diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..366cef4106857b78986b5df89b57eea6482df2df 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2523/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json 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 0000000000000000000000000000000000000000..0828423967b611353e92a1d5727eac8033cb656d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,63 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+model_name: codek-lora-v3
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for codek-lora-v3
+
+This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.6.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```
\ No newline at end of file
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/adapter_model.safetensors b/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7bc67fe2832f12a59749e7daae89efa4700a7a98
--- /dev/null
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e46a1113b9507a30f5ae0d86e5e2510ea0ed32ebc9e137defae0c1d831be14
+size 161533192
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /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/checkpoint-1800/README.md b/checkpoint-1800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-1800/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1800/adapter_config.json b/checkpoint-1800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-1800/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-1800/adapter_model.safetensors b/checkpoint-1800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..24c2c0da9ec3741d4795dda621210d4ae35264c8
--- /dev/null
+++ b/checkpoint-1800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200d5b35f75c4465d25bd9e65e810c371fd47703b1a7fdfb9329f7bae8b9ec72
+size 161533192
diff --git a/checkpoint-1800/chat_template.jinja b/checkpoint-1800/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-1800/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/checkpoint-1800/optimizer.pt b/checkpoint-1800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..62418f6b3b79c153f73bbfe8559a7132d2c89a38
--- /dev/null
+++ b/checkpoint-1800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2380d214b43eb1289d7ad7d295eef26061fb30aec4bb2c3915623da3474cbee0
+size 82465012
diff --git a/checkpoint-1800/rng_state.pth b/checkpoint-1800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..912a8d006b65335a13525cd5a5a5b372796b8ed0
--- /dev/null
+++ b/checkpoint-1800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa18ca9d665eaa374fde78a0c795f2a0417bdc92bd9dac544cf585342f837836
+size 14308
diff --git a/checkpoint-1800/scheduler.pt b/checkpoint-1800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..444eb315d3df7ad8da6255db865024048132b563
--- /dev/null
+++ b/checkpoint-1800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17d47b47f951039fe7533ea36815639b22eec839bc0f49c9979077a7efb826c
+size 1064
diff --git a/checkpoint-1800/tokenizer.json b/checkpoint-1800/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-1800/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-1800/tokenizer_config.json b/checkpoint-1800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-1800/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-1800/trainer_state.json b/checkpoint-1800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b140f8bf99982e1459368d6541aa8e3af2ae77a7
--- /dev/null
+++ b/checkpoint-1800/trainer_state.json
@@ -0,0 +1,1438 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.1403926234384296,
+  "eval_steps": 100,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1046803853769421e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1800/training_args.bin b/checkpoint-1800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-1800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-1900/README.md b/checkpoint-1900/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-1900/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-1900/adapter_config.json b/checkpoint-1900/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-1900/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-1900/adapter_model.safetensors b/checkpoint-1900/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da1a3d91ae9b9c1a85b89a8a88bc18cd4071a8fa
--- /dev/null
+++ b/checkpoint-1900/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab89417f1911aad6e7ab330e019150698d4c1f7967a139ed1af8360a8736624
+size 161533192
diff --git a/checkpoint-1900/chat_template.jinja b/checkpoint-1900/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-1900/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/checkpoint-1900/optimizer.pt b/checkpoint-1900/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ea90042233d1497a9971de8bf9aa8ad04f830e7a
--- /dev/null
+++ b/checkpoint-1900/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98d7016606616d574964a5825a437614a5c986bcdbf31f65d74dd5c7348e2f0
+size 82465012
diff --git a/checkpoint-1900/rng_state.pth b/checkpoint-1900/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b99135a3e92cc681a6f1316bc1b42dc706b332f5
--- /dev/null
+++ b/checkpoint-1900/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74500fe56a00edceb9cab6364c03fae529645b7e8281b3591741e890ae56df43
+size 14308
diff --git a/checkpoint-1900/scheduler.pt b/checkpoint-1900/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..960542e8fa64a0827d446fec8cde9640ad465176
--- /dev/null
+++ b/checkpoint-1900/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a16a0ec1c87f3e4f537ce10292042672b0fb5efc05adf0ce8142ad7a0eb805
+size 1064
diff --git a/checkpoint-1900/tokenizer.json b/checkpoint-1900/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-1900/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-1900/tokenizer_config.json b/checkpoint-1900/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-1900/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-1900/trainer_state.json b/checkpoint-1900/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7cfcb5214c32c2e13d7507fed5867185dc74a416
--- /dev/null
+++ b/checkpoint-1900/trainer_state.json
@@ -0,0 +1,1516 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.2593694229625223,
+  "eval_steps": 100,
+  "global_step": 1900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1655859235023503e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1900/training_args.bin b/checkpoint-1900/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-1900/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2000/README.md b/checkpoint-2000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2000/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2000/adapter_config.json b/checkpoint-2000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2000/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2000/adapter_model.safetensors b/checkpoint-2000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4efb5ae001e36995c902ead43360947bcc01f8b6
--- /dev/null
+++ b/checkpoint-2000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61dffdddb07d3d60c10248d0fe8bf0a7a7118a9ea8731dd54853d710a2ccb5bb
+size 161533192
diff --git a/checkpoint-2000/chat_template.jinja b/checkpoint-2000/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2000/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/checkpoint-2000/optimizer.pt b/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..37b9b69a50c92e400498fff37744171fa2f1f810
--- /dev/null
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe73996bdada82e63f16094c394fc85e5fd76027e10d9484b6dde3fc357d5d19
+size 82465012
diff --git a/checkpoint-2000/rng_state.pth b/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..15d9a164ac2d082e781456a3b040d1280475e4ae
--- /dev/null
+++ b/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fd09a032ea79ea1c39cc20a064da328c30feb62d50e8aaadd13a75ae9899fe
+size 14308
diff --git a/checkpoint-2000/scheduler.pt b/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b1117fd8f04dec8e438de6f782372a824bf4fba7
--- /dev/null
+++ b/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda8f59d9dd4069d1c9ecbca167878db520c63382fbed15e2df9a776c940a66e
+size 1064
diff --git a/checkpoint-2000/tokenizer.json b/checkpoint-2000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2000/tokenizer_config.json b/checkpoint-2000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2000/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2000/trainer_state.json b/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..54a65a4de1e3645b53acbfa7cbdcb71ce5979eb1
--- /dev/null
+++ b/checkpoint-2000/trainer_state.json
@@ -0,0 +1,1594 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.378346222486615,
+  "eval_steps": 100,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2250401371531366e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2000/training_args.bin b/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2100/README.md b/checkpoint-2100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2100/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2100/adapter_config.json b/checkpoint-2100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2100/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2100/adapter_model.safetensors b/checkpoint-2100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6d7b4dd3a86b6b622fb44afd94969f7ec2161c4f
--- /dev/null
+++ b/checkpoint-2100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e2d01dc53a9f5a4ee7b93f9138fd573781571a4b85857e992a7cc35374718f
+size 161533192
diff --git a/checkpoint-2100/chat_template.jinja b/checkpoint-2100/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2100/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/checkpoint-2100/optimizer.pt b/checkpoint-2100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0c51a24ee603a88216090f319d6f12ce5383442b
--- /dev/null
+++ b/checkpoint-2100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44baf4a3d1b57da79fd9413f3adf58a633a0e0462986508fcf2388d9d83e68cc
+size 82465012
diff --git a/checkpoint-2100/rng_state.pth b/checkpoint-2100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6cb26f942197a8c46a850bce9f9be445511b4e57
--- /dev/null
+++ b/checkpoint-2100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c51a801d522120fd29ec6010dde5169ee3280ade08ae5397943dee4695a49f1
+size 14308
diff --git a/checkpoint-2100/scheduler.pt b/checkpoint-2100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3fa2f9da9e9e1c02c374d9ca8c43577ce4e66e76
--- /dev/null
+++ b/checkpoint-2100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd8c7af8b476e17a3d8138177e7402bf7b7a0da7caca0756173bed5c7bd9297
+size 1064
diff --git a/checkpoint-2100/tokenizer.json b/checkpoint-2100/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2100/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2100/tokenizer_config.json b/checkpoint-2100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2100/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2100/trainer_state.json b/checkpoint-2100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..68476bfa9e08a65bd4b0e31908fade2b084f752f
--- /dev/null
+++ b/checkpoint-2100/trainer_state.json
@@ -0,0 +1,1672 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.497323022010708,
+  "eval_steps": 100,
+  "global_step": 2100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 1.551915168762207,
+      "learning_rate": 4.1568944601698346e-05,
+      "loss": 0.06869585514068603,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4021415823914336,
+      "grad_norm": 0.6017701625823975,
+      "learning_rate": 4.0760210270926e-05,
+      "loss": 0.05127396583557129,
+      "step": 2020
+    },
+    {
+      "epoch": 2.414039262343843,
+      "grad_norm": 1.9110032320022583,
+      "learning_rate": 3.995147594015366e-05,
+      "loss": 0.08966401219367981,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4259369422962522,
+      "grad_norm": 1.0562331676483154,
+      "learning_rate": 3.9142741609381326e-05,
+      "loss": 0.0738204300403595,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4378346222486615,
+      "grad_norm": 1.9895752668380737,
+      "learning_rate": 3.833400727860898e-05,
+      "loss": 0.08233752250671386,
+      "step": 2050
+    },
+    {
+      "epoch": 2.449732302201071,
+      "grad_norm": 0.5100411176681519,
+      "learning_rate": 3.752527294783664e-05,
+      "loss": 0.052586525678634644,
+      "step": 2060
+    },
+    {
+      "epoch": 2.46162998215348,
+      "grad_norm": 0.27714085578918457,
+      "learning_rate": 3.671653861706429e-05,
+      "loss": 0.044759953022003175,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4735276621058895,
+      "grad_norm": 0.4177452027797699,
+      "learning_rate": 3.590780428629196e-05,
+      "loss": 0.056336909532547,
+      "step": 2080
+    },
+    {
+      "epoch": 2.485425342058299,
+      "grad_norm": 1.0737571716308594,
+      "learning_rate": 3.509906995551961e-05,
+      "loss": 0.03993419706821442,
+      "step": 2090
+    },
+    {
+      "epoch": 2.497323022010708,
+      "grad_norm": 0.2551257312297821,
+      "learning_rate": 3.429033562474727e-05,
+      "loss": 0.06233363747596741,
+      "step": 2100
+    },
+    {
+      "epoch": 2.497323022010708,
+      "eval_loss": 0.7822292447090149,
+      "eval_runtime": 151.9581,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 1.198,
+      "step": 2100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2873841999724052e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2100/training_args.bin b/checkpoint-2100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2200/README.md b/checkpoint-2200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2200/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2200/adapter_config.json b/checkpoint-2200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2200/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2200/adapter_model.safetensors b/checkpoint-2200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f71aa746c6b19f63e96a213bb7506aaee73c1769
--- /dev/null
+++ b/checkpoint-2200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870a4bf0b4ed15606ec0de7bad15f442f6be3b8ba868bd0c51731c94f7e20fcc
