Upload checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,58 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+base_model: zai-org/Glyph
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: vtc-r1-glyph
+  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. -->
+
+
+## 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-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.22.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2042833294327808.0,
+    "train_loss": 0.4611289887036678,
+    "train_runtime": 68178.0817,
+    "train_samples_per_second": 1.554,
+    "train_steps_per_second": 0.024
+}

chat_template.jinja

@@ -0,0 +1,118 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
+                <|begin_of_image|><|image|><|end_of_image|>
+            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
+                <|begin_of_video|><|video|><|end_of_video|>
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{% if m.content is string %}
+{{ m.content }}
+{%- else %}
+{%- for item in m.content %}
+{% if item.type == 'video' or 'video' in item %}
+<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
+<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
+{{ item.text }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|assistant|>
+{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
+{%- endif -%}

config.json

@@ -0,0 +1,74 @@
+{
+  "architectures": [
+    "Glm4vForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151329,
+  "hidden_size": 4096,
+  "image_end_token_id": 151340,
+  "image_start_token_id": 151339,
+  "image_token_id": 151363,
+  "model_type": "glm4v",
+  "pad_token_id": 151329,
+  "text_config": {
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": [
+      151329,
+      151336,
+      151338
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 13696,
+    "max_position_embeddings": 131072,
+    "model_type": "glm4v_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "mrope_section": [
+        8,
+        12,
+        12
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 500000,
+    "use_cache": false,
+    "video_token_id": null,
+    "vocab_size": 151552
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "video_end_token_id": 151342,
+  "video_start_token_id": 151341,
+  "video_token_id": 151364,
+  "vision_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "depth": 24,
+    "dtype": "float32",
+    "hidden_act": "silu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1536,
+    "image_size": 336,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 13696,
+    "model_type": "glm4v",
+    "num_heads": 12,
+    "out_hidden_size": 4096,
+    "patch_size": 14,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  }
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3c93a42ab7a9ec58dbf9056d0a6959b049d10ee6eb62a2c8a809c106fd7d06
+size 4953999648

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19836b9b52ed640b736bbc5a58ce4af6bc13d8957ba688135017d97b3f91cc0
+size 4895276872

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80da7e8d2a64e54fd941f9420130c4c57618a2837a8f8658e5db1b370e719e27
+size 4895276936

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df34a9d49b8a726fc8821048831249c5c41f122f4a7f7dcdcce952296c25376
+size 4599576544

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec41bffdb8d8639b6e503dd122be3b44dd449e7da0678b4ea9b844a2ddea18f
+size 1241514112

model.safetensors.index.json

@@ -0,0 +1,712 @@
+{
+  "metadata": {
+    "total_parameters": 934400,
+    "total_size": 20585554944
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.post_mlp_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.post_self_attn_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.post_mlp_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.post_self_attn_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.post_mlp_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.post_self_attn_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00005.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
+    "model.visual.downsample.bias": "model-00001-of-00005.safetensors",
+    "model.visual.downsample.weight": "model-00001-of-00005.safetensors",
+    "model.visual.embeddings.position_embedding.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.post_projection_norm.bias": "model-00001-of-00005.safetensors",
+    "model.visual.merger.post_projection_norm.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.merger.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00005.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors",
+    "model.visual.post_conv_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.visual.post_layernorm.weight": "model-00001-of-00005.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Glm4vImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "merge_size": 2,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 9633792,
+    "shortest_edge": 12544
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink",
+    {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecde1f225a86abef606164ceeb446737e592c4e7a40afe5cbf3ce8328e3df99
+size 19970886

tokenizer_config.json

@@ -0,0 +1,336 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|begin_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|end_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151345": {
+      "content": "<|begin_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151346": {
+      "content": "<|end_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151347": {
+      "content": "<|code_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151348": {
+      "content": "<|code_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151349": {
+      "content": "<|code_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151350": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151352": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151353": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151354": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151355": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151356": {
+      "content": "<arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151357": {
+      "content": "</arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151358": {
+      "content": "<arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151359": {
+      "content": "</arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151360": {
+      "content": "/nothink",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151361": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151362": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151363": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151364": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151365": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink",
+    "</answer>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Glm4vProcessor",
+  "remove_space": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2042833294327808.0,
+    "train_loss": 0.4611289887036678,
+    "train_runtime": 68178.0817,
+    "train_samples_per_second": 1.554,
+    "train_steps_per_second": 0.024
+}

