commit 4dcc3ca28079fadcba5107f88b1f5ffa6dd7be4c
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Jul 11 02:58:07 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: bmz123/aligner-7b
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..79c7073
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,98 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+ 
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+checkpoint-1000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/zero_pp_rank_3_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/zero_pp_rank_2_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/merges.txt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/zero_pp_rank_1_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/zero_pp_rank_0_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/zero_pp_rank_0_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/merges.txt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/vocab.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/zero_pp_rank_3_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/zero_pp_rank_2_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/vocab.json filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/zero_pp_rank_1_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/global_step1036/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1036/rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..69a595a
--- /dev/null
+++ b/README.md
@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2.5-7b-thought-aligner-sharegpt-ds3
+  results: []
+base_model:
+  - Qwen/Qwen2.5-7B-Instruct
+---
+<!-- 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. -->
+
+# qwen2.5-7b-thought-aligner-sharegpt-ds3
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the thought_aligner dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.9.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.1
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..482ced4
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..82dd8fa
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 273471074074624.0,
+    "train_loss": 0.24805861423295494,
+    "train_runtime": 7529.4023,
+    "train_samples_per_second": 17.517,
+    "train_steps_per_second": 0.138
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..bdf7919
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..6fccab2
--- /dev/null
+++ b/config.json
@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..fe4ae63
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-error-correction"}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..45e2560
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}
diff --git a/merges.txt b/merges.txt
new file mode 100644
index 0000000..80c1a19
--- /dev/null
+++ b/merges.txt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853
diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors
new file mode 100644
index 0000000..f875a36
--- /dev/null
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60efc0f2ad8d57aeeecbec1cff3895551b47930c2a95c3c20fdbe36b1c624063
+size 4877660776
diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors
new file mode 100644
index 0000000..c18ae3b
--- /dev/null
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58142e0c445d645180977157720b3bfdc25755806f31a53995c6b723e2a1ac54
+size 4932751008
diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors
new file mode 100644
index 0000000..099680e
--- /dev/null
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c670eba05f5037eef17ab1064ddebeccef18f99b4ec80840ed6e07fa5d55aa9a
+size 4330865200
diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors
new file mode 100644
index 0000000..b4c7da0
--- /dev/null
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c08a7b3483b01469260d365a7c03c164a5017a8defa9c516f026a8b271d8fa
+size 1089994880
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..098a4a8
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..ac23c0a
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..51ebb3b
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..fb44f02
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..82dd8fa
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 273471074074624.0,
+    "train_loss": 0.24805861423295494,
+    "train_runtime": 7529.4023,
+    "train_samples_per_second": 17.517,
+    "train_steps_per_second": 0.138
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..936dabf
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,104 @@
+{"current_steps": 10, "total_steps": 1036, "loss": 2.5672, "lr": 9.000000000000001e-07, "epoch": 0.06791171477079797, "percentage": 0.97, "elapsed_time": "0:01:10", "remaining_time": "2:00:23"}
+{"current_steps": 20, "total_steps": 1036, "loss": 1.6271, "lr": 1.9000000000000002e-06, "epoch": 0.13582342954159593, "percentage": 1.93, "elapsed_time": "0:02:32", "remaining_time": "2:08:42"}
+{"current_steps": 30, "total_steps": 1036, "loss": 1.0035, "lr": 2.9e-06, "epoch": 0.2037351443123939, "percentage": 2.9, "elapsed_time": "0:03:42", "remaining_time": "2:04:31"}
+{"current_steps": 40, "total_steps": 1036, "loss": 0.7978, "lr": 3.900000000000001e-06, "epoch": 0.27164685908319186, "percentage": 3.86, "elapsed_time": "0:04:51", "remaining_time": "2:01:06"}
+{"current_steps": 50, "total_steps": 1036, "loss": 0.7342, "lr": 4.9000000000000005e-06, "epoch": 0.3395585738539898, "percentage": 4.83, "elapsed_time": "0:06:01", "remaining_time": "1:58:45"}