+size 161533192
diff --git a/checkpoint-2200/chat_template.jinja b/checkpoint-2200/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2200/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/checkpoint-2200/optimizer.pt b/checkpoint-2200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..39ef10489a794c832d851ba8fffbd64a4cb2d195
--- /dev/null
+++ b/checkpoint-2200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55bb1a9403db00375fe0a5ac974f8a2fdc20592a923cbb15c4493b14cc36a47
+size 82465012
diff --git a/checkpoint-2200/rng_state.pth b/checkpoint-2200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..476aea5c4dcd19d3e6c656da09e25084ad8627db
--- /dev/null
+++ b/checkpoint-2200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbafc7ad4640cd73875486f873375eccedc4c0702851bd98ca9d56e06031af2
+size 14308
diff --git a/checkpoint-2200/scheduler.pt b/checkpoint-2200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61f737836a238c8aae351af42ed634035d7af298
--- /dev/null
+++ b/checkpoint-2200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8030e9a17487fdf2460fd47cfd927148668003bda6463b2f3a0a1b5cbe30ce5f
+size 1064
diff --git a/checkpoint-2200/tokenizer.json b/checkpoint-2200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2200/tokenizer_config.json b/checkpoint-2200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2200/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2200/trainer_state.json b/checkpoint-2200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..69b2a7122913a7b4fa174346f5b0c4da721d5ebe
--- /dev/null
+++ b/checkpoint-2200/trainer_state.json
@@ -0,0 +1,1750 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.616299821534801,
+  "eval_steps": 100,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 1.551915168762207,
+      "learning_rate": 4.1568944601698346e-05,
+      "loss": 0.06869585514068603,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4021415823914336,
+      "grad_norm": 0.6017701625823975,
+      "learning_rate": 4.0760210270926e-05,
+      "loss": 0.05127396583557129,
+      "step": 2020
+    },
+    {
+      "epoch": 2.414039262343843,
+      "grad_norm": 1.9110032320022583,
+      "learning_rate": 3.995147594015366e-05,
+      "loss": 0.08966401219367981,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4259369422962522,
+      "grad_norm": 1.0562331676483154,
+      "learning_rate": 3.9142741609381326e-05,
+      "loss": 0.0738204300403595,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4378346222486615,
+      "grad_norm": 1.9895752668380737,
+      "learning_rate": 3.833400727860898e-05,
+      "loss": 0.08233752250671386,
+      "step": 2050
+    },
+    {
+      "epoch": 2.449732302201071,
+      "grad_norm": 0.5100411176681519,
+      "learning_rate": 3.752527294783664e-05,
+      "loss": 0.052586525678634644,
+      "step": 2060
+    },
+    {
+      "epoch": 2.46162998215348,
+      "grad_norm": 0.27714085578918457,
+      "learning_rate": 3.671653861706429e-05,
+      "loss": 0.044759953022003175,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4735276621058895,
+      "grad_norm": 0.4177452027797699,
+      "learning_rate": 3.590780428629196e-05,
+      "loss": 0.056336909532547,
+      "step": 2080
+    },
+    {
+      "epoch": 2.485425342058299,
+      "grad_norm": 1.0737571716308594,
+      "learning_rate": 3.509906995551961e-05,
+      "loss": 0.03993419706821442,
+      "step": 2090
+    },
+    {
+      "epoch": 2.497323022010708,
+      "grad_norm": 0.2551257312297821,
+      "learning_rate": 3.429033562474727e-05,
+      "loss": 0.06233363747596741,
+      "step": 2100
+    },
+    {
+      "epoch": 2.497323022010708,
+      "eval_loss": 0.7822292447090149,
+      "eval_runtime": 151.9581,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 1.198,
+      "step": 2100
+    },
+    {
+      "epoch": 2.509220701963117,
+      "grad_norm": 0.9730778336524963,
+      "learning_rate": 3.348160129397493e-05,
+      "loss": 0.07784021496772767,
+      "step": 2110
+    },
+    {
+      "epoch": 2.5211183819155263,
+      "grad_norm": 1.0517960786819458,
+      "learning_rate": 3.267286696320259e-05,
+      "loss": 0.07937353253364562,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5330160618679356,
+      "grad_norm": 2.1930930614471436,
+      "learning_rate": 3.186413263243025e-05,
+      "loss": 0.07288457751274109,
+      "step": 2130
+    },
+    {
+      "epoch": 2.544913741820345,
+      "grad_norm": 1.1975257396697998,
+      "learning_rate": 3.1055398301657905e-05,
+      "loss": 0.06836378574371338,
+      "step": 2140
+    },
+    {
+      "epoch": 2.5568114217727542,
+      "grad_norm": 0.8291498422622681,
+      "learning_rate": 3.0246663970885564e-05,
+      "loss": 0.064986652135849,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5687091017251635,
+      "grad_norm": 0.6288985013961792,
+      "learning_rate": 2.9437929640113228e-05,
+      "loss": 0.06470431685447693,
+      "step": 2160
+    },
+    {
+      "epoch": 2.580606781677573,
+      "grad_norm": 0.3969435691833496,
+      "learning_rate": 2.8629195309340884e-05,
+      "loss": 0.04360280632972717,
+      "step": 2170
+    },
+    {
+      "epoch": 2.592504461629982,
+      "grad_norm": 0.8388019800186157,
+      "learning_rate": 2.782046097856854e-05,
+      "loss": 0.06012804508209228,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6044021415823915,
+      "grad_norm": 0.5081242322921753,
+      "learning_rate": 2.7011726647796197e-05,
+      "loss": 0.07594415545463562,
+      "step": 2190
+    },
+    {
+      "epoch": 2.616299821534801,
+      "grad_norm": 0.30208897590637207,
+      "learning_rate": 2.620299231702386e-05,
+      "loss": 0.05154580473899841,
+      "step": 2200
+    },
+    {
+      "epoch": 2.616299821534801,
+      "eval_loss": 0.7940844297409058,
+      "eval_runtime": 149.9653,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 1.214,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3473797590175355e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2200/training_args.bin b/checkpoint-2200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2300/README.md b/checkpoint-2300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2300/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2300/adapter_config.json b/checkpoint-2300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2300/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2300/adapter_model.safetensors b/checkpoint-2300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f53aa1c6e38e4f00b89c2ece91caba8cd5b034e6
--- /dev/null
+++ b/checkpoint-2300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea43778c15d256a935281a828e8595654ba8519a21102f16d7dd4d1497d79e3
+size 161533192
diff --git a/checkpoint-2300/chat_template.jinja b/checkpoint-2300/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2300/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/checkpoint-2300/optimizer.pt b/checkpoint-2300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d8634863ff02ccd7052f84a8d70c245d791b49e5
--- /dev/null
+++ b/checkpoint-2300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fe340632ebb6d38638f6c4e7c9dcf9c712719b12911a253bba1726c754ce4e
+size 82465012
diff --git a/checkpoint-2300/rng_state.pth b/checkpoint-2300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..44d04be111d15a56972d1447f48804e6aa3e406c
--- /dev/null
+++ b/checkpoint-2300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a1908065356b61ddbb4c4ae050c3cfdd373feb7fb0d21003ecdbc23268a24f
+size 14308
diff --git a/checkpoint-2300/scheduler.pt b/checkpoint-2300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..83d500b26a8b29e71c5a1579b7b5ce18cea6889e
--- /dev/null
+++ b/checkpoint-2300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947cbdee57b548e9d5bd5727650611c0ba67850bbcc93bc0aefdf15033bbd7be
+size 1064
diff --git a/checkpoint-2300/tokenizer.json b/checkpoint-2300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2300/tokenizer_config.json b/checkpoint-2300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2300/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2300/trainer_state.json b/checkpoint-2300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..beae6087eeb6f08897a953322f2258ea51df2298
--- /dev/null
+++ b/checkpoint-2300/trainer_state.json
@@ -0,0 +1,1828 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.7352766210588935,
+  "eval_steps": 100,
+  "global_step": 2300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 1.551915168762207,
+      "learning_rate": 4.1568944601698346e-05,
+      "loss": 0.06869585514068603,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4021415823914336,
+      "grad_norm": 0.6017701625823975,
+      "learning_rate": 4.0760210270926e-05,
+      "loss": 0.05127396583557129,
+      "step": 2020
+    },
+    {
+      "epoch": 2.414039262343843,
+      "grad_norm": 1.9110032320022583,
+      "learning_rate": 3.995147594015366e-05,
+      "loss": 0.08966401219367981,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4259369422962522,
+      "grad_norm": 1.0562331676483154,
+      "learning_rate": 3.9142741609381326e-05,
+      "loss": 0.0738204300403595,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4378346222486615,
+      "grad_norm": 1.9895752668380737,
+      "learning_rate": 3.833400727860898e-05,
+      "loss": 0.08233752250671386,
+      "step": 2050
+    },
+    {
+      "epoch": 2.449732302201071,
+      "grad_norm": 0.5100411176681519,
+      "learning_rate": 3.752527294783664e-05,
+      "loss": 0.052586525678634644,
+      "step": 2060
+    },
+    {
+      "epoch": 2.46162998215348,
+      "grad_norm": 0.27714085578918457,
+      "learning_rate": 3.671653861706429e-05,
+      "loss": 0.044759953022003175,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4735276621058895,
+      "grad_norm": 0.4177452027797699,
+      "learning_rate": 3.590780428629196e-05,
+      "loss": 0.056336909532547,
+      "step": 2080
+    },
+    {
+      "epoch": 2.485425342058299,
+      "grad_norm": 1.0737571716308594,
+      "learning_rate": 3.509906995551961e-05,
+      "loss": 0.03993419706821442,
+      "step": 2090
+    },
+    {
+      "epoch": 2.497323022010708,
+      "grad_norm": 0.2551257312297821,
+      "learning_rate": 3.429033562474727e-05,
+      "loss": 0.06233363747596741,
+      "step": 2100
+    },
+    {
+      "epoch": 2.497323022010708,
+      "eval_loss": 0.7822292447090149,
+      "eval_runtime": 151.9581,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 1.198,
+      "step": 2100
+    },
+    {
+      "epoch": 2.509220701963117,
+      "grad_norm": 0.9730778336524963,
+      "learning_rate": 3.348160129397493e-05,
+      "loss": 0.07784021496772767,
+      "step": 2110
+    },
+    {
+      "epoch": 2.5211183819155263,
+      "grad_norm": 1.0517960786819458,
+      "learning_rate": 3.267286696320259e-05,
+      "loss": 0.07937353253364562,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5330160618679356,
+      "grad_norm": 2.1930930614471436,
+      "learning_rate": 3.186413263243025e-05,
+      "loss": 0.07288457751274109,
+      "step": 2130
+    },
+    {
+      "epoch": 2.544913741820345,
+      "grad_norm": 1.1975257396697998,
+      "learning_rate": 3.1055398301657905e-05,
+      "loss": 0.06836378574371338,
+      "step": 2140
+    },
+    {
+      "epoch": 2.5568114217727542,
+      "grad_norm": 0.8291498422622681,
+      "learning_rate": 3.0246663970885564e-05,
+      "loss": 0.064986652135849,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5687091017251635,
+      "grad_norm": 0.6288985013961792,
+      "learning_rate": 2.9437929640113228e-05,
+      "loss": 0.06470431685447693,
+      "step": 2160
+    },
+    {
+      "epoch": 2.580606781677573,
+      "grad_norm": 0.3969435691833496,
+      "learning_rate": 2.8629195309340884e-05,
+      "loss": 0.04360280632972717,
+      "step": 2170
+    },
+    {
+      "epoch": 2.592504461629982,
+      "grad_norm": 0.8388019800186157,
+      "learning_rate": 2.782046097856854e-05,
+      "loss": 0.06012804508209228,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6044021415823915,
+      "grad_norm": 0.5081242322921753,
+      "learning_rate": 2.7011726647796197e-05,
+      "loss": 0.07594415545463562,
+      "step": 2190
+    },
+    {
+      "epoch": 2.616299821534801,
+      "grad_norm": 0.30208897590637207,
+      "learning_rate": 2.620299231702386e-05,
+      "loss": 0.05154580473899841,
+      "step": 2200
+    },
+    {
+      "epoch": 2.616299821534801,
+      "eval_loss": 0.7940844297409058,
+      "eval_runtime": 149.9653,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 1.214,
+      "step": 2200
+    },
+    {
+      "epoch": 2.62819750148721,
+      "grad_norm": 0.521649181842804,
+      "learning_rate": 2.5394257986251517e-05,
+      "loss": 0.04323629140853882,
+      "step": 2210
+    },
+    {
+      "epoch": 2.6400951814396194,
+      "grad_norm": 2.6473941802978516,
+      "learning_rate": 2.4585523655479177e-05,
+      "loss": 0.10532597303390503,
+      "step": 2220
+    },
+    {
+      "epoch": 2.6519928613920287,
+      "grad_norm": 0.6955065727233887,
+      "learning_rate": 2.3776789324706837e-05,
+      "loss": 0.04693872630596161,
+      "step": 2230
+    },
+    {
+      "epoch": 2.663890541344438,
+      "grad_norm": 0.6439285278320312,
+      "learning_rate": 2.2968054993934493e-05,
+      "loss": 0.07398720383644104,
+      "step": 2240
+    },
+    {
+      "epoch": 2.6757882212968473,
+      "grad_norm": 0.6171683073043823,
+      "learning_rate": 2.2159320663162153e-05,
+      "loss": 0.08055143356323242,
+      "step": 2250
+    },
+    {
+      "epoch": 2.6876859012492567,
+      "grad_norm": 1.594099998474121,
+      "learning_rate": 2.135058633238981e-05,
+      "loss": 0.06038923859596253,
+      "step": 2260
+    },
+    {
+      "epoch": 2.6995835812016655,
+      "grad_norm": 0.5130852460861206,
+      "learning_rate": 2.054185200161747e-05,
+      "loss": 0.09171404242515564,
+      "step": 2270
+    },
+    {