trainer_log.jsonl

@@ -0,0 +1,166 @@
+{"current_steps": 10, "total_steps": 1656, "loss": 0.818, "lr": 5.421686746987952e-07, "epoch": 0.006041839740200891, "percentage": 0.6, "elapsed_time": "0:06:47", "remaining_time": "18:37:45"}
+{"current_steps": 20, "total_steps": 1656, "loss": 0.6987, "lr": 1.1445783132530121e-06, "epoch": 0.012083679480401783, "percentage": 1.21, "elapsed_time": "0:13:29", "remaining_time": "18:23:26"}
+{"current_steps": 30, "total_steps": 1656, "loss": 0.5802, "lr": 1.7469879518072292e-06, "epoch": 0.018125519220602675, "percentage": 1.81, "elapsed_time": "0:20:10", "remaining_time": "18:13:09"}
+{"current_steps": 40, "total_steps": 1656, "loss": 0.5258, "lr": 2.349397590361446e-06, "epoch": 0.024167358960803565, "percentage": 2.42, "elapsed_time": "0:26:51", "remaining_time": "18:04:44"}
+{"current_steps": 50, "total_steps": 1656, "loss": 0.5145, "lr": 2.9518072289156627e-06, "epoch": 0.030209198701004455, "percentage": 3.02, "elapsed_time": "0:33:44", "remaining_time": "18:03:36"}
+{"current_steps": 60, "total_steps": 1656, "loss": 0.5015, "lr": 3.5542168674698798e-06, "epoch": 0.03625103844120535, "percentage": 3.62, "elapsed_time": "0:40:26", "remaining_time": "17:55:38"}
+{"current_steps": 70, "total_steps": 1656, "loss": 0.4901, "lr": 4.156626506024097e-06, "epoch": 0.042292878181406236, "percentage": 4.23, "elapsed_time": "0:47:29", "remaining_time": "17:56:02"}
+{"current_steps": 80, "total_steps": 1656, "loss": 0.4796, "lr": 4.759036144578314e-06, "epoch": 0.04833471792160713, "percentage": 4.83, "elapsed_time": "0:54:17", "remaining_time": "17:49:25"}
+{"current_steps": 90, "total_steps": 1656, "loss": 0.4758, "lr": 5.361445783132531e-06, "epoch": 0.05437655766180802, "percentage": 5.43, "elapsed_time": "1:01:11", "remaining_time": "17:44:43"}
+{"current_steps": 100, "total_steps": 1656, "loss": 0.4829, "lr": 5.963855421686747e-06, "epoch": 0.06041839740200891, "percentage": 6.04, "elapsed_time": "1:08:10", "remaining_time": "17:40:44"}
+{"current_steps": 110, "total_steps": 1656, "loss": 0.4812, "lr": 6.566265060240964e-06, "epoch": 0.0664602371422098, "percentage": 6.64, "elapsed_time": "1:14:59", "remaining_time": "17:33:54"}
+{"current_steps": 120, "total_steps": 1656, "loss": 0.4789, "lr": 7.168674698795182e-06, "epoch": 0.0725020768824107, "percentage": 7.25, "elapsed_time": "1:21:47", "remaining_time": "17:27:00"}
+{"current_steps": 130, "total_steps": 1656, "loss": 0.4767, "lr": 7.771084337349398e-06, "epoch": 0.07854391662261158, "percentage": 7.85, "elapsed_time": "1:28:44", "remaining_time": "17:21:40"}
+{"current_steps": 140, "total_steps": 1656, "loss": 0.4748, "lr": 8.373493975903614e-06, "epoch": 0.08458575636281247, "percentage": 8.45, "elapsed_time": "1:35:32", "remaining_time": "17:14:39"}
+{"current_steps": 150, "total_steps": 1656, "loss": 0.471, "lr": 8.975903614457832e-06, "epoch": 0.09062759610301337, "percentage": 9.06, "elapsed_time": "1:42:45", "remaining_time": "17:11:38"}
+{"current_steps": 160, "total_steps": 1656, "loss": 0.482, "lr": 9.57831325301205e-06, "epoch": 0.09666943584321426, "percentage": 9.66, "elapsed_time": "1:49:29", "remaining_time": "17:03:49"}
+{"current_steps": 170, "total_steps": 1656, "loss": 0.4867, "lr": 9.99989997506481e-06, "epoch": 0.10271127558341515, "percentage": 10.27, "elapsed_time": "1:56:22", "remaining_time": "16:57:16"}
+{"current_steps": 180, "total_steps": 1656, "loss": 0.4832, "lr": 9.998121865323769e-06, "epoch": 0.10875311532361603, "percentage": 10.87, "elapsed_time": "2:03:05", "remaining_time": "16:49:21"}
+{"current_steps": 190, "total_steps": 1656, "loss": 0.4836, "lr": 9.994121889085426e-06, "epoch": 0.11479495506381693, "percentage": 11.47, "elapsed_time": "2:10:16", "remaining_time": "16:45:12"}
+{"current_steps": 200, "total_steps": 1656, "loss": 0.4796, "lr": 9.987901824500342e-06, "epoch": 0.12083679480401782, "percentage": 12.08, "elapsed_time": "2:17:08", "remaining_time": "16:38:22"}
+{"current_steps": 210, "total_steps": 1656, "loss": 0.479, "lr": 9.979464436637771e-06, "epoch": 0.12687863454421872, "percentage": 12.68, "elapsed_time": "2:24:05", "remaining_time": "16:32:11"}
+{"current_steps": 220, "total_steps": 1656, "loss": 0.4774, "lr": 9.968813476256483e-06, "epoch": 0.1329204742844196, "percentage": 13.29, "elapsed_time": "2:30:56", "remaining_time": "16:25:11"}
+{"current_steps": 230, "total_steps": 1656, "loss": 0.4775, "lr": 9.955953678137397e-06, "epoch": 0.1389623140246205, "percentage": 13.89, "elapsed_time": "2:37:57", "remaining_time": "16:19:21"}
+{"current_steps": 240, "total_steps": 1656, "loss": 0.4809, "lr": 9.940890758978781e-06, "epoch": 0.1450041537648214, "percentage": 14.49, "elapsed_time": "2:44:48", "remaining_time": "16:12:24"}
+{"current_steps": 250, "total_steps": 1656, "loss": 0.4823, "lr": 9.923631414854946e-06, "epoch": 0.1510459935050223, "percentage": 15.1, "elapsed_time": "2:51:42", "remaining_time": "16:05:43"}
+{"current_steps": 260, "total_steps": 1656, "loss": 0.4732, "lr": 9.904183318239573e-06, "epoch": 0.15708783324522316, "percentage": 15.7, "elapsed_time": "2:58:44", "remaining_time": "15:59:44"}
+{"current_steps": 270, "total_steps": 1656, "loss": 0.4746, "lr": 9.882555114594994e-06, "epoch": 0.16312967298542405, "percentage": 16.3, "elapsed_time": "3:05:45", "remaining_time": "15:53:33"}
+{"current_steps": 280, "total_steps": 1656, "loss": 0.4771, "lr": 9.858756418528928e-06, "epoch": 0.16917151272562495, "percentage": 16.91, "elapsed_time": "3:12:30", "remaining_time": "15:46:01"}
+{"current_steps": 290, "total_steps": 1656, "loss": 0.4703, "lr": 9.832797809520404e-06, "epoch": 0.17521335246582584, "percentage": 17.51, "elapsed_time": "3:19:34", "remaining_time": "15:40:03"}
+{"current_steps": 300, "total_steps": 1656, "loss": 0.4763, "lr": 9.804690827216764e-06, "epoch": 0.18125519220602673, "percentage": 18.12, "elapsed_time": "3:26:11", "remaining_time": "15:31:57"}
+{"current_steps": 310, "total_steps": 1656, "loss": 0.4665, "lr": 9.77444796630381e-06, "epoch": 0.18729703194622763, "percentage": 18.72, "elapsed_time": "3:33:04", "remaining_time": "15:25:09"}
+{"current_steps": 320, "total_steps": 1656, "loss": 0.4781, "lr": 9.742082670951423e-06, "epoch": 0.19333887168642852, "percentage": 19.32, "elapsed_time": "3:39:55", "remaining_time": "15:18:09"}
+{"current_steps": 330, "total_steps": 1656, "loss": 0.4695, "lr": 9.707609328837085e-06, "epoch": 0.19938071142662941, "percentage": 19.93, "elapsed_time": "3:46:36", "remaining_time": "15:10:32"}
+{"current_steps": 340, "total_steps": 1656, "loss": 0.4709, "lr": 9.67104326474998e-06, "epoch": 0.2054225511668303, "percentage": 20.53, "elapsed_time": "3:53:33", "remaining_time": "15:03:58"}
+{"current_steps": 350, "total_steps": 1656, "loss": 0.4687, "lr": 9.632400733778504e-06, "epoch": 0.2114643909070312, "percentage": 21.14, "elapsed_time": "4:00:19", "remaining_time": "14:56:46"}
+{"current_steps": 360, "total_steps": 1656, "loss": 0.4727, "lr": 9.591698914084224e-06, "epoch": 0.21750623064723207, "percentage": 21.74, "elapsed_time": "4:07:21", "remaining_time": "14:50:31"}
+{"current_steps": 370, "total_steps": 1656, "loss": 0.4757, "lr": 9.548955899265495e-06, "epoch": 0.22354807038743296, "percentage": 22.34, "elapsed_time": "4:14:13", "remaining_time": "14:43:36"}
+{"current_steps": 380, "total_steps": 1656, "loss": 0.4628, "lr": 9.504190690314124e-06, "epoch": 0.22958991012763386, "percentage": 22.95, "elapsed_time": "4:21:05", "remaining_time": "14:36:43"}
+{"current_steps": 390, "total_steps": 1656, "loss": 0.4751, "lr": 9.457423187168667e-06, "epoch": 0.23563174986783475, "percentage": 23.55, "elapsed_time": "4:28:07", "remaining_time": "14:30:23"}
+{"current_steps": 400, "total_steps": 1656, "loss": 0.4755, "lr": 9.408674179868101e-06, "epoch": 0.24167358960803564, "percentage": 24.15, "elapsed_time": "4:35:07", "remaining_time": "14:23:53"}
+{"current_steps": 410, "total_steps": 1656, "loss": 0.4688, "lr": 9.357965339309823e-06, "epoch": 0.24771542934823654, "percentage": 24.76, "elapsed_time": "4:42:07", "remaining_time": "14:17:21"}
+{"current_steps": 420, "total_steps": 1656, "loss": 0.468, "lr": 9.305319207616048e-06, "epoch": 0.25375726908843743, "percentage": 25.36, "elapsed_time": "4:48:48", "remaining_time": "14:09:54"}
+{"current_steps": 430, "total_steps": 1656, "loss": 0.4721, "lr": 9.250759188112944e-06, "epoch": 0.2597991088286383, "percentage": 25.97, "elapsed_time": "4:55:51", "remaining_time": "14:03:31"}
+{"current_steps": 440, "total_steps": 1656, "loss": 0.4719, "lr": 9.194309534926896e-06, "epoch": 0.2658409485688392, "percentage": 26.57, "elapsed_time": "5:02:48", "remaining_time": "13:56:51"}
+{"current_steps": 450, "total_steps": 1656, "loss": 0.4676, "lr": 9.13599534220258e-06, "epoch": 0.2718827883090401, "percentage": 27.17, "elapsed_time": "5:09:41", "remaining_time": "13:49:58"}
+{"current_steps": 460, "total_steps": 1656, "loss": 0.4729, "lr": 9.075842532947605e-06, "epoch": 0.277924628049241, "percentage": 27.78, "elapsed_time": "5:16:32", "remaining_time": "13:43:01"}
