commit be70957bb3a39d173c896490f10a22b1a8a1acab
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Tue Jun 16 06:34:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: greyi/effientReason-4b-sft-final
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..9c8bd2c
--- /dev/null
+++ b/README.md
@@ -0,0 +1,8 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3-4B-Instruct-2507
+pipeline_tag: text-generation
+tags:
+- effient
+---
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..70adff8
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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 %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..6dae724
--- /dev/null
+++ b/config.json
@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..736d51d
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.2.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..4fe46eb
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb4576fae1a977002b3da726fadd3cf66578c27ad39afbdaf5f10feee8de953
+size 8044982080
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..207de50
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..2b4432a
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,1792 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 50,
+  "global_step": 246,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02476780185758514,
+      "grad_norm": 0.5827791094779968,
+      "learning_rate": 0.0,
+      "loss": 0.5993257761001587,
+      "step": 1
+    },
+    {
+      "epoch": 0.04953560371517028,
+      "grad_norm": 0.5781313180923462,
+      "learning_rate": 2.5e-07,
+      "loss": 0.5510573387145996,
+      "step": 2
+    },
+    {
+      "epoch": 0.07430340557275542,
+      "grad_norm": 0.5830345153808594,
+      "learning_rate": 5e-07,
+      "loss": 0.500480055809021,
+      "step": 3
+    },
+    {
+      "epoch": 0.09907120743034056,
+      "grad_norm": 0.5189770460128784,
+      "learning_rate": 7.5e-07,
+      "loss": 0.5299410820007324,
+      "step": 4
+    },
+    {
+      "epoch": 0.1238390092879257,
+      "grad_norm": 0.520061194896698,
+      "learning_rate": 1e-06,
+      "loss": 0.5539457201957703,
+      "step": 5
+    },
+    {
+      "epoch": 0.14860681114551083,
+      "grad_norm": 0.5419376492500305,
+      "learning_rate": 1.2499999999999999e-06,
+      "loss": 0.5408970713615417,
+      "step": 6
+    },
+    {
+      "epoch": 0.17337461300309598,
+      "grad_norm": 0.5576385855674744,
+      "learning_rate": 1.5e-06,
+      "loss": 0.5969724655151367,
+      "step": 7
+    },
+    {
+      "epoch": 0.19814241486068113,
+      "grad_norm": 0.5351932048797607,
+      "learning_rate": 1.75e-06,
+      "loss": 0.5394197106361389,
+      "step": 8
+    },
+    {
+      "epoch": 0.22291021671826625,
+      "grad_norm": 0.4773852527141571,
+      "learning_rate": 2e-06,
+      "loss": 0.5735222101211548,
+      "step": 9
+    },
+    {
+      "epoch": 0.2476780185758514,
+      "grad_norm": 0.5032294392585754,
+      "learning_rate": 1.9999128816724105e-06,
+      "loss": 0.5828520059585571,
+      "step": 10
+    },
+    {
+      "epoch": 0.2724458204334365,
+      "grad_norm": 0.49014607071876526,
+      "learning_rate": 1.9996515418688487e-06,
+      "loss": 0.5568044781684875,
+      "step": 11
+    },
+    {
+      "epoch": 0.29721362229102166,
+      "grad_norm": 0.5634818077087402,
+      "learning_rate": 1.9992160261242874e-06,
+      "loss": 0.5982780456542969,
+      "step": 12
+    },
+    {
+      "epoch": 0.3219814241486068,
+      "grad_norm": 0.4928373396396637,
+      "learning_rate": 1.9986064103215337e-06,
+      "loss": 0.563035249710083,
+      "step": 13
+    },
+    {
+      "epoch": 0.34674922600619196,
+      "grad_norm": 0.5265209674835205,
+      "learning_rate": 1.9978228006780053e-06,
+      "loss": 0.588450014591217,
+      "step": 14
+    },
+    {
+      "epoch": 0.3715170278637771,
+      "grad_norm": 0.4966702461242676,
+      "learning_rate": 1.996865333727226e-06,
+      "loss": 0.5518300533294678,
+      "step": 15
+    },
+    {
+      "epoch": 0.39628482972136225,
+      "grad_norm": 0.5559803247451782,
+      "learning_rate": 1.9957341762950344e-06,
+      "loss": 0.5778566002845764,
+      "step": 16
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.5569736957550049,
+      "learning_rate": 1.9944295254705185e-06,
+      "loss": 0.556509256362915,
+      "step": 17
+    },
+    {
+      "epoch": 0.4458204334365325,
+      "grad_norm": 0.5971181988716125,
+      "learning_rate": 1.992951608571673e-06,
+      "loss": 0.5314251780509949,
+      "step": 18
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.529690146446228,
+      "learning_rate": 1.9913006831057965e-06,
+      "loss": 0.5227062702178955,
+      "step": 19
+    },
+    {
+      "epoch": 0.4953560371517028,
+      "grad_norm": 0.6401184797286987,
+      "learning_rate": 1.989477036724619e-06,
+      "loss": 0.5782433152198792,
+      "step": 20
+    },
+    {
+      "epoch": 0.5201238390092879,
+      "grad_norm": 0.539941132068634,
+      "learning_rate": 1.9874809871741874e-06,
+      "loss": 0.5736757516860962,
+      "step": 21
+    },
+    {
+      "epoch": 0.544891640866873,
+      "grad_norm": 0.5726771950721741,
+      "learning_rate": 1.9853128822394975e-06,
+      "loss": 0.5858570337295532,
+      "step": 22
+    },
+    {
+      "epoch": 0.5696594427244582,
+      "grad_norm": 0.55902498960495,
+      "learning_rate": 1.982973099683902e-06,
+      "loss": 0.5574871301651001,
+      "step": 23
+    },
+    {
+      "epoch": 0.5944272445820433,
+      "grad_norm": 0.527619481086731,
+      "learning_rate": 1.9804620471832865e-06,
+      "loss": 0.5171317458152771,
+      "step": 24
+    },
+    {
+      "epoch": 0.6191950464396285,
+      "grad_norm": 0.5026052594184875,
+      "learning_rate": 1.9777801622550405e-06,
+      "loss": 0.5416678190231323,
+      "step": 25
+    },
+    {
+      "epoch": 0.6439628482972136,
+      "grad_norm": 0.47064998745918274,
+      "learning_rate": 1.9749279121818236e-06,
+      "loss": 0.5682564973831177,
+      "step": 26
+    },
+    {