+      "epoch": 2.711481261154075,
+      "grad_norm": 0.5048943161964417,
+      "learning_rate": 1.9733117670845126e-05,
+      "loss": 0.04560606479644776,
+      "step": 2280
+    },
+    {
+      "epoch": 2.723378941106484,
+      "grad_norm": 1.691913366317749,
+      "learning_rate": 1.8924383340072786e-05,
+      "loss": 0.08174195885658264,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "grad_norm": 2.5807952880859375,
+      "learning_rate": 1.8115649009300446e-05,
+      "loss": 0.07424867749214173,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "eval_loss": 0.7955667972564697,
+      "eval_runtime": 151.7304,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 1.199,
+      "step": 2300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.407698896520319e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2300/training_args.bin b/checkpoint-2300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2400/README.md b/checkpoint-2400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2400/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2400/adapter_config.json b/checkpoint-2400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2400/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2400/adapter_model.safetensors b/checkpoint-2400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d8c4ec29c5c91acc35758309b053a8aebcf3453
--- /dev/null
+++ b/checkpoint-2400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5039f72983e862ce927fa983fa632f8048e87e7b43afe258bedc9ff003f6194c
+size 161533192
diff --git a/checkpoint-2400/chat_template.jinja b/checkpoint-2400/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2400/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/checkpoint-2400/optimizer.pt b/checkpoint-2400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..64a52a917a84f65c7e418e3a6489aaad49b46b71
--- /dev/null
+++ b/checkpoint-2400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6ece13a8a692bdaf94f6db9b9bd7b712f372ddd9128c18d49a890574d18c8e
+size 82465012
diff --git a/checkpoint-2400/rng_state.pth b/checkpoint-2400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4d4ee0b52fe9b7bc93a76da1da90a410d8c67249
--- /dev/null
+++ b/checkpoint-2400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f889447933265aff66878ab554cfd961384ddaf03b982b519c703e5229c101a1
+size 14308
diff --git a/checkpoint-2400/scheduler.pt b/checkpoint-2400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dff0df734733feadae37dc92ef1abaca0eed6357
--- /dev/null
+++ b/checkpoint-2400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bf59a9482eccd230b7e6714caa4e7e8319a3be0ccd77223c8ea41440ed9f8c5
+size 1064
diff --git a/checkpoint-2400/tokenizer.json b/checkpoint-2400/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2400/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2400/tokenizer_config.json b/checkpoint-2400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2400/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2400/trainer_state.json b/checkpoint-2400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f24eadc9af2411ec0a4d63603611fc71516d1afb
--- /dev/null
+++ b/checkpoint-2400/trainer_state.json
@@ -0,0 +1,1906 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.854253420582986,
+  "eval_steps": 100,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 1.551915168762207,
+      "learning_rate": 4.1568944601698346e-05,
+      "loss": 0.06869585514068603,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4021415823914336,
+      "grad_norm": 0.6017701625823975,
+      "learning_rate": 4.0760210270926e-05,
+      "loss": 0.05127396583557129,
+      "step": 2020
+    },
+    {
+      "epoch": 2.414039262343843,
+      "grad_norm": 1.9110032320022583,
+      "learning_rate": 3.995147594015366e-05,
+      "loss": 0.08966401219367981,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4259369422962522,
+      "grad_norm": 1.0562331676483154,
+      "learning_rate": 3.9142741609381326e-05,
+      "loss": 0.0738204300403595,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4378346222486615,
+      "grad_norm": 1.9895752668380737,
+      "learning_rate": 3.833400727860898e-05,
+      "loss": 0.08233752250671386,
+      "step": 2050
+    },
+    {
+      "epoch": 2.449732302201071,
+      "grad_norm": 0.5100411176681519,
+      "learning_rate": 3.752527294783664e-05,
+      "loss": 0.052586525678634644,
+      "step": 2060
+    },
+    {
+      "epoch": 2.46162998215348,
+      "grad_norm": 0.27714085578918457,
+      "learning_rate": 3.671653861706429e-05,
+      "loss": 0.044759953022003175,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4735276621058895,
+      "grad_norm": 0.4177452027797699,
+      "learning_rate": 3.590780428629196e-05,
+      "loss": 0.056336909532547,
+      "step": 2080
+    },
+    {
+      "epoch": 2.485425342058299,
+      "grad_norm": 1.0737571716308594,
+      "learning_rate": 3.509906995551961e-05,
+      "loss": 0.03993419706821442,
+      "step": 2090
+    },
+    {
+      "epoch": 2.497323022010708,
+      "grad_norm": 0.2551257312297821,
+      "learning_rate": 3.429033562474727e-05,
+      "loss": 0.06233363747596741,
+      "step": 2100
+    },
+    {
+      "epoch": 2.497323022010708,
+      "eval_loss": 0.7822292447090149,
+      "eval_runtime": 151.9581,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 1.198,
+      "step": 2100
+    },
+    {
+      "epoch": 2.509220701963117,
+      "grad_norm": 0.9730778336524963,
+      "learning_rate": 3.348160129397493e-05,
+      "loss": 0.07784021496772767,
+      "step": 2110
+    },
+    {
+      "epoch": 2.5211183819155263,
+      "grad_norm": 1.0517960786819458,
+      "learning_rate": 3.267286696320259e-05,
+      "loss": 0.07937353253364562,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5330160618679356,
+      "grad_norm": 2.1930930614471436,
+      "learning_rate": 3.186413263243025e-05,
+      "loss": 0.07288457751274109,
+      "step": 2130
+    },
+    {
+      "epoch": 2.544913741820345,
+      "grad_norm": 1.1975257396697998,
+      "learning_rate": 3.1055398301657905e-05,
+      "loss": 0.06836378574371338,
+      "step": 2140
+    },
+    {
+      "epoch": 2.5568114217727542,
+      "grad_norm": 0.8291498422622681,
+      "learning_rate": 3.0246663970885564e-05,
+      "loss": 0.064986652135849,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5687091017251635,
+      "grad_norm": 0.6288985013961792,
+      "learning_rate": 2.9437929640113228e-05,
+      "loss": 0.06470431685447693,
+      "step": 2160
+    },
+    {
+      "epoch": 2.580606781677573,
+      "grad_norm": 0.3969435691833496,
+      "learning_rate": 2.8629195309340884e-05,
+      "loss": 0.04360280632972717,
+      "step": 2170
+    },
+    {
+      "epoch": 2.592504461629982,
+      "grad_norm": 0.8388019800186157,
+      "learning_rate": 2.782046097856854e-05,
+      "loss": 0.06012804508209228,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6044021415823915,
+      "grad_norm": 0.5081242322921753,
+      "learning_rate": 2.7011726647796197e-05,
+      "loss": 0.07594415545463562,
+      "step": 2190
+    },
+    {
+      "epoch": 2.616299821534801,
+      "grad_norm": 0.30208897590637207,
+      "learning_rate": 2.620299231702386e-05,
+      "loss": 0.05154580473899841,
+      "step": 2200
+    },
+    {
+      "epoch": 2.616299821534801,
+      "eval_loss": 0.7940844297409058,
+      "eval_runtime": 149.9653,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 1.214,
+      "step": 2200
+    },
+    {
+      "epoch": 2.62819750148721,
+      "grad_norm": 0.521649181842804,
+      "learning_rate": 2.5394257986251517e-05,
+      "loss": 0.04323629140853882,
+      "step": 2210
+    },
+    {
+      "epoch": 2.6400951814396194,
+      "grad_norm": 2.6473941802978516,
+      "learning_rate": 2.4585523655479177e-05,
+      "loss": 0.10532597303390503,
+      "step": 2220
+    },
+    {
+      "epoch": 2.6519928613920287,
+      "grad_norm": 0.6955065727233887,
+      "learning_rate": 2.3776789324706837e-05,
+      "loss": 0.04693872630596161,
+      "step": 2230
+    },
+    {
+      "epoch": 2.663890541344438,
+      "grad_norm": 0.6439285278320312,
+      "learning_rate": 2.2968054993934493e-05,
+      "loss": 0.07398720383644104,
+      "step": 2240
+    },
+    {
+      "epoch": 2.6757882212968473,
+      "grad_norm": 0.6171683073043823,
+      "learning_rate": 2.2159320663162153e-05,
+      "loss": 0.08055143356323242,
+      "step": 2250
+    },
+    {
+      "epoch": 2.6876859012492567,
+      "grad_norm": 1.594099998474121,
+      "learning_rate": 2.135058633238981e-05,
+      "loss": 0.06038923859596253,
+      "step": 2260
+    },
+    {
+      "epoch": 2.6995835812016655,
+      "grad_norm": 0.5130852460861206,
+      "learning_rate": 2.054185200161747e-05,
+      "loss": 0.09171404242515564,
+      "step": 2270
+    },
+    {
+      "epoch": 2.711481261154075,
+      "grad_norm": 0.5048943161964417,
+      "learning_rate": 1.9733117670845126e-05,
+      "loss": 0.04560606479644776,
+      "step": 2280
+    },
+    {
+      "epoch": 2.723378941106484,
+      "grad_norm": 1.691913366317749,
+      "learning_rate": 1.8924383340072786e-05,
+      "loss": 0.08174195885658264,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "grad_norm": 2.5807952880859375,
+      "learning_rate": 1.8115649009300446e-05,
+      "loss": 0.07424867749214173,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "eval_loss": 0.7955667972564697,
+      "eval_runtime": 151.7304,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 1.199,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7471743010113028,
+      "grad_norm": 1.0159227848052979,
+      "learning_rate": 1.7306914678528106e-05,
+      "loss": 0.041696679592132566,
+      "step": 2310
+    },
+    {
+      "epoch": 2.759071980963712,
+      "grad_norm": 0.6436373591423035,
+      "learning_rate": 1.6498180347755762e-05,
+      "loss": 0.06923379898071289,
+      "step": 2320
+    },
+    {
+      "epoch": 2.7709696609161214,
+      "grad_norm": 2.703979015350342,
+      "learning_rate": 1.5689446016983422e-05,
+      "loss": 0.09573553800582886,
+      "step": 2330
+    },
+    {
+      "epoch": 2.7828673408685307,
+      "grad_norm": 1.3062081336975098,
+      "learning_rate": 1.4880711686211079e-05,
+      "loss": 0.07745556235313415,
+      "step": 2340
+    },
+    {
+      "epoch": 2.79476502082094,
+      "grad_norm": 0.4865114092826843,
+      "learning_rate": 1.407197735543874e-05,
+      "loss": 0.04722094833850861,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8066627007733493,
+      "grad_norm": 2.370136260986328,
+      "learning_rate": 1.3263243024666397e-05,
+      "loss": 0.06862221956253052,
+      "step": 2360
+    },
+    {
+      "epoch": 2.818560380725758,
+      "grad_norm": 2.503732681274414,
+      "learning_rate": 1.2454508693894057e-05,
+      "loss": 0.06837759017944336,
+      "step": 2370
+    },
+    {
+      "epoch": 2.8304580606781675,
+      "grad_norm": 0.30941763520240784,
+      "learning_rate": 1.1645774363121715e-05,
+      "loss": 0.03794792294502258,
+      "step": 2380
+    },
+    {
+      "epoch": 2.842355740630577,
+      "grad_norm": 0.39067885279655457,
+      "learning_rate": 1.0837040032349375e-05,
+      "loss": 0.05413181185722351,
+      "step": 2390
+    },
+    {
+      "epoch": 2.854253420582986,
+      "grad_norm": 2.7522947788238525,
+      "learning_rate": 1.0028305701577033e-05,
+      "loss": 0.05264478325843811,
+      "step": 2400
+    },
+    {
+      "epoch": 2.854253420582986,
+      "eval_loss": 0.7887478470802307,
+      "eval_runtime": 149.3367,
+      "eval_samples_per_second": 4.868,
+      "eval_steps_per_second": 1.219,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.469336496773419e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2400/training_args.bin b/checkpoint-2400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2500/README.md b/checkpoint-2500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2500/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2500/adapter_config.json b/checkpoint-2500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2500/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2500/adapter_model.safetensors b/checkpoint-2500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d894f87ec1c4f1ee8adb3250b17d7dd61e3fe6ab
--- /dev/null
+++ b/checkpoint-2500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51da822505ddb04e66d2eae6b4eedda397aabe878c9c3a48b63ef4c6454dbd2
+size 161533192
diff --git a/checkpoint-2500/chat_template.jinja b/checkpoint-2500/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2500/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/checkpoint-2500/optimizer.pt b/checkpoint-2500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2fa28dd3b402d96f6d5dd6fecbb1021b2875aec7
--- /dev/null
+++ b/checkpoint-2500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12883b3f533931bb7031f366bb67196379b2db562f9177603aa88417dd5c7b14
+size 82465012
diff --git a/checkpoint-2500/rng_state.pth b/checkpoint-2500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..69d71aac46d8722eb58d888b3b306e930aff9582
--- /dev/null
+++ b/checkpoint-2500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99c85fc191214df714c609eb8f0e22058b3fddf90835470732d5f45ecb6f7e5
+size 14308
diff --git a/checkpoint-2500/scheduler.pt b/checkpoint-2500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..248d4a28fdbcfe9d67c513ffcd65b906fce2e1a3
--- /dev/null
+++ b/checkpoint-2500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad24d2312e20fe33d92c62773f3fcf7d479548f73e9f95063fea71e0ff0ee1f
+size 1064
diff --git a/checkpoint-2500/tokenizer.json b/checkpoint-2500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2500/tokenizer_config.json b/checkpoint-2500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2500/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2500/trainer_state.json b/checkpoint-2500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..448e6ec39a689db05a906b6549cb11712ed869cd
--- /dev/null
