Upload seed

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 sft_data.json filter=lfs diff=lfs merge=lfs -text
+seed_oss_36b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

seed_oss_36b/README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Bklight999/World-Knowledge
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft_32k_0317_2w_3epoch
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft_32k_0317_2w_3epoch
+
+This model is a fine-tuned version of [/apdcephfs_fsgm/share_303846923/user/qifanzhang/Models/unsloth/Seed-OSS-36B-Instruct](https://huggingface.co//apdcephfs_fsgm/share_303846923/user/qifanzhang/Models/unsloth/Seed-OSS-36B-Instruct) on the notebook_sft_32k_0315 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- total_train_batch_size: 32
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

seed_oss_36b/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2357169941905408.0,
+    "train_loss": 0.1881681538838239,
+    "train_runtime": 178390.2085,
+    "train_samples_per_second": 0.434,
+    "train_steps_per_second": 0.014
+}

seed_oss_36b/chat_template.jinja

@@ -0,0 +1,173 @@
+{# Unsloth Chat template fixes #}
+{# ----------‑‑‑ special token variables ‑‑‑---------- #}
+{%- set bos_token              = '<seed:bos>'               -%}
+{%- set eos_token              = '<seed:eos>'               -%}
+{%- set pad_token              = '<seed:pad>'               -%}
+{%- set toolcall_begin_token   = '<seed:tool_call>'         -%}
+{%- set toolcall_end_token     = '</seed:tool_call>'        -%}
+{%- set think_begin_token      = '<seed:think>'             -%}
+{%- set think_end_token        = '</seed:think>'            -%}
+{%- set budget_begin_token     = '<seed:cot_budget_reflect>'-%}
+{%- set budget_end_token       = '</seed:cot_budget_reflect>'-%}
+{# -------------- reflection-interval lookup -------------- #}
+{%- if not thinking_budget is defined %}
+{%- set thinking_budget = -1 -%}
+{%- endif -%}
+{%- set budget_reflections_v05 = {
+     0:      0,
+     512:    128,
+     1024:   256,
+     2048:   512,
+     4096:   512,
+     8192:   1024,
+     16384:  1024
+} -%}
+{# 找到 “大于等于 thinking_budget” 的第一个档位 #}
+{%- set ns = namespace(interval = None) -%}
+{%- for k, v in budget_reflections_v05 | dictsort -%}
+    {%- if ns.interval is none and thinking_budget <= k -%}
+        {%- set ns.interval = v -%}
+    {%- endif -%}
+{%- endfor -%}
+{# 若超过最大档位，则用最后一个档位的值 #}
+{%- if ns.interval is none -%}
+    {%- set ns.interval = budget_reflections_v05[16384] -%}
+{%- endif -%}
+{# ---------- 预处理 system 消息 ---------- #}
+{%- if messages[0]["role"] == "system" %}
+{%- set system_message = messages[0]["content"] %}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{# ---------- 确保 tools 存在 ---------- #}
+{%- if not tools is defined or tools is none %}
+{%- set tools = [] %}
+{%- endif %}
+{# tools2doc.jinja #}
+{%- macro py_type(t) -%}
+    {%- if t == "string" -%}str
+    {%- elif t in ("number", "integer") -%}int
+    {%- elif t == "boolean" -%}bool
+    {%- elif t == "array" -%}list
+    {%- else -%}Any{%- endif -%}
+{%- endmacro -%}
+{# ---------- 输出 system 块 ---------- #}
+{%- if system_message is defined %}
+{{ bos_token + "system\n" + system_message }}
+{%- else %}
+{%- if tools is iterable and tools | length > 0 %}
+{{ bos_token + "system\nYou are Doubao, a helpful AI assistant. You may call one or more functions to assist with the user query." }}
+{%- endif %}
+{%- endif %}
+{%- if use_json_tooldef is defined and use_json_tooldef %}
+
+{{"Tool List:\nYou are authorized to use the following tools (described in JSON Schema format). Before performing any task, you must decide how to call them based on the descriptions and parameters of these tools."}}
+{{ tools | tojson|string }}
+{%- else %}
+{%- for item in tools if item.type == "function" %}
+
+
+Function:
+def {{ item.function.name }}(
+{%- for name, spec in item.function.parameters.properties.items() %}
+        {{- name }}: {{ py_type(spec.type) }}{% if not loop.last %},{% endif %}
+{%- endfor %}):
+    """
+    {{ item.function.description | trim }}
+
+    {# ---------- Args ---------- #}
+    {%- if item.function.parameters.properties %}
+    Args:
+    {%- for name, spec in item.function.parameters.properties.items() %}
+
+    - {{ name }} ({{ py_type(spec.type) }})
+      {%- if name in item.function.parameters.required %} [必填]{% else %} [选填]{% endif %}:
+      {{- " " ~ (spec.description or "") }}
+    {%- endfor %}
+    {%- endif %}
+
+    {# ---------- Returns ---------- #}
+    {%- if item.function.returns is defined
+          and item.function.returns.properties is defined
+          and item.function.returns.properties %}
+    Returns:
+    {%- for name, spec in item.function.returns.properties.items() %}
+
+    - {{ name }} ({{ py_type(spec.type) }}):
+      {{- " " ~ (spec.description or "") }}
+    {%- endfor %}
+    {%- endif %}
+
+    """
+{%- endfor %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+
+{{"工具调用请遵循如下格式:\n<seed:tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>value_1</parameter>\n<parameter=example_parameter_2>This is the value for the second parameter\nthat can span\nmultiple lines</parameter>\n</function>\n</seed:tool_call>\n"}}
+{%- endif %}
+{# 结束 system 块行尾 #}
+{%- if system_message is defined or tools is iterable and tools | length > 0 %}
+{{ eos_token }}
+{%- endif %}
+{# ---------- Thinking Budget ---------- #}
+{%- if thinking_budget is defined %}
+{%- if thinking_budget == 0 %}
+{{ bos_token+"system" }}
+{{ "You are an intelligent assistant that can answer questions in one step without the need for reasoning and thinking, that is, your thinking budget is 0. Next, please skip the thinking process and directly start answering the user's questions." }}
+{{ eos_token }}
+{%- elif not thinking_budget == -1 %}
+{{ bos_token+"system" }}
+{{ "You are an intelligent assistant with reflective ability. In the process of thinking and reasoning, you need to strictly follow the thinking budget, which is "}}{{thinking_budget}}{{". That is, you need to complete your thinking within "}}{{thinking_budget}}{{" tokens and start answering the user's questions. You will reflect on your thinking process every "}}{{ns.interval}}{{" tokens, stating how many tokens have been used and how many are left."}}
+{{ eos_token }}
+{%- endif %}
+{%- endif %}
+{# ---------- 逐条写出历史消息 ---------- #}
+{%- for message in loop_messages %}
+{%- if message.role == "assistant"
+  and message.tool_calls is defined
+  and message.tool_calls is iterable
+  and message.tool_calls | length > 0 %}
+{{ bos_token + message.role }}
+{%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+{{ "\n" + think_begin_token + message.reasoning_content | trim + think_end_token }}
+{%- endif %}
+{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+{{ "\n" + message.content | trim + "\n" }}
+{%- endif %}
+{%- for tool_call in message.tool_calls %}
+{%- if tool_call.function is defined %}{% set tool_call = tool_call.function %}{% endif %}
+{{ "\n" + toolcall_begin_token + "\n<function=" + tool_call.name + ">\n" }}
+{%- if tool_call.arguments is defined and tool_call.arguments is mapping %}
+{%- for arg_name, arg_value in tool_call.arguments | items %}
+{{ "<parameter=" + arg_name + ">" }}
+{%- set arg_value = arg_value if arg_value is string else arg_value | string %}
+{{ arg_value+"</parameter>\n" }}
+{%- endfor %}
+{%- endif %}
+{{ "</function>\n" + toolcall_end_token }}
+{%- endfor %}
+{{ eos_token }}
+{%- elif message.role in ["user", "system"] %}
+{{ bos_token + message.role + "\n" + message.content + eos_token }}
+{%- elif message.role == "assistant" %}
+{{ bos_token + message.role }}
+{%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+{{ "\n" + think_begin_token + message.reasoning_content | trim + think_end_token }}
+{%- endif %}
+{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+{{ "\n" + message.content | trim + eos_token }}
+{%- endif %}
+{# 包括 tool 角色，在这个逻辑 #}
+{%- else %}
+{{ bos_token + message.role + "\n" + message.content + eos_token }}
+{%- endif %}
+{%- endfor %}
+{# ---------- 控制模型开始续写 ---------- #}
+{%- if add_generation_prompt %}
+{{ bos_token+"assistant\n" }}
+{%- if thinking_budget == 0 %}
+{{ think_begin_token+budget_begin_token }}
+{%- endif %}
+{%- endif %}
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}

seed_oss_36b/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "SeedOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.1,
+  "attention_out_bias": false,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 524288,
+  "mlp_bias": false,
+  "model_type": "seed_oss",
+  "num_attention_heads": 80,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "residual_dropout": 0.1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "rope_type": "default"
+  },
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "vocab_size": 155136
+}

seed_oss_36b/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 1,
+  "temperature": 1.1,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

seed_oss_36b/model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a213167449293a691ac5b70f9ffc0476af23e03320e0e8c004a1dca00f2365
+size 4954686296

seed_oss_36b/model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e549d153f22eebd091791b6bf261d6db4068c741741f2788051394f1cd3e6d6c
+size 4991407840

seed_oss_36b/model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a2059e17fbc5b8257441eec2b4bcf3e0de2ede7e4a4f9b62772e2f228b9632
+size 4834167328

seed_oss_36b/model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d4a74e5c7b86e9650c1d9376fa74445563aa9b3ea392dd8ff775119b3c3f75
+size 4886550176

seed_oss_36b/model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13cdc81d12940424e8d6fd5af2356fd43a64c85e8bab04300870087b8d3cf202
+size 4834167360

seed_oss_36b/model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5c52e5b585a8332cbfa49f0c5b3f19c7d24a9abc9a5d2c43ccef9548047204
+size 4886550176