+{"current_steps": 60, "total_steps": 1036, "loss": 0.6387, "lr": 5.9e-06, "epoch": 0.4074702886247878, "percentage": 5.79, "elapsed_time": "0:07:15", "remaining_time": "1:57:57"}
+{"current_steps": 70, "total_steps": 1036, "loss": 0.6566, "lr": 6.9e-06, "epoch": 0.47538200339558573, "percentage": 6.76, "elapsed_time": "0:08:30", "remaining_time": "1:57:22"}
+{"current_steps": 80, "total_steps": 1036, "loss": 0.6369, "lr": 7.9e-06, "epoch": 0.5432937181663837, "percentage": 7.72, "elapsed_time": "0:09:44", "remaining_time": "1:56:20"}
+{"current_steps": 90, "total_steps": 1036, "loss": 0.5945, "lr": 8.900000000000001e-06, "epoch": 0.6112054329371817, "percentage": 8.69, "elapsed_time": "0:10:52", "remaining_time": "1:54:22"}
+{"current_steps": 100, "total_steps": 1036, "loss": 0.598, "lr": 9.9e-06, "epoch": 0.6791171477079796, "percentage": 9.65, "elapsed_time": "0:12:00", "remaining_time": "1:52:23"}
+{"current_steps": 110, "total_steps": 1036, "loss": 0.569, "lr": 9.997718922447669e-06, "epoch": 0.7470288624787776, "percentage": 10.62, "elapsed_time": "0:13:14", "remaining_time": "1:51:27"}
+{"current_steps": 120, "total_steps": 1036, "loss": 0.5606, "lr": 9.989836388165012e-06, "epoch": 0.8149405772495756, "percentage": 11.58, "elapsed_time": "0:14:21", "remaining_time": "1:49:34"}
+{"current_steps": 130, "total_steps": 1036, "loss": 0.5565, "lr": 9.976333112771488e-06, "epoch": 0.8828522920203735, "percentage": 12.55, "elapsed_time": "0:15:26", "remaining_time": "1:47:35"}
+{"current_steps": 140, "total_steps": 1036, "loss": 0.5414, "lr": 9.957224306869053e-06, "epoch": 0.9507640067911715, "percentage": 13.51, "elapsed_time": "0:16:39", "remaining_time": "1:46:33"}
+{"current_steps": 150, "total_steps": 1036, "loss": 0.5142, "lr": 9.932531495342005e-06, "epoch": 1.0135823429541595, "percentage": 14.48, "elapsed_time": "0:17:44", "remaining_time": "1:44:47"}
+{"current_steps": 160, "total_steps": 1036, "loss": 0.4346, "lr": 9.90228249311053e-06, "epoch": 1.0814940577249577, "percentage": 15.44, "elapsed_time": "0:18:54", "remaining_time": "1:43:33"}
+{"current_steps": 170, "total_steps": 1036, "loss": 0.4156, "lr": 9.86651137379893e-06, "epoch": 1.1494057724957556, "percentage": 16.41, "elapsed_time": "0:20:05", "remaining_time": "1:42:18"}
+{"current_steps": 180, "total_steps": 1036, "loss": 0.4199, "lr": 9.82525843135379e-06, "epoch": 1.2173174872665535, "percentage": 17.37, "elapsed_time": "0:21:20", "remaining_time": "1:41:30"}
+{"current_steps": 190, "total_steps": 1036, "loss": 0.4088, "lr": 9.778570134655351e-06, "epoch": 1.2852292020373515, "percentage": 18.34, "elapsed_time": "0:22:31", "remaining_time": "1:40:17"}
+{"current_steps": 200, "total_steps": 1036, "loss": 0.4198, "lr": 9.726499075173201e-06, "epoch": 1.3531409168081494, "percentage": 19.31, "elapsed_time": "0:23:42", "remaining_time": "1:39:04"}
+{"current_steps": 210, "total_steps": 1036, "loss": 0.4203, "lr": 9.669103907725243e-06, "epoch": 1.4210526315789473, "percentage": 20.27, "elapsed_time": "0:24:53", "remaining_time": "1:37:55"}
+{"current_steps": 220, "total_steps": 1036, "loss": 0.4288, "lr": 9.606449284406685e-06, "epoch": 1.4889643463497453, "percentage": 21.24, "elapsed_time": "0:26:00", "remaining_time": "1:36:28"}
+{"current_steps": 230, "total_steps": 1036, "loss": 0.403, "lr": 9.538605781763464e-06, "epoch": 1.5568760611205432, "percentage": 22.2, "elapsed_time": "0:27:11", "remaining_time": "1:35:18"}
+{"current_steps": 240, "total_steps": 1036, "loss": 0.4014, "lr": 9.465649821292148e-06, "epoch": 1.6247877758913414, "percentage": 23.17, "elapsed_time": "0:28:21", "remaining_time": "1:34:02"}
+{"current_steps": 250, "total_steps": 1036, "loss": 0.4104, "lr": 9.387663583355862e-06, "epoch": 1.692699490662139, "percentage": 24.13, "elapsed_time": "0:29:26", "remaining_time": "1:32:35"}
+{"current_steps": 260, "total_steps": 1036, "loss": 0.4106, "lr": 9.3047349146132e-06, "epoch": 1.7606112054329373, "percentage": 25.1, "elapsed_time": "0:30:38", "remaining_time": "1:31:27"}
+{"current_steps": 270, "total_steps": 1036, "loss": 0.4055, "lr": 9.21695722906443e-06, "epoch": 1.8285229202037352, "percentage": 26.06, "elapsed_time": "0:31:50", "remaining_time": "1:30:20"}
+{"current_steps": 280, "total_steps": 1036, "loss": 0.4238, "lr": 9.124429402826398e-06, "epoch": 1.8964346349745331, "percentage": 27.03, "elapsed_time": "0:32:59", "remaining_time": "1:29:04"}
+{"current_steps": 290, "total_steps": 1036, "loss": 0.3975, "lr": 9.02725566275473e-06, "epoch": 1.964346349745331, "percentage": 27.99, "elapsed_time": "0:34:13", "remaining_time": "1:28:02"}
+{"current_steps": 300, "total_steps": 1036, "loss": 0.347, "lr": 8.92554546903875e-06, "epoch": 2.027164685908319, "percentage": 28.96, "elapsed_time": "0:35:22", "remaining_time": "1:26:47"}
+{"current_steps": 310, "total_steps": 1036, "loss": 0.2279, "lr": 8.819413391901353e-06, "epoch": 2.095076400679117, "percentage": 29.92, "elapsed_time": "0:36:32", "remaining_time": "1:25:35"}
+{"current_steps": 320, "total_steps": 1036, "loss": 0.2456, "lr": 8.708978982542766e-06, "epoch": 2.1629881154499153, "percentage": 30.89, "elapsed_time": "0:37:42", "remaining_time": "1:24:22"}
+{"current_steps": 330, "total_steps": 1036, "loss": 0.2394, "lr": 8.59436663847354e-06, "epoch": 2.230899830220713, "percentage": 31.85, "elapsed_time": "0:38:54", "remaining_time": "1:23:13"}
+{"current_steps": 340, "total_steps": 1036, "loss": 0.2537, "lr": 8.475705463388467e-06, "epoch": 2.298811544991511, "percentage": 32.82, "elapsed_time": "0:40:08", "remaining_time": "1:22:10"}