+++ b/checkpoint-2500/trainer_state.json
@@ -0,0 +1,1984 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 2.9732302201070793,
+  "eval_steps": 100,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 1.551915168762207,
+      "learning_rate": 4.1568944601698346e-05,
+      "loss": 0.06869585514068603,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4021415823914336,
+      "grad_norm": 0.6017701625823975,
+      "learning_rate": 4.0760210270926e-05,
+      "loss": 0.05127396583557129,
+      "step": 2020
+    },
+    {
+      "epoch": 2.414039262343843,
+      "grad_norm": 1.9110032320022583,
+      "learning_rate": 3.995147594015366e-05,
+      "loss": 0.08966401219367981,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4259369422962522,
+      "grad_norm": 1.0562331676483154,
+      "learning_rate": 3.9142741609381326e-05,
+      "loss": 0.0738204300403595,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4378346222486615,
+      "grad_norm": 1.9895752668380737,
+      "learning_rate": 3.833400727860898e-05,
+      "loss": 0.08233752250671386,
+      "step": 2050
+    },
+    {
+      "epoch": 2.449732302201071,
+      "grad_norm": 0.5100411176681519,
+      "learning_rate": 3.752527294783664e-05,
+      "loss": 0.052586525678634644,
+      "step": 2060
+    },
+    {
+      "epoch": 2.46162998215348,
+      "grad_norm": 0.27714085578918457,
+      "learning_rate": 3.671653861706429e-05,
+      "loss": 0.044759953022003175,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4735276621058895,
+      "grad_norm": 0.4177452027797699,
+      "learning_rate": 3.590780428629196e-05,
+      "loss": 0.056336909532547,
+      "step": 2080
+    },
+    {
+      "epoch": 2.485425342058299,
+      "grad_norm": 1.0737571716308594,
+      "learning_rate": 3.509906995551961e-05,
+      "loss": 0.03993419706821442,
+      "step": 2090
+    },
+    {
+      "epoch": 2.497323022010708,
+      "grad_norm": 0.2551257312297821,
+      "learning_rate": 3.429033562474727e-05,
+      "loss": 0.06233363747596741,
+      "step": 2100
+    },
+    {
+      "epoch": 2.497323022010708,
+      "eval_loss": 0.7822292447090149,
+      "eval_runtime": 151.9581,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 1.198,
+      "step": 2100
+    },
+    {
+      "epoch": 2.509220701963117,
+      "grad_norm": 0.9730778336524963,
+      "learning_rate": 3.348160129397493e-05,
+      "loss": 0.07784021496772767,
+      "step": 2110
+    },
+    {
+      "epoch": 2.5211183819155263,
+      "grad_norm": 1.0517960786819458,
+      "learning_rate": 3.267286696320259e-05,
+      "loss": 0.07937353253364562,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5330160618679356,
+      "grad_norm": 2.1930930614471436,
+      "learning_rate": 3.186413263243025e-05,
+      "loss": 0.07288457751274109,
+      "step": 2130
+    },
+    {
+      "epoch": 2.544913741820345,
+      "grad_norm": 1.1975257396697998,
+      "learning_rate": 3.1055398301657905e-05,
+      "loss": 0.06836378574371338,
+      "step": 2140
+    },
+    {
+      "epoch": 2.5568114217727542,
+      "grad_norm": 0.8291498422622681,
+      "learning_rate": 3.0246663970885564e-05,
+      "loss": 0.064986652135849,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5687091017251635,
+      "grad_norm": 0.6288985013961792,
+      "learning_rate": 2.9437929640113228e-05,
+      "loss": 0.06470431685447693,
+      "step": 2160
+    },
+    {
+      "epoch": 2.580606781677573,
+      "grad_norm": 0.3969435691833496,
+      "learning_rate": 2.8629195309340884e-05,
+      "loss": 0.04360280632972717,
+      "step": 2170
+    },
+    {
+      "epoch": 2.592504461629982,
+      "grad_norm": 0.8388019800186157,
+      "learning_rate": 2.782046097856854e-05,
+      "loss": 0.06012804508209228,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6044021415823915,
+      "grad_norm": 0.5081242322921753,
+      "learning_rate": 2.7011726647796197e-05,
+      "loss": 0.07594415545463562,
+      "step": 2190
+    },
+    {
+      "epoch": 2.616299821534801,
+      "grad_norm": 0.30208897590637207,
+      "learning_rate": 2.620299231702386e-05,
+      "loss": 0.05154580473899841,
+      "step": 2200
+    },
+    {
+      "epoch": 2.616299821534801,
+      "eval_loss": 0.7940844297409058,
+      "eval_runtime": 149.9653,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 1.214,
+      "step": 2200
+    },
+    {
+      "epoch": 2.62819750148721,
+      "grad_norm": 0.521649181842804,
+      "learning_rate": 2.5394257986251517e-05,
+      "loss": 0.04323629140853882,
+      "step": 2210
+    },
+    {
+      "epoch": 2.6400951814396194,
+      "grad_norm": 2.6473941802978516,
+      "learning_rate": 2.4585523655479177e-05,
+      "loss": 0.10532597303390503,
+      "step": 2220
+    },
+    {
+      "epoch": 2.6519928613920287,
+      "grad_norm": 0.6955065727233887,
+      "learning_rate": 2.3776789324706837e-05,
+      "loss": 0.04693872630596161,
+      "step": 2230
+    },
+    {
+      "epoch": 2.663890541344438,
+      "grad_norm": 0.6439285278320312,
+      "learning_rate": 2.2968054993934493e-05,
+      "loss": 0.07398720383644104,
+      "step": 2240
+    },
+    {
+      "epoch": 2.6757882212968473,
+      "grad_norm": 0.6171683073043823,
+      "learning_rate": 2.2159320663162153e-05,
+      "loss": 0.08055143356323242,
+      "step": 2250
+    },
+    {
+      "epoch": 2.6876859012492567,
+      "grad_norm": 1.594099998474121,
+      "learning_rate": 2.135058633238981e-05,
+      "loss": 0.06038923859596253,
+      "step": 2260
+    },
+    {
+      "epoch": 2.6995835812016655,
+      "grad_norm": 0.5130852460861206,
+      "learning_rate": 2.054185200161747e-05,
+      "loss": 0.09171404242515564,
+      "step": 2270
+    },
+    {
+      "epoch": 2.711481261154075,
+      "grad_norm": 0.5048943161964417,
+      "learning_rate": 1.9733117670845126e-05,
+      "loss": 0.04560606479644776,
+      "step": 2280
+    },
+    {
+      "epoch": 2.723378941106484,
+      "grad_norm": 1.691913366317749,
+      "learning_rate": 1.8924383340072786e-05,
+      "loss": 0.08174195885658264,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "grad_norm": 2.5807952880859375,
+      "learning_rate": 1.8115649009300446e-05,
+      "loss": 0.07424867749214173,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "eval_loss": 0.7955667972564697,
+      "eval_runtime": 151.7304,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 1.199,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7471743010113028,
+      "grad_norm": 1.0159227848052979,
+      "learning_rate": 1.7306914678528106e-05,
+      "loss": 0.041696679592132566,
+      "step": 2310
+    },
+    {
+      "epoch": 2.759071980963712,
+      "grad_norm": 0.6436373591423035,
+      "learning_rate": 1.6498180347755762e-05,
+      "loss": 0.06923379898071289,
+      "step": 2320
+    },
+    {
+      "epoch": 2.7709696609161214,
+      "grad_norm": 2.703979015350342,
+      "learning_rate": 1.5689446016983422e-05,
+      "loss": 0.09573553800582886,
+      "step": 2330
+    },
+    {
+      "epoch": 2.7828673408685307,
+      "grad_norm": 1.3062081336975098,
+      "learning_rate": 1.4880711686211079e-05,
+      "loss": 0.07745556235313415,
+      "step": 2340
+    },
+    {
+      "epoch": 2.79476502082094,
+      "grad_norm": 0.4865114092826843,
+      "learning_rate": 1.407197735543874e-05,
+      "loss": 0.04722094833850861,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8066627007733493,
+      "grad_norm": 2.370136260986328,
+      "learning_rate": 1.3263243024666397e-05,
+      "loss": 0.06862221956253052,
+      "step": 2360
+    },
+    {
+      "epoch": 2.818560380725758,
+      "grad_norm": 2.503732681274414,
+      "learning_rate": 1.2454508693894057e-05,
+      "loss": 0.06837759017944336,
+      "step": 2370
+    },
+    {
+      "epoch": 2.8304580606781675,
+      "grad_norm": 0.30941763520240784,
+      "learning_rate": 1.1645774363121715e-05,
+      "loss": 0.03794792294502258,
+      "step": 2380
+    },
+    {
+      "epoch": 2.842355740630577,
+      "grad_norm": 0.39067885279655457,
+      "learning_rate": 1.0837040032349375e-05,
+      "loss": 0.05413181185722351,
+      "step": 2390
+    },
+    {
+      "epoch": 2.854253420582986,
+      "grad_norm": 2.7522947788238525,
+      "learning_rate": 1.0028305701577033e-05,
+      "loss": 0.05264478325843811,
+      "step": 2400
+    },
+    {
+      "epoch": 2.854253420582986,
+      "eval_loss": 0.7887478470802307,
+      "eval_runtime": 149.3367,
+      "eval_samples_per_second": 4.868,
+      "eval_steps_per_second": 1.219,
+      "step": 2400
+    },
+    {
+      "epoch": 2.8661511005353955,
+      "grad_norm": 0.5051487684249878,
+      "learning_rate": 9.219571370804691e-06,
+      "loss": 0.07031412124633789,
+      "step": 2410
+    },
+    {
+      "epoch": 2.8780487804878048,
+      "grad_norm": 0.43260014057159424,
+      "learning_rate": 8.41083704003235e-06,
+      "loss": 0.08607797622680664,
+      "step": 2420
+    },
+    {
+      "epoch": 2.889946460440214,
+      "grad_norm": 1.787656545639038,
+      "learning_rate": 7.602102709260009e-06,
+      "loss": 0.06961020827293396,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9018441403926234,
+      "grad_norm": 0.5731585025787354,
+      "learning_rate": 6.793368378487668e-06,
+      "loss": 0.06185711026191711,
+      "step": 2440
+    },
+    {
+      "epoch": 2.9137418203450327,
+      "grad_norm": 2.8741965293884277,
+      "learning_rate": 5.984634047715326e-06,
+      "loss": 0.07431170344352722,
+      "step": 2450
+    },
+    {
+      "epoch": 2.925639500297442,
+      "grad_norm": 1.372190237045288,
+      "learning_rate": 5.175899716942984e-06,
+      "loss": 0.05746169686317444,
+      "step": 2460
+    },
+    {
+      "epoch": 2.9375371802498513,
+      "grad_norm": 1.294169545173645,
+      "learning_rate": 4.367165386170643e-06,
+      "loss": 0.07876025438308716,
+      "step": 2470
+    },
+    {
+      "epoch": 2.9494348602022606,
+      "grad_norm": 1.7027950286865234,
+      "learning_rate": 3.5584310553983014e-06,
+      "loss": 0.09096775650978088,
+      "step": 2480
+    },
+    {
+      "epoch": 2.96133254015467,
+      "grad_norm": 0.5540681481361389,
+      "learning_rate": 2.7496967246259604e-06,
+      "loss": 0.06888358592987061,
+      "step": 2490
+    },
+    {
+      "epoch": 2.9732302201070793,
+      "grad_norm": 2.2525739669799805,
+      "learning_rate": 1.940962393853619e-06,
+      "loss": 0.05039908289909363,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9732302201070793,
+      "eval_loss": 0.7935085892677307,
+      "eval_runtime": 154.2587,
+      "eval_samples_per_second": 4.713,
+      "eval_steps_per_second": 1.18,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5313679036146176e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2500/training_args.bin b/checkpoint-2500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-2523/README.md b/checkpoint-2523/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-2523/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-2523/adapter_config.json b/checkpoint-2523/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-2523/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-2523/adapter_model.safetensors b/checkpoint-2523/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0c8a229b1af206ee790f758c92b3ab4ba6e7fe1f
--- /dev/null
+++ b/checkpoint-2523/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc7970bd8ac387f95ff11769989e24b4f098ae56852281e050eada125305157
+size 161533192
diff --git a/checkpoint-2523/chat_template.jinja b/checkpoint-2523/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-2523/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/checkpoint-2523/optimizer.pt b/checkpoint-2523/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..21f184a24d818bb553428b72fe2f3cf6acceea76
--- /dev/null
+++ b/checkpoint-2523/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1fc90ade057ee017700d769f1c911dd8d220dd2c42555762c293ebdfd56e52b
+size 82465012
diff --git a/checkpoint-2523/rng_state.pth b/checkpoint-2523/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0605e02a2c8b0eabe9ce420d9ebce2b857d046f2
--- /dev/null
+++ b/checkpoint-2523/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91245035c18e37e42a073a4d6751911c0af5f779c51f893361a6293d6f086770
+size 14308
diff --git a/checkpoint-2523/scheduler.pt b/checkpoint-2523/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..575069f8d41d7742aad3646deaf39437fb97f140
--- /dev/null
+++ b/checkpoint-2523/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509b62c5c4e5a0f7840b6e8d46530810a4ce83c5bf608bdd844facd6d511e621
+size 1064
diff --git a/checkpoint-2523/tokenizer.json b/checkpoint-2523/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-2523/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-2523/tokenizer_config.json b/checkpoint-2523/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-2523/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2523/trainer_state.json b/checkpoint-2523/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4cb7e7f9955d2e41424dd8bec29714102eb8510
--- /dev/null
+++ b/checkpoint-2523/trainer_state.json
@@ -0,0 +1,2006 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 2523,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    },
+    {
+      "epoch": 0.9637120761451516,
+      "grad_norm": 0.4335337281227112,
+      "learning_rate": 0.00013861706429437931,
+      "loss": 0.36781046390533445,
+      "step": 810
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.3875080347061157,
+      "learning_rate": 0.00013780832996360695,
+      "loss": 0.491288423538208,
+      "step": 820
+    },
+    {
+      "epoch": 0.9875074360499703,
+      "grad_norm": 0.6576387286186218,
+      "learning_rate": 0.00013699959563283462,
+      "loss": 0.3506373643875122,
+      "step": 830
+    },
+    {
+      "epoch": 0.9994051160023796,
+      "grad_norm": 0.6819862127304077,
+      "learning_rate": 0.0001361908613020623,
+      "loss": 0.3644376277923584,