seed_oss_36b/model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4bdf0eeb941ba511094615987c13eb70ddeb4416707f2959385bf08294a095
+size 4834167360

seed_oss_36b/model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0df199141e9b91aba4c8def0595320264c07a58a87b5bb447a0bcaacc2efdd
+size 4886550176

seed_oss_36b/model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47eb9f470e35b4dcf882ead4b1d9dec8302bb51b69534c603178ffb9b7fe12d7
+size 4834167360

seed_oss_36b/model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d232b475b2a3ead5a89f39850ba487804f273de24db65b922586b5235e400b
+size 4886550176

seed_oss_36b/model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f4420025a81f9dab905dbb9ad7576fd0f304badaa9bf6cfee5e203469d6e95
+size 4834167360

seed_oss_36b/model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078eeb9bff1343375489f770ce097e36dd6609ded65d57c753666b75407ba85b
+size 4886550176

seed_oss_36b/model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1246dc12584cb703b3b15b4cecea792b33e2e39d4f9c0f9e3c9d9f7e1e6234
+size 4834167360

seed_oss_36b/model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399d75dc096cce78b8e9b516de46006b69f5ad720b0ac901bcc31eeed7ea8154
+size 4886550176

seed_oss_36b/model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff222d68f4d03975cdb6eff0a8902236e3b2da8fe159144bed2c7fda4f88e9e7
+size 4031898896

seed_oss_36b/model.safetensors.index.json

@@ -0,0 +1,779 @@
+{
+  "metadata": {
+    "total_parameters": 1446912,
+    "total_size": 72302209024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

seed_oss_36b/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<seed:bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<seed:eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<seed:pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

seed_oss_36b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bd848f52451824a3033a9f1e67eea5b399a13c90f845a332d3a29537e05827
+size 11883696

seed_oss_36b/tokenizer_config.json

@@ -0,0 +1,1038 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<seed:bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<seed:pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<seed:eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<seed:think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "</seed:think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<seed:cot_budget_reflect>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "</seed:cot_budget_reflect>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<seed:tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "</seed:tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<[PLHD9_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<[PLHD10_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<[PLHD11_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<[PLHD12_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<[PLHD13_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<[PLHD14_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<[PLHD15_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<[PLHD16_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<[PLHD17_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<[PLHD18_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<[PLHD19_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<[PLHD20_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<[PLHD21_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<[PLHD22_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<[PLHD23_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<[PLHD24_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<[PLHD25_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<[PLHD26_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<[PLHD27_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<[PLHD28_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<[PLHD29_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<[PLHD30_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<[PLHD31_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<[PLHD32_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<[PLHD33_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<[PLHD34_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<[PLHD35_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<[PLHD36_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<[PLHD37_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "<[PLHD38_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<[PLHD39_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "<[PLHD40_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "<[PLHD41_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "<[PLHD42_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "<[PLHD43_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "<[PLHD44_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<[PLHD45_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "<[PLHD46_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "<[PLHD47_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "<[PLHD48_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "<[PLHD49_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50": {
+      "content": "<[PLHD50_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51": {
+      "content": "<[PLHD51_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "<[PLHD52_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<[PLHD53_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54": {
+      "content": "<[PLHD54_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "<[PLHD55_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "<[PLHD56_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "content": "<[PLHD57_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "<[PLHD58_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "<[PLHD59_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<[PLHD60_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "<[PLHD61_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "<[PLHD62_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "<[PLHD63_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "<[PLHD64_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<[PLHD65_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "<[PLHD66_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "<[PLHD67_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<[PLHD68_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "<[PLHD69_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "<[PLHD70_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<[PLHD71_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "<[PLHD72_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73": {
+      "content": "<[PLHD73_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<[PLHD74_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "<[PLHD75_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "content": "<[PLHD76_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "content": "<[PLHD77_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "78": {
+      "content": "<[PLHD78_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<[PLHD79_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<[PLHD80_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "content": "<[PLHD81_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "82": {
+      "content": "<[PLHD82_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "83": {
+      "content": "<[PLHD83_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84": {
+      "content": "<[PLHD84_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "85": {
+      "content": "<[PLHD85_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "86": {
+      "content": "<[PLHD86_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "87": {
+      "content": "<[PLHD87_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "88": {
+      "content": "<[PLHD88_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "89": {
+      "content": "<[PLHD89_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "90": {
+      "content": "<[PLHD90_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "<[PLHD91_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "<[PLHD92_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "content": "<[PLHD93_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "94": {
+      "content": "<[PLHD94_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "<[PLHD95_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<[PLHD96_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "<[PLHD97_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "98": {
+      "content": "<[PLHD98_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "99": {
+      "content": "<[PLHD99_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<[PLHD100_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "<[PLHD101_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<[PLHD102_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<[PLHD103_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "<[PLHD104_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<[PLHD105_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<[PLHD106_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<[PLHD107_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "<[PLHD108_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "109": {
+      "content": "<[PLHD109_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110": {
+      "content": "<[PLHD110_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "111": {
+      "content": "<[PLHD111_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "112": {
+      "content": "<[PLHD112_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "113": {
+      "content": "<[PLHD113_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "114": {
+      "content": "<[PLHD114_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "115": {
+      "content": "<[PLHD115_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "116": {
+      "content": "<[PLHD116_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "117": {
+      "content": "<[PLHD117_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "118": {
+      "content": "<[PLHD118_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "119": {
+      "content": "<[PLHD119_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120": {
+      "content": "<[PLHD120_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "121": {
+      "content": "<[PLHD121_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "122": {
+      "content": "<[PLHD122_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "123": {
+      "content": "<[PLHD123_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "124": {
+      "content": "<[PLHD124_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "125": {
+      "content": "<[PLHD125_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126": {
+      "content": "<[PLHD126_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "127": {
+      "content": "<[PLHD127_never_used]>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<seed:bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<seed:eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<seed:pad>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}