+      "epoch": 0.6687306501547987,
+      "grad_norm": 0.5842341184616089,
+      "learning_rate": 1.9719057939301475e-06,
+      "loss": 0.5644649267196655,
+      "step": 27
+    },
+    {
+      "epoch": 0.6934984520123839,
+      "grad_norm": 0.49904075264930725,
+      "learning_rate": 1.9687143340637884e-06,
+      "loss": 0.5811545252799988,
+      "step": 28
+    },
+    {
+      "epoch": 0.718266253869969,
+      "grad_norm": 1.2309396266937256,
+      "learning_rate": 1.9653540886520385e-06,
+      "loss": 0.605437695980072,
+      "step": 29
+    },
+    {
+      "epoch": 0.7430340557275542,
+      "grad_norm": 0.5156847834587097,
+      "learning_rate": 1.9618256431728192e-06,
+      "loss": 0.5422309637069702,
+      "step": 30
+    },
+    {
+      "epoch": 0.7678018575851393,
+      "grad_norm": 0.6013903617858887,
+      "learning_rate": 1.958129612410668e-06,
+      "loss": 0.54377281665802,
+      "step": 31
+    },
+    {
+      "epoch": 0.7925696594427245,
+      "grad_norm": 0.5307015180587769,
+      "learning_rate": 1.954266640349623e-06,
+      "loss": 0.5074729919433594,
+      "step": 32
+    },
+    {
+      "epoch": 0.8173374613003096,
+      "grad_norm": 0.5950272679328918,
+      "learning_rate": 1.950237400061015e-06,
+      "loss": 0.5290631055831909,
+      "step": 33
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.5664405226707458,
+      "learning_rate": 1.9460425935861946e-06,
+      "loss": 0.600000262260437,
+      "step": 34
+    },
+    {
+      "epoch": 0.8668730650154799,
+      "grad_norm": 0.5338588953018188,
+      "learning_rate": 1.9416829518142113e-06,
+      "loss": 0.5680241584777832,
+      "step": 35
+    },
+    {
+      "epoch": 0.891640866873065,
+      "grad_norm": 0.5495931506156921,
+      "learning_rate": 1.9371592343544655e-06,
+      "loss": 0.5304821729660034,
+      "step": 36
+    },
+    {
+      "epoch": 0.9164086687306502,
+      "grad_norm": 0.47950977087020874,
+      "learning_rate": 1.932472229404356e-06,
+      "loss": 0.5156245827674866,
+      "step": 37
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.5299308896064758,
+      "learning_rate": 1.9276227536119477e-06,
+      "loss": 0.5732549428939819,
+      "step": 38
+    },
+    {
+      "epoch": 0.9659442724458205,
+      "grad_norm": 0.5737171173095703,
+      "learning_rate": 1.9226116519336828e-06,
+      "loss": 0.5309604406356812,
+      "step": 39
+    },
+    {
+      "epoch": 0.9907120743034056,
+      "grad_norm": 0.693321168422699,
+      "learning_rate": 1.917439797487156e-06,
+      "loss": 0.5797507762908936,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9561907649040222,
+      "learning_rate": 1.9121080913989878e-06,
+      "loss": 0.5909802913665771,
+      "step": 41
+    },
+    {
+      "epoch": 1.0247678018575852,
+      "grad_norm": 0.6066501140594482,
+      "learning_rate": 1.9066174626478126e-06,
+      "loss": 0.6078804135322571,
+      "step": 42
+    },
+    {
+      "epoch": 1.0495356037151702,
+      "grad_norm": 0.5243707299232483,
+      "learning_rate": 1.9009688679024189e-06,
+      "loss": 0.5241413116455078,
+      "step": 43
+    },
+    {
+      "epoch": 1.0743034055727554,
+      "grad_norm": 0.5240072011947632,
+      "learning_rate": 1.8951632913550625e-06,
+      "loss": 0.5645661950111389,
+      "step": 44
+    },
+    {
+      "epoch": 1.0990712074303406,
+      "grad_norm": 0.6983147263526917,
+      "learning_rate": 1.889201744549981e-06,
+      "loss": 0.5029958486557007,
+      "step": 45
+    },
+    {
+      "epoch": 1.1238390092879258,
+      "grad_norm": 0.6109921932220459,
+      "learning_rate": 1.8830852662071505e-06,
+      "loss": 0.5748687386512756,
+      "step": 46
+    },
+    {
+      "epoch": 1.1486068111455108,
+      "grad_norm": 0.5242897868156433,
+      "learning_rate": 1.8768149220412987e-06,
+      "loss": 0.5576164722442627,
+      "step": 47
+    },
+    {
+      "epoch": 1.173374613003096,
+      "grad_norm": 0.5376689434051514,
+      "learning_rate": 1.8703918045762194e-06,
+      "loss": 0.5489684343338013,
+      "step": 48
+    },
+    {
+      "epoch": 1.1981424148606812,
+      "grad_norm": 0.5369903445243835,
+      "learning_rate": 1.863817032954416e-06,
+      "loss": 0.5305777192115784,
+      "step": 49
+    },
+    {
+      "epoch": 1.2229102167182662,
+      "grad_norm": 0.482452392578125,
+      "learning_rate": 1.8570917527421045e-06,
+      "loss": 0.4907306134700775,
+      "step": 50
+    },
+    {
+      "epoch": 1.2229102167182662,
+      "eval_accuracy": 0.8213776795920542,
+      "eval_loss": 0.5645560622215271,
+      "eval_runtime": 16.7311,
+      "eval_samples_per_second": 4.064,
+      "eval_steps_per_second": 2.032,
+      "step": 50
+    },
+    {
+      "epoch": 1.2476780185758514,
+      "grad_norm": 0.5009844899177551,
+      "learning_rate": 1.8502171357296142e-06,
+      "loss": 0.5544570088386536,
+      "step": 51
+    },
+    {
+      "epoch": 1.2724458204334366,
+      "grad_norm": 0.5807215571403503,
+      "learning_rate": 1.8431943797272185e-06,
+      "loss": 0.5804014205932617,
+      "step": 52
+    },
+    {
+      "epoch": 1.2972136222910216,
+      "grad_norm": 0.5564484596252441,
+      "learning_rate": 1.836024708356434e-06,
+      "loss": 0.5661737322807312,
+      "step": 53
+    },
+    {
+      "epoch": 1.3219814241486068,
+      "grad_norm": 0.5095818042755127,
+      "learning_rate": 1.8287093708368186e-06,
+      "loss": 0.5299423336982727,
+      "step": 54
+    },
+    {
+      "epoch": 1.346749226006192,
+      "grad_norm": 0.5763193368911743,
+      "learning_rate": 1.8212496417683135e-06,
+      "loss": 0.5352605581283569,
+      "step": 55
+    },
+    {
+      "epoch": 1.3715170278637772,
+      "grad_norm": 0.5195797681808472,
+      "learning_rate": 1.81364682090916e-06,
+      "loss": 0.530654788017273,
+      "step": 56
+    },
+    {
+      "epoch": 1.3962848297213624,
+      "grad_norm": 0.5399932861328125,
+      "learning_rate": 1.805902232949435e-06,
+      "loss": 0.5673707723617554,
+      "step": 57
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.5126509666442871,