+      "step": 840
+    },
+    {
+      "epoch": 1.0107079119571682,
+      "grad_norm": 0.6187142729759216,
+      "learning_rate": 0.00013538212697128993,
+      "loss": 0.21315438747406007,
+      "step": 850
+    },
+    {
+      "epoch": 1.0226055919095776,
+      "grad_norm": 0.5705106854438782,
+      "learning_rate": 0.0001345733926405176,
+      "loss": 0.12631564140319823,
+      "step": 860
+    },
+    {
+      "epoch": 1.0345032718619869,
+      "grad_norm": 2.418121576309204,
+      "learning_rate": 0.00013376465830974526,
+      "loss": 0.2968762397766113,
+      "step": 870
+    },
+    {
+      "epoch": 1.0464009518143962,
+      "grad_norm": 1.7101433277130127,
+      "learning_rate": 0.00013295592397897293,
+      "loss": 0.24875276088714598,
+      "step": 880
+    },
+    {
+      "epoch": 1.0582986317668055,
+      "grad_norm": 0.7908554673194885,
+      "learning_rate": 0.00013214718964820057,
+      "loss": 0.12594165802001953,
+      "step": 890
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "grad_norm": 2.1652631759643555,
+      "learning_rate": 0.00013133845531742823,
+      "loss": 0.2673641681671143,
+      "step": 900
+    },
+    {
+      "epoch": 1.0701963117192148,
+      "eval_loss": 0.6557393670082092,
+      "eval_runtime": 148.1641,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 1.228,
+      "step": 900
+    },
+    {
+      "epoch": 1.0820939916716241,
+      "grad_norm": 2.1860005855560303,
+      "learning_rate": 0.00013052972098665587,
+      "loss": 0.25303189754486083,
+      "step": 910
+    },
+    {
+      "epoch": 1.0939916716240332,
+      "grad_norm": 2.427250385284424,
+      "learning_rate": 0.00012972098665588354,
+      "loss": 0.2357541799545288,
+      "step": 920
+    },
+    {
+      "epoch": 1.1058893515764425,
+      "grad_norm": 1.33892822265625,
+      "learning_rate": 0.0001289122523251112,
+      "loss": 0.16873008012771606,
+      "step": 930
+    },
+    {
+      "epoch": 1.1177870315288518,
+      "grad_norm": 2.110456705093384,
+      "learning_rate": 0.00012810351799433887,
+      "loss": 0.2664030075073242,
+      "step": 940
+    },
+    {
+      "epoch": 1.1296847114812612,
+      "grad_norm": 0.4718581736087799,
+      "learning_rate": 0.00012729478366356654,
+      "loss": 0.17133421897888185,
+      "step": 950
+    },
+    {
+      "epoch": 1.1415823914336705,
+      "grad_norm": 0.6589707136154175,
+      "learning_rate": 0.00012648604933279418,
+      "loss": 0.2367629051208496,
+      "step": 960
+    },
+    {
+      "epoch": 1.1534800713860798,
+      "grad_norm": 0.6303382515907288,
+      "learning_rate": 0.00012567731500202185,
+      "loss": 0.30923507213592527,
+      "step": 970
+    },
+    {
+      "epoch": 1.165377751338489,
+      "grad_norm": 1.6443407535552979,
+      "learning_rate": 0.00012486858067124948,
+      "loss": 0.23930892944335938,
+      "step": 980
+    },
+    {
+      "epoch": 1.1772754312908982,
+      "grad_norm": 2.7950127124786377,
+      "learning_rate": 0.00012405984634047715,
+      "loss": 0.24230880737304689,
+      "step": 990
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "grad_norm": 2.755117177963257,
+      "learning_rate": 0.00012325111200970482,
+      "loss": 0.2482537269592285,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1891731112433075,
+      "eval_loss": 0.6479437351226807,
+      "eval_runtime": 142.6808,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.276,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2010707911957168,
+      "grad_norm": 1.0761902332305908,
+      "learning_rate": 0.00012244237767893248,
+      "loss": 0.18213424682617188,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2129684711481261,
+      "grad_norm": 0.399354487657547,
+      "learning_rate": 0.00012163364334816014,
+      "loss": 0.2177332878112793,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2248661511005354,
+      "grad_norm": 0.5789953470230103,
+      "learning_rate": 0.00012082490901738779,
+      "loss": 0.2425436019897461,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2367638310529447,
+      "grad_norm": 1.1803412437438965,
+      "learning_rate": 0.00012001617468661546,
+      "loss": 0.23786463737487792,
+      "step": 1040
+    },
+    {
+      "epoch": 1.248661511005354,
+      "grad_norm": 2.5271270275115967,
+      "learning_rate": 0.0001192074403558431,
+      "loss": 0.23577113151550294,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2605591909577631,
+      "grad_norm": 1.0553990602493286,
+      "learning_rate": 0.00011839870602507078,
+      "loss": 0.22944607734680175,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2724568709101725,
+      "grad_norm": 0.8833849430084229,
+      "learning_rate": 0.00011758997169429842,
+      "loss": 0.2348541498184204,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2843545508625818,
+      "grad_norm": 0.5712324976921082,
+      "learning_rate": 0.00011678123736352608,
+      "loss": 0.23939337730407714,
+      "step": 1080
+    },
+    {
+      "epoch": 1.296252230814991,
+      "grad_norm": 1.1101552248001099,
+      "learning_rate": 0.00011597250303275375,
+      "loss": 0.1721956491470337,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "grad_norm": 2.259507894515991,
+      "learning_rate": 0.0001151637687019814,
+      "loss": 0.2358708143234253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3081499107674004,
+      "eval_loss": 0.6394524574279785,
+      "eval_runtime": 142.3401,
+      "eval_samples_per_second": 5.107,
+      "eval_steps_per_second": 1.279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3200475907198097,
+      "grad_norm": 1.9693511724472046,
+      "learning_rate": 0.00011435503437120907,
+      "loss": 0.2196721076965332,
+      "step": 1110
+    },
+    {
+      "epoch": 1.331945270672219,
+      "grad_norm": 0.4268541634082794,
+      "learning_rate": 0.00011354630004043671,
+      "loss": 0.13150120973587037,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3438429506246283,
+      "grad_norm": 2.330213785171509,
+      "learning_rate": 0.00011273756570966438,
+      "loss": 0.21918668746948242,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3557406305770374,
+      "grad_norm": 0.5232792496681213,
+      "learning_rate": 0.00011192883137889203,
+      "loss": 0.28672659397125244,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3676383105294467,
+      "grad_norm": 0.7693712115287781,
+      "learning_rate": 0.0001111200970481197,
+      "loss": 0.13414368629455567,
+      "step": 1150
+    },
+    {
+      "epoch": 1.379535990481856,
+      "grad_norm": 2.319396734237671,
+      "learning_rate": 0.00011031136271734736,
+      "loss": 0.2267531394958496,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3914336704342654,
+      "grad_norm": 0.5921527743339539,
+      "learning_rate": 0.00010950262838657502,
+      "loss": 0.25402560234069826,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4033313503866747,
+      "grad_norm": 2.0321357250213623,
+      "learning_rate": 0.00010869389405580268,
+      "loss": 0.25376124382019044,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4152290303390838,
+      "grad_norm": 0.38882723450660706,
+      "learning_rate": 0.00010788515972503032,
+      "loss": 0.22503962516784667,
+      "step": 1190
+    },
+    {
+      "epoch": 1.427126710291493,
+      "grad_norm": 1.3018765449523926,
+      "learning_rate": 0.00010707642539425799,
+      "loss": 0.2776267290115356,
+      "step": 1200
+    },
+    {
+      "epoch": 1.427126710291493,
+      "eval_loss": 0.6352964043617249,
+      "eval_runtime": 142.7248,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 1.275,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 1.2818971872329712,
+      "learning_rate": 0.00010626769106348564,
+      "loss": 0.2819439172744751,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4509220701963117,
+      "grad_norm": 2.7062032222747803,
+      "learning_rate": 0.00010545895673271331,
+      "loss": 0.27474424839019773,
+      "step": 1220
+    },
+    {
+      "epoch": 1.462819750148721,
+      "grad_norm": 1.595563530921936,
+      "learning_rate": 0.00010465022240194098,
+      "loss": 0.2381807565689087,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4747174301011303,
+      "grad_norm": 2.4552483558654785,
+      "learning_rate": 0.00010384148807116863,
+      "loss": 0.20328295230865479,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4866151100535396,
+      "grad_norm": 0.7772732973098755,
+      "learning_rate": 0.0001030327537403963,
+      "loss": 0.36213810443878175,
+      "step": 1250
+    },
+    {
+      "epoch": 1.498512790005949,
+      "grad_norm": 0.5157018899917603,
+      "learning_rate": 0.00010222401940962393,
+      "loss": 0.2579164505004883,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5104104699583583,
+      "grad_norm": 0.9393762946128845,
+      "learning_rate": 0.0001014152850788516,
+      "loss": 0.2738668441772461,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5223081499107673,
+      "grad_norm": 1.3828178644180298,
+      "learning_rate": 0.00010060655074807925,
+      "loss": 0.2687704563140869,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5342058298631767,
+      "grad_norm": 2.448199987411499,
+      "learning_rate": 9.979781641730692e-05,
+      "loss": 0.25954508781433105,
+      "step": 1290
+    },
+    {
+      "epoch": 1.546103509815586,
+      "grad_norm": 0.5786930918693542,
+      "learning_rate": 9.898908208653457e-05,
+      "loss": 0.3727055311203003,
+      "step": 1300
+    },
+    {
+      "epoch": 1.546103509815586,
+      "eval_loss": 0.6408339738845825,
+      "eval_runtime": 143.0994,
+      "eval_samples_per_second": 5.08,
+      "eval_steps_per_second": 1.272,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5580011897679953,
+      "grad_norm": 0.7677634954452515,
+      "learning_rate": 9.818034775576224e-05,
+      "loss": 0.1762090802192688,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5698988697204044,
+      "grad_norm": 0.6897227764129639,
+      "learning_rate": 9.73716134249899e-05,
+      "loss": 0.18234789371490479,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5817965496728137,
+      "grad_norm": 0.4356502294540405,
+      "learning_rate": 9.656287909421755e-05,
+      "loss": 0.17166239023208618,
+      "step": 1330
+    },
+    {
+      "epoch": 1.593694229625223,
+      "grad_norm": 0.8925612568855286,
+      "learning_rate": 9.575414476344521e-05,
+      "loss": 0.2909604549407959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6055919095776323,
+      "grad_norm": 1.331018328666687,
+      "learning_rate": 9.494541043267288e-05,
+      "loss": 0.3194843292236328,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6174895895300416,
+      "grad_norm": 0.7012219429016113,
+      "learning_rate": 9.413667610190053e-05,
+      "loss": 0.23222012519836427,
+      "step": 1360
+    },
+    {
+      "epoch": 1.629387269482451,
+      "grad_norm": 0.2544768154621124,
+      "learning_rate": 9.332794177112819e-05,
+      "loss": 0.23880724906921386,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6412849494348603,
+      "grad_norm": 1.3657277822494507,
+      "learning_rate": 9.251920744035585e-05,
+      "loss": 0.19748220443725586,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6531826293872696,
+      "grad_norm": 2.1993489265441895,
+      "learning_rate": 9.171047310958351e-05,
+      "loss": 0.30321478843688965,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "grad_norm": 0.4869902729988098,
+      "learning_rate": 9.090173877881116e-05,
+      "loss": 0.3128593921661377,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6650803093396789,
+      "eval_loss": 0.6290650367736816,
+      "eval_runtime": 142.7458,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.275,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6769779892920882,
+      "grad_norm": 0.8744633197784424,
+      "learning_rate": 9.009300444803883e-05,
+      "loss": 0.20709736347198487,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6888756692444973,
+      "grad_norm": 0.45242759585380554,
+      "learning_rate": 8.928427011726648e-05,
+      "loss": 0.24040257930755615,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7007733491969066,
+      "grad_norm": 2.7029457092285156,
+      "learning_rate": 8.847553578649415e-05,
+      "loss": 0.20522713661193848,
+      "step": 1430
+    },
+    {
+      "epoch": 1.712671029149316,
+      "grad_norm": 1.108100414276123,
+      "learning_rate": 8.76668014557218e-05,
+      "loss": 0.22306106090545655,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7245687091017252,
+      "grad_norm": 0.3601689636707306,
+      "learning_rate": 8.685806712494947e-05,
+      "loss": 0.22542276382446289,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7364663890541343,
+      "grad_norm": 2.1732895374298096,
+      "learning_rate": 8.604933279417712e-05,
+      "loss": 0.21184999942779542,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7483640690065436,
+      "grad_norm": 0.7454811334609985,
+      "learning_rate": 8.524059846340477e-05,
+      "loss": 0.16401395797729493,
+      "step": 1470
+    },
+    {
+      "epoch": 1.760261748958953,
+      "grad_norm": 0.9580848217010498,
+      "learning_rate": 8.443186413263243e-05,
+      "loss": 0.3019646883010864,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7721594289113622,
+      "grad_norm": 0.49919596314430237,
+      "learning_rate": 8.362312980186009e-05,
+      "loss": 0.1772990345954895,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "grad_norm": 0.4589841365814209,
+      "learning_rate": 8.281439547108775e-05,
+      "loss": 0.2236480712890625,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7840571088637716,
+      "eval_loss": 0.6338388919830322,
+      "eval_runtime": 142.4382,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 1.278,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7959547888161809,