+{"current_steps": 350, "total_steps": 1036, "loss": 0.2555, "lr": 8.35312912173928e-06, "epoch": 2.366723259762309, "percentage": 33.78, "elapsed_time": "0:41:14", "remaining_time": "1:20:49"}
+{"current_steps": 360, "total_steps": 1036, "loss": 0.2424, "lr": 8.226775688169943e-06, "epoch": 2.434634974533107, "percentage": 34.75, "elapsed_time": "0:42:25", "remaining_time": "1:19:40"}
+{"current_steps": 370, "total_steps": 1036, "loss": 0.2458, "lr": 8.096787491984128e-06, "epoch": 2.502546689303905, "percentage": 35.71, "elapsed_time": "0:43:45", "remaining_time": "1:18:46"}
+{"current_steps": 380, "total_steps": 1036, "loss": 0.2545, "lr": 7.963310956820085e-06, "epoch": 2.570458404074703, "percentage": 36.68, "elapsed_time": "0:44:54", "remaining_time": "1:17:31"}
+{"current_steps": 390, "total_steps": 1036, "loss": 0.2544, "lr": 7.826496435713497e-06, "epoch": 2.6383701188455007, "percentage": 37.64, "elapsed_time": "0:46:04", "remaining_time": "1:16:19"}
+{"current_steps": 400, "total_steps": 1036, "loss": 0.2587, "lr": 7.686498041734121e-06, "epoch": 2.706281833616299, "percentage": 38.61, "elapsed_time": "0:47:18", "remaining_time": "1:15:12"}
+{"current_steps": 410, "total_steps": 1036, "loss": 0.2537, "lr": 7.543473474386962e-06, "epoch": 2.774193548387097, "percentage": 39.58, "elapsed_time": "0:48:25", "remaining_time": "1:13:56"}
+{"current_steps": 420, "total_steps": 1036, "loss": 0.2549, "lr": 7.397583841973584e-06, "epoch": 2.8421052631578947, "percentage": 40.54, "elapsed_time": "0:49:36", "remaining_time": "1:12:45"}
+{"current_steps": 430, "total_steps": 1036, "loss": 0.2576, "lr": 7.248993480113585e-06, "epoch": 2.910016977928693, "percentage": 41.51, "elapsed_time": "0:50:43", "remaining_time": "1:11:29"}
+{"current_steps": 440, "total_steps": 1036, "loss": 0.2597, "lr": 7.09786976663073e-06, "epoch": 2.9779286926994906, "percentage": 42.47, "elapsed_time": "0:51:54", "remaining_time": "1:10:18"}
+{"current_steps": 450, "total_steps": 1036, "loss": 0.1914, "lr": 6.944382933012207e-06, "epoch": 3.0407470288624787, "percentage": 43.44, "elapsed_time": "0:53:00", "remaining_time": "1:09:01"}
+{"current_steps": 460, "total_steps": 1036, "loss": 0.1304, "lr": 6.788705872653429e-06, "epoch": 3.108658743633277, "percentage": 44.4, "elapsed_time": "0:54:09", "remaining_time": "1:07:49"}
+{"current_steps": 470, "total_steps": 1036, "loss": 0.1348, "lr": 6.631013946104348e-06, "epoch": 3.1765704584040746, "percentage": 45.37, "elapsed_time": "0:55:21", "remaining_time": "1:06:40"}
+{"current_steps": 480, "total_steps": 1036, "loss": 0.1306, "lr": 6.4714847835366625e-06, "epoch": 3.2444821731748728, "percentage": 46.33, "elapsed_time": "0:56:33", "remaining_time": "1:05:30"}
+{"current_steps": 490, "total_steps": 1036, "loss": 0.1341, "lr": 6.310298084654467e-06, "epoch": 3.3123938879456705, "percentage": 47.3, "elapsed_time": "0:57:46", "remaining_time": "1:04:22"}
+{"current_steps": 500, "total_steps": 1036, "loss": 0.138, "lr": 6.147635416273679e-06, "epoch": 3.3803056027164686, "percentage": 48.26, "elapsed_time": "0:58:58", "remaining_time": "1:03:13"}
+{"current_steps": 510, "total_steps": 1036, "loss": 0.1367, "lr": 5.983680007798277e-06, "epoch": 3.4482173174872663, "percentage": 49.23, "elapsed_time": "1:00:07", "remaining_time": "1:02:00"}
+{"current_steps": 520, "total_steps": 1036, "loss": 0.1341, "lr": 5.818616544823755e-06, "epoch": 3.5161290322580645, "percentage": 50.19, "elapsed_time": "1:01:19", "remaining_time": "1:00:50"}
+{"current_steps": 530, "total_steps": 1036, "loss": 0.1417, "lr": 5.65263096110026e-06, "epoch": 3.5840407470288627, "percentage": 51.16, "elapsed_time": "1:02:31", "remaining_time": "0:59:41"}
+{"current_steps": 540, "total_steps": 1036, "loss": 0.1432, "lr": 5.485910229089739e-06, "epoch": 3.6519524617996604, "percentage": 52.12, "elapsed_time": "1:03:36", "remaining_time": "0:58:25"}
+{"current_steps": 550, "total_steps": 1036, "loss": 0.1378, "lr": 5.3186421493530845e-06, "epoch": 3.7198641765704585, "percentage": 53.09, "elapsed_time": "1:04:46", "remaining_time": "0:57:14"}
+{"current_steps": 560, "total_steps": 1036, "loss": 0.1396, "lr": 5.151015139004445e-06, "epoch": 3.7877758913412563, "percentage": 54.05, "elapsed_time": "1:06:02", "remaining_time": "0:56:08"}
+{"current_steps": 570, "total_steps": 1036, "loss": 0.1443, "lr": 4.983218019471027e-06, "epoch": 3.8556876061120544, "percentage": 55.02, "elapsed_time": "1:07:11", "remaining_time": "0:54:55"}
+{"current_steps": 580, "total_steps": 1036, "loss": 0.1328, "lr": 4.815439803797483e-06, "epoch": 3.923599320882852, "percentage": 55.98, "elapsed_time": "1:08:27", "remaining_time": "0:53:49"}
+{"current_steps": 590, "total_steps": 1036, "loss": 0.1334, "lr": 4.647869483734441e-06, "epoch": 3.9915110356536503, "percentage": 56.95, "elapsed_time": "1:09:36", "remaining_time": "0:52:37"}
+{"current_steps": 600, "total_steps": 1036, "loss": 0.0788, "lr": 4.4806958168510235e-06, "epoch": 4.054329371816638, "percentage": 57.92, "elapsed_time": "1:10:40", "remaining_time": "0:51:21"}
+{"current_steps": 610, "total_steps": 1036, "loss": 0.062, "lr": 4.314107113911151e-06, "epoch": 4.122241086587437, "percentage": 58.88, "elapsed_time": "1:11:55", "remaining_time": "0:50:13"}
+{"current_steps": 620, "total_steps": 1036, "loss": 0.0649, "lr": 4.148291026753159e-06, "epoch": 4.190152801358234, "percentage": 59.85, "elapsed_time": "1:13:02", "remaining_time": "0:49:00"}