seed_oss_36b/trainer_log.jsonl

@@ -0,0 +1,243 @@
+{"current_steps": 10, "total_steps": 2421, "loss": 0.7862, "lr": 3.7037037037037036e-08, "epoch": 0.012391573729863693, "percentage": 0.41, "elapsed_time": "0:11:49", "remaining_time": "1 day, 23:31:08"}
+{"current_steps": 20, "total_steps": 2421, "loss": 0.7082, "lr": 7.818930041152264e-08, "epoch": 0.024783147459727387, "percentage": 0.83, "elapsed_time": "0:26:30", "remaining_time": "2 days, 5:01:33"}
+{"current_steps": 30, "total_steps": 2421, "loss": 0.722, "lr": 1.1934156378600823e-07, "epoch": 0.03717472118959108, "percentage": 1.24, "elapsed_time": "0:37:02", "remaining_time": "2 days, 1:11:33"}
+{"current_steps": 40, "total_steps": 2421, "loss": 0.6811, "lr": 1.604938271604938e-07, "epoch": 0.04956629491945477, "percentage": 1.65, "elapsed_time": "0:55:03", "remaining_time": "2 days, 6:37:28"}
+{"current_steps": 50, "total_steps": 2421, "loss": 0.6647, "lr": 2.016460905349794e-07, "epoch": 0.061957868649318466, "percentage": 2.07, "elapsed_time": "1:04:41", "remaining_time": "2 days, 3:07:34"}
+{"current_steps": 60, "total_steps": 2421, "loss": 0.5526, "lr": 2.4279835390946503e-07, "epoch": 0.07434944237918216, "percentage": 2.48, "elapsed_time": "1:22:49", "remaining_time": "2 days, 6:19:22"}
+{"current_steps": 70, "total_steps": 2421, "loss": 0.5335, "lr": 2.839506172839506e-07, "epoch": 0.08674101610904585, "percentage": 2.89, "elapsed_time": "1:30:02", "remaining_time": "2 days, 2:23:50"}
+{"current_steps": 80, "total_steps": 2421, "loss": 0.4589, "lr": 3.2510288065843623e-07, "epoch": 0.09913258983890955, "percentage": 3.3, "elapsed_time": "1:39:55", "remaining_time": "2 days, 0:43:52"}
+{"current_steps": 90, "total_steps": 2421, "loss": 0.3682, "lr": 3.662551440329218e-07, "epoch": 0.11152416356877323, "percentage": 3.72, "elapsed_time": "1:54:34", "remaining_time": "2 days, 1:27:29"}
+{"current_steps": 100, "total_steps": 2421, "loss": 0.3385, "lr": 4.0740740740740737e-07, "epoch": 0.12391573729863693, "percentage": 4.13, "elapsed_time": "2:01:16", "remaining_time": "1 day, 22:54:49"}
+{"current_steps": 110, "total_steps": 2421, "loss": 0.3392, "lr": 4.48559670781893e-07, "epoch": 0.13630731102850063, "percentage": 4.54, "elapsed_time": "2:09:14", "remaining_time": "1 day, 21:15:09"}
+{"current_steps": 120, "total_steps": 2421, "loss": 0.3246, "lr": 4.897119341563785e-07, "epoch": 0.14869888475836432, "percentage": 4.96, "elapsed_time": "2:14:40", "remaining_time": "1 day, 19:02:28"}
+{"current_steps": 130, "total_steps": 2421, "loss": 0.2724, "lr": 5.308641975308642e-07, "epoch": 0.161090458488228, "percentage": 5.37, "elapsed_time": "2:29:53", "remaining_time": "1 day, 20:01:31"}
+{"current_steps": 140, "total_steps": 2421, "loss": 0.2456, "lr": 5.720164609053498e-07, "epoch": 0.1734820322180917, "percentage": 5.78, "elapsed_time": "2:44:04", "remaining_time": "1 day, 20:33:08"}
+{"current_steps": 150, "total_steps": 2421, "loss": 0.2693, "lr": 6.131687242798354e-07, "epoch": 0.18587360594795538, "percentage": 6.2, "elapsed_time": "3:00:48", "remaining_time": "1 day, 21:37:32"}
+{"current_steps": 160, "total_steps": 2421, "loss": 0.2309, "lr": 6.54320987654321e-07, "epoch": 0.1982651796778191, "percentage": 6.61, "elapsed_time": "3:10:24", "remaining_time": "1 day, 20:50:39"}
+{"current_steps": 170, "total_steps": 2421, "loss": 0.2529, "lr": 6.954732510288066e-07, "epoch": 0.21065675340768278, "percentage": 7.02, "elapsed_time": "3:20:35", "remaining_time": "1 day, 20:16:07"}
+{"current_steps": 180, "total_steps": 2421, "loss": 0.2378, "lr": 7.366255144032922e-07, "epoch": 0.22304832713754646, "percentage": 7.43, "elapsed_time": "3:31:27", "remaining_time": "1 day, 19:52:42"}
+{"current_steps": 190, "total_steps": 2421, "loss": 0.2358, "lr": 7.777777777777778e-07, "epoch": 0.23543990086741015, "percentage": 7.85, "elapsed_time": "3:47:49", "remaining_time": "1 day, 20:35:08"}
+{"current_steps": 200, "total_steps": 2421, "loss": 0.2311, "lr": 8.189300411522634e-07, "epoch": 0.24783147459727387, "percentage": 8.26, "elapsed_time": "4:00:58", "remaining_time": "1 day, 20:36:04"}
+{"current_steps": 210, "total_steps": 2421, "loss": 0.2419, "lr": 8.600823045267489e-07, "epoch": 0.26022304832713755, "percentage": 8.67, "elapsed_time": "4:11:14", "remaining_time": "1 day, 20:05:11"}
+{"current_steps": 220, "total_steps": 2421, "loss": 0.2375, "lr": 9.012345679012346e-07, "epoch": 0.27261462205700127, "percentage": 9.09, "elapsed_time": "4:15:39", "remaining_time": "1 day, 18:37:42"}
+{"current_steps": 230, "total_steps": 2421, "loss": 0.2324, "lr": 9.423868312757202e-07, "epoch": 0.2850061957868649, "percentage": 9.5, "elapsed_time": "4:31:09", "remaining_time": "1 day, 19:03:03"}
+{"current_steps": 240, "total_steps": 2421, "loss": 0.2218, "lr": 9.835390946502057e-07, "epoch": 0.29739776951672864, "percentage": 9.91, "elapsed_time": "4:42:28", "remaining_time": "1 day, 18:47:00"}
+{"current_steps": 250, "total_steps": 2421, "loss": 0.2141, "lr": 9.999812749151967e-07, "epoch": 0.3097893432465923, "percentage": 10.33, "elapsed_time": "5:01:33", "remaining_time": "1 day, 19:38:43"}
+{"current_steps": 260, "total_steps": 2421, "loss": 0.1965, "lr": 9.998668489204264e-07, "epoch": 0.322180916976456, "percentage": 10.74, "elapsed_time": "5:23:26", "remaining_time": "1 day, 20:48:17"}
+{"current_steps": 270, "total_steps": 2421, "loss": 0.231, "lr": 9.99648423533726e-07, "epoch": 0.3345724907063197, "percentage": 11.15, "elapsed_time": "5:39:52", "remaining_time": "1 day, 21:07:39"}
+{"current_steps": 280, "total_steps": 2421, "loss": 0.2075, "lr": 9.993260441994114e-07, "epoch": 0.3469640644361834, "percentage": 11.57, "elapsed_time": "5:50:10", "remaining_time": "1 day, 20:37:38"}
+{"current_steps": 290, "total_steps": 2421, "loss": 0.2053, "lr": 9.988997779898544e-07, "epoch": 0.3593556381660471, "percentage": 11.98, "elapsed_time": "6:00:07", "remaining_time": "1 day, 20:06:20"}
+{"current_steps": 300, "total_steps": 2421, "loss": 0.1919, "lr": 9.98369713591525e-07, "epoch": 0.37174721189591076, "percentage": 12.39, "elapsed_time": "6:15:09", "remaining_time": "1 day, 20:12:19"}
+{"current_steps": 310, "total_steps": 2421, "loss": 0.1861, "lr": 9.977359612865422e-07, "epoch": 0.38413878562577447, "percentage": 12.8, "elapsed_time": "6:30:44", "remaining_time": "1 day, 20:20:52"}
+{"current_steps": 320, "total_steps": 2421, "loss": 0.213, "lr": 9.969986529297278e-07, "epoch": 0.3965303593556382, "percentage": 13.22, "elapsed_time": "6:43:33", "remaining_time": "1 day, 20:09:39"}
+{"current_steps": 330, "total_steps": 2421, "loss": 0.2068, "lr": 9.96157941921174e-07, "epoch": 0.40892193308550184, "percentage": 13.63, "elapsed_time": "6:53:39", "remaining_time": "1 day, 19:41:04"}
+{"current_steps": 340, "total_steps": 2421, "loss": 0.2058, "lr": 9.95214003174328e-07, "epoch": 0.42131350681536556, "percentage": 14.04, "elapsed_time": "7:01:18", "remaining_time": "1 day, 18:58:38"}
+{"current_steps": 350, "total_steps": 2421, "loss": 0.2143, "lr": 9.941670330796007e-07, "epoch": 0.43370508054522927, "percentage": 14.46, "elapsed_time": "7:12:50", "remaining_time": "1 day, 18:41:09"}
+{"current_steps": 360, "total_steps": 2421, "loss": 0.1796, "lr": 9.930172494635056e-07, "epoch": 0.44609665427509293, "percentage": 14.87, "elapsed_time": "7:33:07", "remaining_time": "1 day, 19:14:08"}
+{"current_steps": 370, "total_steps": 2421, "loss": 0.2041, "lr": 9.917648915433411e-07, "epoch": 0.45848822800495664, "percentage": 15.28, "elapsed_time": "7:51:35", "remaining_time": "1 day, 19:34:10"}
+{"current_steps": 380, "total_steps": 2421, "loss": 0.1869, "lr": 9.904102198774188e-07, "epoch": 0.4708798017348203, "percentage": 15.7, "elapsed_time": "8:03:25", "remaining_time": "1 day, 19:16:31"}
+{"current_steps": 390, "total_steps": 2421, "loss": 0.1941, "lr": 9.889535163108536e-07, "epoch": 0.483271375464684, "percentage": 16.11, "elapsed_time": "8:11:20", "remaining_time": "1 day, 18:38:44"}
+{"current_steps": 400, "total_steps": 2421, "loss": 0.2044, "lr": 9.873950839169247e-07, "epoch": 0.49566294919454773, "percentage": 16.52, "elapsed_time": "8:17:15", "remaining_time": "1 day, 17:52:25"}
+{"current_steps": 410, "total_steps": 2421, "loss": 0.1784, "lr": 9.857352469340204e-07, "epoch": 0.5080545229244114, "percentage": 16.94, "elapsed_time": "8:38:27", "remaining_time": "1 day, 18:22:56"}