+{"current_steps": 470, "total_steps": 1656, "loss": 0.4735, "lr": 9.013877847508684e-06, "epoch": 0.2839664677894419, "percentage": 28.38, "elapsed_time": "5:23:32", "remaining_time": "13:36:25"}
+{"current_steps": 480, "total_steps": 1656, "loss": 0.4655, "lr": 8.95012883168448e-06, "epoch": 0.2900083075296428, "percentage": 28.99, "elapsed_time": "5:30:18", "remaining_time": "13:29:16"}
+{"current_steps": 490, "total_steps": 1656, "loss": 0.4604, "lr": 8.884623824480388e-06, "epoch": 0.2960501472698437, "percentage": 29.59, "elapsed_time": "5:37:01", "remaining_time": "13:21:57"}
+{"current_steps": 500, "total_steps": 1656, "loss": 0.4727, "lr": 8.817391945510697e-06, "epoch": 0.3020919870100446, "percentage": 30.19, "elapsed_time": "5:43:52", "remaining_time": "13:15:02"}
+{"current_steps": 510, "total_steps": 1656, "loss": 0.4696, "lr": 8.748463082053765e-06, "epoch": 0.3081338267502455, "percentage": 30.8, "elapsed_time": "5:50:44", "remaining_time": "13:08:08"}
+{"current_steps": 520, "total_steps": 1656, "loss": 0.4667, "lr": 8.677867875765904e-06, "epoch": 0.3141756664904463, "percentage": 31.4, "elapsed_time": "5:57:38", "remaining_time": "13:01:18"}
+{"current_steps": 530, "total_steps": 1656, "loss": 0.4665, "lr": 8.605637709059937e-06, "epoch": 0.3202175062306472, "percentage": 32.0, "elapsed_time": "6:04:32", "remaining_time": "12:54:27"}
+{"current_steps": 540, "total_steps": 1656, "loss": 0.4596, "lr": 8.531804691154454e-06, "epoch": 0.3262593459708481, "percentage": 32.61, "elapsed_time": "6:11:35", "remaining_time": "12:47:57"}
+{"current_steps": 550, "total_steps": 1656, "loss": 0.4635, "lr": 8.45640164379996e-06, "epoch": 0.332301185711049, "percentage": 33.21, "elapsed_time": "6:18:19", "remaining_time": "12:40:47"}
+{"current_steps": 560, "total_steps": 1656, "loss": 0.4614, "lr": 8.379462086688302e-06, "epoch": 0.3383430254512499, "percentage": 33.82, "elapsed_time": "6:25:03", "remaining_time": "12:33:37"}
+{"current_steps": 570, "total_steps": 1656, "loss": 0.4613, "lr": 8.301020222551795e-06, "epoch": 0.3443848651914508, "percentage": 34.42, "elapsed_time": "6:32:06", "remaining_time": "12:27:03"}
+{"current_steps": 580, "total_steps": 1656, "loss": 0.4625, "lr": 8.221110921958748e-06, "epoch": 0.3504267049316517, "percentage": 35.02, "elapsed_time": "6:38:44", "remaining_time": "12:19:44"}
+{"current_steps": 590, "total_steps": 1656, "loss": 0.4643, "lr": 8.139769707812083e-06, "epoch": 0.35646854467185257, "percentage": 35.63, "elapsed_time": "6:45:36", "remaining_time": "12:12:50"}
+{"current_steps": 600, "total_steps": 1656, "loss": 0.4647, "lr": 8.057032739557973e-06, "epoch": 0.36251038441205347, "percentage": 36.23, "elapsed_time": "6:52:32", "remaining_time": "12:06:04"}
+{"current_steps": 610, "total_steps": 1656, "loss": 0.4664, "lr": 7.972936797111515e-06, "epoch": 0.36855222415225436, "percentage": 36.84, "elapsed_time": "6:59:31", "remaining_time": "11:59:22"}
+{"current_steps": 620, "total_steps": 1656, "loss": 0.4687, "lr": 7.887519264506577e-06, "epoch": 0.37459406389245525, "percentage": 37.44, "elapsed_time": "7:06:23", "remaining_time": "11:52:29"}
+{"current_steps": 630, "total_steps": 1656, "loss": 0.4675, "lr": 7.800818113277085e-06, "epoch": 0.38063590363265615, "percentage": 38.04, "elapsed_time": "7:13:08", "remaining_time": "11:45:24"}
+{"current_steps": 640, "total_steps": 1656, "loss": 0.4696, "lr": 7.712871885577147e-06, "epoch": 0.38667774337285704, "percentage": 38.65, "elapsed_time": "7:19:53", "remaining_time": "11:38:20"}
+{"current_steps": 650, "total_steps": 1656, "loss": 0.4679, "lr": 7.623719677047521e-06, "epoch": 0.39271958311305794, "percentage": 39.25, "elapsed_time": "7:26:41", "remaining_time": "11:31:19"}
+{"current_steps": 660, "total_steps": 1656, "loss": 0.4636, "lr": 7.533401119436012e-06, "epoch": 0.39876142285325883, "percentage": 39.86, "elapsed_time": "7:33:30", "remaining_time": "11:24:23"}
+{"current_steps": 670, "total_steps": 1656, "loss": 0.4573, "lr": 7.441956362979584e-06, "epoch": 0.4048032625934597, "percentage": 40.46, "elapsed_time": "7:40:22", "remaining_time": "11:17:29"}
+{"current_steps": 680, "total_steps": 1656, "loss": 0.467, "lr": 7.349426058555943e-06, "epoch": 0.4108451023336606, "percentage": 41.06, "elapsed_time": "7:47:11", "remaining_time": "11:10:33"}
+{"current_steps": 690, "total_steps": 1656, "loss": 0.4619, "lr": 7.255851339612597e-06, "epoch": 0.4168869420738615, "percentage": 41.67, "elapsed_time": "7:54:12", "remaining_time": "11:03:53"}
+{"current_steps": 700, "total_steps": 1656, "loss": 0.4491, "lr": 7.161273803881381e-06, "epoch": 0.4229287818140624, "percentage": 42.27, "elapsed_time": "8:00:58", "remaining_time": "10:56:52"}
+{"current_steps": 710, "total_steps": 1656, "loss": 0.4532, "lr": 7.0657354948865786e-06, "epoch": 0.4289706215542633, "percentage": 42.87, "elapsed_time": "8:07:47", "remaining_time": "10:49:55"}
+{"current_steps": 720, "total_steps": 1656, "loss": 0.4646, "lr": 6.969278883254896e-06, "epoch": 0.43501246129446414, "percentage": 43.48, "elapsed_time": "8:14:41", "remaining_time": "10:43:05"}
+{"current_steps": 730, "total_steps": 1656, "loss": 0.4542, "lr": 6.871946847835548e-06, "epoch": 0.44105430103466503, "percentage": 44.08, "elapsed_time": "8:21:31", "remaining_time": "10:36:10"}
+{"current_steps": 740, "total_steps": 1656, "loss": 0.4532, "lr": 6.773782656638889e-06, "epoch": 0.4470961407748659, "percentage": 44.69, "elapsed_time": "8:28:04", "remaining_time": "10:28:55"}
+{"current_steps": 750, "total_steps": 1656, "loss": 0.464, "lr": 6.674829947602034e-06, "epoch": 0.4531379805150668, "percentage": 45.29, "elapsed_time": "8:34:53", "remaining_time": "10:21:59"}
+{"current_steps": 760, "total_steps": 1656, "loss": 0.4604, "lr": 6.575132709190041e-06, "epoch": 0.4591798202552677, "percentage": 45.89, "elapsed_time": "8:41:45", "remaining_time": "10:15:07"}
+{"current_steps": 770, "total_steps": 1656, "loss": 0.4604, "lr": 6.474735260841264e-06, "epoch": 0.4652216599954686, "percentage": 46.5, "elapsed_time": "8:48:35", "remaining_time": "10:08:12"}
+{"current_steps": 780, "total_steps": 1656, "loss": 0.464, "lr": 6.373682233265581e-06, "epoch": 0.4712634997356695, "percentage": 47.1, "elapsed_time": "8:55:33", "remaining_time": "10:01:28"}
+{"current_steps": 790, "total_steps": 1656, "loss": 0.4679, "lr": 6.2720185486042405e-06, "epoch": 0.4773053394758704, "percentage": 47.71, "elapsed_time": "9:02:35", "remaining_time": "9:54:47"}
+{"current_steps": 800, "total_steps": 1656, "loss": 0.4613, "lr": 6.169789400460167e-06, "epoch": 0.4833471792160713, "percentage": 48.31, "elapsed_time": "9:09:39", "remaining_time": "9:48:08"}
+{"current_steps": 810, "total_steps": 1656, "loss": 0.4561, "lr": 6.067040233807579e-06, "epoch": 0.4893890189562722, "percentage": 48.91, "elapsed_time": "9:16:26", "remaining_time": "9:41:10"}
+{"current_steps": 820, "total_steps": 1656, "loss": 0.4488, "lr": 5.963816724789868e-06, "epoch": 0.4954308586964731, "percentage": 49.52, "elapsed_time": "9:23:11", "remaining_time": "9:34:10"}
+{"current_steps": 830, "total_steps": 1656, "loss": 0.4618, "lr": 5.860164760414715e-06, "epoch": 0.501472698436674, "percentage": 50.12, "elapsed_time": "9:30:00", "remaining_time": "9:27:16"}
+{"current_steps": 840, "total_steps": 1656, "loss": 0.4593, "lr": 5.7561304181554626e-06, "epoch": 0.5075145381768749, "percentage": 50.72, "elapsed_time": "9:36:58", "remaining_time": "9:20:29"}
+{"current_steps": 850, "total_steps": 1656, "loss": 0.4502, "lr": 5.651759945467829e-06, "epoch": 0.5135563779170758, "percentage": 51.33, "elapsed_time": "9:44:00", "remaining_time": "9:13:46"}
+{"current_steps": 860, "total_steps": 1656, "loss": 0.4619, "lr": 5.5470997392310475e-06, "epoch": 0.5195982176572767, "percentage": 51.93, "elapsed_time": "9:51:06", "remaining_time": "9:07:07"}
+{"current_steps": 870, "total_steps": 1656, "loss": 0.4588, "lr": 5.442196325122583e-06, "epoch": 0.5256400573974775, "percentage": 52.54, "elapsed_time": "9:57:48", "remaining_time": "9:00:05"}
+{"current_steps": 880, "total_steps": 1656, "loss": 0.4606, "lr": 5.337096336935596e-06, "epoch": 0.5316818971376784, "percentage": 53.14, "elapsed_time": "10:04:36", "remaining_time": "8:53:09"}
+{"current_steps": 890, "total_steps": 1656, "loss": 0.4408, "lr": 5.231846495848343e-06, "epoch": 0.5377237368778793, "percentage": 53.74, "elapsed_time": "10:11:24", "remaining_time": "8:46:13"}
+{"current_steps": 900, "total_steps": 1656, "loss": 0.4538, "lr": 5.12649358965473e-06, "epoch": 0.5437655766180802, "percentage": 54.35, "elapsed_time": "10:18:04", "remaining_time": "8:39:10"}
+{"current_steps": 910, "total_steps": 1656, "loss": 0.4532, "lr": 5.021084451965257e-06, "epoch": 0.5498074163582811, "percentage": 54.95, "elapsed_time": "10:25:03", "remaining_time": "8:32:24"}
+{"current_steps": 920, "total_steps": 1656, "loss": 0.4496, "lr": 4.915665941387589e-06, "epoch": 0.555849256098482, "percentage": 55.56, "elapsed_time": "10:31:57", "remaining_time": "8:25:33"}