+{"current_steps": 630, "total_steps": 1036, "loss": 0.0662, "lr": 3.983434336911636e-06, "epoch": 4.258064516129032, "percentage": 60.81, "elapsed_time": "1:14:13", "remaining_time": "0:47:49"}
+{"current_steps": 640, "total_steps": 1036, "loss": 0.0633, "lr": 3.819722745219617e-06, "epoch": 4.325976230899831, "percentage": 61.78, "elapsed_time": "1:15:25", "remaining_time": "0:46:39"}
+{"current_steps": 650, "total_steps": 1036, "loss": 0.0662, "lr": 3.657340662628116e-06, "epoch": 4.393887945670628, "percentage": 62.74, "elapsed_time": "1:16:37", "remaining_time": "0:45:30"}
+{"current_steps": 660, "total_steps": 1036, "loss": 0.0625, "lr": 3.4964710024786354e-06, "epoch": 4.461799660441426, "percentage": 63.71, "elapsed_time": "1:17:46", "remaining_time": "0:44:18"}
+{"current_steps": 670, "total_steps": 1036, "loss": 0.0628, "lr": 3.337294974462623e-06, "epoch": 4.529711375212224, "percentage": 64.67, "elapsed_time": "1:19:00", "remaining_time": "0:43:09"}
+{"current_steps": 680, "total_steps": 1036, "loss": 0.0655, "lr": 3.1799918805000097e-06, "epoch": 4.597623089983022, "percentage": 65.64, "elapsed_time": "1:20:07", "remaining_time": "0:41:56"}
+{"current_steps": 690, "total_steps": 1036, "loss": 0.0616, "lr": 3.024738912766717e-06, "epoch": 4.66553480475382, "percentage": 66.6, "elapsed_time": "1:21:26", "remaining_time": "0:40:50"}
+{"current_steps": 700, "total_steps": 1036, "loss": 0.0614, "lr": 2.87171095409866e-06, "epoch": 4.733446519524618, "percentage": 67.57, "elapsed_time": "1:22:35", "remaining_time": "0:39:38"}
+{"current_steps": 710, "total_steps": 1036, "loss": 0.0635, "lr": 2.7210803809970853e-06, "epoch": 4.8013582342954155, "percentage": 68.53, "elapsed_time": "1:23:47", "remaining_time": "0:38:28"}
+{"current_steps": 720, "total_steps": 1036, "loss": 0.0614, "lr": 2.5730168694571457e-06, "epoch": 4.869269949066214, "percentage": 69.5, "elapsed_time": "1:24:56", "remaining_time": "0:37:16"}
+{"current_steps": 730, "total_steps": 1036, "loss": 0.0598, "lr": 2.4276872038384037e-06, "epoch": 4.937181663837012, "percentage": 70.46, "elapsed_time": "1:26:07", "remaining_time": "0:36:06"}
+{"current_steps": 740, "total_steps": 1036, "loss": 0.0595, "lr": 2.2852550889926067e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:27:11", "remaining_time": "0:34:52"}
+{"current_steps": 750, "total_steps": 1036, "loss": 0.024, "lr": 2.1458809658603288e-06, "epoch": 5.067911714770798, "percentage": 72.39, "elapsed_time": "1:28:21", "remaining_time": "0:33:41"}
+{"current_steps": 760, "total_steps": 1036, "loss": 0.022, "lr": 2.009721830744201e-06, "epoch": 5.135823429541596, "percentage": 73.36, "elapsed_time": "1:29:26", "remaining_time": "0:32:28"}
+{"current_steps": 770, "total_steps": 1036, "loss": 0.0214, "lr": 1.87693105846232e-06, "epoch": 5.203735144312394, "percentage": 74.32, "elapsed_time": "1:30:38", "remaining_time": "0:31:18"}
+{"current_steps": 780, "total_steps": 1036, "loss": 0.0224, "lr": 1.7476582295810314e-06, "epoch": 5.271646859083192, "percentage": 75.29, "elapsed_time": "1:31:49", "remaining_time": "0:30:08"}
+{"current_steps": 790, "total_steps": 1036, "loss": 0.0212, "lr": 1.6220489619216988e-06, "epoch": 5.3395585738539895, "percentage": 76.25, "elapsed_time": "1:32:54", "remaining_time": "0:28:55"}
+{"current_steps": 800, "total_steps": 1036, "loss": 0.0213, "lr": 1.5002447465312675e-06, "epoch": 5.407470288624788, "percentage": 77.22, "elapsed_time": "1:34:09", "remaining_time": "0:27:46"}
+{"current_steps": 810, "total_steps": 1036, "loss": 0.0201, "lr": 1.3823827883013723e-06, "epoch": 5.475382003395586, "percentage": 78.19, "elapsed_time": "1:35:21", "remaining_time": "0:26:36"}
+{"current_steps": 820, "total_steps": 1036, "loss": 0.0214, "lr": 1.2685958514155456e-06, "epoch": 5.5432937181663835, "percentage": 79.15, "elapsed_time": "1:36:32", "remaining_time": "0:25:25"}
+{"current_steps": 830, "total_steps": 1036, "loss": 0.0213, "lr": 1.159012109798598e-06, "epoch": 5.611205432937181, "percentage": 80.12, "elapsed_time": "1:37:39", "remaining_time": "0:24:14"}
+{"current_steps": 840, "total_steps": 1036, "loss": 0.0191, "lr": 1.0537550027366444e-06, "epoch": 5.67911714770798, "percentage": 81.08, "elapsed_time": "1:38:53", "remaining_time": "0:23:04"}
+{"current_steps": 850, "total_steps": 1036, "loss": 0.0206, "lr": 9.529430958304092e-07, "epoch": 5.7470288624787775, "percentage": 82.05, "elapsed_time": "1:40:00", "remaining_time": "0:21:52"}
+{"current_steps": 860, "total_steps": 1036, "loss": 0.0192, "lr": 8.566899474384299e-07, "epoch": 5.814940577249575, "percentage": 83.01, "elapsed_time": "1:41:14", "remaining_time": "0:20:43"}
+{"current_steps": 870, "total_steps": 1036, "loss": 0.0213, "lr": 7.651039807606137e-07, "epoch": 5.882852292020374, "percentage": 83.98, "elapsed_time": "1:42:28", "remaining_time": "0:19:33"}
+{"current_steps": 880, "total_steps": 1036, "loss": 0.0189, "lr": 6.782883617062286e-07, "epoch": 5.950764006791172, "percentage": 84.94, "elapsed_time": "1:43:42", "remaining_time": "0:18:22"}
+{"current_steps": 890, "total_steps": 1036, "loss": 0.0157, "lr": 5.963408826839079e-07, "epoch": 6.01358234295416, "percentage": 85.91, "elapsed_time": "1:44:54", "remaining_time": "0:17:12"}
+{"current_steps": 900, "total_steps": 1036, "loss": 0.0064, "lr": 5.19353852444569e-07, "epoch": 6.081494057724957, "percentage": 86.87, "elapsed_time": "1:46:06", "remaining_time": "0:16:02"}