+      "learning_rate": 1.7980172272802397e-06,
+      "loss": 0.5673764944076538,
+      "step": 58
+    },
+    {
+      "epoch": 1.4458204334365325,
+      "grad_norm": 0.5293602347373962,
+      "learning_rate": 1.789993177758588e-06,
+      "loss": 0.5548557043075562,
+      "step": 59
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.47508999705314636,
+      "learning_rate": 1.7818314824680298e-06,
+      "loss": 0.5592916011810303,
+      "step": 60
+    },
+    {
+      "epoch": 1.4953560371517027,
+      "grad_norm": 0.506854236125946,
+      "learning_rate": 1.773533563475053e-06,
+      "loss": 0.5494035482406616,
+      "step": 61
+    },
+    {
+      "epoch": 1.520123839009288,
+      "grad_norm": 0.6375800371170044,
+      "learning_rate": 1.7651008665813081e-06,
+      "loss": 0.5607191324234009,
+      "step": 62
+    },
+    {
+      "epoch": 1.5448916408668731,
+      "grad_norm": 0.4859982132911682,
+      "learning_rate": 1.7565348610716958e-06,
+      "loss": 0.5413356423377991,
+      "step": 63
+    },
+    {
+      "epoch": 1.5696594427244581,
+      "grad_norm": 0.5644744634628296,
+      "learning_rate": 1.7478370394583643e-06,
+      "loss": 0.5568721294403076,
+      "step": 64
+    },
+    {
+      "epoch": 1.5944272445820433,
+      "grad_norm": 0.5623730421066284,
+      "learning_rate": 1.739008917220659e-06,
+      "loss": 0.5305633544921875,
+      "step": 65
+    },
+    {
+      "epoch": 1.6191950464396285,
+      "grad_norm": 0.46600863337516785,
+      "learning_rate": 1.7300520325410698e-06,
+      "loss": 0.519407331943512,
+      "step": 66
+    },
+    {
+      "epoch": 1.6439628482972135,
+      "grad_norm": 0.5476927161216736,
+      "learning_rate": 1.7209679460372249e-06,
+      "loss": 0.5438145399093628,
+      "step": 67
+    },
+    {
+      "epoch": 1.6687306501547987,
+      "grad_norm": 0.5339446663856506,
+      "learning_rate": 1.711758240489971e-06,
+      "loss": 0.5288221836090088,
+      "step": 68
+    },
+    {
+      "epoch": 1.693498452012384,
+      "grad_norm": 0.4474664628505707,
+      "learning_rate": 1.7024245205675985e-06,
+      "loss": 0.5665724277496338,
+      "step": 69
+    },
+    {
+      "epoch": 1.718266253869969,
+      "grad_norm": 0.5247179865837097,
+      "learning_rate": 1.6929684125462468e-06,
+      "loss": 0.5420582294464111,
+      "step": 70
+    },
+    {
+      "epoch": 1.7430340557275543,
+      "grad_norm": 0.6573188304901123,
+      "learning_rate": 1.6833915640265483e-06,
+      "loss": 0.538118839263916,
+      "step": 71
+    },
+    {
+      "epoch": 1.7678018575851393,
+      "grad_norm": 0.5430057644844055,
+      "learning_rate": 1.6736956436465573e-06,
+      "loss": 0.5287379026412964,
+      "step": 72
+    },
+    {
+      "epoch": 1.7925696594427245,
+      "grad_norm": 1.451054334640503,
+      "learning_rate": 1.6638823407910082e-06,
+      "loss": 0.5065432190895081,
+      "step": 73
+    },
+    {
+      "epoch": 1.8173374613003097,
+      "grad_norm": 1.7800654172897339,
+      "learning_rate": 1.6539533652969682e-06,
+      "loss": 0.5422472357749939,
+      "step": 74
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.5204485654830933,
+      "learning_rate": 1.6439104471559156e-06,
+      "loss": 0.4941398501396179,
+      "step": 75
+    },
+    {
+      "epoch": 1.86687306501548,
+      "grad_norm": 0.4798074960708618,
+      "learning_rate": 1.6337553362123161e-06,
+      "loss": 0.5543307065963745,
+      "step": 76
+    },
+    {
+      "epoch": 1.891640866873065,
+      "grad_norm": 0.4639158248901367,
+      "learning_rate": 1.6234898018587336e-06,
+      "loss": 0.5305337905883789,
+      "step": 77
+    },
+    {
+      "epoch": 1.91640866873065,
+      "grad_norm": 0.4957791566848755,
+      "learning_rate": 1.613115632727537e-06,
+      "loss": 0.4810314178466797,
+      "step": 78
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.542951762676239,
+      "learning_rate": 1.6026346363792564e-06,
+      "loss": 0.5742234587669373,
+      "step": 79
+    },
+    {
+      "epoch": 1.9659442724458205,
+      "grad_norm": 0.518661618232727,
+      "learning_rate": 1.592048638987638e-06,
+      "loss": 0.5540245771408081,
+      "step": 80
+    },
+    {
+      "epoch": 1.9907120743034055,
+      "grad_norm": 0.48943665623664856,
+      "learning_rate": 1.5813594850214597e-06,
+      "loss": 0.509993851184845,
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8778729438781738,
+      "learning_rate": 1.570569036923155e-06,
+      "loss": 0.539715051651001,
+      "step": 82
+    },
+    {
+      "epoch": 2.024767801857585,
+      "grad_norm": 0.4994299113750458,
+      "learning_rate": 1.5596791747843082e-06,
+      "loss": 0.5089604258537292,
+      "step": 83
+    },
+    {
+      "epoch": 2.0495356037151704,
+      "grad_norm": 0.5828955173492432,
+      "learning_rate": 1.548691796018074e-06,
+      "loss": 0.5253075361251831,
+      "step": 84
+    },
+    {
+      "epoch": 2.0743034055727554,
+      "grad_norm": 0.5461580753326416,
+      "learning_rate": 1.5376088150285774e-06,
+      "loss": 0.5154924392700195,
+      "step": 85
+    },
+    {
+      "epoch": 2.0990712074303404,
+      "grad_norm": 0.965928852558136,
+      "learning_rate": 1.5264321628773558e-06,
+      "loss": 0.5028945803642273,
+      "step": 86
+    },
+    {
+      "epoch": 2.123839009287926,
+      "grad_norm": 0.45946890115737915,
+      "learning_rate": 1.5151637869468958e-06,
+      "loss": 0.5220765471458435,
+      "step": 87
+    },
+    {
+      "epoch": 2.1486068111455108,
+      "grad_norm": 0.4885327219963074,
+      "learning_rate": 1.5038056506013295e-06,
+      "loss": 0.5020776391029358,
+      "step": 88
+    },
+    {
+      "epoch": 2.173374613003096,
+      "grad_norm": 0.5246437191963196,
+      "learning_rate": 1.492359732844342e-06,
+      "loss": 0.46335524320602417,
+      "step": 89
+    },
+    {
+      "epoch": 2.198142414860681,
+      "grad_norm": 0.5331137180328369,
+      "learning_rate": 1.4808280279743591e-06,
+      "loss": 0.5037820339202881,
+      "step": 90