+{"current_steps": 420, "total_steps": 2421, "loss": 0.1927, "lr": 9.83974350698178e-07, "epoch": 0.5204460966542751, "percentage": 17.35, "elapsed_time": "8:47:45", "remaining_time": "1 day, 17:54:23"}
+{"current_steps": 430, "total_steps": 2421, "loss": 0.1784, "lr": 9.821127615712364e-07, "epoch": 0.5328376703841388, "percentage": 17.76, "elapsed_time": "9:05:03", "remaining_time": "1 day, 18:03:46"}
+{"current_steps": 440, "total_steps": 2421, "loss": 0.214, "lr": 9.801508668646117e-07, "epoch": 0.5452292441140025, "percentage": 18.17, "elapsed_time": "9:10:36", "remaining_time": "1 day, 17:19:01"}
+{"current_steps": 450, "total_steps": 2421, "loss": 0.1758, "lr": 9.780890747587162e-07, "epoch": 0.5576208178438662, "percentage": 18.59, "elapsed_time": "9:21:10", "remaining_time": "1 day, 16:57:56"}
+{"current_steps": 460, "total_steps": 2421, "loss": 0.207, "lr": 9.759278142180347e-07, "epoch": 0.5700123915737298, "percentage": 19.0, "elapsed_time": "9:34:17", "remaining_time": "1 day, 16:48:14"}
+{"current_steps": 470, "total_steps": 2421, "loss": 0.1916, "lr": 9.736675349018767e-07, "epoch": 0.5824039653035935, "percentage": 19.41, "elapsed_time": "9:44:57", "remaining_time": "1 day, 16:28:11"}
+{"current_steps": 480, "total_steps": 2421, "loss": 0.2158, "lr": 9.713087070708224e-07, "epoch": 0.5947955390334573, "percentage": 19.83, "elapsed_time": "9:50:43", "remaining_time": "1 day, 15:48:43"}
+{"current_steps": 490, "total_steps": 2421, "loss": 0.1918, "lr": 9.688518214888835e-07, "epoch": 0.6071871127633209, "percentage": 20.24, "elapsed_time": "9:57:20", "remaining_time": "1 day, 15:13:59"}
+{"current_steps": 500, "total_steps": 2421, "loss": 0.1847, "lr": 9.662973893213975e-07, "epoch": 0.6195786864931846, "percentage": 20.65, "elapsed_time": "10:09:02", "remaining_time": "1 day, 14:59:58"}
+{"current_steps": 510, "total_steps": 2421, "loss": 0.1866, "lr": 9.636459420286778e-07, "epoch": 0.6319702602230484, "percentage": 21.07, "elapsed_time": "10:20:02", "remaining_time": "1 day, 14:43:21"}
+{"current_steps": 520, "total_steps": 2421, "loss": 0.1757, "lr": 9.60898031255441e-07, "epoch": 0.644361833952912, "percentage": 21.48, "elapsed_time": "10:38:37", "remaining_time": "1 day, 14:54:38"}
+{"current_steps": 530, "total_steps": 2421, "loss": 0.2255, "lr": 9.580542287160346e-07, "epoch": 0.6567534076827757, "percentage": 21.89, "elapsed_time": "10:46:19", "remaining_time": "1 day, 14:26:01"}
+{"current_steps": 540, "total_steps": 2421, "loss": 0.2097, "lr": 9.551151260754905e-07, "epoch": 0.6691449814126395, "percentage": 22.3, "elapsed_time": "10:54:26", "remaining_time": "1 day, 13:59:39"}
+{"current_steps": 550, "total_steps": 2421, "loss": 0.1717, "lr": 9.520813348264251e-07, "epoch": 0.6815365551425031, "percentage": 22.72, "elapsed_time": "11:07:42", "remaining_time": "1 day, 13:51:23"}
+{"current_steps": 560, "total_steps": 2421, "loss": 0.1784, "lr": 9.489534861618166e-07, "epoch": 0.6939281288723668, "percentage": 23.13, "elapsed_time": "11:17:05", "remaining_time": "1 day, 13:30:07"}
+{"current_steps": 570, "total_steps": 2421, "loss": 0.1835, "lr": 9.457322308436829e-07, "epoch": 0.7063197026022305, "percentage": 23.54, "elapsed_time": "11:32:38", "remaining_time": "1 day, 13:29:16"}
+{"current_steps": 580, "total_steps": 2421, "loss": 0.1979, "lr": 9.424182390676871e-07, "epoch": 0.7187112763320942, "percentage": 23.96, "elapsed_time": "11:37:57", "remaining_time": "1 day, 12:55:24"}
+{"current_steps": 590, "total_steps": 2421, "loss": 0.1906, "lr": 9.390122003237009e-07, "epoch": 0.7311028500619579, "percentage": 24.37, "elapsed_time": "11:54:18", "remaining_time": "1 day, 12:56:47"}
+{"current_steps": 600, "total_steps": 2421, "loss": 0.189, "lr": 9.355148232523536e-07, "epoch": 0.7434944237918215, "percentage": 24.78, "elapsed_time": "12:06:36", "remaining_time": "1 day, 12:45:15"}
+{"current_steps": 610, "total_steps": 2421, "loss": 0.1925, "lr": 9.319268354975957e-07, "epoch": 0.7558859975216853, "percentage": 25.2, "elapsed_time": "12:21:43", "remaining_time": "1 day, 12:42:04"}
+{"current_steps": 620, "total_steps": 2421, "loss": 0.1974, "lr": 9.282489835553104e-07, "epoch": 0.7682775712515489, "percentage": 25.61, "elapsed_time": "12:37:35", "remaining_time": "1 day, 12:40:40"}
+{"current_steps": 630, "total_steps": 2421, "loss": 0.182, "lr": 9.244820326180011e-07, "epoch": 0.7806691449814126, "percentage": 26.02, "elapsed_time": "12:47:40", "remaining_time": "1 day, 12:22:22"}
+{"current_steps": 640, "total_steps": 2421, "loss": 0.1879, "lr": 9.206267664155906e-07, "epoch": 0.7930607187112764, "percentage": 26.44, "elapsed_time": "13:04:05", "remaining_time": "1 day, 12:21:59"}
+{"current_steps": 650, "total_steps": 2421, "loss": 0.1679, "lr": 9.166839870523626e-07, "epoch": 0.80545229244114, "percentage": 26.85, "elapsed_time": "13:23:38", "remaining_time": "1 day, 12:29:37"}
+{"current_steps": 660, "total_steps": 2421, "loss": 0.1994, "lr": 9.126545148400806e-07, "epoch": 0.8178438661710037, "percentage": 27.26, "elapsed_time": "13:32:25", "remaining_time": "1 day, 12:07:43"}
+{"current_steps": 670, "total_steps": 2421, "loss": 0.1824, "lr": 9.085391881273181e-07, "epoch": 0.8302354399008675, "percentage": 27.67, "elapsed_time": "13:43:03", "remaining_time": "1 day, 11:51:01"}
+{"current_steps": 680, "total_steps": 2421, "loss": 0.1747, "lr": 9.043388631250379e-07, "epoch": 0.8426270136307311, "percentage": 28.09, "elapsed_time": "13:54:13", "remaining_time": "1 day, 11:35:50"}
+{"current_steps": 690, "total_steps": 2421, "loss": 0.1822, "lr": 9.000544137284518e-07, "epoch": 0.8550185873605948, "percentage": 28.5, "elapsed_time": "14:01:35", "remaining_time": "1 day, 11:11:17"}
+{"current_steps": 700, "total_steps": 2421, "loss": 0.1722, "lr": 8.956867313352054e-07, "epoch": 0.8674101610904585, "percentage": 28.91, "elapsed_time": "14:09:53", "remaining_time": "1 day, 10:49:31"}
+{"current_steps": 710, "total_steps": 2421, "loss": 0.1824, "lr": 8.912367246599174e-07, "epoch": 0.8798017348203222, "percentage": 29.33, "elapsed_time": "14:15:47", "remaining_time": "1 day, 10:22:20"}
+{"current_steps": 720, "total_steps": 2421, "loss": 0.2045, "lr": 8.867053195451182e-07, "epoch": 0.8921933085501859, "percentage": 29.74, "elapsed_time": "14:25:54", "remaining_time": "1 day, 10:05:42"}
+{"current_steps": 730, "total_steps": 2421, "loss": 0.1888, "lr": 8.820934587686245e-07, "epoch": 0.9045848822800495, "percentage": 30.15, "elapsed_time": "14:35:09", "remaining_time": "1 day, 9:47:13"}
+{"current_steps": 740, "total_steps": 2421, "loss": 0.1929, "lr": 8.77402101847391e-07, "epoch": 0.9169764560099133, "percentage": 30.57, "elapsed_time": "14:41:31", "remaining_time": "1 day, 9:22:29"}
+{"current_steps": 750, "total_steps": 2421, "loss": 0.1975, "lr": 8.726322248378774e-07, "epoch": 0.929368029739777, "percentage": 30.98, "elapsed_time": "14:59:18", "remaining_time": "1 day, 9:23:38"}
+{"current_steps": 760, "total_steps": 2421, "loss": 0.1908, "lr": 8.677848201329774e-07, "epoch": 0.9417596034696406, "percentage": 31.39, "elapsed_time": "15:11:56", "remaining_time": "1 day, 9:13:04"}
+{"current_steps": 770, "total_steps": 2421, "loss": 0.181, "lr": 8.628608962555466e-07, "epoch": 0.9541511771995044, "percentage": 31.81, "elapsed_time": "15:28:32", "remaining_time": "1 day, 9:10:57"}
+{"current_steps": 780, "total_steps": 2421, "loss": 0.17, "lr": 8.578614776485743e-07, "epoch": 0.966542750929368, "percentage": 32.22, "elapsed_time": "15:42:05", "remaining_time": "1 day, 9:02:00"}
+{"current_steps": 790, "total_steps": 2421, "loss": 0.1703, "lr": 8.527876044620452e-07, "epoch": 0.9789343246592317, "percentage": 32.63, "elapsed_time": "15:55:21", "remaining_time": "1 day, 8:52:22"}
+{"current_steps": 800, "total_steps": 2421, "loss": 0.1945, "lr": 8.476403323365309e-07, "epoch": 0.9913258983890955, "percentage": 33.04, "elapsed_time": "16:08:52", "remaining_time": "1 day, 8:43:11"}
+{"current_steps": 810, "total_steps": 2421, "loss": 0.169, "lr": 8.424207321835597e-07, "epoch": 1.003717472118959, "percentage": 33.46, "elapsed_time": "16:32:31", "remaining_time": "1 day, 8:54:02"}