+{"current_steps": 910, "total_steps": 1036, "loss": 0.0063, "lr": 4.4741399210133154e-07, "epoch": 6.149405772495755, "percentage": 87.84, "elapsed_time": "1:47:20", "remaining_time": "0:14:51"}
+{"current_steps": 920, "total_steps": 1036, "loss": 0.0054, "lr": 3.8060233744356634e-07, "epoch": 6.217317487266554, "percentage": 88.8, "elapsed_time": "1:48:33", "remaining_time": "0:13:41"}
+{"current_steps": 930, "total_steps": 1036, "loss": 0.0059, "lr": 3.189941476551034e-07, "epoch": 6.2852292020373515, "percentage": 89.77, "elapsed_time": "1:49:44", "remaining_time": "0:12:30"}
+{"current_steps": 940, "total_steps": 1036, "loss": 0.0055, "lr": 2.6265882053943204e-07, "epoch": 6.353140916808149, "percentage": 90.73, "elapsed_time": "1:50:54", "remaining_time": "0:11:19"}
+{"current_steps": 950, "total_steps": 1036, "loss": 0.0055, "lr": 2.1165981434738025e-07, "epoch": 6.421052631578947, "percentage": 91.7, "elapsed_time": "1:52:01", "remaining_time": "0:10:08"}
+{"current_steps": 960, "total_steps": 1036, "loss": 0.0049, "lr": 1.6605457629533417e-07, "epoch": 6.4889643463497455, "percentage": 92.66, "elapsed_time": "1:53:12", "remaining_time": "0:08:57"}
+{"current_steps": 970, "total_steps": 1036, "loss": 0.0056, "lr": 1.2589447785450903e-07, "epoch": 6.556876061120543, "percentage": 93.63, "elapsed_time": "1:54:28", "remaining_time": "0:07:47"}
+{"current_steps": 980, "total_steps": 1036, "loss": 0.0053, "lr": 9.122475688417954e-08, "epoch": 6.624787775891341, "percentage": 94.59, "elapsed_time": "1:55:34", "remaining_time": "0:06:36"}
+{"current_steps": 990, "total_steps": 1036, "loss": 0.0054, "lr": 6.208446667403167e-08, "epoch": 6.6926994906621395, "percentage": 95.56, "elapsed_time": "1:56:44", "remaining_time": "0:05:25"}
+{"current_steps": 1000, "total_steps": 1036, "loss": 0.0051, "lr": 3.8506431953060365e-08, "epoch": 6.760611205432937, "percentage": 96.53, "elapsed_time": "1:57:50", "remaining_time": "0:04:14"}
+{"current_steps": 1010, "total_steps": 1036, "loss": 0.0052, "lr": 2.0517211914545254e-08, "epoch": 6.828522920203735, "percentage": 97.49, "elapsed_time": "2:00:08", "remaining_time": "0:03:05"}
+{"current_steps": 1020, "total_steps": 1036, "loss": 0.0052, "lr": 8.137070298769312e-09, "epoch": 6.896434634974533, "percentage": 98.46, "elapsed_time": "2:01:19", "remaining_time": "0:01:54"}
+{"current_steps": 1030, "total_steps": 1036, "loss": 0.0053, "lr": 1.3799525671720492e-09, "epoch": 6.964346349745331, "percentage": 99.42, "elapsed_time": "2:02:26", "remaining_time": "0:00:42"}
+{"current_steps": 1036, "total_steps": 1036, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:05:29", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..32e6d28
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,764 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1036,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06791171477079797,
+      "grad_norm": 39.06894209264497,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.5672,
+      "step": 10
+    },
+    {
+      "epoch": 0.13582342954159593,
+      "grad_norm": 9.408641592679151,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 1.6271,
+      "step": 20
+    },
+    {
+      "epoch": 0.2037351443123939,
+      "grad_norm": 3.5736160912411656,
+      "learning_rate": 2.9e-06,
+      "loss": 1.0035,
+      "step": 30
+    },
+    {
+      "epoch": 0.27164685908319186,
+      "grad_norm": 3.159979908410021,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.7978,
+      "step": 40
+    },
+    {
+      "epoch": 0.3395585738539898,
+      "grad_norm": 3.23976253664356,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.7342,
+      "step": 50
+    },
+    {
+      "epoch": 0.4074702886247878,
+      "grad_norm": 2.5239516324886613,
+      "learning_rate": 5.9e-06,
+      "loss": 0.6387,
+      "step": 60
+    },
+    {
+      "epoch": 0.47538200339558573,
+      "grad_norm": 2.864395183943674,
+      "learning_rate": 6.9e-06,
+      "loss": 0.6566,
+      "step": 70
+    },
+    {
+      "epoch": 0.5432937181663837,
+      "grad_norm": 2.221989312084371,
+      "learning_rate": 7.9e-06,
+      "loss": 0.6369,
+      "step": 80
+    },
+    {
+      "epoch": 0.6112054329371817,
+      "grad_norm": 2.622798646579124,
+      "learning_rate": 8.900000000000001e-06,
+      "loss": 0.5945,
+      "step": 90
+    },
+    {
+      "epoch": 0.6791171477079796,
+      "grad_norm": 2.727376011862893,
+      "learning_rate": 9.9e-06,
+      "loss": 0.598,
+      "step": 100
+    },
+    {
+      "epoch": 0.7470288624787776,
+      "grad_norm": 2.588442039618945,
+      "learning_rate": 9.997718922447669e-06,
+      "loss": 0.569,
+      "step": 110
+    },
+    {
+      "epoch": 0.8149405772495756,
+      "grad_norm": 2.3467194997795335,
+      "learning_rate": 9.989836388165012e-06,
+      "loss": 0.5606,
+      "step": 120
+    },
+    {
+      "epoch": 0.8828522920203735,
+      "grad_norm": 2.3847506796962556,
+      "learning_rate": 9.976333112771488e-06,
+      "loss": 0.5565,
+      "step": 130
+    },
+    {
+      "epoch": 0.9507640067911715,
+      "grad_norm": 2.1204168574702957,
+      "learning_rate": 9.957224306869053e-06,
+      "loss": 0.5414,
+      "step": 140
+    },
+    {
+      "epoch": 1.0135823429541595,
+      "grad_norm": 2.0962709577545704,
+      "learning_rate": 9.932531495342005e-06,
+      "loss": 0.5142,
+      "step": 150
+    },
+    {
+      "epoch": 1.0814940577249577,