+    },
+    {
+      "epoch": 2.222910216718266,
+      "grad_norm": 0.5505975484848022,
+      "learning_rate": 1.4692125452370662e-06,
+      "loss": 0.5359715223312378,
+      "step": 91
+    },
+    {
+      "epoch": 2.2476780185758516,
+      "grad_norm": 0.5390040278434753,
+      "learning_rate": 1.4575153084753232e-06,
+      "loss": 0.5337521433830261,
+      "step": 92
+    },
+    {
+      "epoch": 2.2724458204334366,
+      "grad_norm": 0.44791266322135925,
+      "learning_rate": 1.4457383557765383e-06,
+      "loss": 0.5155265927314758,
+      "step": 93
+    },
+    {
+      "epoch": 2.2972136222910216,
+      "grad_norm": 0.4978775382041931,
+      "learning_rate": 1.433883739117558e-06,
+      "loss": 0.4920554757118225,
+      "step": 94
+    },
+    {
+      "epoch": 2.321981424148607,
+      "grad_norm": 0.5269660353660583,
+      "learning_rate": 1.4219535240071376e-06,
+      "loss": 0.5533995628356934,
+      "step": 95
+    },
+    {
+      "epoch": 2.346749226006192,
+      "grad_norm": 0.4875043034553528,
+      "learning_rate": 1.4099497891260537e-06,
+      "loss": 0.523270845413208,
+      "step": 96
+    },
+    {
+      "epoch": 2.371517027863777,
+      "grad_norm": 0.5254143476486206,
+      "learning_rate": 1.3978746259649208e-06,
+      "loss": 0.5255824327468872,
+      "step": 97
+    },
+    {
+      "epoch": 2.3962848297213624,
+      "grad_norm": 0.5345160365104675,
+      "learning_rate": 1.3857301384597794e-06,
+      "loss": 0.5329371094703674,
+      "step": 98
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.46321746706962585,
+      "learning_rate": 1.3735184426255114e-06,
+      "loss": 0.5548917055130005,
+      "step": 99
+    },
+    {
+      "epoch": 2.4458204334365323,
+      "grad_norm": 0.5209585428237915,
+      "learning_rate": 1.3612416661871531e-06,
+      "loss": 0.5931960940361023,
+      "step": 100
+    },
+    {
+      "epoch": 2.4458204334365323,
+      "eval_accuracy": 0.8215138901886158,
+      "eval_loss": 0.562470018863678,
+      "eval_runtime": 16.4711,
+      "eval_samples_per_second": 4.128,
+      "eval_steps_per_second": 2.064,
+      "step": 100
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.483987033367157,
+      "learning_rate": 1.3489019482091667e-06,
+      "loss": 0.5425853133201599,
+      "step": 101
+    },
+    {
+      "epoch": 2.4953560371517027,
+      "grad_norm": 0.44485101103782654,
+      "learning_rate": 1.336501438722739e-06,
+      "loss": 0.5403157472610474,
+      "step": 102
+    },
+    {
+      "epoch": 2.5201238390092877,
+      "grad_norm": 0.5460787415504456,
+      "learning_rate": 1.324042298351166e-06,
+      "loss": 0.5747348666191101,
+      "step": 103
+    },
+    {
+      "epoch": 2.544891640866873,
+      "grad_norm": 0.45323142409324646,
+      "learning_rate": 1.3115266979333914e-06,
+      "loss": 0.5297880172729492,
+      "step": 104
+    },
+    {
+      "epoch": 2.569659442724458,
+      "grad_norm": 0.6902194619178772,
+      "learning_rate": 1.2989568181457702e-06,
+      "loss": 0.5073508024215698,
+      "step": 105
+    },
+    {
+      "epoch": 2.594427244582043,
+      "grad_norm": 0.5212258100509644,
+      "learning_rate": 1.2863348491221127e-06,
+      "loss": 0.5311723351478577,
+      "step": 106
+    },
+    {
+      "epoch": 2.6191950464396285,
+      "grad_norm": 0.5578774809837341,
+      "learning_rate": 1.273662990072083e-06,
+      "loss": 0.5304839015007019,
+      "step": 107
+    },
+    {
+      "epoch": 2.6439628482972135,
+      "grad_norm": 0.504798173904419,
+      "learning_rate": 1.2609434488980166e-06,
+      "loss": 0.4865831136703491,
+      "step": 108
+    },
+    {
+      "epoch": 2.6687306501547985,
+      "grad_norm": 0.4682161211967468,
+      "learning_rate": 1.2481784418102239e-06,
+      "loss": 0.5439316630363464,
+      "step": 109
+    },
+    {
+      "epoch": 2.693498452012384,
+      "grad_norm": 0.5871185064315796,
+      "learning_rate": 1.2353701929408424e-06,
+      "loss": 0.477615088224411,
+      "step": 110
+    },
+    {
+      "epoch": 2.718266253869969,
+      "grad_norm": 0.4735322594642639,
+      "learning_rate": 1.2225209339563143e-06,
+      "loss": 0.5605683326721191,
+      "step": 111
+    },
+    {
+      "epoch": 2.7430340557275543,
+      "grad_norm": 0.5656632781028748,
+      "learning_rate": 1.2096329036685466e-06,
+      "loss": 0.5053581595420837,
+      "step": 112
+    },
+    {
+      "epoch": 2.7678018575851393,
+      "grad_norm": 0.501797616481781,
+      "learning_rate": 1.196708347644828e-06,
+      "loss": 0.5080878734588623,
+      "step": 113
+    },
+    {
+      "epoch": 2.7925696594427247,
+      "grad_norm": 1.2063102722167969,
+      "learning_rate": 1.1837495178165704e-06,
+      "loss": 0.552485466003418,
+      "step": 114
+    },
+    {
+      "epoch": 2.8173374613003097,
+      "grad_norm": 0.5052933096885681,
+      "learning_rate": 1.1707586720869374e-06,
+      "loss": 0.5424617528915405,
+      "step": 115
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.5184856057167053,
+      "learning_rate": 1.1577380739374373e-06,
+      "loss": 0.5432671904563904,
+      "step": 116
+    },
+    {
+      "epoch": 2.86687306501548,
+      "grad_norm": 0.5071874260902405,
+      "learning_rate": 1.1446899920335405e-06,
+      "loss": 0.5507460832595825,
+      "step": 117
+    },
+    {
+      "epoch": 2.891640866873065,
+      "grad_norm": 0.519482433795929,
+      "learning_rate": 1.1316166998293935e-06,
+      "loss": 0.5559477210044861,
+      "step": 118
+    },
+    {
+      "epoch": 2.91640866873065,
+      "grad_norm": 0.5042552947998047,
+      "learning_rate": 1.1185204751717027e-06,
+      "loss": 0.5015457272529602,
+      "step": 119
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 1.3727635145187378,
+      "learning_rate": 1.1054035999028476e-06,
+      "loss": 0.5176253318786621,
+      "step": 120
+    },
+    {
+      "epoch": 2.9659442724458205,
+      "grad_norm": 0.5206997990608215,
+      "learning_rate": 1.092268359463302e-06,
+      "loss": 0.5474892258644104,
+      "step": 121