+{"current_steps": 930, "total_steps": 1656, "loss": 0.4521, "lr": 4.8102849206960144e-06, "epoch": 0.5618910958386829, "percentage": 56.16, "elapsed_time": "10:38:49", "remaining_time": "8:18:41"}
+{"current_steps": 940, "total_steps": 1656, "loss": 0.4537, "lr": 4.704988235999059e-06, "epoch": 0.5679329355788838, "percentage": 56.76, "elapsed_time": "10:45:56", "remaining_time": "8:12:01"}
+{"current_steps": 950, "total_steps": 1656, "loss": 0.4437, "lr": 4.5998226959145e-06, "epoch": 0.5739747753190847, "percentage": 57.37, "elapsed_time": "10:52:43", "remaining_time": "8:05:04"}
+{"current_steps": 960, "total_steps": 1656, "loss": 0.4506, "lr": 4.494835050761055e-06, "epoch": 0.5800166150592856, "percentage": 57.97, "elapsed_time": "10:59:53", "remaining_time": "7:58:25"}
+{"current_steps": 970, "total_steps": 1656, "loss": 0.4496, "lr": 4.390071971775977e-06, "epoch": 0.5860584547994865, "percentage": 58.57, "elapsed_time": "11:06:43", "remaining_time": "7:51:31"}
+{"current_steps": 980, "total_steps": 1656, "loss": 0.4442, "lr": 4.285580030367812e-06, "epoch": 0.5921002945396874, "percentage": 59.18, "elapsed_time": "11:13:40", "remaining_time": "7:44:41"}
+{"current_steps": 990, "total_steps": 1656, "loss": 0.4515, "lr": 4.18140567741353e-06, "epoch": 0.5981421342798883, "percentage": 59.78, "elapsed_time": "11:20:33", "remaining_time": "7:37:49"}
+{"current_steps": 1000, "total_steps": 1656, "loss": 0.4484, "lr": 4.07759522260924e-06, "epoch": 0.6041839740200892, "percentage": 60.39, "elapsed_time": "11:27:32", "remaining_time": "7:31:01"}
+{"current_steps": 1010, "total_steps": 1656, "loss": 0.4487, "lr": 3.974194813883672e-06, "epoch": 0.6102258137602901, "percentage": 60.99, "elapsed_time": "11:34:28", "remaining_time": "7:24:11"}
+{"current_steps": 1020, "total_steps": 1656, "loss": 0.4487, "lr": 3.871250416883547e-06, "epoch": 0.616267653500491, "percentage": 61.59, "elapsed_time": "11:41:31", "remaining_time": "7:17:25"}
+{"current_steps": 1030, "total_steps": 1656, "loss": 0.4476, "lr": 3.7688077945400135e-06, "epoch": 0.6223094932406917, "percentage": 62.2, "elapsed_time": "11:48:24", "remaining_time": "7:10:32"}
+{"current_steps": 1040, "total_steps": 1656, "loss": 0.4419, "lr": 3.6669124867251705e-06, "epoch": 0.6283513329808926, "percentage": 62.8, "elapsed_time": "11:55:10", "remaining_time": "7:03:36"}
+{"current_steps": 1050, "total_steps": 1656, "loss": 0.4433, "lr": 3.56560979000776e-06, "epoch": 0.6343931727210935, "percentage": 63.41, "elapsed_time": "12:01:59", "remaining_time": "6:56:41"}
+{"current_steps": 1060, "total_steps": 1656, "loss": 0.434, "lr": 3.4649447375170243e-06, "epoch": 0.6404350124612944, "percentage": 64.01, "elapsed_time": "12:08:45", "remaining_time": "6:49:45"}
+{"current_steps": 1070, "total_steps": 1656, "loss": 0.4449, "lr": 3.3649620789236613e-06, "epoch": 0.6464768522014953, "percentage": 64.61, "elapsed_time": "12:15:39", "remaining_time": "6:42:53"}
+{"current_steps": 1080, "total_steps": 1656, "loss": 0.4487, "lr": 3.265706260546793e-06, "epoch": 0.6525186919416962, "percentage": 65.22, "elapsed_time": "12:22:14", "remaining_time": "6:35:51"}
+{"current_steps": 1090, "total_steps": 1656, "loss": 0.4492, "lr": 3.1672214055957885e-06, "epoch": 0.6585605316818971, "percentage": 65.82, "elapsed_time": "12:29:03", "remaining_time": "6:28:57"}
+{"current_steps": 1100, "total_steps": 1656, "loss": 0.4435, "lr": 3.0695512945557175e-06, "epoch": 0.664602371422098, "percentage": 66.43, "elapsed_time": "12:36:05", "remaining_time": "6:22:10"}
+{"current_steps": 1110, "total_steps": 1656, "loss": 0.445, "lr": 2.972739345725163e-06, "epoch": 0.6706442111622989, "percentage": 67.03, "elapsed_time": "12:43:02", "remaining_time": "6:15:20"}
+{"current_steps": 1120, "total_steps": 1656, "loss": 0.4458, "lr": 2.876828595915043e-06, "epoch": 0.6766860509024998, "percentage": 67.63, "elapsed_time": "12:49:56", "remaining_time": "6:08:28"}
+{"current_steps": 1130, "total_steps": 1656, "loss": 0.4362, "lr": 2.781861681317004e-06, "epoch": 0.6827278906427007, "percentage": 68.24, "elapsed_time": "12:56:42", "remaining_time": "6:01:32"}
+{"current_steps": 1140, "total_steps": 1656, "loss": 0.4396, "lr": 2.687880818549927e-06, "epoch": 0.6887697303829016, "percentage": 68.84, "elapsed_time": "13:03:21", "remaining_time": "5:54:34"}
+{"current_steps": 1150, "total_steps": 1656, "loss": 0.4362, "lr": 2.5949277858929297e-06, "epoch": 0.6948115701231025, "percentage": 69.44, "elapsed_time": "13:10:09", "remaining_time": "5:47:40"}
+{"current_steps": 1160, "total_steps": 1656, "loss": 0.4453, "lr": 2.5030439047132484e-06, "epoch": 0.7008534098633034, "percentage": 70.05, "elapsed_time": "13:16:57", "remaining_time": "5:40:45"}
+{"current_steps": 1170, "total_steps": 1656, "loss": 0.4436, "lr": 2.4122700210972218e-06, "epoch": 0.7068952496035042, "percentage": 70.65, "elapsed_time": "13:23:45", "remaining_time": "5:33:52"}
+{"current_steps": 1180, "total_steps": 1656, "loss": 0.4437, "lr": 2.322646487692556e-06, "epoch": 0.7129370893437051, "percentage": 71.26, "elapsed_time": "13:30:24", "remaining_time": "5:26:54"}
+{"current_steps": 1190, "total_steps": 1656, "loss": 0.4495, "lr": 2.2342131457699575e-06, "epoch": 0.718978929083906, "percentage": 71.86, "elapsed_time": "13:37:21", "remaining_time": "5:20:04"}
+{"current_steps": 1200, "total_steps": 1656, "loss": 0.4383, "lr": 2.1470093075120686e-06, "epoch": 0.7250207688241069, "percentage": 72.46, "elapsed_time": "13:44:21", "remaining_time": "5:13:15"}
+{"current_steps": 1210, "total_steps": 1656, "loss": 0.4463, "lr": 2.061073738537635e-06, "epoch": 0.7310626085643078, "percentage": 73.07, "elapsed_time": "13:51:33", "remaining_time": "5:06:30"}
+{"current_steps": 1220, "total_steps": 1656, "loss": 0.4436, "lr": 1.9764446406686177e-06, "epoch": 0.7371044483045087, "percentage": 73.67, "elapsed_time": "13:58:26", "remaining_time": "4:59:38"}
+{"current_steps": 1230, "total_steps": 1656, "loss": 0.4432, "lr": 1.8931596349479385e-06, "epoch": 0.7431462880447096, "percentage": 74.28, "elapsed_time": "14:05:15", "remaining_time": "4:52:44"}
+{"current_steps": 1240, "total_steps": 1656, "loss": 0.4338, "lr": 1.8112557449154316e-06, "epoch": 0.7491881277849105, "percentage": 74.88, "elapsed_time": "14:12:03", "remaining_time": "4:45:51"}
+{"current_steps": 1250, "total_steps": 1656, "loss": 0.4407, "lr": 1.7307693801493619e-06, "epoch": 0.7552299675251114, "percentage": 75.48, "elapsed_time": "14:18:55", "remaining_time": "4:38:58"}
+{"current_steps": 1260, "total_steps": 1656, "loss": 0.4488, "lr": 1.6517363200809222e-06, "epoch": 0.7612718072653123, "percentage": 76.09, "elapsed_time": "14:25:56", "remaining_time": "4:32:09"}
+{"current_steps": 1270, "total_steps": 1656, "loss": 0.435, "lr": 1.5741916980888267e-06, "epoch": 0.7673136470055132, "percentage": 76.69, "elapsed_time": "14:32:29", "remaining_time": "4:25:10"}
+{"current_steps": 1280, "total_steps": 1656, "loss": 0.4436, "lr": 1.4981699858811038e-06, "epoch": 0.7733554867457141, "percentage": 77.29, "elapsed_time": "14:39:16", "remaining_time": "4:18:17"}
+{"current_steps": 1290, "total_steps": 1656, "loss": 0.4407, "lr": 1.423704978171046e-06, "epoch": 0.779397326485915, "percentage": 77.9, "elapsed_time": "14:46:00", "remaining_time": "4:11:22"}
+{"current_steps": 1300, "total_steps": 1656, "loss": 0.4498, "lr": 1.3508297776540845e-06, "epoch": 0.7854391662261159, "percentage": 78.5, "elapsed_time": "14:53:16", "remaining_time": "4:04:37"}
+{"current_steps": 1310, "total_steps": 1656, "loss": 0.4352, "lr": 1.2795767802923192e-06, "epoch": 0.7914810059663168, "percentage": 79.11, "elapsed_time": "14:59:58", "remaining_time": "3:57:42"}
+{"current_steps": 1320, "total_steps": 1656, "loss": 0.4384, "lr": 1.2099776609132048e-06, "epoch": 0.7975228457065177, "percentage": 79.71, "elapsed_time": "15:06:44", "remaining_time": "3:50:48"}
+{"current_steps": 1330, "total_steps": 1656, "loss": 0.441, "lr": 1.1420633591288072e-06, "epoch": 0.8035646854467186, "percentage": 80.31, "elapsed_time": "15:13:20", "remaining_time": "3:43:52"}
+{"current_steps": 1340, "total_steps": 1656, "loss": 0.4375, "lr": 1.0758640655819107e-06, "epoch": 0.8096065251869194, "percentage": 80.92, "elapsed_time": "15:20:05", "remaining_time": "3:36:58"}
+{"current_steps": 1350, "total_steps": 1656, "loss": 0.4439, "lr": 1.0114092085250566e-06, "epoch": 0.8156483649271203, "percentage": 81.52, "elapsed_time": "15:26:41", "remaining_time": "3:30:03"}
+{"current_steps": 1360, "total_steps": 1656, "loss": 0.4359, "lr": 9.487274407384972e-07, "epoch": 0.8216902046673212, "percentage": 82.13, "elapsed_time": "15:33:37", "remaining_time": "3:23:12"}
+{"current_steps": 1370, "total_steps": 1656, "loss": 0.4366, "lr": 8.878466267928814e-07, "epoch": 0.8277320444075221, "percentage": 82.73, "elapsed_time": "15:40:27", "remaining_time": "3:16:19"}
+{"current_steps": 1380, "total_steps": 1656, "loss": 0.4398, "lr": 8.287938306623349e-07, "epoch": 0.833773884147723, "percentage": 83.33, "elapsed_time": "15:47:22", "remaining_time": "3:09:28"}