+{"current_steps": 820, "total_steps": 2421, "loss": 0.1722, "lr": 8.37129889962809e-07, "epoch": 1.016109045848823, "percentage": 33.87, "elapsed_time": "16:45:44", "remaining_time": "1 day, 8:43:39"}
+{"current_steps": 830, "total_steps": 2421, "loss": 0.1795, "lr": 8.31768906456167e-07, "epoch": 1.0285006195786865, "percentage": 34.28, "elapsed_time": "16:54:37", "remaining_time": "1 day, 8:24:54"}
+{"current_steps": 840, "total_steps": 2421, "loss": 0.1726, "lr": 8.263388970387101e-07, "epoch": 1.0408921933085502, "percentage": 34.7, "elapsed_time": "17:07:52", "remaining_time": "1 day, 8:14:36"}
+{"current_steps": 850, "total_steps": 2421, "loss": 0.1788, "lr": 8.20840991446645e-07, "epoch": 1.0532837670384139, "percentage": 35.11, "elapsed_time": "17:12:22", "remaining_time": "1 day, 7:48:04"}
+{"current_steps": 860, "total_steps": 2421, "loss": 0.1565, "lr": 8.152763335422612e-07, "epoch": 1.0656753407682775, "percentage": 35.52, "elapsed_time": "17:23:06", "remaining_time": "1 day, 7:33:22"}
+{"current_steps": 870, "total_steps": 2421, "loss": 0.1632, "lr": 8.096460810759471e-07, "epoch": 1.0780669144981412, "percentage": 35.94, "elapsed_time": "17:32:25", "remaining_time": "1 day, 7:16:12"}
+{"current_steps": 880, "total_steps": 2421, "loss": 0.1754, "lr": 8.039514054453141e-07, "epoch": 1.090458488228005, "percentage": 36.35, "elapsed_time": "17:40:00", "remaining_time": "1 day, 6:56:13"}
+{"current_steps": 890, "total_steps": 2421, "loss": 0.1603, "lr": 7.981934914514829e-07, "epoch": 1.1028500619578687, "percentage": 36.76, "elapsed_time": "17:53:52", "remaining_time": "1 day, 6:47:18"}
+{"current_steps": 900, "total_steps": 2421, "loss": 0.1602, "lr": 7.923735370525808e-07, "epoch": 1.1152416356877324, "percentage": 37.17, "elapsed_time": "18:07:04", "remaining_time": "1 day, 6:37:09"}
+{"current_steps": 910, "total_steps": 2421, "loss": 0.1615, "lr": 7.86492753114501e-07, "epoch": 1.127633209417596, "percentage": 37.59, "elapsed_time": "18:16:30", "remaining_time": "1 day, 6:20:41"}
+{"current_steps": 920, "total_steps": 2421, "loss": 0.1753, "lr": 7.805523631589774e-07, "epoch": 1.1400247831474597, "percentage": 38.0, "elapsed_time": "18:35:56", "remaining_time": "1 day, 6:20:40"}
+{"current_steps": 930, "total_steps": 2421, "loss": 0.1562, "lr": 7.745536031090251e-07, "epoch": 1.1524163568773234, "percentage": 38.41, "elapsed_time": "18:56:44", "remaining_time": "1 day, 6:22:27"}
+{"current_steps": 940, "total_steps": 2421, "loss": 0.1653, "lr": 7.684977210318023e-07, "epoch": 1.164807930607187, "percentage": 38.83, "elapsed_time": "19:12:58", "remaining_time": "1 day, 6:16:33"}
+{"current_steps": 950, "total_steps": 2421, "loss": 0.164, "lr": 7.62385976878944e-07, "epoch": 1.177199504337051, "percentage": 39.24, "elapsed_time": "19:25:08", "remaining_time": "1 day, 6:04:07"}
+{"current_steps": 960, "total_steps": 2421, "loss": 0.171, "lr": 7.562196422244245e-07, "epoch": 1.1895910780669146, "percentage": 39.65, "elapsed_time": "19:37:31", "remaining_time": "1 day, 5:52:03"}
+{"current_steps": 970, "total_steps": 2421, "loss": 0.1618, "lr": 7.5e-07, "epoch": 1.2019826517967782, "percentage": 40.07, "elapsed_time": "19:43:36", "remaining_time": "1 day, 5:30:32"}
+{"current_steps": 980, "total_steps": 2421, "loss": 0.1504, "lr": 7.437283442282902e-07, "epoch": 1.2143742255266419, "percentage": 40.48, "elapsed_time": "20:03:01", "remaining_time": "1 day, 5:28:55"}
+{"current_steps": 990, "total_steps": 2421, "loss": 0.1887, "lr": 7.374059797535515e-07, "epoch": 1.2267657992565055, "percentage": 40.89, "elapsed_time": "20:10:20", "remaining_time": "1 day, 5:09:29"}
+{"current_steps": 1000, "total_steps": 2421, "loss": 0.1603, "lr": 7.31034221970198e-07, "epoch": 1.2391573729863692, "percentage": 41.31, "elapsed_time": "20:23:56", "remaining_time": "1 day, 4:59:13"}
+{"current_steps": 1010, "total_steps": 2421, "loss": 0.163, "lr": 7.246143965491287e-07, "epoch": 1.251548946716233, "percentage": 41.72, "elapsed_time": "20:40:17", "remaining_time": "1 day, 4:52:43"}
+{"current_steps": 1020, "total_steps": 2421, "loss": 0.1614, "lr": 7.181478391619161e-07, "epoch": 1.2639405204460967, "percentage": 42.13, "elapsed_time": "20:52:52", "remaining_time": "1 day, 4:40:51"}
+{"current_steps": 1030, "total_steps": 2421, "loss": 0.162, "lr": 7.116358952029139e-07, "epoch": 1.2763320941759604, "percentage": 42.54, "elapsed_time": "21:09:40", "remaining_time": "1 day, 4:34:40"}
+{"current_steps": 1040, "total_steps": 2421, "loss": 0.1696, "lr": 7.05079919509342e-07, "epoch": 1.288723667905824, "percentage": 42.96, "elapsed_time": "21:21:46", "remaining_time": "1 day, 4:22:03"}
+{"current_steps": 1050, "total_steps": 2421, "loss": 0.1772, "lr": 6.984812760794078e-07, "epoch": 1.3011152416356877, "percentage": 43.37, "elapsed_time": "21:32:41", "remaining_time": "1 day, 4:07:52"}
+{"current_steps": 1060, "total_steps": 2421, "loss": 0.163, "lr": 6.918413377885192e-07, "epoch": 1.3135068153655514, "percentage": 43.78, "elapsed_time": "21:49:15", "remaining_time": "1 day, 4:01:02"}
+{"current_steps": 1070, "total_steps": 2421, "loss": 0.1565, "lr": 6.851614861036532e-07, "epoch": 1.325898389095415, "percentage": 44.2, "elapsed_time": "22:00:27", "remaining_time": "1 day, 3:47:13"}
+{"current_steps": 1080, "total_steps": 2421, "loss": 0.1486, "lr": 6.784431107959358e-07, "epoch": 1.3382899628252787, "percentage": 44.61, "elapsed_time": "22:18:04", "remaining_time": "1 day, 3:41:26"}
+{"current_steps": 1090, "total_steps": 2421, "loss": 0.1841, "lr": 6.716876096514943e-07, "epoch": 1.3506815365551426, "percentage": 45.02, "elapsed_time": "22:23:37", "remaining_time": "1 day, 3:20:42"}
+{"current_steps": 1100, "total_steps": 2421, "loss": 0.144, "lr": 6.64896388180641e-07, "epoch": 1.3630731102850062, "percentage": 45.44, "elapsed_time": "22:38:08", "remaining_time": "1 day, 3:10:59"}
+{"current_steps": 1110, "total_steps": 2421, "loss": 0.1627, "lr": 6.580708593254526e-07, "epoch": 1.3754646840148699, "percentage": 45.85, "elapsed_time": "22:47:48", "remaining_time": "1 day, 2:55:30"}
+{"current_steps": 1120, "total_steps": 2421, "loss": 0.172, "lr": 6.512124431658005e-07, "epoch": 1.3878562577447335, "percentage": 46.26, "elapsed_time": "23:04:49", "remaining_time": "1 day, 2:48:37"}
+{"current_steps": 1130, "total_steps": 2421, "loss": 0.1705, "lr": 6.443225666238975e-07, "epoch": 1.4002478314745972, "percentage": 46.67, "elapsed_time": "23:21:23", "remaining_time": "1 day, 2:41:03"}
+{"current_steps": 1140, "total_steps": 2421, "loss": 0.1404, "lr": 6.37402663167421e-07, "epoch": 1.412639405204461, "percentage": 47.09, "elapsed_time": "23:34:43", "remaining_time": "1 day, 2:29:42"}
+{"current_steps": 1150, "total_steps": 2421, "loss": 0.1534, "lr": 6.304541725112734e-07, "epoch": 1.4250309789343247, "percentage": 47.5, "elapsed_time": "23:54:47", "remaining_time": "1 day, 2:25:45"}
+{"current_steps": 1160, "total_steps": 2421, "loss": 0.1636, "lr": 6.234785403180437e-07, "epoch": 1.4374225526641884, "percentage": 47.91, "elapsed_time": "1 day, 0:12:55", "remaining_time": "1 day, 2:19:25"}
+{"current_steps": 1170, "total_steps": 2421, "loss": 0.153, "lr": 6.16477217897232e-07, "epoch": 1.449814126394052, "percentage": 48.33, "elapsed_time": "1 day, 0:31:44", "remaining_time": "1 day, 2:13:37"}
+{"current_steps": 1180, "total_steps": 2421, "loss": 0.1508, "lr": 6.094516619032975e-07, "epoch": 1.4622057001239157, "percentage": 48.74, "elapsed_time": "1 day, 0:48:34", "remaining_time": "1 day, 2:05:31"}
+{"current_steps": 1190, "total_steps": 2421, "loss": 0.1548, "lr": 6.024033340325954e-07, "epoch": 1.4745972738537794, "percentage": 49.15, "elapsed_time": "1 day, 0:58:12", "remaining_time": "1 day, 1:49:49"}
+{"current_steps": 1200, "total_steps": 2421, "loss": 0.1785, "lr": 5.953337007192658e-07, "epoch": 1.486988847583643, "percentage": 49.57, "elapsed_time": "1 day, 1:07:48", "remaining_time": "1 day, 1:34:11"}
+{"current_steps": 1210, "total_steps": 2421, "loss": 0.17, "lr": 5.882442328301355e-07, "epoch": 1.4993804213135067, "percentage": 49.98, "elapsed_time": "1 day, 1:15:24", "remaining_time": "1 day, 1:16:39"}
+{"current_steps": 1220, "total_steps": 2421, "loss": 0.1788, "lr": 5.811364053586972e-07, "epoch": 1.5117719950433703, "percentage": 50.39, "elapsed_time": "1 day, 1:24:51", "remaining_time": "1 day, 1:01:07"}