+    },
+    {
+      "epoch": 2.9907120743034055,
+      "grad_norm": 0.472130686044693,
+      "learning_rate": 1.0791170424934246e-06,
+      "loss": 0.4985366463661194,
+      "step": 122
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.058793544769287,
+      "learning_rate": 1.0659519404346952e-06,
+      "loss": 0.48316121101379395,
+      "step": 123
+    },
+    {
+      "epoch": 3.024767801857585,
+      "grad_norm": 0.5421841740608215,
+      "learning_rate": 1.0527753471304623e-06,
+      "loss": 0.5144573450088501,
+      "step": 124
+    },
+    {
+      "epoch": 3.0495356037151704,
+      "grad_norm": 0.5197970271110535,
+      "learning_rate": 1.0395895584262695e-06,
+      "loss": 0.5817261934280396,
+      "step": 125
+    },
+    {
+      "epoch": 3.0743034055727554,
+      "grad_norm": 0.49334728717803955,
+      "learning_rate": 1.0263968717698363e-06,
+      "loss": 0.5018012523651123,
+      "step": 126
+    },
+    {
+      "epoch": 3.0990712074303404,
+      "grad_norm": 0.6232290267944336,
+      "learning_rate": 1.013199585810759e-06,
+      "loss": 0.5584498643875122,
+      "step": 127
+    },
+    {
+      "epoch": 3.123839009287926,
+      "grad_norm": 0.455437034368515,
+      "learning_rate": 1e-06,
+      "loss": 0.5036893486976624,
+      "step": 128
+    },
+    {
+      "epoch": 3.1486068111455108,
+      "grad_norm": 0.48946836590766907,
+      "learning_rate": 9.868004141892412e-07,
+      "loss": 0.5123312473297119,
+      "step": 129
+    },
+    {
+      "epoch": 3.173374613003096,
+      "grad_norm": 0.5698655843734741,
+      "learning_rate": 9.736031282301638e-07,
+      "loss": 0.5401725172996521,
+      "step": 130
+    },
+    {
+      "epoch": 3.198142414860681,
+      "grad_norm": 0.9283490180969238,
+      "learning_rate": 9.604104415737308e-07,
+      "loss": 0.48566514253616333,
+      "step": 131
+    },
+    {
+      "epoch": 3.222910216718266,
+      "grad_norm": 2.0157785415649414,
+      "learning_rate": 9.472246528695375e-07,
+      "loss": 0.4537651538848877,
+      "step": 132
+    },
+    {
+      "epoch": 3.2476780185758516,
+      "grad_norm": 0.5449803471565247,
+      "learning_rate": 9.340480595653045e-07,
+      "loss": 0.5530433654785156,
+      "step": 133
+    },
+    {
+      "epoch": 3.2724458204334366,
+      "grad_norm": 0.4725954532623291,
+      "learning_rate": 9.208829575065753e-07,
+      "loss": 0.5256283283233643,
+      "step": 134
+    },
+    {
+      "epoch": 3.2972136222910216,
+      "grad_norm": 0.4579267203807831,
+      "learning_rate": 9.077316405366981e-07,
+      "loss": 0.5190701484680176,
+      "step": 135
+    },
+    {
+      "epoch": 3.321981424148607,
+      "grad_norm": 0.544757604598999,
+      "learning_rate": 8.945964000971523e-07,
+      "loss": 0.5290215015411377,
+      "step": 136
+    },
+    {
+      "epoch": 3.346749226006192,
+      "grad_norm": 0.4990670084953308,
+      "learning_rate": 8.814795248282973e-07,
+      "loss": 0.5203908085823059,
+      "step": 137
+    },
+    {
+      "epoch": 3.371517027863777,
+      "grad_norm": 0.5583924651145935,
+      "learning_rate": 8.683833001706067e-07,
+      "loss": 0.499897837638855,
+      "step": 138
+    },
+    {
+      "epoch": 3.3962848297213624,
+      "grad_norm": 0.47875887155532837,
+      "learning_rate": 8.553100079664598e-07,
+      "loss": 0.4940932095050812,
+      "step": 139
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.4689862132072449,
+      "learning_rate": 8.422619260625624e-07,
+      "loss": 0.488369345664978,
+      "step": 140
+    },
+    {
+      "epoch": 3.4458204334365323,
+      "grad_norm": 0.5019742846488953,
+      "learning_rate": 8.292413279130624e-07,
+      "loss": 0.49827271699905396,
+      "step": 141
+    },
+    {
+      "epoch": 3.4705882352941178,
+      "grad_norm": 0.47474774718284607,
+      "learning_rate": 8.162504821834295e-07,
+      "loss": 0.5006945133209229,
+      "step": 142
+    },
+    {
+      "epoch": 3.4953560371517027,
+      "grad_norm": 0.5412342548370361,
+      "learning_rate": 8.032916523551719e-07,
+      "loss": 0.5021499395370483,
+      "step": 143
+    },
+    {
+      "epoch": 3.5201238390092877,
+      "grad_norm": 0.46898508071899414,
+      "learning_rate": 7.903670963314535e-07,
+      "loss": 0.5173486471176147,
+      "step": 144
+    },
+    {
+      "epoch": 3.544891640866873,
+      "grad_norm": 0.5036367177963257,
+      "learning_rate": 7.774790660436857e-07,
+      "loss": 0.5127341151237488,
+      "step": 145
+    },
+    {
+      "epoch": 3.569659442724458,
+      "grad_norm": 0.4592057466506958,
+      "learning_rate": 7.646298070591577e-07,
+      "loss": 0.5291725397109985,
+      "step": 146
+    },
+    {
+      "epoch": 3.594427244582043,
+      "grad_norm": 0.579252302646637,
+      "learning_rate": 7.518215581897763e-07,
+      "loss": 0.5540162324905396,
+      "step": 147
+    },
+    {
+      "epoch": 3.6191950464396285,
+      "grad_norm": 0.5662134885787964,
+      "learning_rate": 7.390565511019833e-07,
+      "loss": 0.5307095646858215,
+      "step": 148
+    },
+    {
+      "epoch": 3.6439628482972135,
+      "grad_norm": 0.5780702233314514,
+      "learning_rate": 7.263370099279171e-07,
+      "loss": 0.48574694991111755,
+      "step": 149
+    },
+    {
+      "epoch": 3.6687306501547985,
+      "grad_norm": 0.5063837766647339,
+      "learning_rate": 7.136651508778874e-07,
+      "loss": 0.5621860027313232,
+      "step": 150
+    },
+    {
+      "epoch": 3.6687306501547985,
+      "eval_accuracy": 0.8215492383391412,
+      "eval_loss": 0.5617780685424805,
+      "eval_runtime": 16.4087,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 2.072,
+      "step": 150
+    },
+    {
+      "epoch": 3.693498452012384,
+      "grad_norm": 0.5430096387863159,
+      "learning_rate": 7.010431818542297e-07,
+      "loss": 0.4991950988769531,
+      "step": 151
+    },
+    {
+      "epoch": 3.718266253869969,
+      "grad_norm": 0.4858173727989197,
+      "learning_rate": 6.884733020666084e-07,
+      "loss": 0.47163355350494385,
+      "step": 152
+    },