+{"current_steps": 1390, "total_steps": 1656, "loss": 0.4409, "lr": 7.715953036934304e-07, "epoch": 0.8398157238879239, "percentage": 83.94, "elapsed_time": "15:54:11", "remaining_time": "3:02:36"}
+{"current_steps": 1400, "total_steps": 1656, "loss": 0.4407, "lr": 7.162764729354033e-07, "epoch": 0.8458575636281248, "percentage": 84.54, "elapsed_time": "16:00:54", "remaining_time": "2:55:42"}
+{"current_steps": 1410, "total_steps": 1656, "loss": 0.4297, "lr": 6.628619298368133e-07, "epoch": 0.8518994033683257, "percentage": 85.14, "elapsed_time": "16:07:38", "remaining_time": "2:48:49"}
+{"current_steps": 1420, "total_steps": 1656, "loss": 0.4397, "lr": 6.11375419313644e-07, "epoch": 0.8579412431085266, "percentage": 85.75, "elapsed_time": "16:14:15", "remaining_time": "2:41:55"}
+{"current_steps": 1430, "total_steps": 1656, "loss": 0.4473, "lr": 5.618398291937393e-07, "epoch": 0.8639830828487275, "percentage": 86.35, "elapsed_time": "16:21:06", "remaining_time": "2:35:03"}
+{"current_steps": 1440, "total_steps": 1656, "loss": 0.4424, "lr": 5.142771800422403e-07, "epoch": 0.8700249225889283, "percentage": 86.96, "elapsed_time": "16:27:56", "remaining_time": "2:28:11"}
+{"current_steps": 1450, "total_steps": 1656, "loss": 0.4412, "lr": 4.687086153725534e-07, "epoch": 0.8760667623291292, "percentage": 87.56, "elapsed_time": "16:34:41", "remaining_time": "2:21:18"}
+{"current_steps": 1460, "total_steps": 1656, "loss": 0.4332, "lr": 4.2515439224721066e-07, "epoch": 0.8821086020693301, "percentage": 88.16, "elapsed_time": "16:41:33", "remaining_time": "2:14:27"}
+{"current_steps": 1470, "total_steps": 1656, "loss": 0.4348, "lr": 3.8363387227278947e-07, "epoch": 0.888150441809531, "percentage": 88.77, "elapsed_time": "16:48:18", "remaining_time": "2:07:34"}
+{"current_steps": 1480, "total_steps": 1656, "loss": 0.4442, "lr": 3.441655129928972e-07, "epoch": 0.8941922815497318, "percentage": 89.37, "elapsed_time": "16:55:32", "remaining_time": "2:00:46"}
+{"current_steps": 1490, "total_steps": 1656, "loss": 0.4395, "lr": 3.067668596830481e-07, "epoch": 0.9002341212899327, "percentage": 89.98, "elapsed_time": "17:02:18", "remaining_time": "1:53:53"}
+{"current_steps": 1500, "total_steps": 1656, "loss": 0.4366, "lr": 2.714545375510852e-07, "epoch": 0.9062759610301336, "percentage": 90.58, "elapsed_time": "17:09:08", "remaining_time": "1:47:01"}
+{"current_steps": 1510, "total_steps": 1656, "loss": 0.4321, "lr": 2.382442443466043e-07, "epoch": 0.9123178007703345, "percentage": 91.18, "elapsed_time": "17:16:06", "remaining_time": "1:40:10"}
+{"current_steps": 1520, "total_steps": 1656, "loss": 0.4312, "lr": 2.0715074338266915e-07, "epoch": 0.9183596405105354, "percentage": 91.79, "elapsed_time": "17:22:54", "remaining_time": "1:33:18"}
+{"current_steps": 1530, "total_steps": 1656, "loss": 0.4388, "lr": 1.7818785697292895e-07, "epoch": 0.9244014802507363, "percentage": 92.39, "elapsed_time": "17:29:41", "remaining_time": "1:26:26"}
+{"current_steps": 1540, "total_steps": 1656, "loss": 0.4491, "lr": 1.5136846028704132e-07, "epoch": 0.9304433199909372, "percentage": 93.0, "elapsed_time": "17:36:32", "remaining_time": "1:19:35"}
+{"current_steps": 1550, "total_steps": 1656, "loss": 0.4322, "lr": 1.2670447562713684e-07, "epoch": 0.9364851597311381, "percentage": 93.6, "elapsed_time": "17:43:19", "remaining_time": "1:12:43"}
+{"current_steps": 1560, "total_steps": 1656, "loss": 0.4354, "lr": 1.042068671278823e-07, "epoch": 0.942526999471339, "percentage": 94.2, "elapsed_time": "17:50:09", "remaining_time": "1:05:51"}
+{"current_steps": 1570, "total_steps": 1656, "loss": 0.4316, "lr": 8.388563588247523e-08, "epoch": 0.9485688392115399, "percentage": 94.81, "elapsed_time": "17:57:01", "remaining_time": "0:58:59"}
+{"current_steps": 1580, "total_steps": 1656, "loss": 0.4354, "lr": 6.574981549676007e-08, "epoch": 0.9546106789517408, "percentage": 95.41, "elapsed_time": "18:04:01", "remaining_time": "0:52:08"}
+{"current_steps": 1590, "total_steps": 1656, "loss": 0.4331, "lr": 4.980746807342285e-08, "epoch": 0.9606525186919417, "percentage": 96.01, "elapsed_time": "18:10:55", "remaining_time": "0:45:17"}
+{"current_steps": 1600, "total_steps": 1656, "loss": 0.4397, "lr": 3.6065680628062924e-08, "epoch": 0.9666943584321426, "percentage": 96.62, "elapsed_time": "18:17:42", "remaining_time": "0:38:25"}
+{"current_steps": 1610, "total_steps": 1656, "loss": 0.4266, "lr": 2.4530561938729825e-08, "epoch": 0.9727361981723435, "percentage": 97.22, "elapsed_time": "18:24:26", "remaining_time": "0:31:33"}
+{"current_steps": 1620, "total_steps": 1656, "loss": 0.4335, "lr": 1.520723983032324e-08, "epoch": 0.9787780379125444, "percentage": 97.83, "elapsed_time": "18:31:10", "remaining_time": "0:24:41"}
+{"current_steps": 1630, "total_steps": 1656, "loss": 0.4373, "lr": 8.099858895072587e-09, "epoch": 0.9848198776527453, "percentage": 98.43, "elapsed_time": "18:38:09", "remaining_time": "0:17:50"}
+{"current_steps": 1640, "total_steps": 1656, "loss": 0.4371, "lr": 3.2115786500924728e-09, "epoch": 0.9908617173929462, "percentage": 99.03, "elapsed_time": "18:45:03", "remaining_time": "0:10:58"}
+{"current_steps": 1650, "total_steps": 1656, "loss": 0.4329, "lr": 5.445721328567466e-10, "epoch": 0.996903557133147, "percentage": 99.64, "elapsed_time": "18:52:00", "remaining_time": "0:04:06"}
+{"current_steps": 1656, "total_steps": 1656, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "18:56:18", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1198 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1656,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006041839740200891,
+      "grad_norm": 8.275440544361343,
+      "learning_rate": 5.421686746987952e-07,
+      "loss": 0.818,
+      "step": 10
+    },
+    {
+      "epoch": 0.012083679480401783,
+      "grad_norm": 2.7914609484184627,
+      "learning_rate": 1.1445783132530121e-06,
+      "loss": 0.6987,
+      "step": 20
+    },
+    {
+      "epoch": 0.018125519220602675,
+      "grad_norm": 1.3664105415610248,
+      "learning_rate": 1.7469879518072292e-06,
+      "loss": 0.5802,
+      "step": 30
+    },
+    {
+      "epoch": 0.024167358960803565,
+      "grad_norm": 0.8594872429754616,
+      "learning_rate": 2.349397590361446e-06,
+      "loss": 0.5258,
+      "step": 40
+    },
+    {
+      "epoch": 0.030209198701004455,
+      "grad_norm": 0.7434393729226938,
+      "learning_rate": 2.9518072289156627e-06,
+      "loss": 0.5145,
+      "step": 50
+    },
+    {
+      "epoch": 0.03625103844120535,
+      "grad_norm": 0.8872227027342147,
+      "learning_rate": 3.5542168674698798e-06,
+      "loss": 0.5015,
+      "step": 60
+    },
+    {
+      "epoch": 0.042292878181406236,
+      "grad_norm": 0.8429713488596823,
+      "learning_rate": 4.156626506024097e-06,
+      "loss": 0.4901,
+      "step": 70
+    },
+    {
+      "epoch": 0.04833471792160713,
+      "grad_norm": 0.9065488209295363,
+      "learning_rate": 4.759036144578314e-06,
+      "loss": 0.4796,
+      "step": 80
+    },
+    {
+      "epoch": 0.05437655766180802,
+      "grad_norm": 0.9651498125714989,
+      "learning_rate": 5.361445783132531e-06,
+      "loss": 0.4758,
+      "step": 90
+    },
+    {
+      "epoch": 0.06041839740200891,
+      "grad_norm": 0.8301785431193227,
+      "learning_rate": 5.963855421686747e-06,
+      "loss": 0.4829,
+      "step": 100
+    },
+    {
+      "epoch": 0.0664602371422098,
+      "grad_norm": 0.8886113651753562,
+      "learning_rate": 6.566265060240964e-06,
+      "loss": 0.4812,
+      "step": 110
+    },
+    {
+      "epoch": 0.0725020768824107,
+      "grad_norm": 0.9862797318907437,
+      "learning_rate": 7.168674698795182e-06,
+      "loss": 0.4789,
+      "step": 120
+    },
+    {
+      "epoch": 0.07854391662261158,
+      "grad_norm": 1.0637568246181046,
+      "learning_rate": 7.771084337349398e-06,
+      "loss": 0.4767,
+      "step": 130
+    },
+    {
+      "epoch": 0.08458575636281247,
+      "grad_norm": 1.019587639434787,
+      "learning_rate": 8.373493975903614e-06,
+      "loss": 0.4748,
+      "step": 140
+    },
+    {
+      "epoch": 0.09062759610301337,
+      "grad_norm": 1.0494143456183387,
+      "learning_rate": 8.975903614457832e-06,
+      "loss": 0.471,
+      "step": 150
+    },
+    {
+      "epoch": 0.09666943584321426,
+      "grad_norm": 1.0167856442156524,
+      "learning_rate": 9.57831325301205e-06,
+      "loss": 0.482,
+      "step": 160
+    },
+    {
+      "epoch": 0.10271127558341515,
+      "grad_norm": 0.9927765526681102,
+      "learning_rate": 9.99989997506481e-06,
+      "loss": 0.4867,
+      "step": 170
+    },
+    {
+      "epoch": 0.10875311532361603,
+      "grad_norm": 0.8252285160527216,
+      "learning_rate": 9.998121865323769e-06,
+      "loss": 0.4832,
+      "step": 180
+    },
+    {
+      "epoch": 0.11479495506381693,
+      "grad_norm": 1.0494152999510933,
+      "learning_rate": 9.994121889085426e-06,