+{"current_steps": 1230, "total_steps": 2421, "loss": 0.1911, "lr": 5.740116971182321e-07, "epoch": 1.5241635687732342, "percentage": 50.81, "elapsed_time": "1 day, 1:35:18", "remaining_time": "1 day, 0:46:38"}
+{"current_steps": 1240, "total_steps": 2421, "loss": 0.1687, "lr": 5.668715904341365e-07, "epoch": 1.5365551425030979, "percentage": 51.22, "elapsed_time": "1 day, 1:48:37", "remaining_time": "1 day, 0:34:56"}
+{"current_steps": 1250, "total_steps": 2421, "loss": 0.1595, "lr": 5.597175708355162e-07, "epoch": 1.5489467162329615, "percentage": 51.63, "elapsed_time": "1 day, 2:02:36", "remaining_time": "1 day, 0:23:51"}
+{"current_steps": 1260, "total_steps": 2421, "loss": 0.1618, "lr": 5.525511267461185e-07, "epoch": 1.5613382899628254, "percentage": 52.04, "elapsed_time": "1 day, 2:12:15", "remaining_time": "1 day, 0:08:42"}
+{"current_steps": 1270, "total_steps": 2421, "loss": 0.1533, "lr": 5.453737491746572e-07, "epoch": 1.573729863692689, "percentage": 52.46, "elapsed_time": "1 day, 2:32:40", "remaining_time": "1 day, 0:03:25"}
+{"current_steps": 1280, "total_steps": 2421, "loss": 0.1681, "lr": 5.38186931404603e-07, "epoch": 1.5861214374225527, "percentage": 52.87, "elapsed_time": "1 day, 2:41:05", "remaining_time": "23:47:13"}
+{"current_steps": 1290, "total_steps": 2421, "loss": 0.1656, "lr": 5.309921686834996e-07, "epoch": 1.5985130111524164, "percentage": 53.28, "elapsed_time": "1 day, 3:00:05", "remaining_time": "23:40:24"}
+{"current_steps": 1300, "total_steps": 2421, "loss": 0.1718, "lr": 5.237909579118712e-07, "epoch": 1.61090458488228, "percentage": 53.7, "elapsed_time": "1 day, 3:09:54", "remaining_time": "23:25:29"}
+{"current_steps": 1310, "total_steps": 2421, "loss": 0.1584, "lr": 5.165847973317854e-07, "epoch": 1.6232961586121437, "percentage": 54.11, "elapsed_time": "1 day, 3:21:30", "remaining_time": "23:12:09"}
+{"current_steps": 1320, "total_steps": 2421, "loss": 0.1824, "lr": 5.093751862151388e-07, "epoch": 1.6356877323420074, "percentage": 54.52, "elapsed_time": "1 day, 3:27:46", "remaining_time": "22:54:23"}
+{"current_steps": 1330, "total_steps": 2421, "loss": 0.1708, "lr": 5.021636245517261e-07, "epoch": 1.648079306071871, "percentage": 54.94, "elapsed_time": "1 day, 3:32:43", "remaining_time": "22:35:44"}
+{"current_steps": 1340, "total_steps": 2421, "loss": 0.1482, "lr": 4.949516127371617e-07, "epoch": 1.6604708798017347, "percentage": 55.35, "elapsed_time": "1 day, 3:39:57", "remaining_time": "22:19:07"}
+{"current_steps": 1350, "total_steps": 2421, "loss": 0.1634, "lr": 4.877406512607159e-07, "epoch": 1.6728624535315983, "percentage": 55.76, "elapsed_time": "1 day, 3:50:42", "remaining_time": "22:05:25"}
+{"current_steps": 1360, "total_steps": 2421, "loss": 0.1587, "lr": 4.805322403931311e-07, "epoch": 1.6852540272614622, "percentage": 56.18, "elapsed_time": "1 day, 4:00:17", "remaining_time": "21:50:52"}
+{"current_steps": 1370, "total_steps": 2421, "loss": 0.156, "lr": 4.7332787987448597e-07, "epoch": 1.6976456009913259, "percentage": 56.59, "elapsed_time": "1 day, 4:15:33", "remaining_time": "21:40:45"}
+{"current_steps": 1380, "total_steps": 2421, "loss": 0.1606, "lr": 4.6612906860216606e-07, "epoch": 1.7100371747211895, "percentage": 57.0, "elapsed_time": "1 day, 4:29:34", "remaining_time": "21:29:37"}
+{"current_steps": 1390, "total_steps": 2421, "loss": 0.1712, "lr": 4.589373043190137e-07, "epoch": 1.7224287484510534, "percentage": 57.41, "elapsed_time": "1 day, 4:42:17", "remaining_time": "21:17:28"}
+{"current_steps": 1400, "total_steps": 2421, "loss": 0.1642, "lr": 4.5175408330171514e-07, "epoch": 1.734820322180917, "percentage": 57.83, "elapsed_time": "1 day, 4:54:46", "remaining_time": "21:05:09"}
+{"current_steps": 1410, "total_steps": 2421, "loss": 0.1612, "lr": 4.445809000494945e-07, "epoch": 1.7472118959107807, "percentage": 58.24, "elapsed_time": "1 day, 5:04:04", "remaining_time": "20:50:32"}
+{"current_steps": 1420, "total_steps": 2421, "loss": 0.1566, "lr": 4.3741924697317704e-07, "epoch": 1.7596034696406444, "percentage": 58.65, "elapsed_time": "1 day, 5:16:28", "remaining_time": "20:38:11"}
+{"current_steps": 1430, "total_steps": 2421, "loss": 0.1453, "lr": 4.3027061408468636e-07, "epoch": 1.771995043370508, "percentage": 59.07, "elapsed_time": "1 day, 5:32:43", "remaining_time": "20:28:30"}
+{"current_steps": 1440, "total_steps": 2421, "loss": 0.1517, "lr": 4.231364886870416e-07, "epoch": 1.7843866171003717, "percentage": 59.48, "elapsed_time": "1 day, 5:44:14", "remaining_time": "20:15:30"}
+{"current_steps": 1450, "total_steps": 2421, "loss": 0.1531, "lr": 4.160183550649175e-07, "epoch": 1.7967781908302354, "percentage": 59.89, "elapsed_time": "1 day, 5:58:53", "remaining_time": "20:04:38"}
+{"current_steps": 1460, "total_steps": 2421, "loss": 0.1749, "lr": 4.0891769417583317e-07, "epoch": 1.809169764560099, "percentage": 60.31, "elapsed_time": "1 day, 6:15:25", "remaining_time": "19:54:56"}
+{"current_steps": 1470, "total_steps": 2421, "loss": 0.1589, "lr": 4.0183598334203227e-07, "epoch": 1.8215613382899627, "percentage": 60.72, "elapsed_time": "1 day, 6:29:17", "remaining_time": "19:43:26"}
+{"current_steps": 1480, "total_steps": 2421, "loss": 0.1612, "lr": 3.9477469594311975e-07, "epoch": 1.8339529120198264, "percentage": 61.13, "elapsed_time": "1 day, 6:39:26", "remaining_time": "19:29:32"}
+{"current_steps": 1490, "total_steps": 2421, "loss": 0.1521, "lr": 3.877353011095199e-07, "epoch": 1.8463444857496902, "percentage": 61.54, "elapsed_time": "1 day, 6:56:12", "remaining_time": "19:19:49"}
+{"current_steps": 1500, "total_steps": 2421, "loss": 0.1762, "lr": 3.8071926341681677e-07, "epoch": 1.858736059479554, "percentage": 61.96, "elapsed_time": "1 day, 7:00:53", "remaining_time": "19:02:35"}
+{"current_steps": 1510, "total_steps": 2421, "loss": 0.1557, "lr": 3.7372804258104363e-07, "epoch": 1.8711276332094176, "percentage": 62.37, "elapsed_time": "1 day, 7:14:05", "remaining_time": "18:50:39"}
+{"current_steps": 1520, "total_steps": 2421, "loss": 0.1539, "lr": 3.6676309315498255e-07, "epoch": 1.8835192069392814, "percentage": 62.78, "elapsed_time": "1 day, 7:24:40", "remaining_time": "18:37:09"}
+{"current_steps": 1530, "total_steps": 2421, "loss": 0.1637, "lr": 3.598258642255386e-07, "epoch": 1.895910780669145, "percentage": 63.2, "elapsed_time": "1 day, 7:33:54", "remaining_time": "18:22:55"}
+{"current_steps": 1540, "total_steps": 2421, "loss": 0.1626, "lr": 3.5291779911225185e-07, "epoch": 1.9083023543990087, "percentage": 63.61, "elapsed_time": "1 day, 7:52:26", "remaining_time": "18:14:04"}
+{"current_steps": 1550, "total_steps": 2421, "loss": 0.1621, "lr": 3.460403350670077e-07, "epoch": 1.9206939281288724, "percentage": 64.02, "elapsed_time": "1 day, 8:07:51", "remaining_time": "18:03:19"}
+{"current_steps": 1560, "total_steps": 2421, "loss": 0.1516, "lr": 3.3919490297501163e-07, "epoch": 1.933085501858736, "percentage": 64.44, "elapsed_time": "1 day, 8:17:48", "remaining_time": "17:49:31"}
+{"current_steps": 1570, "total_steps": 2421, "loss": 0.1695, "lr": 3.323829270570867e-07, "epoch": 1.9454770755885997, "percentage": 64.85, "elapsed_time": "1 day, 8:31:19", "remaining_time": "17:37:41"}
+{"current_steps": 1580, "total_steps": 2421, "loss": 0.179, "lr": 3.2560582457335915e-07, "epoch": 1.9578686493184634, "percentage": 65.26, "elapsed_time": "1 day, 8:40:03", "remaining_time": "17:23:17"}
+{"current_steps": 1590, "total_steps": 2421, "loss": 0.1717, "lr": 3.18865005528391e-07, "epoch": 1.970260223048327, "percentage": 65.68, "elapsed_time": "1 day, 8:49:28", "remaining_time": "17:09:19"}
+{"current_steps": 1600, "total_steps": 2421, "loss": 0.1667, "lr": 3.121618723778224e-07, "epoch": 1.9826517967781907, "percentage": 66.09, "elapsed_time": "1 day, 8:55:17", "remaining_time": "16:53:34"}
+{"current_steps": 1610, "total_steps": 2421, "loss": 0.1723, "lr": 3.0549781973658605e-07, "epoch": 1.9950433705080544, "percentage": 66.5, "elapsed_time": "1 day, 9:02:24", "remaining_time": "16:38:35"}
+{"current_steps": 1620, "total_steps": 2421, "loss": 0.1426, "lr": 2.988742340887505e-07, "epoch": 2.007434944237918, "percentage": 66.91, "elapsed_time": "1 day, 9:25:57", "remaining_time": "16:31:50"}