+      "grad_norm": 1.2061543464660645,
+      "learning_rate": 8.200566114031541e-05,
+      "loss": 0.152615225315094,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8078524687685902,
+      "grad_norm": 0.8690841794013977,
+      "learning_rate": 8.119692680954308e-05,
+      "loss": 0.15312827825546266,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8197501487209995,
+      "grad_norm": 1.1968799829483032,
+      "learning_rate": 8.038819247877073e-05,
+      "loss": 0.1551919937133789,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8316478286734088,
+      "grad_norm": 0.5277600884437561,
+      "learning_rate": 7.957945814799839e-05,
+      "loss": 0.3069296360015869,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8435455086258181,
+      "grad_norm": 1.039868950843811,
+      "learning_rate": 7.877072381722604e-05,
+      "loss": 0.20282301902770997,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8554431885782272,
+      "grad_norm": 0.60517817735672,
+      "learning_rate": 7.79619894864537e-05,
+      "loss": 0.23913111686706542,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8673408685306365,
+      "grad_norm": 2.21573805809021,
+      "learning_rate": 7.715325515568136e-05,
+      "loss": 0.2257241725921631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8792385484830458,
+      "grad_norm": 0.2944304645061493,
+      "learning_rate": 7.634452082490901e-05,
+      "loss": 0.1661970019340515,
+      "step": 1580
+    },
+    {
+      "epoch": 1.891136228435455,
+      "grad_norm": 1.1983428001403809,
+      "learning_rate": 7.553578649413668e-05,
+      "loss": 0.2087465763092041,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "grad_norm": 0.8915425539016724,
+      "learning_rate": 7.472705216336434e-05,
+      "loss": 0.21896538734436036,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9030339083878642,
+      "eval_loss": 0.6456941962242126,
+      "eval_runtime": 142.943,
+      "eval_samples_per_second": 5.086,
+      "eval_steps_per_second": 1.273,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9149315883402735,
+      "grad_norm": 2.590047836303711,
+      "learning_rate": 7.3918317832592e-05,
+      "loss": 0.29830474853515626,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9268292682926829,
+      "grad_norm": 2.7200751304626465,
+      "learning_rate": 7.310958350181965e-05,
+      "loss": 0.2548383712768555,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9387269482450922,
+      "grad_norm": 0.47415056824684143,
+      "learning_rate": 7.230084917104732e-05,
+      "loss": 0.17630742788314818,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9506246281975015,
+      "grad_norm": 0.6399453282356262,
+      "learning_rate": 7.149211484027497e-05,
+      "loss": 0.21350162029266356,
+      "step": 1640
+    },
+    {
+      "epoch": 1.9625223081499108,
+      "grad_norm": 0.9102665781974792,
+      "learning_rate": 7.068338050950262e-05,
+      "loss": 0.1667860984802246,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9744199881023201,
+      "grad_norm": 1.439720869064331,
+      "learning_rate": 6.987464617873029e-05,
+      "loss": 0.15564169883728027,
+      "step": 1660
+    },
+    {
+      "epoch": 1.9863176680547294,
+      "grad_norm": 1.2843844890594482,
+      "learning_rate": 6.906591184795796e-05,
+      "loss": 0.23316650390625,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9982153480071387,
+      "grad_norm": 0.7496667504310608,
+      "learning_rate": 6.825717751718561e-05,
+      "loss": 0.11828969717025757,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0095181439619276,
+      "grad_norm": 0.5547150373458862,
+      "learning_rate": 6.744844318641326e-05,
+      "loss": 0.1567418694496155,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "grad_norm": 1.1936298608779907,
+      "learning_rate": 6.663970885564093e-05,
+      "loss": 0.07190254330635071,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0214158239143365,
+      "eval_loss": 0.7682034373283386,
+      "eval_runtime": 142.5675,
+      "eval_samples_per_second": 5.099,
+      "eval_steps_per_second": 1.277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.033313503866746,
+      "grad_norm": 0.8649502992630005,
+      "learning_rate": 6.583097452486858e-05,
+      "loss": 0.09684446454048157,
+      "step": 1710
+    },
+    {
+      "epoch": 2.045211183819155,
+      "grad_norm": 1.6249701976776123,
+      "learning_rate": 6.502224019409624e-05,
+      "loss": 0.10573645830154418,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0571088637715644,
+      "grad_norm": 1.6712027788162231,
+      "learning_rate": 6.42135058633239e-05,
+      "loss": 0.06878747344017029,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0690065437239737,
+      "grad_norm": 1.998836636543274,
+      "learning_rate": 6.340477153255156e-05,
+      "loss": 0.09289296865463256,
+      "step": 1740
+    },
+    {
+      "epoch": 2.080904223676383,
+      "grad_norm": 2.0230648517608643,
+      "learning_rate": 6.259603720177922e-05,
+      "loss": 0.08702811002731323,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0928019036287924,
+      "grad_norm": 0.6234531998634338,
+      "learning_rate": 6.178730287100688e-05,
+      "loss": 0.09178865551948548,
+      "step": 1760
+    },
+    {
+      "epoch": 2.1046995835812017,
+      "grad_norm": 1.0890167951583862,
+      "learning_rate": 6.0978568540234536e-05,
+      "loss": 0.07926965951919555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.116597263533611,
+      "grad_norm": 0.565838634967804,
+      "learning_rate": 6.0169834209462196e-05,
+      "loss": 0.06830034255981446,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1284949434860203,
+      "grad_norm": 0.24224597215652466,
+      "learning_rate": 5.936109987868985e-05,
+      "loss": 0.0387349396944046,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "grad_norm": 0.6451993584632874,
+      "learning_rate": 5.855236554791751e-05,
+      "loss": 0.08081170320510864,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1403926234384296,
+      "eval_loss": 0.7727965712547302,
+      "eval_runtime": 142.002,
+      "eval_samples_per_second": 5.12,
+      "eval_steps_per_second": 1.282,
+      "step": 1800
+    },
+    {
+      "epoch": 2.152290303390839,
+      "grad_norm": 1.7233307361602783,
+      "learning_rate": 5.774363121714517e-05,
+      "loss": 0.11144195795059204,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1641879833432482,
+      "grad_norm": 0.2479274868965149,
+      "learning_rate": 5.693489688637282e-05,
+      "loss": 0.08321853876113891,
+      "step": 1820
+    },
+    {
+      "epoch": 2.176085663295657,
+      "grad_norm": 0.47092318534851074,
+      "learning_rate": 5.6126162555600495e-05,
+      "loss": 0.07725490927696228,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1879833432480664,
+      "grad_norm": 0.8377601504325867,
+      "learning_rate": 5.531742822482815e-05,
+      "loss": 0.07388485074043274,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1998810232004757,
+      "grad_norm": 0.6015790700912476,
+      "learning_rate": 5.450869389405581e-05,
+      "loss": 0.07375617027282715,
+      "step": 1850
+    },
+    {
+      "epoch": 2.211778703152885,
+      "grad_norm": 0.4269079864025116,
+      "learning_rate": 5.369995956328346e-05,
+      "loss": 0.06217494010925293,
+      "step": 1860
+    },
+    {
+      "epoch": 2.2236763831052944,
+      "grad_norm": 0.6257069110870361,
+      "learning_rate": 5.289122523251112e-05,
+      "loss": 0.06257326006889344,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2355740630577037,
+      "grad_norm": 0.5031505823135376,
+      "learning_rate": 5.208249090173878e-05,
+      "loss": 0.05843117833137512,
+      "step": 1880
+    },
+    {
+      "epoch": 2.247471743010113,
+      "grad_norm": 1.6474521160125732,
+      "learning_rate": 5.1273756570966434e-05,
+      "loss": 0.09191031455993652,
+      "step": 1890
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "grad_norm": 3.4019672870635986,
+      "learning_rate": 5.04650222401941e-05,
+      "loss": 0.0880321979522705,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2593694229625223,
+      "eval_loss": 0.7820757627487183,
+      "eval_runtime": 144.3502,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2712671029149316,
+      "grad_norm": 1.2383092641830444,
+      "learning_rate": 4.9656287909421754e-05,
+      "loss": 0.05248329639434814,
+      "step": 1910
+    },
+    {
+      "epoch": 2.283164782867341,
+      "grad_norm": 0.3616305887699127,
+      "learning_rate": 4.884755357864942e-05,
+      "loss": 0.09794200658798217,
+      "step": 1920
+    },
+    {
+      "epoch": 2.2950624628197502,
+      "grad_norm": 1.8042008876800537,
+      "learning_rate": 4.8038819247877074e-05,
+      "loss": 0.08606679439544677,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3069601427721595,
+      "grad_norm": 1.1796011924743652,
+      "learning_rate": 4.7230084917104734e-05,
+      "loss": 0.06636201143264771,
+      "step": 1940
+    },
+    {
+      "epoch": 2.318857822724569,
+      "grad_norm": 2.172945499420166,
+      "learning_rate": 4.6421350586332394e-05,
+      "loss": 0.08974570631980897,
+      "step": 1950
+    },
+    {
+      "epoch": 2.330755502676978,
+      "grad_norm": 0.9927220940589905,
+      "learning_rate": 4.5612616255560053e-05,
+      "loss": 0.06555870771408082,
+      "step": 1960
+    },
+    {
+      "epoch": 2.3426531826293875,
+      "grad_norm": 0.7290642261505127,
+      "learning_rate": 4.480388192478771e-05,
+      "loss": 0.08729156255722045,
+      "step": 1970
+    },
+    {
+      "epoch": 2.3545508625817964,
+      "grad_norm": 1.645143985748291,
+      "learning_rate": 4.3995147594015366e-05,
+      "loss": 0.06546041369438171,
+      "step": 1980
+    },
+    {
+      "epoch": 2.3664485425342057,
+      "grad_norm": 0.5619677305221558,
+      "learning_rate": 4.3186413263243026e-05,
+      "loss": 0.09512026906013489,
+      "step": 1990
+    },
+    {
+      "epoch": 2.378346222486615,
+      "grad_norm": 0.5704317092895508,
+      "learning_rate": 4.2377678932470686e-05,
+      "loss": 0.07127516269683838,
+      "step": 2000
+    },
+    {
+      "epoch": 2.378346222486615,
+      "eval_loss": 0.7547894716262817,
+      "eval_runtime": 143.1861,
+      "eval_samples_per_second": 5.077,
+      "eval_steps_per_second": 1.271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 1.551915168762207,
+      "learning_rate": 4.1568944601698346e-05,
+      "loss": 0.06869585514068603,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4021415823914336,
+      "grad_norm": 0.6017701625823975,
+      "learning_rate": 4.0760210270926e-05,
+      "loss": 0.05127396583557129,
+      "step": 2020
+    },
+    {
+      "epoch": 2.414039262343843,
+      "grad_norm": 1.9110032320022583,
+      "learning_rate": 3.995147594015366e-05,
+      "loss": 0.08966401219367981,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4259369422962522,
+      "grad_norm": 1.0562331676483154,
+      "learning_rate": 3.9142741609381326e-05,
+      "loss": 0.0738204300403595,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4378346222486615,
+      "grad_norm": 1.9895752668380737,
+      "learning_rate": 3.833400727860898e-05,
+      "loss": 0.08233752250671386,
+      "step": 2050
+    },
+    {
+      "epoch": 2.449732302201071,
+      "grad_norm": 0.5100411176681519,
+      "learning_rate": 3.752527294783664e-05,
+      "loss": 0.052586525678634644,
+      "step": 2060
+    },
+    {
+      "epoch": 2.46162998215348,
+      "grad_norm": 0.27714085578918457,
+      "learning_rate": 3.671653861706429e-05,
+      "loss": 0.044759953022003175,
+      "step": 2070
+    },
+    {
+      "epoch": 2.4735276621058895,
+      "grad_norm": 0.4177452027797699,
+      "learning_rate": 3.590780428629196e-05,
+      "loss": 0.056336909532547,
+      "step": 2080
+    },
+    {
+      "epoch": 2.485425342058299,
+      "grad_norm": 1.0737571716308594,
+      "learning_rate": 3.509906995551961e-05,
+      "loss": 0.03993419706821442,
+      "step": 2090
+    },
+    {
+      "epoch": 2.497323022010708,
+      "grad_norm": 0.2551257312297821,
+      "learning_rate": 3.429033562474727e-05,
+      "loss": 0.06233363747596741,
+      "step": 2100
+    },
+    {
+      "epoch": 2.497323022010708,
+      "eval_loss": 0.7822292447090149,
+      "eval_runtime": 151.9581,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 1.198,
+      "step": 2100
+    },
+    {
+      "epoch": 2.509220701963117,
+      "grad_norm": 0.9730778336524963,
+      "learning_rate": 3.348160129397493e-05,
+      "loss": 0.07784021496772767,
+      "step": 2110
+    },
+    {
+      "epoch": 2.5211183819155263,
+      "grad_norm": 1.0517960786819458,
+      "learning_rate": 3.267286696320259e-05,
+      "loss": 0.07937353253364562,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5330160618679356,
+      "grad_norm": 2.1930930614471436,
+      "learning_rate": 3.186413263243025e-05,
+      "loss": 0.07288457751274109,
+      "step": 2130
+    },
+    {
+      "epoch": 2.544913741820345,
+      "grad_norm": 1.1975257396697998,
+      "learning_rate": 3.1055398301657905e-05,
+      "loss": 0.06836378574371338,
+      "step": 2140
+    },
+    {
+      "epoch": 2.5568114217727542,
+      "grad_norm": 0.8291498422622681,
+      "learning_rate": 3.0246663970885564e-05,
+      "loss": 0.064986652135849,
+      "step": 2150
+    },
+    {
+      "epoch": 2.5687091017251635,
+      "grad_norm": 0.6288985013961792,
+      "learning_rate": 2.9437929640113228e-05,
+      "loss": 0.06470431685447693,
+      "step": 2160
+    },
+    {
+      "epoch": 2.580606781677573,
+      "grad_norm": 0.3969435691833496,
+      "learning_rate": 2.8629195309340884e-05,
+      "loss": 0.04360280632972717,
+      "step": 2170
+    },
+    {
+      "epoch": 2.592504461629982,
+      "grad_norm": 0.8388019800186157,
+      "learning_rate": 2.782046097856854e-05,