+      "grad_norm": 2.420185175502751,
+      "learning_rate": 9.90228249311053e-06,
+      "loss": 0.4346,
+      "step": 160
+    },
+    {
+      "epoch": 1.1494057724957556,
+      "grad_norm": 2.175482934612183,
+      "learning_rate": 9.86651137379893e-06,
+      "loss": 0.4156,
+      "step": 170
+    },
+    {
+      "epoch": 1.2173174872665535,
+      "grad_norm": 2.015548954416845,
+      "learning_rate": 9.82525843135379e-06,
+      "loss": 0.4199,
+      "step": 180
+    },
+    {
+      "epoch": 1.2852292020373515,
+      "grad_norm": 2.2212942924087415,
+      "learning_rate": 9.778570134655351e-06,
+      "loss": 0.4088,
+      "step": 190
+    },
+    {
+      "epoch": 1.3531409168081494,
+      "grad_norm": 2.2774181484385014,
+      "learning_rate": 9.726499075173201e-06,
+      "loss": 0.4198,
+      "step": 200
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 1.951548193520802,
+      "learning_rate": 9.669103907725243e-06,
+      "loss": 0.4203,
+      "step": 210
+    },
+    {
+      "epoch": 1.4889643463497453,
+      "grad_norm": 2.0166680690881154,
+      "learning_rate": 9.606449284406685e-06,
+      "loss": 0.4288,
+      "step": 220
+    },
+    {
+      "epoch": 1.5568760611205432,
+      "grad_norm": 2.1215872162254445,
+      "learning_rate": 9.538605781763464e-06,
+      "loss": 0.403,
+      "step": 230
+    },
+    {
+      "epoch": 1.6247877758913414,
+      "grad_norm": 2.21540975350655,
+      "learning_rate": 9.465649821292148e-06,
+      "loss": 0.4014,
+      "step": 240
+    },
+    {
+      "epoch": 1.692699490662139,
+      "grad_norm": 2.2219332688595976,
+      "learning_rate": 9.387663583355862e-06,
+      "loss": 0.4104,
+      "step": 250
+    },
+    {
+      "epoch": 1.7606112054329373,
+      "grad_norm": 2.139070251547491,
+      "learning_rate": 9.3047349146132e-06,
+      "loss": 0.4106,
+      "step": 260
+    },
+    {
+      "epoch": 1.8285229202037352,
+      "grad_norm": 2.114857623710178,
+      "learning_rate": 9.21695722906443e-06,
+      "loss": 0.4055,
+      "step": 270
+    },
+    {
+      "epoch": 1.8964346349745331,
+      "grad_norm": 2.0517966830796586,
+      "learning_rate": 9.124429402826398e-06,
+      "loss": 0.4238,
+      "step": 280
+    },
+    {
+      "epoch": 1.964346349745331,
+      "grad_norm": 1.8301929541835302,
+      "learning_rate": 9.02725566275473e-06,
+      "loss": 0.3975,
+      "step": 290
+    },
+    {
+      "epoch": 2.027164685908319,
+      "grad_norm": 1.61769307419241,
+      "learning_rate": 8.92554546903875e-06,
+      "loss": 0.347,
+      "step": 300
+    },
+    {
+      "epoch": 2.095076400679117,
+      "grad_norm": 1.7835414384395631,
+      "learning_rate": 8.819413391901353e-06,
+      "loss": 0.2279,
+      "step": 310
+    },
+    {
+      "epoch": 2.1629881154499153,
+      "grad_norm": 1.7449573933209457,
+      "learning_rate": 8.708978982542766e-06,
+      "loss": 0.2456,
+      "step": 320
+    },
+    {
+      "epoch": 2.230899830220713,
+      "grad_norm": 1.8762842446890258,
+      "learning_rate": 8.59436663847354e-06,
+      "loss": 0.2394,
+      "step": 330
+    },
+    {
+      "epoch": 2.298811544991511,
+      "grad_norm": 1.7977301694269836,
+      "learning_rate": 8.475705463388467e-06,
+      "loss": 0.2537,
+      "step": 340
+    },
+    {
+      "epoch": 2.366723259762309,
+      "grad_norm": 1.693865524446407,
+      "learning_rate": 8.35312912173928e-06,
+      "loss": 0.2555,
+      "step": 350
+    },
+    {
+      "epoch": 2.434634974533107,
+      "grad_norm": 1.9696999644652728,
+      "learning_rate": 8.226775688169943e-06,
+      "loss": 0.2424,
+      "step": 360
+    },
+    {
+      "epoch": 2.502546689303905,
+      "grad_norm": 1.7928317986379525,
+      "learning_rate": 8.096787491984128e-06,
+      "loss": 0.2458,
+      "step": 370
+    },
+    {
+      "epoch": 2.570458404074703,
+      "grad_norm": 1.6035422026428618,
+      "learning_rate": 7.963310956820085e-06,
+      "loss": 0.2545,
+      "step": 380
+    },
+    {
+      "epoch": 2.6383701188455007,
+      "grad_norm": 1.7086388697991841,
+      "learning_rate": 7.826496435713497e-06,
+      "loss": 0.2544,
+      "step": 390
+    },
+    {
+      "epoch": 2.706281833616299,
+      "grad_norm": 1.7784954050779234,
+      "learning_rate": 7.686498041734121e-06,
+      "loss": 0.2587,
+      "step": 400
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 1.8489681135255784,
+      "learning_rate": 7.543473474386962e-06,
+      "loss": 0.2537,
+      "step": 410
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 1.6154424089494572,
+      "learning_rate": 7.397583841973584e-06,
+      "loss": 0.2549,
+      "step": 420
+    },
+    {
+      "epoch": 2.910016977928693,
+      "grad_norm": 1.6945683455240643,
+      "learning_rate": 7.248993480113585e-06,
+      "loss": 0.2576,
+      "step": 430
+    },
+    {
+      "epoch": 2.9779286926994906,
+      "grad_norm": 1.7774529548842273,
+      "learning_rate": 7.09786976663073e-06,
+      "loss": 0.2597,
+      "step": 440
+    },
+    {
+      "epoch": 3.0407470288624787,
+      "grad_norm": 1.3291164143277696,
+      "learning_rate": 6.944382933012207e-06,
+      "loss": 0.1914,
+      "step": 450
+    },
+    {
+      "epoch": 3.108658743633277,
+      "grad_norm": 1.4399162979563198,
+      "learning_rate": 6.788705872653429e-06,
+      "loss": 0.1304,
+      "step": 460
+    },
+    {
+      "epoch": 3.1765704584040746,