+{"current_steps": 1630, "total_steps": 2421, "loss": 0.1374, "lr": 2.922924934990568e-07, "epoch": 2.019826517967782, "percentage": 67.33, "elapsed_time": "1 day, 9:36:29", "remaining_time": "16:18:33"}
+{"current_steps": 1640, "total_steps": 2421, "loss": 0.1482, "lr": 2.857539673262067e-07, "epoch": 2.032218091697646, "percentage": 67.74, "elapsed_time": "1 day, 9:49:39", "remaining_time": "16:06:33"}
+{"current_steps": 1650, "total_steps": 2421, "loss": 0.1508, "lr": 2.792600159379611e-07, "epoch": 2.0446096654275094, "percentage": 68.15, "elapsed_time": "1 day, 10:11:57", "remaining_time": "15:58:49"}
+{"current_steps": 1660, "total_steps": 2421, "loss": 0.1481, "lr": 2.7281199042811045e-07, "epoch": 2.057001239157373, "percentage": 68.57, "elapsed_time": "1 day, 10:20:22", "remaining_time": "15:44:32"}
+{"current_steps": 1670, "total_steps": 2421, "loss": 0.1581, "lr": 2.6641123233537394e-07, "epoch": 2.0693928128872368, "percentage": 68.98, "elapsed_time": "1 day, 10:27:29", "remaining_time": "15:29:45"}
+{"current_steps": 1680, "total_steps": 2421, "loss": 0.1443, "lr": 2.600590733642861e-07, "epoch": 2.0817843866171004, "percentage": 69.39, "elapsed_time": "1 day, 10:40:25", "remaining_time": "15:17:36"}
+{"current_steps": 1690, "total_steps": 2421, "loss": 0.1502, "lr": 2.537568351081311e-07, "epoch": 2.094175960346964, "percentage": 69.81, "elapsed_time": "1 day, 10:55:16", "remaining_time": "15:06:18"}
+{"current_steps": 1700, "total_steps": 2421, "loss": 0.149, "lr": 2.475058287739793e-07, "epoch": 2.1065675340768277, "percentage": 70.22, "elapsed_time": "1 day, 11:05:52", "remaining_time": "14:53:08"}
+{"current_steps": 1710, "total_steps": 2421, "loss": 0.166, "lr": 2.413073549098845e-07, "epoch": 2.1189591078066914, "percentage": 70.63, "elapsed_time": "1 day, 11:11:16", "remaining_time": "14:37:50"}
+{"current_steps": 1720, "total_steps": 2421, "loss": 0.1479, "lr": 2.3516270313430081e-07, "epoch": 2.131350681536555, "percentage": 71.05, "elapsed_time": "1 day, 11:20:29", "remaining_time": "14:24:13"}
+{"current_steps": 1730, "total_steps": 2421, "loss": 0.1563, "lr": 2.2907315186777053e-07, "epoch": 2.1437422552664187, "percentage": 71.46, "elapsed_time": "1 day, 11:26:34", "remaining_time": "14:09:23"}
+{"current_steps": 1740, "total_steps": 2421, "loss": 0.163, "lr": 2.2303996806694486e-07, "epoch": 2.1561338289962824, "percentage": 71.87, "elapsed_time": "1 day, 11:34:20", "remaining_time": "13:55:20"}
+{"current_steps": 1750, "total_steps": 2421, "loss": 0.1391, "lr": 2.170644069609876e-07, "epoch": 2.168525402726146, "percentage": 72.28, "elapsed_time": "1 day, 11:59:54", "remaining_time": "13:48:10"}
+{"current_steps": 1760, "total_steps": 2421, "loss": 0.1437, "lr": 2.111477117904189e-07, "epoch": 2.18091697645601, "percentage": 72.7, "elapsed_time": "1 day, 12:10:50", "remaining_time": "13:35:18"}
+{"current_steps": 1770, "total_steps": 2421, "loss": 0.1414, "lr": 2.0529111354845507e-07, "epoch": 2.193308550185874, "percentage": 73.11, "elapsed_time": "1 day, 12:16:31", "remaining_time": "13:20:30"}
+{"current_steps": 1780, "total_steps": 2421, "loss": 0.1491, "lr": 1.9949583072489452e-07, "epoch": 2.2057001239157374, "percentage": 73.52, "elapsed_time": "1 day, 12:32:12", "remaining_time": "13:09:26"}
+{"current_steps": 1790, "total_steps": 2421, "loss": 0.1392, "lr": 1.9376306905260604e-07, "epoch": 2.218091697645601, "percentage": 73.94, "elapsed_time": "1 day, 12:48:46", "remaining_time": "12:58:37"}
+{"current_steps": 1800, "total_steps": 2421, "loss": 0.1519, "lr": 1.880940212566706e-07, "epoch": 2.2304832713754648, "percentage": 74.35, "elapsed_time": "1 day, 13:02:37", "remaining_time": "12:46:48"}
+{"current_steps": 1810, "total_steps": 2421, "loss": 0.1519, "lr": 1.8248986680623074e-07, "epoch": 2.2428748451053284, "percentage": 74.76, "elapsed_time": "1 day, 13:17:53", "remaining_time": "12:35:26"}
+{"current_steps": 1820, "total_steps": 2421, "loss": 0.1492, "lr": 1.7695177166909668e-07, "epoch": 2.255266418835192, "percentage": 75.18, "elapsed_time": "1 day, 13:37:25", "remaining_time": "12:25:26"}
+{"current_steps": 1830, "total_steps": 2421, "loss": 0.1439, "lr": 1.714808880691611e-07, "epoch": 2.2676579925650557, "percentage": 75.59, "elapsed_time": "1 day, 13:47:45", "remaining_time": "12:12:22"}
+{"current_steps": 1840, "total_steps": 2421, "loss": 0.1421, "lr": 1.6607835424667577e-07, "epoch": 2.2800495662949194, "percentage": 76.0, "elapsed_time": "1 day, 14:08:06", "remaining_time": "12:02:29"}
+{"current_steps": 1850, "total_steps": 2421, "loss": 0.1523, "lr": 1.6074529422143396e-07, "epoch": 2.292441140024783, "percentage": 76.41, "elapsed_time": "1 day, 14:16:43", "remaining_time": "11:48:53"}
+{"current_steps": 1860, "total_steps": 2421, "loss": 0.1491, "lr": 1.5548281755891508e-07, "epoch": 2.3048327137546467, "percentage": 76.83, "elapsed_time": "1 day, 14:30:11", "remaining_time": "11:36:46"}
+{"current_steps": 1870, "total_steps": 2421, "loss": 0.1328, "lr": 1.5029201913943425e-07, "epoch": 2.3172242874845104, "percentage": 77.24, "elapsed_time": "1 day, 14:52:21", "remaining_time": "11:27:13"}
+{"current_steps": 1880, "total_steps": 2421, "loss": 0.136, "lr": 1.4517397893034716e-07, "epoch": 2.329615861214374, "percentage": 77.65, "elapsed_time": "1 day, 15:11:40", "remaining_time": "11:16:43"}
+{"current_steps": 1890, "total_steps": 2421, "loss": 0.1569, "lr": 1.4012976176135978e-07, "epoch": 2.3420074349442377, "percentage": 78.07, "elapsed_time": "1 day, 15:17:23", "remaining_time": "11:02:18"}
+{"current_steps": 1900, "total_steps": 2421, "loss": 0.1436, "lr": 1.3516041710298497e-07, "epoch": 2.354399008674102, "percentage": 78.48, "elapsed_time": "1 day, 15:36:56", "remaining_time": "10:51:47"}
+{"current_steps": 1910, "total_steps": 2421, "loss": 0.154, "lr": 1.3026697884819644e-07, "epoch": 2.3667905824039654, "percentage": 78.89, "elapsed_time": "1 day, 15:45:00", "remaining_time": "10:38:04"}
+{"current_steps": 1920, "total_steps": 2421, "loss": 0.1503, "lr": 1.25450465097322e-07, "epoch": 2.379182156133829, "percentage": 79.31, "elapsed_time": "1 day, 15:57:02", "remaining_time": "10:25:28"}
+{"current_steps": 1930, "total_steps": 2421, "loss": 0.152, "lr": 1.2071187794622477e-07, "epoch": 2.3915737298636928, "percentage": 79.72, "elapsed_time": "1 day, 16:04:03", "remaining_time": "10:11:36"}
+{"current_steps": 1940, "total_steps": 2421, "loss": 0.1491, "lr": 1.1605220327781228e-07, "epoch": 2.4039653035935564, "percentage": 80.13, "elapsed_time": "1 day, 16:16:42", "remaining_time": "9:59:11"}
+{"current_steps": 1950, "total_steps": 2421, "loss": 0.1624, "lr": 1.1147241055691908e-07, "epoch": 2.41635687732342, "percentage": 80.55, "elapsed_time": "1 day, 16:33:36", "remaining_time": "9:47:48"}
+{"current_steps": 1960, "total_steps": 2421, "loss": 0.1514, "lr": 1.0697345262860635e-07, "epoch": 2.4287484510532837, "percentage": 80.96, "elapsed_time": "1 day, 16:42:34", "remaining_time": "9:34:30"}
+{"current_steps": 1970, "total_steps": 2421, "loss": 0.15, "lr": 1.0255626551991764e-07, "epoch": 2.4411400247831474, "percentage": 81.37, "elapsed_time": "1 day, 16:53:22", "remaining_time": "9:21:39"}
+{"current_steps": 1980, "total_steps": 2421, "loss": 0.1674, "lr": 9.822176824513522e-08, "epoch": 2.453531598513011, "percentage": 81.78, "elapsed_time": "1 day, 16:58:02", "remaining_time": "9:07:28"}
+{"current_steps": 1990, "total_steps": 2421, "loss": 0.1579, "lr": 9.39708626145751e-08, "epoch": 2.4659231722428747, "percentage": 82.2, "elapsed_time": "1 day, 17:12:50", "remaining_time": "8:55:34"}
+{"current_steps": 2000, "total_steps": 2421, "loss": 0.161, "lr": 8.980443304696107e-08, "epoch": 2.4783147459727384, "percentage": 82.61, "elapsed_time": "1 day, 17:21:08", "remaining_time": "8:42:16"}
+{"current_steps": 2010, "total_steps": 2421, "loss": 0.1563, "lr": 8.572334638541856e-08, "epoch": 2.4907063197026025, "percentage": 83.02, "elapsed_time": "1 day, 17:33:30", "remaining_time": "8:29:51"}
+{"current_steps": 2020, "total_steps": 2421, "loss": 0.147, "lr": 8.172845171712378e-08, "epoch": 2.503097893432466, "percentage": 83.44, "elapsed_time": "1 day, 17:44:16", "remaining_time": "8:17:08"}
+{"current_steps": 2030, "total_steps": 2421, "loss": 0.1423, "lr": 7.782058019664773e-08, "epoch": 2.51548946716233, "percentage": 83.85, "elapsed_time": "1 day, 17:50:46", "remaining_time": "8:03:36"}