+      "loss": 0.06012804508209228,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6044021415823915,
+      "grad_norm": 0.5081242322921753,
+      "learning_rate": 2.7011726647796197e-05,
+      "loss": 0.07594415545463562,
+      "step": 2190
+    },
+    {
+      "epoch": 2.616299821534801,
+      "grad_norm": 0.30208897590637207,
+      "learning_rate": 2.620299231702386e-05,
+      "loss": 0.05154580473899841,
+      "step": 2200
+    },
+    {
+      "epoch": 2.616299821534801,
+      "eval_loss": 0.7940844297409058,
+      "eval_runtime": 149.9653,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 1.214,
+      "step": 2200
+    },
+    {
+      "epoch": 2.62819750148721,
+      "grad_norm": 0.521649181842804,
+      "learning_rate": 2.5394257986251517e-05,
+      "loss": 0.04323629140853882,
+      "step": 2210
+    },
+    {
+      "epoch": 2.6400951814396194,
+      "grad_norm": 2.6473941802978516,
+      "learning_rate": 2.4585523655479177e-05,
+      "loss": 0.10532597303390503,
+      "step": 2220
+    },
+    {
+      "epoch": 2.6519928613920287,
+      "grad_norm": 0.6955065727233887,
+      "learning_rate": 2.3776789324706837e-05,
+      "loss": 0.04693872630596161,
+      "step": 2230
+    },
+    {
+      "epoch": 2.663890541344438,
+      "grad_norm": 0.6439285278320312,
+      "learning_rate": 2.2968054993934493e-05,
+      "loss": 0.07398720383644104,
+      "step": 2240
+    },
+    {
+      "epoch": 2.6757882212968473,
+      "grad_norm": 0.6171683073043823,
+      "learning_rate": 2.2159320663162153e-05,
+      "loss": 0.08055143356323242,
+      "step": 2250
+    },
+    {
+      "epoch": 2.6876859012492567,
+      "grad_norm": 1.594099998474121,
+      "learning_rate": 2.135058633238981e-05,
+      "loss": 0.06038923859596253,
+      "step": 2260
+    },
+    {
+      "epoch": 2.6995835812016655,
+      "grad_norm": 0.5130852460861206,
+      "learning_rate": 2.054185200161747e-05,
+      "loss": 0.09171404242515564,
+      "step": 2270
+    },
+    {
+      "epoch": 2.711481261154075,
+      "grad_norm": 0.5048943161964417,
+      "learning_rate": 1.9733117670845126e-05,
+      "loss": 0.04560606479644776,
+      "step": 2280
+    },
+    {
+      "epoch": 2.723378941106484,
+      "grad_norm": 1.691913366317749,
+      "learning_rate": 1.8924383340072786e-05,
+      "loss": 0.08174195885658264,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "grad_norm": 2.5807952880859375,
+      "learning_rate": 1.8115649009300446e-05,
+      "loss": 0.07424867749214173,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7352766210588935,
+      "eval_loss": 0.7955667972564697,
+      "eval_runtime": 151.7304,
+      "eval_samples_per_second": 4.791,
+      "eval_steps_per_second": 1.199,
+      "step": 2300
+    },
+    {
+      "epoch": 2.7471743010113028,
+      "grad_norm": 1.0159227848052979,
+      "learning_rate": 1.7306914678528106e-05,
+      "loss": 0.041696679592132566,
+      "step": 2310
+    },
+    {
+      "epoch": 2.759071980963712,
+      "grad_norm": 0.6436373591423035,
+      "learning_rate": 1.6498180347755762e-05,
+      "loss": 0.06923379898071289,
+      "step": 2320
+    },
+    {
+      "epoch": 2.7709696609161214,
+      "grad_norm": 2.703979015350342,
+      "learning_rate": 1.5689446016983422e-05,
+      "loss": 0.09573553800582886,
+      "step": 2330
+    },
+    {
+      "epoch": 2.7828673408685307,
+      "grad_norm": 1.3062081336975098,
+      "learning_rate": 1.4880711686211079e-05,
+      "loss": 0.07745556235313415,
+      "step": 2340
+    },
+    {
+      "epoch": 2.79476502082094,
+      "grad_norm": 0.4865114092826843,
+      "learning_rate": 1.407197735543874e-05,
+      "loss": 0.04722094833850861,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8066627007733493,
+      "grad_norm": 2.370136260986328,
+      "learning_rate": 1.3263243024666397e-05,
+      "loss": 0.06862221956253052,
+      "step": 2360
+    },
+    {
+      "epoch": 2.818560380725758,
+      "grad_norm": 2.503732681274414,
+      "learning_rate": 1.2454508693894057e-05,
+      "loss": 0.06837759017944336,
+      "step": 2370
+    },
+    {
+      "epoch": 2.8304580606781675,
+      "grad_norm": 0.30941763520240784,
+      "learning_rate": 1.1645774363121715e-05,
+      "loss": 0.03794792294502258,
+      "step": 2380
+    },
+    {
+      "epoch": 2.842355740630577,
+      "grad_norm": 0.39067885279655457,
+      "learning_rate": 1.0837040032349375e-05,
+      "loss": 0.05413181185722351,
+      "step": 2390
+    },
+    {
+      "epoch": 2.854253420582986,
+      "grad_norm": 2.7522947788238525,
+      "learning_rate": 1.0028305701577033e-05,
+      "loss": 0.05264478325843811,
+      "step": 2400
+    },
+    {
+      "epoch": 2.854253420582986,
+      "eval_loss": 0.7887478470802307,
+      "eval_runtime": 149.3367,
+      "eval_samples_per_second": 4.868,
+      "eval_steps_per_second": 1.219,
+      "step": 2400
+    },
+    {
+      "epoch": 2.8661511005353955,
+      "grad_norm": 0.5051487684249878,
+      "learning_rate": 9.219571370804691e-06,
+      "loss": 0.07031412124633789,
+      "step": 2410
+    },
+    {
+      "epoch": 2.8780487804878048,
+      "grad_norm": 0.43260014057159424,
+      "learning_rate": 8.41083704003235e-06,
+      "loss": 0.08607797622680664,
+      "step": 2420
+    },
+    {
+      "epoch": 2.889946460440214,
+      "grad_norm": 1.787656545639038,
+      "learning_rate": 7.602102709260009e-06,
+      "loss": 0.06961020827293396,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9018441403926234,
+      "grad_norm": 0.5731585025787354,
+      "learning_rate": 6.793368378487668e-06,
+      "loss": 0.06185711026191711,
+      "step": 2440
+    },
+    {
+      "epoch": 2.9137418203450327,
+      "grad_norm": 2.8741965293884277,
+      "learning_rate": 5.984634047715326e-06,
+      "loss": 0.07431170344352722,
+      "step": 2450
+    },
+    {
+      "epoch": 2.925639500297442,
+      "grad_norm": 1.372190237045288,
+      "learning_rate": 5.175899716942984e-06,
+      "loss": 0.05746169686317444,
+      "step": 2460
+    },
+    {
+      "epoch": 2.9375371802498513,
+      "grad_norm": 1.294169545173645,
+      "learning_rate": 4.367165386170643e-06,
+      "loss": 0.07876025438308716,
+      "step": 2470
+    },
+    {
+      "epoch": 2.9494348602022606,
+      "grad_norm": 1.7027950286865234,
+      "learning_rate": 3.5584310553983014e-06,
+      "loss": 0.09096775650978088,
+      "step": 2480
+    },
+    {
+      "epoch": 2.96133254015467,
+      "grad_norm": 0.5540681481361389,
+      "learning_rate": 2.7496967246259604e-06,
+      "loss": 0.06888358592987061,
+      "step": 2490
+    },
+    {
+      "epoch": 2.9732302201070793,
+      "grad_norm": 2.2525739669799805,
+      "learning_rate": 1.940962393853619e-06,
+      "loss": 0.05039908289909363,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9732302201070793,
+      "eval_loss": 0.7935085892677307,
+      "eval_runtime": 154.2587,
+      "eval_samples_per_second": 4.713,
+      "eval_steps_per_second": 1.18,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9851279000594886,
+      "grad_norm": 0.31110718846321106,
+      "learning_rate": 1.1322280630812779e-06,
+      "loss": 0.057289916276931765,
+      "step": 2510
+    },
+    {
+      "epoch": 2.997025580011898,
+      "grad_norm": 0.7514714002609253,
+      "learning_rate": 3.234937323089365e-07,
+      "loss": 0.06889436841011047,
+      "step": 2520
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7937434911727905,
+      "eval_runtime": 147.493,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 1.234,
+      "step": 2523
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.545780499418115e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2523/training_args.bin b/checkpoint-2523/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-2523/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..cadd1abe3238c5b3ea68d7f494365299d13a6a65
--- /dev/null
+++ b/checkpoint-800/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1
\ No newline at end of file
diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..87451c1e66fd973ab5bddc76ab0b38e1d7bfa829
--- /dev/null
+++ b/checkpoint-800/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}
\ No newline at end of file
diff --git a/checkpoint-800/adapter_model.safetensors b/checkpoint-800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7bc67fe2832f12a59749e7daae89efa4700a7a98
--- /dev/null
+++ b/checkpoint-800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e46a1113b9507a30f5ae0d86e5e2510ea0ed32ebc9e137defae0c1d831be14
+size 161533192
diff --git a/checkpoint-800/chat_template.jinja b/checkpoint-800/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..bdf7919a96cfe43d50914a007b9c0877bd0ec27e
--- /dev/null
+++ b/checkpoint-800/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/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fc2d8c61138e3550565accb45720dd7d1eb81710
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9789f8a242b24246986307fde33d8c5fe02f41298e3ca9d0fe498da5ce139c
+size 82465012
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f93eb9efb1f98f8b4452fe23ec82a5910e6b1c4b
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8c6528a646fa6e0683197578779777e9d6bb2f7f437bd207ca19c8e9d16c15
+size 14308
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..35bb99b47c20f806fef8f9e34b07ef3a237ca1ab
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34254902f7cb31db641ea23fe1433afdc1b0a0b3f61dea70511b1674dbe6c9cb
+size 1064
diff --git a/checkpoint-800/tokenizer.json b/checkpoint-800/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/checkpoint-800/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/checkpoint-800/tokenizer_config.json b/checkpoint-800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7bfe2147ea620d07713a7792df0183aa45595f5
--- /dev/null
+++ b/checkpoint-800/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b5a2e75b2ced19bd9a8d4e76a6b7388e08f14c12
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,658 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.5888198614120483,
+  "best_model_checkpoint": "/workspace/codek/outputs/codek-lora-v3/checkpoint-800",
+  "epoch": 0.9518143961927424,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01189767995240928,
+      "grad_norm": 0.5428410768508911,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9758113861083985,
+      "step": 10
+    },
+    {
+      "epoch": 0.02379535990481856,
+      "grad_norm": 4.67169189453125,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6493405342102051,
+      "step": 20
+    },
+    {
+      "epoch": 0.03569303985722784,
+      "grad_norm": 1.070132851600647,
+      "learning_rate": 0.000116,
+      "loss": 1.06031494140625,
+      "step": 30
+    },
+    {
+      "epoch": 0.04759071980963712,
+      "grad_norm": 1.9386584758758545,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6819836139678955,
+      "step": 40
+    },
+    {
+      "epoch": 0.0594883997620464,
+      "grad_norm": 0.4872680604457855,
+      "learning_rate": 0.000196,
+      "loss": 0.5926659107208252,
+      "step": 50
+    },
+    {
+      "epoch": 0.07138607971445568,
+      "grad_norm": 2.355872869491577,
+      "learning_rate": 0.0001992721391023049,
+      "loss": 0.6537514686584472,
+      "step": 60
+    },
+    {
+      "epoch": 0.08328375966686496,
+      "grad_norm": 2.0048632621765137,
+      "learning_rate": 0.00019846340477153255,
+      "loss": 0.5464569568634033,
+      "step": 70
+    },
+    {
+      "epoch": 0.09518143961927424,
+      "grad_norm": 0.354509562253952,
+      "learning_rate": 0.00019765467044076022,
+      "loss": 0.35349245071411134,
+      "step": 80
+    },
+    {
+      "epoch": 0.10707911957168352,
+      "grad_norm": 0.594601571559906,
+      "learning_rate": 0.00019684593610998788,
+      "loss": 0.6311532497406006,
+      "step": 90
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "grad_norm": 0.6164997220039368,
+      "learning_rate": 0.00019603720177921555,
+      "loss": 0.6391933917999267,
+      "step": 100
+    },
+    {
+      "epoch": 0.1189767995240928,
+      "eval_loss": 0.6638074517250061,
+      "eval_runtime": 145.0623,
+      "eval_samples_per_second": 5.012,
+      "eval_steps_per_second": 1.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.13087447947650208,
+      "grad_norm": 0.44855809211730957,
+      "learning_rate": 0.0001952284674484432,
+      "loss": 0.5943772792816162,
+      "step": 110
+    },
+    {
+      "epoch": 0.14277215942891136,
+      "grad_norm": 0.5330596566200256,
+      "learning_rate": 0.00019441973311767086,
+      "loss": 0.6163853168487549,
+      "step": 120
+    },
+    {
+      "epoch": 0.15466983938132065,
+      "grad_norm": 2.245134115219116,
+      "learning_rate": 0.00019361099878689852,
+      "loss": 0.6799118995666504,
+      "step": 130
+    },
+    {
+      "epoch": 0.16656751933372993,
+      "grad_norm": 0.6131016612052917,
+      "learning_rate": 0.00019280226445612616,
+      "loss": 0.5579062938690186,
+      "step": 140
+    },
+    {
+      "epoch": 0.17846519928613921,
+      "grad_norm": 2.133678436279297,
+      "learning_rate": 0.00019199353012535383,
+      "loss": 0.6677299976348877,
+      "step": 150
+    },
+    {
+      "epoch": 0.19036287923854847,
+      "grad_norm": 2.461663246154785,
+      "learning_rate": 0.0001911847957945815,
+      "loss": 0.5393151760101318,
+      "step": 160
+    },
+    {
+      "epoch": 0.20226055919095776,
+      "grad_norm": 0.8805132508277893,
+      "learning_rate": 0.00019037606146380916,
+      "loss": 0.3627098321914673,
+      "step": 170
+    },
+    {
+      "epoch": 0.21415823914336704,
+      "grad_norm": 0.6360796093940735,
+      "learning_rate": 0.0001895673271330368,
+      "loss": 0.39393203258514403,
+      "step": 180
+    },
+    {
+      "epoch": 0.22605591909577633,
+      "grad_norm": 0.6658252477645874,
+      "learning_rate": 0.00018875859280226447,
+      "loss": 0.4603158473968506,
+      "step": 190
