
"step": 61
|
||||
},
|
||||
{
|
||||
"epoch": 0.23903614457831326,
|
||||
"grad_norm": 0.14368009567260742,
|
||||
"learning_rate": 3.128205128205129e-05,
|
||||
"loss": 0.0107,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 0.24289156626506025,
|
||||
"grad_norm": 0.11151304095983505,
|
||||
"learning_rate": 3.1794871794871795e-05,
|
||||
"loss": 0.0114,
|
||||
"step": 63
|
||||
},
|
||||
{
|
||||
"epoch": 0.24674698795180722,
|
||||
"grad_norm": 0.16931672394275665,
|
||||
"learning_rate": 3.230769230769231e-05,
|
||||
"loss": 0.0101,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 0.25060240963855424,
|
||||
"grad_norm": 0.13678501546382904,
|
||||
"learning_rate": 3.282051282051282e-05,
|
||||
"loss": 0.0074,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.2544578313253012,
|
||||
"grad_norm": 0.12231199443340302,
|
||||
"learning_rate": 3.3333333333333335e-05,
|
||||
"loss": 0.0117,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 0.2583132530120482,
|
||||
"grad_norm": 0.2577515244483948,
|
||||
"learning_rate": 3.384615384615385e-05,
|
||||
"loss": 0.0304,
|
||||
"step": 67
|
||||
},
|
||||
{
|
||||
"epoch": 0.2621686746987952,
|
||||
"grad_norm": 0.10441906005144119,
|
||||
"learning_rate": 3.435897435897436e-05,
|
||||
"loss": 0.0077,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 0.26602409638554214,
|
||||
"grad_norm": 0.18340735137462616,
|
||||
"learning_rate": 3.4871794871794875e-05,
|
||||
"loss": 0.0131,
|
||||
"step": 69
|
||||
},
|
||||
{
|
||||
"epoch": 0.26987951807228916,
|
||||
"grad_norm": 0.26318177580833435,
|
||||
"learning_rate": 3.538461538461539e-05,
|
||||
"loss": 0.0166,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.2737349397590361,
|
||||
"grad_norm": 0.0868140459060669,
|
||||
"learning_rate": 3.58974358974359e-05,
|
||||
"loss": 0.0079,
|
||||
"step": 71
|
||||
},
|
||||
{
|
||||
"epoch": 0.27759036144578314,
|
||||
"grad_norm": 0.1882234513759613,
|
||||
"learning_rate": 3.6410256410256416e-05,
|
||||
"loss": 0.0113,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 0.2814457831325301,
|
||||
"grad_norm": 0.1313207447528839,
|
||||
"learning_rate": 3.692307692307693e-05,
|
||||
"loss": 0.01,
|
||||
"step": 73
|
||||
},
|
||||
{
|
||||
"epoch": 0.2853012048192771,
|
||||
"grad_norm": 0.21643561124801636,
|
||||
"learning_rate": 3.7435897435897436e-05,
|
||||
"loss": 0.0126,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 0.2891566265060241,
|
||||
"grad_norm": 0.35117974877357483,
|
||||
"learning_rate": 3.794871794871795e-05,
|
||||
"loss": 0.0322,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.2930120481927711,
|
||||
"grad_norm": 0.14641538262367249,
|
||||
"learning_rate": 3.846153846153846e-05,
|
||||
"loss": 0.0086,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 0.29686746987951806,
|
||||
"grad_norm": 0.18411016464233398,
|
||||
"learning_rate": 3.8974358974358976e-05,
|
||||
"loss": 0.0254,
|
||||
"step": 77
|
||||
},
|
||||
{
|
||||
"epoch": 0.3007228915662651,
|
||||
"grad_norm": 0.17950740456581116,
|
||||
"learning_rate": 3.948717948717949e-05,
|
||||
"loss": 0.0191,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 0.30457831325301205,
|
||||
"grad_norm": 0.14514976739883423,
|
||||
"learning_rate": 4e-05,
|
||||
"loss": 0.0107,
|
||||
"step": 79
|
||||
},
|
||||
{
|
||||
"epoch": 0.30843373493975906,
|
||||
"grad_norm": 0.22098544239997864,
|
||||
"learning_rate": 3.999979972589652e-05,
|
||||
"loss": 0.0176,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.312289156626506,
|
||||
"grad_norm": 0.11959940195083618,
|
||||
"learning_rate": 3.9999198907597046e-05,
|
||||
"loss": 0.0168,
|
||||
"step": 81
|
||||
},
|
||||
{
|
||||
"epoch": 0.316144578313253,
|
||||
"grad_norm": 0.13479092717170715,
|
||||
"learning_rate": 3.999819755713442e-05,
|
||||
"loss": 0.0246,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"grad_norm": 0.15680080652236938,
|
||||
"learning_rate": 3.9996795694563096e-05,
|
||||
"loss": 0.0147,
|
||||
"step": 83
|
||||
},
|
||||
{
|
||||
"epoch": 0.32385542168674697,
|
||||
"grad_norm": 0.1106104925274849,
|
||||
"learning_rate": 3.999499334795875e-05,
|
||||
"loss": 0.017,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 0.327710843373494,
|
||||
"grad_norm": 0.13254176080226898,
|
||||
"learning_rate": 3.999279055341771e-05,
|
||||
"loss": 0.0096,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.33156626506024095,
|
||||
"grad_norm": 0.1391618400812149,
|
||||
"learning_rate": 3.999018735505626e-05,
|
||||
"loss": 0.0165,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 0.33542168674698797,
|
||||
"grad_norm": 0.15080322325229645,
|
||||
"learning_rate": 3.998718380500971e-05,
|
||||
"loss": 0.0127,
|
||||
"step": 87
|
||||
},
|
||||
{
|
||||
"epoch": 0.33927710843373493,
|
||||
"grad_norm": 0.20322079956531525,
|
||||
"learning_rate": 3.998377996343139e-05,
|
||||
"loss": 0.053,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 0.34313253012048195,
|
||||
"grad_norm": 0.10287915915250778,
|
||||
"learning_rate": 3.997997589849145e-05,
|
||||
"loss": 0.0112,
|
||||
"step": 89
|
||||
},
|
||||
{
|
||||
"epoch": 0.3469879518072289,
|
||||
"grad_norm": 0.14580729603767395,
|
||||
"learning_rate": 3.9975771686375434e-05,
|
||||
"loss": 0.009,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.35084337349397593,
|
||||
"grad_norm": 0.16750818490982056,
|
||||
"learning_rate": 3.9971167411282835e-05,
|
||||
"loss": 0.0137,
|
||||
"step": 91
|
||||
},
|
||||
{
|
||||
"epoch": 0.3546987951807229,
|
||||
"grad_norm": 0.0841616690158844,
|
||||
"learning_rate": 3.996616316542537e-05,
|
||||
"loss": 0.0054,
|
||||
"step": 92
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 780,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 92,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 7.243155759200993e+17,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-92/training_args.bin
Normal file
3
checkpoint-92/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9720c5d84d356da89e25010a2952663008d7684cb32017e16211358466623f9
|
||||
size 7825
|
||||
1
checkpoint-92/vocab.json
Normal file
1
checkpoint-92/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user