+    {
+      "epoch": 3.7430340557275543,
+      "grad_norm": 0.4979320168495178,
+      "learning_rate": 6.759577016488343e-07,
+      "loss": 0.5382797718048096,
+      "step": 153
+    },
+    {
+      "epoch": 3.7678018575851393,
+      "grad_norm": 0.47822287678718567,
+      "learning_rate": 6.63498561277261e-07,
+      "loss": 0.5248020887374878,
+      "step": 154
+    },
+    {
+      "epoch": 3.7925696594427247,
+      "grad_norm": 0.5561540722846985,
+      "learning_rate": 6.510980517908333e-07,
+      "loss": 0.47944825887680054,
+      "step": 155
+    },
+    {
+      "epoch": 3.8173374613003097,
+      "grad_norm": 0.510204553604126,
+      "learning_rate": 6.387583338128471e-07,
+      "loss": 0.5094054937362671,
+      "step": 156
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.4817684590816498,
+      "learning_rate": 6.264815573744884e-07,
+      "loss": 0.4909018874168396,
+      "step": 157
+    },
+    {
+      "epoch": 3.86687306501548,
+      "grad_norm": 0.4790090024471283,
+      "learning_rate": 6.142698615402204e-07,
+      "loss": 0.47690001130104065,
+      "step": 158
+    },
+    {
+      "epoch": 3.891640866873065,
+      "grad_norm": 0.4971541464328766,
+      "learning_rate": 6.021253740350792e-07,
+      "loss": 0.5042445659637451,
+      "step": 159
+    },
+    {
+      "epoch": 3.91640866873065,
+      "grad_norm": 0.5663966536521912,
+      "learning_rate": 5.900502108739465e-07,
+      "loss": 0.5802559852600098,
+      "step": 160
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.6140542030334473,
+      "learning_rate": 5.780464759928623e-07,
+      "loss": 0.5226213932037354,
+      "step": 161
+    },
+    {
+      "epoch": 3.9659442724458205,
+      "grad_norm": 0.510217010974884,
+      "learning_rate": 5.661162608824419e-07,
+      "loss": 0.487061470746994,
+      "step": 162
+    },
+    {
+      "epoch": 3.9907120743034055,
+      "grad_norm": 0.47863468527793884,
+      "learning_rate": 5.542616442234618e-07,
+      "loss": 0.49519461393356323,
+      "step": 163
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8134075999259949,
+      "learning_rate": 5.424846915246769e-07,
+      "loss": 0.5006481409072876,
+      "step": 164
+    },
+    {
+      "epoch": 4.024767801857585,
+      "grad_norm": 0.5010446906089783,
+      "learning_rate": 5.307874547629339e-07,
+      "loss": 0.5043383240699768,
+      "step": 165
+    },
+    {
+      "epoch": 4.04953560371517,
+      "grad_norm": 0.5629169344902039,
+      "learning_rate": 5.191719720256407e-07,
+      "loss": 0.5104990005493164,
+      "step": 166
+    },
+    {
+      "epoch": 4.074303405572755,
+      "grad_norm": 0.5630432367324829,
+      "learning_rate": 5.076402671556577e-07,
+      "loss": 0.4841610789299011,
+      "step": 167
+    },
+    {
+      "epoch": 4.099071207430341,
+      "grad_norm": 0.46193253993988037,
+      "learning_rate": 4.961943493986708e-07,
+      "loss": 0.5317561030387878,
+      "step": 168
+    },
+    {
+      "epoch": 4.123839009287925,
+      "grad_norm": 0.5281070470809937,
+      "learning_rate": 4.848362130531039e-07,
+      "loss": 0.5141686201095581,
+      "step": 169
+    },
+    {
+      "epoch": 4.148606811145511,
+      "grad_norm": 0.927697479724884,
+      "learning_rate": 4.7356783712264403e-07,
+      "loss": 0.46369314193725586,
+      "step": 170
+    },
+    {
+      "epoch": 4.173374613003096,
+      "grad_norm": 0.5692654252052307,
+      "learning_rate": 4.623911849714225e-07,
+      "loss": 0.48228251934051514,
+      "step": 171
+    },
+    {
+      "epoch": 4.198142414860681,
+      "grad_norm": 0.48862549662590027,
+      "learning_rate": 4.5130820398192636e-07,
+      "loss": 0.5285767316818237,
+      "step": 172
+    },
+    {
+      "epoch": 4.222910216718266,
+      "grad_norm": 0.5772708058357239,
+      "learning_rate": 4.40320825215692e-07,
+      "loss": 0.5200311541557312,
+      "step": 173
+    },
+    {
+      "epoch": 4.247678018575852,
+      "grad_norm": 0.5576812028884888,
+      "learning_rate": 4.294309630768451e-07,
+      "loss": 0.5052947402000427,
+      "step": 174
+    },
+    {
+      "epoch": 4.272445820433436,
+      "grad_norm": 0.48456260561943054,
+      "learning_rate": 4.1864051497854027e-07,
+      "loss": 0.5091853141784668,
+      "step": 175
+    },
+    {
+      "epoch": 4.2972136222910216,
+      "grad_norm": 0.4992901086807251,
+      "learning_rate": 4.079513610123618e-07,
+      "loss": 0.5285595655441284,
+      "step": 176
+    },
+    {
+      "epoch": 4.321981424148607,
+      "grad_norm": 0.560563862323761,
+      "learning_rate": 3.973653636207437e-07,
+      "loss": 0.5327163338661194,
+      "step": 177
+    },
+    {
+      "epoch": 4.346749226006192,
+      "grad_norm": 0.48380428552627563,
+      "learning_rate": 3.8688436727246296e-07,
+      "loss": 0.4750836491584778,
+      "step": 178
+    },
+    {
+      "epoch": 4.371517027863777,
+      "grad_norm": 0.4964829385280609,
+      "learning_rate": 3.765101981412665e-07,
+      "loss": 0.46454548835754395,
+      "step": 179
+    },
+    {
+      "epoch": 4.396284829721362,
+      "grad_norm": 0.4538560211658478,
+      "learning_rate": 3.6624466378768384e-07,
+      "loss": 0.51465904712677,
+      "step": 180
+    },
+    {
+      "epoch": 4.421052631578947,
+      "grad_norm": 0.6692084074020386,
+      "learning_rate": 3.560895528440844e-07,
+      "loss": 0.4617176055908203,
+      "step": 181
+    },
+    {
+      "epoch": 4.445820433436532,
+      "grad_norm": 0.47236230969429016,
+      "learning_rate": 3.4604663470303186e-07,
+      "loss": 0.5083804130554199,
+      "step": 182
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.4774688184261322,
+      "learning_rate": 3.3611765920899183e-07,
+      "loss": 0.5058382749557495,
+      "step": 183
+    },
+    {
+      "epoch": 4.495356037151703,
+      "grad_norm": 0.47210627794265747,
+      "learning_rate": 3.263043563534428e-07,
+      "loss": 0.5376588106155396,
+      "step": 184
+    },
+    {
+      "epoch": 4.520123839009288,
+      "grad_norm": 0.4772137403488159,