+      "grad_norm": 1.4090235140542846,
+      "learning_rate": 6.631013946104348e-06,
+      "loss": 0.1348,
+      "step": 470
+    },
+    {
+      "epoch": 3.2444821731748728,
+      "grad_norm": 1.5024124740765719,
+      "learning_rate": 6.4714847835366625e-06,
+      "loss": 0.1306,
+      "step": 480
+    },
+    {
+      "epoch": 3.3123938879456705,
+      "grad_norm": 1.4037148184869794,
+      "learning_rate": 6.310298084654467e-06,
+      "loss": 0.1341,
+      "step": 490
+    },
+    {
+      "epoch": 3.3803056027164686,
+      "grad_norm": 1.5382989963970903,
+      "learning_rate": 6.147635416273679e-06,
+      "loss": 0.138,
+      "step": 500
+    },
+    {
+      "epoch": 3.4482173174872663,
+      "grad_norm": 1.4075458945664348,
+      "learning_rate": 5.983680007798277e-06,
+      "loss": 0.1367,
+      "step": 510
+    },
+    {
+      "epoch": 3.5161290322580645,
+      "grad_norm": 1.379295875695038,
+      "learning_rate": 5.818616544823755e-06,
+      "loss": 0.1341,
+      "step": 520
+    },
+    {
+      "epoch": 3.5840407470288627,
+      "grad_norm": 1.6516703780226065,
+      "learning_rate": 5.65263096110026e-06,
+      "loss": 0.1417,
+      "step": 530
+    },
+    {
+      "epoch": 3.6519524617996604,
+      "grad_norm": 1.4236024491217225,
+      "learning_rate": 5.485910229089739e-06,
+      "loss": 0.1432,
+      "step": 540
+    },
+    {
+      "epoch": 3.7198641765704585,
+      "grad_norm": 1.5628385416315445,
+      "learning_rate": 5.3186421493530845e-06,
+      "loss": 0.1378,
+      "step": 550
+    },
+    {
+      "epoch": 3.7877758913412563,
+      "grad_norm": 1.5399714943796112,
+      "learning_rate": 5.151015139004445e-06,
+      "loss": 0.1396,
+      "step": 560
+    },
+    {
+      "epoch": 3.8556876061120544,
+      "grad_norm": 1.5044051222954915,
+      "learning_rate": 4.983218019471027e-06,
+      "loss": 0.1443,
+      "step": 570
+    },
+    {
+      "epoch": 3.923599320882852,
+      "grad_norm": 1.2731582701152808,
+      "learning_rate": 4.815439803797483e-06,
+      "loss": 0.1328,
+      "step": 580
+    },
+    {
+      "epoch": 3.9915110356536503,
+      "grad_norm": 1.2890321476898117,
+      "learning_rate": 4.647869483734441e-06,
+      "loss": 0.1334,
+      "step": 590
+    },
+    {
+      "epoch": 4.054329371816638,
+      "grad_norm": 1.3973597889025486,
+      "learning_rate": 4.4806958168510235e-06,
+      "loss": 0.0788,
+      "step": 600
+    },
+    {
+      "epoch": 4.122241086587437,
+      "grad_norm": 1.1936189947404265,
+      "learning_rate": 4.314107113911151e-06,
+      "loss": 0.062,
+      "step": 610
+    },
+    {
+      "epoch": 4.190152801358234,
+      "grad_norm": 1.091238397517897,
+      "learning_rate": 4.148291026753159e-06,
+      "loss": 0.0649,
+      "step": 620
+    },
+    {
+      "epoch": 4.258064516129032,
+      "grad_norm": 1.1958745470057501,
+      "learning_rate": 3.983434336911636e-06,
+      "loss": 0.0662,
+      "step": 630
+    },
+    {
+      "epoch": 4.325976230899831,
+      "grad_norm": 1.1212711189708877,
+      "learning_rate": 3.819722745219617e-06,
+      "loss": 0.0633,
+      "step": 640
+    },
+    {
+      "epoch": 4.393887945670628,
+      "grad_norm": 1.3264229165705554,
+      "learning_rate": 3.657340662628116e-06,
+      "loss": 0.0662,
+      "step": 650
+    },
+    {
+      "epoch": 4.461799660441426,
+      "grad_norm": 1.1770811940347883,
+      "learning_rate": 3.4964710024786354e-06,
+      "loss": 0.0625,
+      "step": 660
+    },
+    {
+      "epoch": 4.529711375212224,
+      "grad_norm": 1.2943958821442108,
+      "learning_rate": 3.337294974462623e-06,
+      "loss": 0.0628,
+      "step": 670
+    },
+    {
+      "epoch": 4.597623089983022,
+      "grad_norm": 1.345364224404323,
+      "learning_rate": 3.1799918805000097e-06,
+      "loss": 0.0655,
+      "step": 680
+    },
+    {
+      "epoch": 4.66553480475382,
+      "grad_norm": 1.0977379456012588,
+      "learning_rate": 3.024738912766717e-06,
+      "loss": 0.0616,
+      "step": 690
+    },
+    {
+      "epoch": 4.733446519524618,
+      "grad_norm": 1.1868517773950296,
+      "learning_rate": 2.87171095409866e-06,
+      "loss": 0.0614,
+      "step": 700
+    },
+    {
+      "epoch": 4.8013582342954155,
+      "grad_norm": 1.110887449804357,
+      "learning_rate": 2.7210803809970853e-06,
+      "loss": 0.0635,
+      "step": 710
+    },
+    {
+      "epoch": 4.869269949066214,
+      "grad_norm": 1.2822194078234743,
+      "learning_rate": 2.5730168694571457e-06,
+      "loss": 0.0614,
+      "step": 720
+    },
+    {
+      "epoch": 4.937181663837012,
+      "grad_norm": 1.0805554157065451,
+      "learning_rate": 2.4276872038384037e-06,
+      "loss": 0.0598,
+      "step": 730
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.320950039949113,
+      "learning_rate": 2.2852550889926067e-06,
+      "loss": 0.0595,
+      "step": 740
+    },
+    {
+      "epoch": 5.067911714770798,
+      "grad_norm": 0.7541720353663811,
+      "learning_rate": 2.1458809658603288e-06,
+      "loss": 0.024,
+      "step": 750
+    },
+    {
+      "epoch": 5.135823429541596,
+      "grad_norm": 0.9116539389923982,
+      "learning_rate": 2.009721830744201e-06,
+      "loss": 0.022,
+      "step": 760
+    },
+    {
+      "epoch": 5.203735144312394,
+      "grad_norm": 0.8703094574463964,
+      "learning_rate": 1.87693105846232e-06,
+      "loss": 0.0214,
+      "step": 770