+      "loss": 0.4836,
+      "step": 190
+    },
+    {
+      "epoch": 0.12083679480401782,
+      "grad_norm": 0.8683126435696938,
+      "learning_rate": 9.987901824500342e-06,
+      "loss": 0.4796,
+      "step": 200
+    },
+    {
+      "epoch": 0.12687863454421872,
+      "grad_norm": 1.0765238837274924,
+      "learning_rate": 9.979464436637771e-06,
+      "loss": 0.479,
+      "step": 210
+    },
+    {
+      "epoch": 0.1329204742844196,
+      "grad_norm": 0.9747782968326728,
+      "learning_rate": 9.968813476256483e-06,
+      "loss": 0.4774,
+      "step": 220
+    },
+    {
+      "epoch": 0.1389623140246205,
+      "grad_norm": 1.0422947760995596,
+      "learning_rate": 9.955953678137397e-06,
+      "loss": 0.4775,
+      "step": 230
+    },
+    {
+      "epoch": 0.1450041537648214,
+      "grad_norm": 0.8638869125481701,
+      "learning_rate": 9.940890758978781e-06,
+      "loss": 0.4809,
+      "step": 240
+    },
+    {
+      "epoch": 0.1510459935050223,
+      "grad_norm": 0.9908759029078118,
+      "learning_rate": 9.923631414854946e-06,
+      "loss": 0.4823,
+      "step": 250
+    },
+    {
+      "epoch": 0.15708783324522316,
+      "grad_norm": 0.8594590054265251,
+      "learning_rate": 9.904183318239573e-06,
+      "loss": 0.4732,
+      "step": 260
+    },
+    {
+      "epoch": 0.16312967298542405,
+      "grad_norm": 0.8537166815636835,
+      "learning_rate": 9.882555114594994e-06,
+      "loss": 0.4746,
+      "step": 270
+    },
+    {
+      "epoch": 0.16917151272562495,
+      "grad_norm": 0.7988607086870596,
+      "learning_rate": 9.858756418528928e-06,
+      "loss": 0.4771,
+      "step": 280
+    },
+    {
+      "epoch": 0.17521335246582584,
+      "grad_norm": 0.8128733549061342,
+      "learning_rate": 9.832797809520404e-06,
+      "loss": 0.4703,
+      "step": 290
+    },
+    {
+      "epoch": 0.18125519220602673,
+      "grad_norm": 0.8670976233152772,
+      "learning_rate": 9.804690827216764e-06,
+      "loss": 0.4763,
+      "step": 300
+    },
+    {
+      "epoch": 0.18729703194622763,
+      "grad_norm": 0.9163703807052254,
+      "learning_rate": 9.77444796630381e-06,
+      "loss": 0.4665,
+      "step": 310
+    },
+    {
+      "epoch": 0.19333887168642852,
+      "grad_norm": 1.0505077270930072,
+      "learning_rate": 9.742082670951423e-06,
+      "loss": 0.4781,
+      "step": 320
+    },
+    {
+      "epoch": 0.19938071142662941,
+      "grad_norm": 0.9771619804123264,
+      "learning_rate": 9.707609328837085e-06,
+      "loss": 0.4695,
+      "step": 330
+    },
+    {
+      "epoch": 0.2054225511668303,
+      "grad_norm": 0.8443160970596196,
+      "learning_rate": 9.67104326474998e-06,
+      "loss": 0.4709,
+      "step": 340
+    },
+    {
+      "epoch": 0.2114643909070312,
+      "grad_norm": 0.7405442085507775,
+      "learning_rate": 9.632400733778504e-06,
+      "loss": 0.4687,
+      "step": 350
+    },
+    {
+      "epoch": 0.21750623064723207,
+      "grad_norm": 1.06910781919214,
+      "learning_rate": 9.591698914084224e-06,
+      "loss": 0.4727,
+      "step": 360
+    },
+    {
+      "epoch": 0.22354807038743296,
+      "grad_norm": 0.9783321165505232,
+      "learning_rate": 9.548955899265495e-06,
+      "loss": 0.4757,
+      "step": 370
+    },
+    {
+      "epoch": 0.22958991012763386,
+      "grad_norm": 0.856614778477577,
+      "learning_rate": 9.504190690314124e-06,
+      "loss": 0.4628,
+      "step": 380
+    },
+    {
+      "epoch": 0.23563174986783475,
+      "grad_norm": 0.8407994854798428,
+      "learning_rate": 9.457423187168667e-06,
+      "loss": 0.4751,
+      "step": 390
+    },
+    {
+      "epoch": 0.24167358960803564,
+      "grad_norm": 0.835330085907184,
+      "learning_rate": 9.408674179868101e-06,
+      "loss": 0.4755,
+      "step": 400
+    },
+    {
+      "epoch": 0.24771542934823654,
+      "grad_norm": 0.8184694750958316,
+      "learning_rate": 9.357965339309823e-06,
+      "loss": 0.4688,
+      "step": 410
+    },
+    {
+      "epoch": 0.25375726908843743,
+      "grad_norm": 0.8556998098855371,
+      "learning_rate": 9.305319207616048e-06,
+      "loss": 0.468,
+      "step": 420
+    },
+    {
+      "epoch": 0.2597991088286383,
+      "grad_norm": 0.7125631433834922,
+      "learning_rate": 9.250759188112944e-06,
+      "loss": 0.4721,
+      "step": 430
+    },
+    {
+      "epoch": 0.2658409485688392,
+      "grad_norm": 0.8684064304089488,
+      "learning_rate": 9.194309534926896e-06,
+      "loss": 0.4719,
+      "step": 440
+    },
+    {
+      "epoch": 0.2718827883090401,
+      "grad_norm": 0.8581281745281804,
+      "learning_rate": 9.13599534220258e-06,
+      "loss": 0.4676,
+      "step": 450
+    },
+    {
+      "epoch": 0.277924628049241,
+      "grad_norm": 0.8073909041822805,
+      "learning_rate": 9.075842532947605e-06,
+      "loss": 0.4729,
+      "step": 460
+    },
+    {
+      "epoch": 0.2839664677894419,
+      "grad_norm": 0.7760503268897376,
+      "learning_rate": 9.013877847508684e-06,
+      "loss": 0.4735,
+      "step": 470
+    },
+    {
+      "epoch": 0.2900083075296428,
+      "grad_norm": 1.007511777834999,
+      "learning_rate": 8.95012883168448e-06,
+      "loss": 0.4655,
+      "step": 480
+    },
+    {
+      "epoch": 0.2960501472698437,
+      "grad_norm": 0.8792795612951879,
+      "learning_rate": 8.884623824480388e-06,
+      "loss": 0.4604,
+      "step": 490
+    },
+    {
+      "epoch": 0.3020919870100446,
+      "grad_norm": 0.7649844789740483,
+      "learning_rate": 8.817391945510697e-06,
+      "loss": 0.4727,
+      "step": 500
+    },
+    {
+      "epoch": 0.3081338267502455,
+      "grad_norm": 0.7112188721793731,
+      "learning_rate": 8.748463082053765e-06,
+      "loss": 0.4696,
+      "step": 510
+    },
+    {
+      "epoch": 0.3141756664904463,
+      "grad_norm": 0.982736127204613,
+      "learning_rate": 8.677867875765904e-06,
+      "loss": 0.4667,
+      "step": 520
+    },
+    {
+      "epoch": 0.3202175062306472,
+      "grad_norm": 0.7380835460961964,
+      "learning_rate": 8.605637709059937e-06,
+      "loss": 0.4665,
+      "step": 530
+    },
+    {
+      "epoch": 0.3262593459708481,
+      "grad_norm": 0.889341527636709,
+      "learning_rate": 8.531804691154454e-06,
+      "loss": 0.4596,
+      "step": 540
+    },
+    {
+      "epoch": 0.332301185711049,
+      "grad_norm": 0.8717590020119719,
+      "learning_rate": 8.45640164379996e-06,
+      "loss": 0.4635,
+      "step": 550
+    },
+    {
+      "epoch": 0.3383430254512499,
+      "grad_norm": 0.8593981074116124,
+      "learning_rate": 8.379462086688302e-06,
+      "loss": 0.4614,
+      "step": 560
+    },
+    {
+      "epoch": 0.3443848651914508,
+      "grad_norm": 0.7452870255566968,
+      "learning_rate": 8.301020222551795e-06,
+      "loss": 0.4613,
+      "step": 570
+    },
+    {
+      "epoch": 0.3504267049316517,
+      "grad_norm": 0.6738237626130682,
+      "learning_rate": 8.221110921958748e-06,
+      "loss": 0.4625,
+      "step": 580
+    },
+    {
+      "epoch": 0.35646854467185257,
+      "grad_norm": 0.7475917228131528,
+      "learning_rate": 8.139769707812083e-06,
+      "loss": 0.4643,
+      "step": 590
+    },
+    {
+      "epoch": 0.36251038441205347,
+      "grad_norm": 0.8625312431506086,
+      "learning_rate": 8.057032739557973e-06,
+      "loss": 0.4647,
+      "step": 600
+    },
+    {
+      "epoch": 0.36855222415225436,
+      "grad_norm": 0.7686541350728158,
+      "learning_rate": 7.972936797111515e-06,
+      "loss": 0.4664,
+      "step": 610
+    },
+    {
+      "epoch": 0.37459406389245525,
+      "grad_norm": 0.793893791173724,
+      "learning_rate": 7.887519264506577e-06,
+      "loss": 0.4687,
+      "step": 620
+    },
+    {
+      "epoch": 0.38063590363265615,
+      "grad_norm": 0.8889160126310801,
+      "learning_rate": 7.800818113277085e-06,
+      "loss": 0.4675,
+      "step": 630
+    },
+    {
+      "epoch": 0.38667774337285704,
+      "grad_norm": 0.73855111981923,
+      "learning_rate": 7.712871885577147e-06,
+      "loss": 0.4696,
+      "step": 640
+    },
+    {
+      "epoch": 0.39271958311305794,
+      "grad_norm": 0.9038531350448926,
+      "learning_rate": 7.623719677047521e-06,
+      "loss": 0.4679,
+      "step": 650
+    },
+    {
+      "epoch": 0.39876142285325883,
+      "grad_norm": 0.8258158060448149,
+      "learning_rate": 7.533401119436012e-06,
+      "loss": 0.4636,
+      "step": 660
+    },
+    {
+      "epoch": 0.4048032625934597,
+      "grad_norm": 0.7984996623335708,
+      "learning_rate": 7.441956362979584e-06,
+      "loss": 0.4573,
+      "step": 670
+    },
+    {
+      "epoch": 0.4108451023336606,
+      "grad_norm": 0.9068733833902644,
+      "learning_rate": 7.349426058555943e-06,
+      "loss": 0.467,
+      "step": 680
+    },
+    {
+      "epoch": 0.4168869420738615,
+      "grad_norm": 0.7305483298541591,
+      "learning_rate": 7.255851339612597e-06,
+      "loss": 0.4619,
+      "step": 690
+    },
+    {