+      "learning_rate": 3.166084359734513e-07,
+      "loss": 0.5304179191589355,
+      "step": 185
+    },
+    {
+      "epoch": 4.544891640866873,
+      "grad_norm": 0.4682233929634094,
+      "learning_rate": 3.070315874537531e-07,
+      "loss": 0.4820975661277771,
+      "step": 186
+    },
+    {
+      "epoch": 4.569659442724459,
+      "grad_norm": 0.48219650983810425,
+      "learning_rate": 2.975754794324015e-07,
+      "loss": 0.5084782838821411,
+      "step": 187
+    },
+    {
+      "epoch": 4.594427244582043,
+      "grad_norm": 0.43362459540367126,
+      "learning_rate": 2.8824175951002916e-07,
+      "loss": 0.47581952810287476,
+      "step": 188
+    },
+    {
+      "epoch": 4.6191950464396285,
+      "grad_norm": 0.567948579788208,
+      "learning_rate": 2.790320539627754e-07,
+      "loss": 0.5314459800720215,
+      "step": 189
+    },
+    {
+      "epoch": 4.643962848297214,
+      "grad_norm": 0.5087016224861145,
+      "learning_rate": 2.6994796745893e-07,
+      "loss": 0.4740360379219055,
+      "step": 190
+    },
+    {
+      "epoch": 4.6687306501547985,
+      "grad_norm": 0.5123845338821411,
+      "learning_rate": 2.60991082779341e-07,
+      "loss": 0.5245854258537292,
+      "step": 191
+    },
+    {
+      "epoch": 4.693498452012384,
+      "grad_norm": 0.4884699285030365,
+      "learning_rate": 2.521629605416354e-07,
+      "loss": 0.5254173278808594,
+      "step": 192
+    },
+    {
+      "epoch": 4.718266253869969,
+      "grad_norm": 0.5492839217185974,
+      "learning_rate": 2.434651389283042e-07,
+      "loss": 0.5060293674468994,
+      "step": 193
+    },
+    {
+      "epoch": 4.743034055727554,
+      "grad_norm": 0.4537581503391266,
+      "learning_rate": 2.3489913341869193e-07,
+      "loss": 0.5028636455535889,
+      "step": 194
+    },
+    {
+      "epoch": 4.767801857585139,
+      "grad_norm": 0.5206896662712097,
+      "learning_rate": 2.264664365249469e-07,
+      "loss": 0.509818971157074,
+      "step": 195
+    },
+    {
+      "epoch": 4.792569659442725,
+      "grad_norm": 0.5348969101905823,
+      "learning_rate": 2.181685175319702e-07,
+      "loss": 0.4900963306427002,
+      "step": 196
+    },
+    {
+      "epoch": 4.817337461300309,
+      "grad_norm": 0.478466659784317,
+      "learning_rate": 2.100068222414121e-07,
+      "loss": 0.5366532802581787,
+      "step": 197
+    },
+    {
+      "epoch": 4.842105263157895,
+      "grad_norm": 0.4873082637786865,
+      "learning_rate": 2.0198277271976049e-07,
+      "loss": 0.5138839483261108,
+      "step": 198
+    },
+    {
+      "epoch": 4.86687306501548,
+      "grad_norm": 0.5307355523109436,
+      "learning_rate": 1.9409776705056514e-07,
+      "loss": 0.48487958312034607,
+      "step": 199
+    },
+    {
+      "epoch": 4.891640866873065,
+      "grad_norm": 0.6182578206062317,
+      "learning_rate": 1.863531790908398e-07,
+      "loss": 0.49715912342071533,
+      "step": 200
+    },
+    {
+      "epoch": 4.891640866873065,
+      "eval_accuracy": 0.8215848485329422,
+      "eval_loss": 0.5621271133422852,
+      "eval_runtime": 16.3624,
+      "eval_samples_per_second": 4.156,
+      "eval_steps_per_second": 2.078,
+      "step": 200
+    },
+    {
+      "epoch": 4.91640866873065,
+      "grad_norm": 0.5110271573066711,
+      "learning_rate": 1.787503582316864e-07,
+      "loss": 0.5255718231201172,
+      "step": 201
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.4957195222377777,
+      "learning_rate": 1.7129062916318137e-07,
+      "loss": 0.5106043219566345,
+      "step": 202
+    },
+    {
+      "epoch": 4.965944272445821,
+      "grad_norm": 1.4632741212844849,
+      "learning_rate": 1.6397529164356606e-07,
+      "loss": 0.5344016551971436,
+      "step": 203
+    },
+    {
+      "epoch": 4.9907120743034055,
+      "grad_norm": 0.533440113067627,
+      "learning_rate": 1.5680562027278154e-07,
+      "loss": 0.5215489268302917,
+      "step": 204
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8572560548782349,
+      "learning_rate": 1.49782864270386e-07,
+      "loss": 0.5227999687194824,
+      "step": 205
+    },
+    {
+      "epoch": 5.024767801857585,
+      "grad_norm": 0.43222400546073914,
+      "learning_rate": 1.429082472578954e-07,
+      "loss": 0.5099145174026489,
+      "step": 206
+    },
+    {
+      "epoch": 5.04953560371517,
+      "grad_norm": 0.47421810030937195,
+      "learning_rate": 1.3618296704558364e-07,
+      "loss": 0.5271211862564087,
+      "step": 207
+    },
+    {
+      "epoch": 5.074303405572755,
+      "grad_norm": 0.5383461117744446,
+      "learning_rate": 1.2960819542378053e-07,
+      "loss": 0.548247218132019,
+      "step": 208
+    },
+    {
+      "epoch": 5.099071207430341,
+      "grad_norm": 0.513953685760498,
+      "learning_rate": 1.2318507795870137e-07,
+      "loss": 0.47977253794670105,
+      "step": 209
+    },
+    {
+      "epoch": 5.123839009287925,
+      "grad_norm": 0.5112437605857849,
+      "learning_rate": 1.1691473379284944e-07,
+      "loss": 0.4924686551094055,
+      "step": 210
+    },
+    {
+      "epoch": 5.148606811145511,
+      "grad_norm": 0.5439184308052063,
+      "learning_rate": 1.1079825545001886e-07,
+      "loss": 0.4926351308822632,
+      "step": 211
+    },
+    {
+      "epoch": 5.173374613003096,
+      "grad_norm": 0.47784221172332764,
+      "learning_rate": 1.0483670864493777e-07,
+      "loss": 0.5255255699157715,
+      "step": 212
+    },
+    {
+      "epoch": 5.198142414860681,
+      "grad_norm": 0.48372480273246765,
+      "learning_rate": 9.903113209758096e-08,
+      "loss": 0.5388856530189514,
+      "step": 213
+    },
+    {
+      "epoch": 5.222910216718266,
+      "grad_norm": 0.4922617971897125,
+      "learning_rate": 9.338253735218748e-08,
+      "loss": 0.4714866280555725,
+      "step": 214
+    },
+    {
+      "epoch": 5.247678018575852,
+      "grad_norm": 0.5694555044174194,
+      "learning_rate": 8.789190860101226e-08,
+      "loss": 0.49757862091064453,
+      "step": 215
+    },
+    {
+      "epoch": 5.272445820433436,
+      "grad_norm": 0.5285799503326416,