+    },
+    {
+      "epoch": 5.271646859083192,
+      "grad_norm": 0.8382504818211445,
+      "learning_rate": 1.7476582295810314e-06,
+      "loss": 0.0224,
+      "step": 780
+    },
+    {
+      "epoch": 5.3395585738539895,
+      "grad_norm": 0.8489442445106106,
+      "learning_rate": 1.6220489619216988e-06,
+      "loss": 0.0212,
+      "step": 790
+    },
+    {
+      "epoch": 5.407470288624788,
+      "grad_norm": 0.8903040566842944,
+      "learning_rate": 1.5002447465312675e-06,
+      "loss": 0.0213,
+      "step": 800
+    },
+    {
+      "epoch": 5.475382003395586,
+      "grad_norm": 0.9430023584705125,
+      "learning_rate": 1.3823827883013723e-06,
+      "loss": 0.0201,
+      "step": 810
+    },
+    {
+      "epoch": 5.5432937181663835,
+      "grad_norm": 0.877235765811111,
+      "learning_rate": 1.2685958514155456e-06,
+      "loss": 0.0214,
+      "step": 820
+    },
+    {
+      "epoch": 5.611205432937181,
+      "grad_norm": 1.0592040952393595,
+      "learning_rate": 1.159012109798598e-06,
+      "loss": 0.0213,
+      "step": 830
+    },
+    {
+      "epoch": 5.67911714770798,
+      "grad_norm": 0.9416315998080429,
+      "learning_rate": 1.0537550027366444e-06,
+      "loss": 0.0191,
+      "step": 840
+    },
+    {
+      "epoch": 5.7470288624787775,
+      "grad_norm": 0.8017668057640382,
+      "learning_rate": 9.529430958304092e-07,
+      "loss": 0.0206,
+      "step": 850
+    },
+    {
+      "epoch": 5.814940577249575,
+      "grad_norm": 0.8439085846162264,
+      "learning_rate": 8.566899474384299e-07,
+      "loss": 0.0192,
+      "step": 860
+    },
+    {
+      "epoch": 5.882852292020374,
+      "grad_norm": 0.9517820142849852,
+      "learning_rate": 7.651039807606137e-07,
+      "loss": 0.0213,
+      "step": 870
+    },
+    {
+      "epoch": 5.950764006791172,
+      "grad_norm": 0.9056469249009282,
+      "learning_rate": 6.782883617062286e-07,
+      "loss": 0.0189,
+      "step": 880
+    },
+    {
+      "epoch": 6.01358234295416,
+      "grad_norm": 0.4576722465983699,
+      "learning_rate": 5.963408826839079e-07,
+      "loss": 0.0157,
+      "step": 890
+    },
+    {
+      "epoch": 6.081494057724957,
+      "grad_norm": 0.28634320188291257,
+      "learning_rate": 5.19353852444569e-07,
+      "loss": 0.0064,
+      "step": 900
+    },
+    {
+      "epoch": 6.149405772495755,
+      "grad_norm": 0.4684376300431715,
+      "learning_rate": 4.4741399210133154e-07,
+      "loss": 0.0063,
+      "step": 910
+    },
+    {
+      "epoch": 6.217317487266554,
+      "grad_norm": 0.30013129798891736,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.0054,
+      "step": 920
+    },
+    {
+      "epoch": 6.2852292020373515,
+      "grad_norm": 0.5743674767243917,
+      "learning_rate": 3.189941476551034e-07,
+      "loss": 0.0059,
+      "step": 930
+    },
+    {
+      "epoch": 6.353140916808149,
+      "grad_norm": 0.42277606258594225,
+      "learning_rate": 2.6265882053943204e-07,
+      "loss": 0.0055,
+      "step": 940
+    },
+    {
+      "epoch": 6.421052631578947,
+      "grad_norm": 0.45134401222170456,
+      "learning_rate": 2.1165981434738025e-07,
+      "loss": 0.0055,
+      "step": 950
+    },
+    {
+      "epoch": 6.4889643463497455,
+      "grad_norm": 0.37311468378603657,
+      "learning_rate": 1.6605457629533417e-07,
+      "loss": 0.0049,
+      "step": 960
+    },
+    {
+      "epoch": 6.556876061120543,
+      "grad_norm": 0.4991066248356068,
+      "learning_rate": 1.2589447785450903e-07,
+      "loss": 0.0056,
+      "step": 970
+    },
+    {
+      "epoch": 6.624787775891341,
+      "grad_norm": 0.42890580429476455,
+      "learning_rate": 9.122475688417954e-08,
+      "loss": 0.0053,
+      "step": 980
+    },
+    {
+      "epoch": 6.6926994906621395,
+      "grad_norm": 0.44354296838652474,
+      "learning_rate": 6.208446667403167e-08,
+      "loss": 0.0054,
+      "step": 990
+    },
+    {
+      "epoch": 6.760611205432937,
+      "grad_norm": 0.32840772053670925,
+      "learning_rate": 3.8506431953060365e-08,
+      "loss": 0.0051,
+      "step": 1000
+    },
+    {
+      "epoch": 6.828522920203735,
+      "grad_norm": 0.6268189928914281,
+      "learning_rate": 2.0517211914545254e-08,
+      "loss": 0.0052,
+      "step": 1010
+    },
+    {
+      "epoch": 6.896434634974533,
+      "grad_norm": 0.2742284364295698,
+      "learning_rate": 8.137070298769312e-09,
+      "loss": 0.0052,
+      "step": 1020
+    },
+    {
+      "epoch": 6.964346349745331,
+      "grad_norm": 0.4536117363233092,
+      "learning_rate": 1.3799525671720492e-09,
+      "loss": 0.0053,
+      "step": 1030
+    },
+    {
+      "epoch": 7.0,
+      "step": 1036,
+      "total_flos": 273471074074624.0,
+      "train_loss": 0.24805861423295494,
+      "train_runtime": 7529.4023,
+      "train_samples_per_second": 17.517,
+      "train_steps_per_second": 0.138
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1036,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 273471074074624.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..f71e484
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5616160e7eee8759f49236b6fb869b421a3a17589e48667ff83ab8ea3947a195
+size 8209
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..522af07
Binary files /dev/null and b/training_loss.png differ
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..6c49fc6
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
+size 2776833