+      "epoch": 0.4229287818140624,
+      "grad_norm": 0.7441065423891078,
+      "learning_rate": 7.161273803881381e-06,
+      "loss": 0.4491,
+      "step": 700
+    },
+    {
+      "epoch": 0.4289706215542633,
+      "grad_norm": 0.9276808876681103,
+      "learning_rate": 7.0657354948865786e-06,
+      "loss": 0.4532,
+      "step": 710
+    },
+    {
+      "epoch": 0.43501246129446414,
+      "grad_norm": 0.6605412717277142,
+      "learning_rate": 6.969278883254896e-06,
+      "loss": 0.4646,
+      "step": 720
+    },
+    {
+      "epoch": 0.44105430103466503,
+      "grad_norm": 0.6593545188739028,
+      "learning_rate": 6.871946847835548e-06,
+      "loss": 0.4542,
+      "step": 730
+    },
+    {
+      "epoch": 0.4470961407748659,
+      "grad_norm": 0.7295116693541216,
+      "learning_rate": 6.773782656638889e-06,
+      "loss": 0.4532,
+      "step": 740
+    },
+    {
+      "epoch": 0.4531379805150668,
+      "grad_norm": 0.7877222556349484,
+      "learning_rate": 6.674829947602034e-06,
+      "loss": 0.464,
+      "step": 750
+    },
+    {
+      "epoch": 0.4591798202552677,
+      "grad_norm": 0.7208466663864777,
+      "learning_rate": 6.575132709190041e-06,
+      "loss": 0.4604,
+      "step": 760
+    },
+    {
+      "epoch": 0.4652216599954686,
+      "grad_norm": 0.8296261142467121,
+      "learning_rate": 6.474735260841264e-06,
+      "loss": 0.4604,
+      "step": 770
+    },
+    {
+      "epoch": 0.4712634997356695,
+      "grad_norm": 0.7971141568003346,
+      "learning_rate": 6.373682233265581e-06,
+      "loss": 0.464,
+      "step": 780
+    },
+    {
+      "epoch": 0.4773053394758704,
+      "grad_norm": 0.8736349174540989,
+      "learning_rate": 6.2720185486042405e-06,
+      "loss": 0.4679,
+      "step": 790
+    },
+    {
+      "epoch": 0.4833471792160713,
+      "grad_norm": 0.9309796515999401,
+      "learning_rate": 6.169789400460167e-06,
+      "loss": 0.4613,
+      "step": 800
+    },
+    {
+      "epoch": 0.4893890189562722,
+      "grad_norm": 0.7752657579479202,
+      "learning_rate": 6.067040233807579e-06,
+      "loss": 0.4561,
+      "step": 810
+    },
+    {
+      "epoch": 0.4954308586964731,
+      "grad_norm": 0.8534120955438902,
+      "learning_rate": 5.963816724789868e-06,
+      "loss": 0.4488,
+      "step": 820
+    },
+    {
+      "epoch": 0.501472698436674,
+      "grad_norm": 0.8496125433352629,
+      "learning_rate": 5.860164760414715e-06,
+      "loss": 0.4618,
+      "step": 830
+    },
+    {
+      "epoch": 0.5075145381768749,
+      "grad_norm": 0.8251415980778435,
+      "learning_rate": 5.7561304181554626e-06,
+      "loss": 0.4593,
+      "step": 840
+    },
+    {
+      "epoch": 0.5135563779170758,
+      "grad_norm": 0.7139950510608393,
+      "learning_rate": 5.651759945467829e-06,
+      "loss": 0.4502,
+      "step": 850
+    },
+    {
+      "epoch": 0.5195982176572767,
+      "grad_norm": 0.601943553224525,
+      "learning_rate": 5.5470997392310475e-06,
+      "loss": 0.4619,
+      "step": 860
+    },
+    {
+      "epoch": 0.5256400573974775,
+      "grad_norm": 0.8153866464407951,
+      "learning_rate": 5.442196325122583e-06,
+      "loss": 0.4588,
+      "step": 870
+    },
+    {
+      "epoch": 0.5316818971376784,
+      "grad_norm": 0.8344346217932002,
+      "learning_rate": 5.337096336935596e-06,
+      "loss": 0.4606,
+      "step": 880
+    },
+    {
+      "epoch": 0.5377237368778793,
+      "grad_norm": 0.7492780666259381,
+      "learning_rate": 5.231846495848343e-06,
+      "loss": 0.4408,
+      "step": 890
+    },
+    {
+      "epoch": 0.5437655766180802,
+      "grad_norm": 0.7261206428098568,
+      "learning_rate": 5.12649358965473e-06,
+      "loss": 0.4538,
+      "step": 900
+    },
+    {
+      "epoch": 0.5498074163582811,
+      "grad_norm": 0.7279393955754347,
+      "learning_rate": 5.021084451965257e-06,
+      "loss": 0.4532,
+      "step": 910
+    },
+    {
+      "epoch": 0.555849256098482,
+      "grad_norm": 0.825743775909579,
+      "learning_rate": 4.915665941387589e-06,
+      "loss": 0.4496,
+      "step": 920
+    },
+    {
+      "epoch": 0.5618910958386829,
+      "grad_norm": 0.7524696024763261,
+      "learning_rate": 4.8102849206960144e-06,
+      "loss": 0.4521,
+      "step": 930
+    },
+    {
+      "epoch": 0.5679329355788838,
+      "grad_norm": 0.6103762891076722,
+      "learning_rate": 4.704988235999059e-06,
+      "loss": 0.4537,
+      "step": 940
+    },
+    {
+      "epoch": 0.5739747753190847,
+      "grad_norm": 0.7615515295808474,
+      "learning_rate": 4.5998226959145e-06,
+      "loss": 0.4437,
+      "step": 950
+    },
+    {
+      "epoch": 0.5800166150592856,
+      "grad_norm": 0.8148357524689337,
+      "learning_rate": 4.494835050761055e-06,
+      "loss": 0.4506,
+      "step": 960
+    },
+    {
+      "epoch": 0.5860584547994865,
+      "grad_norm": 0.746845262451762,
+      "learning_rate": 4.390071971775977e-06,
+      "loss": 0.4496,
+      "step": 970
+    },
+    {
+      "epoch": 0.5921002945396874,
+      "grad_norm": 0.7650124837023387,
+      "learning_rate": 4.285580030367812e-06,
+      "loss": 0.4442,
+      "step": 980
+    },
+    {
+      "epoch": 0.5981421342798883,
+      "grad_norm": 0.7044872850784959,
+      "learning_rate": 4.18140567741353e-06,
+      "loss": 0.4515,
+      "step": 990
+    },
+    {
+      "epoch": 0.6041839740200892,
+      "grad_norm": 0.6835203586178121,
+      "learning_rate": 4.07759522260924e-06,
+      "loss": 0.4484,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6102258137602901,
+      "grad_norm": 0.7875522158264618,
+      "learning_rate": 3.974194813883672e-06,
+      "loss": 0.4487,
+      "step": 1010
+    },
+    {
+      "epoch": 0.616267653500491,
+      "grad_norm": 1.0731871419616035,
+      "learning_rate": 3.871250416883547e-06,
+      "loss": 0.4487,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6223094932406917,
+      "grad_norm": 0.7645842030603645,
+      "learning_rate": 3.7688077945400135e-06,
+      "loss": 0.4476,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6283513329808926,
+      "grad_norm": 0.8262016423595615,
+      "learning_rate": 3.6669124867251705e-06,
+      "loss": 0.4419,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6343931727210935,
+      "grad_norm": 0.8630082766433129,
+      "learning_rate": 3.56560979000776e-06,
+      "loss": 0.4433,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6404350124612944,
+      "grad_norm": 0.6739630234814128,
+      "learning_rate": 3.4649447375170243e-06,
+      "loss": 0.434,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6464768522014953,
+      "grad_norm": 0.8005468876181695,
+      "learning_rate": 3.3649620789236613e-06,
+      "loss": 0.4449,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6525186919416962,
+      "grad_norm": 0.6927017507913021,
+      "learning_rate": 3.265706260546793e-06,
+      "loss": 0.4487,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6585605316818971,
+      "grad_norm": 0.7470116822150206,
+      "learning_rate": 3.1672214055957885e-06,
+      "loss": 0.4492,
+      "step": 1090
+    },
+    {
+      "epoch": 0.664602371422098,
+      "grad_norm": 0.7165981129271416,
+      "learning_rate": 3.0695512945557175e-06,
+      "loss": 0.4435,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6706442111622989,
+      "grad_norm": 0.6713758708690007,
+      "learning_rate": 2.972739345725163e-06,
+      "loss": 0.445,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6766860509024998,
+      "grad_norm": 0.7528881198034107,
+      "learning_rate": 2.876828595915043e-06,
+      "loss": 0.4458,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6827278906427007,
+      "grad_norm": 1.3727779517766678,
+      "learning_rate": 2.781861681317004e-06,
+      "loss": 0.4362,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6887697303829016,
+      "grad_norm": 0.8146352120444986,
+      "learning_rate": 2.687880818549927e-06,
+      "loss": 0.4396,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6948115701231025,
+      "grad_norm": 0.6965825401455522,
+      "learning_rate": 2.5949277858929297e-06,
+      "loss": 0.4362,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7008534098633034,
+      "grad_norm": 0.6495955670121708,
+      "learning_rate": 2.5030439047132484e-06,
+      "loss": 0.4453,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7068952496035042,
+      "grad_norm": 0.6114269361750394,
+      "learning_rate": 2.4122700210972218e-06,
+      "loss": 0.4436,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7129370893437051,
+      "grad_norm": 0.851795747172313,
+      "learning_rate": 2.322646487692556e-06,
+      "loss": 0.4437,
+      "step": 1180
+    },
+    {
+      "epoch": 0.718978929083906,
+      "grad_norm": 0.775135762171182,
+      "learning_rate": 2.2342131457699575e-06,
+      "loss": 0.4495,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7250207688241069,
+      "grad_norm": 0.6479257056864712,