+{"current_steps": 2040, "total_steps": 2421, "loss": 0.1544, "lr": 7.400054487303059e-08, "epoch": 2.5278810408921935, "percentage": 84.26, "elapsed_time": "1 day, 17:57:34", "remaining_time": "7:50:11"}
+{"current_steps": 2050, "total_steps": 2421, "loss": 0.1622, "lr": 7.026914052062432e-08, "epoch": 2.540272614622057, "percentage": 84.68, "elapsed_time": "1 day, 18:08:16", "remaining_time": "7:37:33"}
+{"current_steps": 2060, "total_steps": 2421, "loss": 0.1561, "lr": 6.662714347373589e-08, "epoch": 2.5526641883519208, "percentage": 85.09, "elapsed_time": "1 day, 18:13:12", "remaining_time": "7:23:55"}
+{"current_steps": 2070, "total_steps": 2421, "loss": 0.1343, "lr": 6.307531146510753e-08, "epoch": 2.5650557620817844, "percentage": 85.5, "elapsed_time": "1 day, 18:24:05", "remaining_time": "7:11:23"}
+{"current_steps": 2080, "total_steps": 2421, "loss": 0.1578, "lr": 5.961438346826792e-08, "epoch": 2.577447335811648, "percentage": 85.91, "elapsed_time": "1 day, 18:33:47", "remaining_time": "6:58:40"}
+{"current_steps": 2090, "total_steps": 2421, "loss": 0.14, "lr": 5.624507954378499e-08, "epoch": 2.5898389095415117, "percentage": 86.33, "elapsed_time": "1 day, 18:40:02", "remaining_time": "6:45:26"}
+{"current_steps": 2100, "total_steps": 2421, "loss": 0.1478, "lr": 5.296810068945473e-08, "epoch": 2.6022304832713754, "percentage": 86.74, "elapsed_time": "1 day, 18:49:00", "remaining_time": "6:32:41"}
+{"current_steps": 2110, "total_steps": 2421, "loss": 0.166, "lr": 4.97841286944557e-08, "epoch": 2.614622057001239, "percentage": 87.15, "elapsed_time": "1 day, 19:01:49", "remaining_time": "6:20:32"}
+{"current_steps": 2120, "total_steps": 2421, "loss": 0.1494, "lr": 4.669382599749927e-08, "epoch": 2.6270136307311027, "percentage": 87.57, "elapsed_time": "1 day, 19:20:31", "remaining_time": "6:09:13"}
+{"current_steps": 2130, "total_steps": 2421, "loss": 0.137, "lr": 4.3697835549007464e-08, "epoch": 2.6394052044609664, "percentage": 87.98, "elapsed_time": "1 day, 19:42:25", "remaining_time": "5:58:16"}
+{"current_steps": 2140, "total_steps": 2421, "loss": 0.1447, "lr": 4.07967806773436e-08, "epoch": 2.65179677819083, "percentage": 88.39, "elapsed_time": "1 day, 19:58:17", "remaining_time": "5:46:25"}
+{"current_steps": 2150, "total_steps": 2421, "loss": 0.1304, "lr": 3.7991264959126856e-08, "epoch": 2.6641883519206937, "percentage": 88.81, "elapsed_time": "1 day, 20:10:15", "remaining_time": "5:34:03"}
+{"current_steps": 2160, "total_steps": 2421, "loss": 0.1549, "lr": 3.5281872093654855e-08, "epoch": 2.6765799256505574, "percentage": 89.22, "elapsed_time": "1 day, 20:17:19", "remaining_time": "5:21:05"}
+{"current_steps": 2170, "total_steps": 2421, "loss": 0.1506, "lr": 3.2669165781463395e-08, "epoch": 2.6889714993804215, "percentage": 89.63, "elapsed_time": "1 day, 20:40:18", "remaining_time": "5:10:01"}
+{"current_steps": 2180, "total_steps": 2421, "loss": 0.1447, "lr": 3.015368960704584e-08, "epoch": 2.701363073110285, "percentage": 90.05, "elapsed_time": "1 day, 20:53:34", "remaining_time": "4:57:46"}
+{"current_steps": 2190, "total_steps": 2421, "loss": 0.1363, "lr": 2.7735966925757804e-08, "epoch": 2.7137546468401488, "percentage": 90.46, "elapsed_time": "1 day, 21:03:04", "remaining_time": "4:45:07"}
+{"current_steps": 2200, "total_steps": 2421, "loss": 0.1678, "lr": 2.541650075493129e-08, "epoch": 2.7261462205700124, "percentage": 90.87, "elapsed_time": "1 day, 21:10:22", "remaining_time": "4:32:16"}
+{"current_steps": 2210, "total_steps": 2421, "loss": 0.1432, "lr": 2.3195773669219766e-08, "epoch": 2.738537794299876, "percentage": 91.28, "elapsed_time": "1 day, 21:16:37", "remaining_time": "4:19:22"}
+{"current_steps": 2220, "total_steps": 2421, "loss": 0.1419, "lr": 2.1074247700196335e-08, "epoch": 2.7509293680297398, "percentage": 91.7, "elapsed_time": "1 day, 21:36:13", "remaining_time": "4:07:44"}
+{"current_steps": 2230, "total_steps": 2421, "loss": 0.1433, "lr": 1.9052364240226327e-08, "epoch": 2.7633209417596034, "percentage": 92.11, "elapsed_time": "1 day, 21:41:42", "remaining_time": "3:54:49"}
+{"current_steps": 2240, "total_steps": 2421, "loss": 0.1289, "lr": 1.71305439506334e-08, "epoch": 2.775712515489467, "percentage": 92.52, "elapsed_time": "1 day, 21:56:08", "remaining_time": "3:42:42"}
+{"current_steps": 2250, "total_steps": 2421, "loss": 0.1446, "lr": 1.530918667417963e-08, "epoch": 2.7881040892193307, "percentage": 92.94, "elapsed_time": "1 day, 22:06:42", "remaining_time": "3:30:16"}
+{"current_steps": 2260, "total_steps": 2421, "loss": 0.1344, "lr": 1.3588671351876357e-08, "epoch": 2.8004956629491944, "percentage": 93.35, "elapsed_time": "1 day, 22:23:34", "remaining_time": "3:18:17"}
+{"current_steps": 2270, "total_steps": 2421, "loss": 0.152, "lr": 1.1969355944143832e-08, "epoch": 2.8128872366790585, "percentage": 93.76, "elapsed_time": "1 day, 22:38:00", "remaining_time": "3:06:07"}
+{"current_steps": 2280, "total_steps": 2421, "loss": 0.1444, "lr": 1.0451577356336116e-08, "epoch": 2.825278810408922, "percentage": 94.18, "elapsed_time": "1 day, 22:49:14", "remaining_time": "2:53:43"}
+{"current_steps": 2290, "total_steps": 2421, "loss": 0.1468, "lr": 9.035651368646646e-09, "epoch": 2.837670384138786, "percentage": 94.59, "elapsed_time": "1 day, 23:02:52", "remaining_time": "2:41:29"}
+{"current_steps": 2300, "total_steps": 2421, "loss": 0.1561, "lr": 7.721872570408683e-09, "epoch": 2.8500619578686495, "percentage": 95.0, "elapsed_time": "1 day, 23:10:36", "remaining_time": "2:28:54"}
+{"current_steps": 2310, "total_steps": 2421, "loss": 0.1521, "lr": 6.510514298804837e-09, "epoch": 2.862453531598513, "percentage": 95.42, "elapsed_time": "1 day, 23:27:02", "remaining_time": "2:16:48"}
+{"current_steps": 2320, "total_steps": 2421, "loss": 0.1499, "lr": 5.401828581997947e-09, "epoch": 2.874845105328377, "percentage": 95.83, "elapsed_time": "1 day, 23:37:03", "remaining_time": "2:04:22"}
+{"current_steps": 2330, "total_steps": 2421, "loss": 0.1441, "lr": 4.396046086695915e-09, "epoch": 2.8872366790582404, "percentage": 96.24, "elapsed_time": "1 day, 23:48:40", "remaining_time": "1:52:02"}
+{"current_steps": 2340, "total_steps": 2421, "loss": 0.1418, "lr": 3.4933760701602586e-09, "epoch": 2.899628252788104, "percentage": 96.65, "elapsed_time": "2 days, 0:10:29", "remaining_time": "1:40:03"}
+{"current_steps": 2350, "total_steps": 2421, "loss": 0.1764, "lr": 2.69400633666933e-09, "epoch": 2.9120198265179678, "percentage": 97.07, "elapsed_time": "2 days, 0:22:08", "remaining_time": "1:27:40"}
+{"current_steps": 2360, "total_steps": 2421, "loss": 0.1367, "lr": 1.9981031984448448e-09, "epoch": 2.9244114002478314, "percentage": 97.48, "elapsed_time": "2 days, 0:28:35", "remaining_time": "1:15:10"}
+{"current_steps": 2370, "total_steps": 2421, "loss": 0.1497, "lr": 1.4058114410498979e-09, "epoch": 2.936802973977695, "percentage": 97.89, "elapsed_time": "2 days, 0:33:36", "remaining_time": "1:02:41"}
+{"current_steps": 2380, "total_steps": 2421, "loss": 0.1518, "lr": 9.1725429326589e-10, "epoch": 2.9491945477075587, "percentage": 98.31, "elapsed_time": "2 days, 0:46:11", "remaining_time": "0:50:24"}
+{"current_steps": 2390, "total_steps": 2421, "loss": 0.144, "lr": 5.325334014539829e-10, "epoch": 2.9615861214374224, "percentage": 98.72, "elapsed_time": "2 days, 0:56:19", "remaining_time": "0:38:05"}
+{"current_steps": 2400, "total_steps": 2421, "loss": 0.1495, "lr": 2.517288084074587e-10, "epoch": 2.973977695167286, "percentage": 99.13, "elapsed_time": "2 days, 1:13:00", "remaining_time": "0:25:50"}
+{"current_steps": 2410, "total_steps": 2421, "loss": 0.164, "lr": 7.489893669809788e-11, "epoch": 2.9863692688971497, "percentage": 99.55, "elapsed_time": "2 days, 1:23:23", "remaining_time": "0:13:31"}
+{"current_steps": 2420, "total_steps": 2421, "loss": 0.1579, "lr": 2.0805765215681226e-12, "epoch": 2.9987608426270134, "percentage": 99.96, "elapsed_time": "2 days, 1:30:50", "remaining_time": "0:01:13"}
+{"current_steps": 2421, "total_steps": 2421, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2 days, 1:33:10", "remaining_time": "0:00:00"}

seed_oss_36b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a5f3b48685d917805865a2a7d60e63625c957afb7cc482560eb8744b933202
+size 8401