+      "learning_rate": 8.256020251284379e-08,
+      "loss": 0.5523006916046143,
+      "step": 216
+    },
+    {
+      "epoch": 5.2972136222910216,
+      "grad_norm": 0.542019784450531,
+      "learning_rate": 7.73883480663171e-08,
+      "loss": 0.4939878582954407,
+      "step": 217
+    },
+    {
+      "epoch": 5.321981424148607,
+      "grad_norm": 0.4783063232898712,
+      "learning_rate": 7.23772463880522e-08,
+      "loss": 0.5162045359611511,
+      "step": 218
+    },
+    {
+      "epoch": 5.346749226006192,
+      "grad_norm": 0.4960096776485443,
+      "learning_rate": 6.75277705956443e-08,
+      "loss": 0.5186662673950195,
+      "step": 219
+    },
+    {
+      "epoch": 5.371517027863777,
+      "grad_norm": 0.4951794147491455,
+      "learning_rate": 6.284076564553464e-08,
+      "loss": 0.48755860328674316,
+      "step": 220
+    },
+    {
+      "epoch": 5.396284829721362,
+      "grad_norm": 0.4898841381072998,
+      "learning_rate": 5.831704818578842e-08,
+      "loss": 0.5034775733947754,
+      "step": 221
+    },
+    {
+      "epoch": 5.421052631578947,
+      "grad_norm": 0.540875256061554,
+      "learning_rate": 5.395740641380531e-08,
+      "loss": 0.4632171094417572,
+      "step": 222
+    },
+    {
+      "epoch": 5.445820433436532,
+      "grad_norm": 0.45750898122787476,
+      "learning_rate": 4.976259993898502e-08,
+      "loss": 0.49796921014785767,
+      "step": 223
+    },
+    {
+      "epoch": 5.470588235294118,
+      "grad_norm": 0.5052651166915894,
+      "learning_rate": 4.573335965037706e-08,
+      "loss": 0.47650158405303955,
+      "step": 224
+    },
+    {
+      "epoch": 5.495356037151703,
+      "grad_norm": 0.4999431371688843,
+      "learning_rate": 4.187038758933203e-08,
+      "loss": 0.49834519624710083,
+      "step": 225
+    },
+    {
+      "epoch": 5.520123839009288,
+      "grad_norm": 0.5175738334655762,
+      "learning_rate": 3.817435682718095e-08,
+      "loss": 0.46955606341362,
+      "step": 226
+    },
+    {
+      "epoch": 5.544891640866873,
+      "grad_norm": 0.4690812826156616,
+      "learning_rate": 3.464591134796135e-08,
+      "loss": 0.5154824256896973,
+      "step": 227
+    },
+    {
+      "epoch": 5.569659442724459,
+      "grad_norm": 0.4758513867855072,
+      "learning_rate": 3.1285665936211516e-08,
+      "loss": 0.5336707830429077,
+      "step": 228
+    },
+    {
+      "epoch": 5.594427244582043,
+      "grad_norm": 0.442473441362381,
+      "learning_rate": 2.8094206069852355e-08,
+      "loss": 0.4967498779296875,
+      "step": 229
+    },
+    {
+      "epoch": 5.6191950464396285,
+      "grad_norm": 0.4868296682834625,
+      "learning_rate": 2.507208781817638e-08,
+      "loss": 0.5311983823776245,
+      "step": 230
+    },
+    {
+      "epoch": 5.643962848297214,
+      "grad_norm": 0.5476986169815063,
+      "learning_rate": 2.221983774495928e-08,
+      "loss": 0.5054424405097961,
+      "step": 231
+    },
+    {
+      "epoch": 5.6687306501547985,
+      "grad_norm": 0.4974565804004669,
+      "learning_rate": 1.953795281671333e-08,
+      "loss": 0.5006812214851379,
+      "step": 232
+    },
+    {
+      "epoch": 5.693498452012384,
+      "grad_norm": 0.5025091767311096,
+      "learning_rate": 1.7026900316098212e-08,
+      "loss": 0.527012825012207,
+      "step": 233
+    },
+    {
+      "epoch": 5.718266253869969,
+      "grad_norm": 0.46924424171447754,
+      "learning_rate": 1.4687117760502576e-08,
+      "loss": 0.4735889434814453,
+      "step": 234
+    },
+    {
+      "epoch": 5.743034055727554,
+      "grad_norm": 0.454560786485672,
+      "learning_rate": 1.2519012825812803e-08,
+      "loss": 0.49276185035705566,
+      "step": 235
+    },
+    {
+      "epoch": 5.767801857585139,
+      "grad_norm": 0.4710627496242523,
+      "learning_rate": 1.0522963275380492e-08,
+      "loss": 0.5048189759254456,
+      "step": 236
+    },
+    {
+      "epoch": 5.792569659442725,
+      "grad_norm": 0.4550038278102875,
+      "learning_rate": 8.699316894203223e-09,
+      "loss": 0.513171911239624,
+      "step": 237
+    },
+    {
+      "epoch": 5.817337461300309,
+      "grad_norm": 0.5602344870567322,
+      "learning_rate": 7.048391428326584e-09,
+      "loss": 0.5195218324661255,
+      "step": 238
+    },
+    {
+      "epoch": 5.842105263157895,
+      "grad_norm": 0.4764668643474579,
+      "learning_rate": 5.570474529481561e-09,
+      "loss": 0.49439120292663574,
+      "step": 239
+    },
+    {
+      "epoch": 5.86687306501548,
+      "grad_norm": 0.7008131146430969,
+      "learning_rate": 4.265823704965532e-09,
+      "loss": 0.5026534795761108,
+      "step": 240
+    },
+    {
+      "epoch": 5.891640866873065,
+      "grad_norm": 0.5155523419380188,
+      "learning_rate": 3.1346662727740338e-09,
+      "loss": 0.505569338798523,
+      "step": 241
+    },
+    {
+      "epoch": 5.91640866873065,
+      "grad_norm": 0.48813626170158386,
+      "learning_rate": 2.1771993219946718e-09,
+      "loss": 0.4332225024700165,
+      "step": 242
+    },
+    {
+      "epoch": 5.9411764705882355,
+      "grad_norm": 0.5733649134635925,
+      "learning_rate": 1.393589678466367e-09,
+      "loss": 0.5184577703475952,
+      "step": 243
+    },
+    {
+      "epoch": 5.965944272445821,
+      "grad_norm": 0.47005656361579895,
+      "learning_rate": 7.839738757123848e-10,
+      "loss": 0.48927992582321167,
+      "step": 244
+    },
+    {
+      "epoch": 5.9907120743034055,
+      "grad_norm": 0.519534170627594,
+      "learning_rate": 3.484581311511414e-10,
+      "loss": 0.5252695679664612,
+      "step": 245
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.8245697617530823,
+      "learning_rate": 8.711832758934168e-11,
+      "loss": 0.485756516456604,
+      "step": 246
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 246,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 63272699183104.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..6cde948
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e151eb3bede97e3b0bbf5cb7808e6e319167cdb2bf9a4ef9feac3203f17eb78
+size 7569