+      "learning_rate": 2.1470093075120686e-06,
+      "loss": 0.4383,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7310626085643078,
+      "grad_norm": 0.8263286588325557,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.4463,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7371044483045087,
+      "grad_norm": 0.6982438518266665,
+      "learning_rate": 1.9764446406686177e-06,
+      "loss": 0.4436,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7431462880447096,
+      "grad_norm": 0.6700592747869402,
+      "learning_rate": 1.8931596349479385e-06,
+      "loss": 0.4432,
+      "step": 1230
+    },
+    {
+      "epoch": 0.7491881277849105,
+      "grad_norm": 0.5967953856950272,
+      "learning_rate": 1.8112557449154316e-06,
+      "loss": 0.4338,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7552299675251114,
+      "grad_norm": 0.6985853030295077,
+      "learning_rate": 1.7307693801493619e-06,
+      "loss": 0.4407,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7612718072653123,
+      "grad_norm": 0.7016362891096635,
+      "learning_rate": 1.6517363200809222e-06,
+      "loss": 0.4488,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7673136470055132,
+      "grad_norm": 0.8402985241208492,
+      "learning_rate": 1.5741916980888267e-06,
+      "loss": 0.435,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7733554867457141,
+      "grad_norm": 0.8240304279049092,
+      "learning_rate": 1.4981699858811038e-06,
+      "loss": 0.4436,
+      "step": 1280
+    },
+    {
+      "epoch": 0.779397326485915,
+      "grad_norm": 0.6660945380738031,
+      "learning_rate": 1.423704978171046e-06,
+      "loss": 0.4407,
+      "step": 1290
+    },
+    {
+      "epoch": 0.7854391662261159,
+      "grad_norm": 0.5874782271939601,
+      "learning_rate": 1.3508297776540845e-06,
+      "loss": 0.4498,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7914810059663168,
+      "grad_norm": 0.5796653208549384,
+      "learning_rate": 1.2795767802923192e-06,
+      "loss": 0.4352,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7975228457065177,
+      "grad_norm": 0.9463374855160357,
+      "learning_rate": 1.2099776609132048e-06,
+      "loss": 0.4384,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8035646854467186,
+      "grad_norm": 0.6012369149099516,
+      "learning_rate": 1.1420633591288072e-06,
+      "loss": 0.441,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8096065251869194,
+      "grad_norm": 0.7550415373921882,
+      "learning_rate": 1.0758640655819107e-06,
+      "loss": 0.4375,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8156483649271203,
+      "grad_norm": 0.7006495875182843,
+      "learning_rate": 1.0114092085250566e-06,
+      "loss": 0.4439,
+      "step": 1350
+    },
+    {
+      "epoch": 0.8216902046673212,
+      "grad_norm": 0.6206161322638641,
+      "learning_rate": 9.487274407384972e-07,
+      "loss": 0.4359,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8277320444075221,
+      "grad_norm": 0.6290155968597686,
+      "learning_rate": 8.878466267928814e-07,
+      "loss": 0.4366,
+      "step": 1370
+    },
+    {
+      "epoch": 0.833773884147723,
+      "grad_norm": 0.6195315234512612,
+      "learning_rate": 8.287938306623349e-07,
+      "loss": 0.4398,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8398157238879239,
+      "grad_norm": 0.8102446928428507,
+      "learning_rate": 7.715953036934304e-07,
+      "loss": 0.4409,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8458575636281248,
+      "grad_norm": 0.789309132604837,
+      "learning_rate": 7.162764729354033e-07,
+      "loss": 0.4407,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8518994033683257,
+      "grad_norm": 0.6558463034047459,
+      "learning_rate": 6.628619298368133e-07,
+      "loss": 0.4297,
+      "step": 1410
+    },
+    {
+      "epoch": 0.8579412431085266,
+      "grad_norm": 0.6589202868449741,
+      "learning_rate": 6.11375419313644e-07,
+      "loss": 0.4397,
+      "step": 1420
+    },
+    {
+      "epoch": 0.8639830828487275,
+      "grad_norm": 0.6171089586498126,
+      "learning_rate": 5.618398291937393e-07,
+      "loss": 0.4473,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8700249225889283,
+      "grad_norm": 0.8171417567736048,
+      "learning_rate": 5.142771800422403e-07,
+      "loss": 0.4424,
+      "step": 1440
+    },
+    {
+      "epoch": 0.8760667623291292,
+      "grad_norm": 0.813136783771392,
+      "learning_rate": 4.687086153725534e-07,
+      "loss": 0.4412,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8821086020693301,
+      "grad_norm": 0.6976453824184702,
+      "learning_rate": 4.2515439224721066e-07,
+      "loss": 0.4332,
+      "step": 1460
+    },
+    {
+      "epoch": 0.888150441809531,
+      "grad_norm": 0.5748251232369562,
+      "learning_rate": 3.8363387227278947e-07,
+      "loss": 0.4348,
+      "step": 1470
+    },
+    {
+      "epoch": 0.8941922815497318,
+      "grad_norm": 0.720005515762108,
+      "learning_rate": 3.441655129928972e-07,
+      "loss": 0.4442,
+      "step": 1480
+    },
+    {
+      "epoch": 0.9002341212899327,
+      "grad_norm": 0.7252408165512142,
+      "learning_rate": 3.067668596830481e-07,
+      "loss": 0.4395,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9062759610301336,
+      "grad_norm": 0.7144631857492548,
+      "learning_rate": 2.714545375510852e-07,
+      "loss": 0.4366,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9123178007703345,
+      "grad_norm": 0.6635911944336934,
+      "learning_rate": 2.382442443466043e-07,
+      "loss": 0.4321,
+      "step": 1510
+    },
+    {
+      "epoch": 0.9183596405105354,
+      "grad_norm": 0.7758826608638922,
+      "learning_rate": 2.0715074338266915e-07,
+      "loss": 0.4312,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9244014802507363,
+      "grad_norm": 0.7230232505488107,
+      "learning_rate": 1.7818785697292895e-07,
+      "loss": 0.4388,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9304433199909372,
+      "grad_norm": 0.6580184350979571,
+      "learning_rate": 1.5136846028704132e-07,
+      "loss": 0.4491,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9364851597311381,
+      "grad_norm": 0.5586825913101796,
+      "learning_rate": 1.2670447562713684e-07,
+      "loss": 0.4322,
+      "step": 1550
+    },
+    {
+      "epoch": 0.942526999471339,
+      "grad_norm": 0.647195128183336,
+      "learning_rate": 1.042068671278823e-07,
+      "loss": 0.4354,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9485688392115399,
+      "grad_norm": 0.6035271594962103,
+      "learning_rate": 8.388563588247523e-08,
+      "loss": 0.4316,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9546106789517408,
+      "grad_norm": 0.6113112433338288,
+      "learning_rate": 6.574981549676007e-08,
+      "loss": 0.4354,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9606525186919417,
+      "grad_norm": 0.7146951417286433,
+      "learning_rate": 4.980746807342285e-08,
+      "loss": 0.4331,
+      "step": 1590
+    },
+    {
+      "epoch": 0.9666943584321426,
+      "grad_norm": 0.6521596489801758,
+      "learning_rate": 3.6065680628062924e-08,
+      "loss": 0.4397,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9727361981723435,
+      "grad_norm": 0.8208153994914311,
+      "learning_rate": 2.4530561938729825e-08,
+      "loss": 0.4266,
+      "step": 1610
+    },
+    {
+      "epoch": 0.9787780379125444,
+      "grad_norm": 0.6500288352676025,
+      "learning_rate": 1.520723983032324e-08,
+      "loss": 0.4335,
+      "step": 1620
+    },
+    {
+      "epoch": 0.9848198776527453,
+      "grad_norm": 0.6538530895079608,
+      "learning_rate": 8.099858895072587e-09,
+      "loss": 0.4373,
+      "step": 1630
+    },
+    {
+      "epoch": 0.9908617173929462,
+      "grad_norm": 0.8433082091701005,
+      "learning_rate": 3.2115786500924728e-09,
+      "loss": 0.4371,
+      "step": 1640
+    },
+    {
+      "epoch": 0.996903557133147,
+      "grad_norm": 0.6909298344072548,
+      "learning_rate": 5.445721328567466e-10,
+      "loss": 0.4329,
+      "step": 1650
+    },
+    {
+      "epoch": 1.0,
+      "step": 1656,
+      "total_flos": 2042833294327808.0,
+      "train_loss": 0.4611289887036678,
+      "train_runtime": 68178.0817,
+      "train_samples_per_second": 1.554,
+      "train_steps_per_second": 0.024
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1656,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2042833294327808.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c78718594bbbb82032eb3d948b24558d99add709431dbe1e4ff24c1162a316e
+size 7672

video_preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_image_size": {
+    "longest_edge": 47040000
+  },
+  "merge_size": 2,
+  "num_frames": 16,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 47040000,
+    "shortest_edge": 12544
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Glm4vVideoProcessor"
+}