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "grad_norm": 0.8778694868087769,
+      "learning_rate": 0.0001879498584714921,
+      "loss": 0.3169058561325073,
+      "step": 200
+    },
+    {
+      "epoch": 0.2379535990481856,
+      "eval_loss": 0.6359900832176208,
+      "eval_runtime": 148.4485,
+      "eval_samples_per_second": 4.897,
+      "eval_steps_per_second": 1.226,
+      "step": 200
+    },
+    {
+      "epoch": 0.2498512790005949,
+      "grad_norm": 0.9706892371177673,
+      "learning_rate": 0.00018714112414071977,
+      "loss": 0.5271358013153076,
+      "step": 210
+    },
+    {
+      "epoch": 0.26174895895300415,
+      "grad_norm": 2.4584925174713135,
+      "learning_rate": 0.00018633238980994744,
+      "loss": 0.5194128036499024,
+      "step": 220
+    },
+    {
+      "epoch": 0.27364663890541346,
+      "grad_norm": 2.380593776702881,
+      "learning_rate": 0.0001855236554791751,
+      "loss": 0.36130523681640625,
+      "step": 230
+    },
+    {
+      "epoch": 0.2855443188578227,
+      "grad_norm": 0.3882339596748352,
+      "learning_rate": 0.00018471492114840277,
+      "loss": 0.5675658702850341,
+      "step": 240
+    },
+    {
+      "epoch": 0.297441998810232,
+      "grad_norm": 0.5137739181518555,
+      "learning_rate": 0.00018390618681763041,
+      "loss": 0.4355769634246826,
+      "step": 250
+    },
+    {
+      "epoch": 0.3093396787626413,
+      "grad_norm": 2.0276546478271484,
+      "learning_rate": 0.00018309745248685808,
+      "loss": 0.45575518608093263,
+      "step": 260
+    },
+    {
+      "epoch": 0.32123735871505055,
+      "grad_norm": 0.7296242713928223,
+      "learning_rate": 0.00018228871815608572,
+      "loss": 0.3975461483001709,
+      "step": 270
+    },
+    {
+      "epoch": 0.33313503866745986,
+      "grad_norm": 0.4104812741279602,
+      "learning_rate": 0.0001814799838253134,
+      "loss": 0.4124011993408203,
+      "step": 280
+    },
+    {
+      "epoch": 0.3450327186198691,
+      "grad_norm": 2.2240512371063232,
+      "learning_rate": 0.00018067124949454105,
+      "loss": 0.44806156158447263,
+      "step": 290
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "grad_norm": 0.5039843916893005,
+      "learning_rate": 0.00017986251516376872,
+      "loss": 0.5462466716766358,
+      "step": 300
+    },
+    {
+      "epoch": 0.35693039857227843,
+      "eval_loss": 0.6173338294029236,
+      "eval_runtime": 142.4876,
+      "eval_samples_per_second": 5.102,
+      "eval_steps_per_second": 1.277,
+      "step": 300
+    },
+    {
+      "epoch": 0.3688280785246877,
+      "grad_norm": 2.1521501541137695,
+      "learning_rate": 0.0001790537808329964,
+      "loss": 0.5577811241149903,
+      "step": 310
+    },
+    {
+      "epoch": 0.38072575847709694,
+      "grad_norm": 1.0199904441833496,
+      "learning_rate": 0.00017824504650222403,
+      "loss": 0.4318714141845703,
+      "step": 320
+    },
+    {
+      "epoch": 0.39262343842950626,
+      "grad_norm": 0.7938897013664246,
+      "learning_rate": 0.0001774363121714517,
+      "loss": 0.5028730869293213,
+      "step": 330
+    },
+    {
+      "epoch": 0.4045211183819155,
+      "grad_norm": 1.0197608470916748,
+      "learning_rate": 0.00017662757784067933,
+      "loss": 0.4412552833557129,
+      "step": 340
+    },
+    {
+      "epoch": 0.4164187983343248,
+      "grad_norm": 2.1586694717407227,
+      "learning_rate": 0.000175818843509907,
+      "loss": 0.6107489109039307,
+      "step": 350
+    },
+    {
+      "epoch": 0.4283164782867341,
+      "grad_norm": 0.5125121474266052,
+      "learning_rate": 0.00017501010917913467,
+      "loss": 0.41151204109191897,
+      "step": 360
+    },
+    {
+      "epoch": 0.4402141582391434,
+      "grad_norm": 0.854578971862793,
+      "learning_rate": 0.00017420137484836233,
+      "loss": 0.37861664295196534,
+      "step": 370
+    },
+    {
+      "epoch": 0.45211183819155265,
+      "grad_norm": 0.3810710608959198,
+      "learning_rate": 0.00017339264051759,
+      "loss": 0.554447078704834,
+      "step": 380
+    },
+    {
+      "epoch": 0.4640095181439619,
+      "grad_norm": 0.6537095308303833,
+      "learning_rate": 0.00017258390618681764,
+      "loss": 0.4039173126220703,
+      "step": 390
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "grad_norm": 0.3078782856464386,
+      "learning_rate": 0.0001717751718560453,
+      "loss": 0.36465888023376464,
+      "step": 400
+    },
+    {
+      "epoch": 0.4759071980963712,
+      "eval_loss": 0.6045503616333008,
+      "eval_runtime": 142.1172,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.281,
+      "step": 400
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 2.2536327838897705,
+      "learning_rate": 0.00017096643752527295,
+      "loss": 0.6744783878326416,
+      "step": 410
+    },
+    {
+      "epoch": 0.4997025580011898,
+      "grad_norm": 1.0270065069198608,
+      "learning_rate": 0.0001701577031945006,
+      "loss": 0.3990432024002075,
+      "step": 420
+    },
+    {
+      "epoch": 0.5116002379535991,
+      "grad_norm": 0.8148894906044006,
+      "learning_rate": 0.00016934896886372825,
+      "loss": 0.44692273139953614,
+      "step": 430
+    },
+    {
+      "epoch": 0.5234979179060083,
+      "grad_norm": 1.3633968830108643,
+      "learning_rate": 0.00016854023453295595,
+      "loss": 0.643745756149292,
+      "step": 440
+    },
+    {
+      "epoch": 0.5353955978584176,
+      "grad_norm": 2.3843679428100586,
+      "learning_rate": 0.0001677315002021836,
+      "loss": 0.5624740600585938,
+      "step": 450
+    },
+    {
+      "epoch": 0.5472932778108269,
+      "grad_norm": 2.0721166133880615,
+      "learning_rate": 0.00016692276587141125,
+      "loss": 0.5419316768646241,
+      "step": 460
+    },
+    {
+      "epoch": 0.5591909577632361,
+      "grad_norm": 0.4449078142642975,
+      "learning_rate": 0.00016611403154063892,
+      "loss": 0.48584938049316406,
+      "step": 470
+    },
+    {
+      "epoch": 0.5710886377156454,
+      "grad_norm": 0.7449671030044556,
+      "learning_rate": 0.00016530529720986656,
+      "loss": 0.7389155387878418,
+      "step": 480
+    },
+    {
+      "epoch": 0.5829863176680548,
+      "grad_norm": 0.50657719373703,
+      "learning_rate": 0.00016449656287909422,
+      "loss": 0.4307733058929443,
+      "step": 490
+    },
+    {
+      "epoch": 0.594883997620464,
+      "grad_norm": 0.4837963581085205,
+      "learning_rate": 0.00016368782854832186,
+      "loss": 0.5735152244567872,
+      "step": 500
+    },
+    {
+      "epoch": 0.594883997620464,
+      "eval_loss": 0.6034532189369202,
+      "eval_runtime": 142.6906,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 1.275,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067816775728733,
+      "grad_norm": 1.4207062721252441,
+      "learning_rate": 0.00016287909421754953,
+      "loss": 0.5803914070129395,
+      "step": 510
+    },
+    {
+      "epoch": 0.6186793575252826,
+      "grad_norm": 1.859832763671875,
+      "learning_rate": 0.00016207035988677722,
+      "loss": 0.6262160301208496,
+      "step": 520
+    },
+    {
+      "epoch": 0.6305770374776919,
+      "grad_norm": 0.6771688461303711,
+      "learning_rate": 0.00016126162555600486,
+      "loss": 0.511366891860962,
+      "step": 530
+    },
+    {
+      "epoch": 0.6424747174301011,
+      "grad_norm": 0.6743080615997314,
+      "learning_rate": 0.00016045289122523253,
+      "loss": 0.360305118560791,
+      "step": 540
+    },
+    {
+      "epoch": 0.6543723973825104,
+      "grad_norm": 0.7527660131454468,
+      "learning_rate": 0.00015964415689446017,
+      "loss": 0.4684628963470459,
+      "step": 550
+    },
+    {
+      "epoch": 0.6662700773349197,
+      "grad_norm": 0.48323220014572144,
+      "learning_rate": 0.00015883542256368784,
+      "loss": 0.37999782562255857,
+      "step": 560
+    },
+    {
+      "epoch": 0.6781677572873289,
+      "grad_norm": 0.6131327748298645,
+      "learning_rate": 0.00015802668823291548,
+      "loss": 0.4337103843688965,
+      "step": 570
+    },
+    {
+      "epoch": 0.6900654372397382,
+      "grad_norm": 2.4380738735198975,
+      "learning_rate": 0.00015721795390214314,
+      "loss": 0.5413307666778564,
+      "step": 580
+    },
+    {
+      "epoch": 0.7019631171921475,
+      "grad_norm": 0.8438555002212524,
+      "learning_rate": 0.0001564092195713708,
+      "loss": 0.46597776412963865,
+      "step": 590
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "grad_norm": 0.6677970290184021,
+      "learning_rate": 0.00015560048524059848,
+      "loss": 0.49952197074890137,
+      "step": 600
+    },
+    {
+      "epoch": 0.7138607971445569,
+      "eval_loss": 0.5968995690345764,
+      "eval_runtime": 144.369,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 1.261,
+      "step": 600
+    },
+    {
+      "epoch": 0.7257584770969661,
+      "grad_norm": 0.6519638895988464,
+      "learning_rate": 0.00015479175090982614,
+      "loss": 0.5322952747344971,
+      "step": 610
+    },
+    {
+      "epoch": 0.7376561570493754,
+      "grad_norm": 2.2388486862182617,
+      "learning_rate": 0.00015398301657905378,
+      "loss": 0.4521610736846924,
+      "step": 620
+    },
+    {
+      "epoch": 0.7495538370017847,
+      "grad_norm": 0.5438874363899231,
+      "learning_rate": 0.00015317428224828145,
+      "loss": 0.32070658206939695,
+      "step": 630
+    },
+    {
+      "epoch": 0.7614515169541939,
+      "grad_norm": 0.9428866505622864,
+      "learning_rate": 0.0001523655479175091,
+      "loss": 0.43947296142578124,
+      "step": 640
+    },
+    {
+      "epoch": 0.7733491969066032,
+      "grad_norm": 2.1778297424316406,
+      "learning_rate": 0.00015155681358673676,
+      "loss": 0.3582610130310059,
+      "step": 650
+    },
+    {
+      "epoch": 0.7852468768590125,
+      "grad_norm": 0.9862648844718933,
+      "learning_rate": 0.00015074807925596442,
+      "loss": 0.2572986602783203,
+      "step": 660
+    },
+    {
+      "epoch": 0.7971445568114218,
+      "grad_norm": 2.2405526638031006,
+      "learning_rate": 0.0001499393449251921,
+      "loss": 0.5751560211181641,
+      "step": 670
+    },
+    {
+      "epoch": 0.809042236763831,
+      "grad_norm": 0.9659500122070312,
+      "learning_rate": 0.00014913061059441976,
+      "loss": 0.3901207447052002,
+      "step": 680
+    },
+    {
+      "epoch": 0.8209399167162403,
+      "grad_norm": 0.603147029876709,
+      "learning_rate": 0.0001483218762636474,
+      "loss": 0.4886178970336914,
+      "step": 690
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "grad_norm": 1.395334005355835,
+      "learning_rate": 0.00014751314193287506,
+      "loss": 0.33148694038391113,
+      "step": 700
+    },
+    {
+      "epoch": 0.8328375966686496,
+      "eval_loss": 0.5894402861595154,
+      "eval_runtime": 143.9201,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 1.265,
+      "step": 700
+    },
+    {
+      "epoch": 0.8447352766210589,
+      "grad_norm": 0.37410464882850647,
+      "learning_rate": 0.0001467044076021027,
+      "loss": 0.4385047435760498,
+      "step": 710
+    },
+    {
+      "epoch": 0.8566329565734682,
+      "grad_norm": 0.556503415107727,
+      "learning_rate": 0.00014589567327133037,
+      "loss": 0.4530733585357666,
+      "step": 720
+    },
+    {
+      "epoch": 0.8685306365258775,
+      "grad_norm": 0.5830616354942322,
+      "learning_rate": 0.00014508693894055803,
+      "loss": 0.351526141166687,
+      "step": 730
+    },
+    {
+      "epoch": 0.8804283164782868,
+      "grad_norm": 1.0821419954299927,
+      "learning_rate": 0.0001442782046097857,
+      "loss": 0.37159755229949953,
+      "step": 740
+    },
+    {
+      "epoch": 0.892325996430696,
+      "grad_norm": 0.7333435416221619,
+      "learning_rate": 0.00014346947027901334,
+      "loss": 0.2786282777786255,
+      "step": 750
+    },
+    {
+      "epoch": 0.9042236763831053,
+      "grad_norm": 1.016577124595642,
+      "learning_rate": 0.000142660735948241,
+      "loss": 0.45658392906188966,
+      "step": 760
+    },
+    {
+      "epoch": 0.9161213563355146,
+      "grad_norm": 0.9072016477584839,
+      "learning_rate": 0.00014185200161746867,
+      "loss": 0.5834776878356933,
+      "step": 770
+    },
+    {
+      "epoch": 0.9280190362879238,
+      "grad_norm": 0.7650527954101562,
+      "learning_rate": 0.00014104326728669631,
+      "loss": 0.36519818305969237,
+      "step": 780
+    },
+    {
+      "epoch": 0.9399167162403331,
+      "grad_norm": 0.6731218695640564,
+      "learning_rate": 0.00014023453295592398,
+      "loss": 0.2340949296951294,
+      "step": 790
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "grad_norm": 0.5773884654045105,
+      "learning_rate": 0.00013942579862515165,
+      "loss": 0.2930734395980835,
+      "step": 800
+    },
+    {
+      "epoch": 0.9518143961927424,
+      "eval_loss": 0.5888198614120483,
+      "eval_runtime": 141.9299,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 1.282,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.901846706398208e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d256811821f5d1ff7eea6a239ec113ca5ea42f61
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47abdcb2d959c9b661bff96e3d57dc8b08d6ada3c77f1465a0ab8cd65cc50264
+size 5368
diff --git a/runs/Apr03_20-31-57_134732f29987/events.out.tfevents.1775248317.134732f29987.3416.0 b/runs/Apr03_20-31-57_134732f29987/events.out.tfevents.1775248317.134732f29987.3416.0
new file mode 100644
index 0000000000000000000000000000000000000000..694656f4952b6645814e224889dd6a3842ead3f6
--- /dev/null
+++ b/runs/Apr03_20-31-57_134732f29987/events.out.tfevents.1775248317.134732f29987.3416.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23bbc67136b88a99b433c048e0f9782d27e6f8146048e846b0331bfb82fc2a25
+size 66280
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..5340d8195cfed687e080acf4f7cfdc46d18d5924
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9e10a1d2fd15fe561580a4e87181604c751b2b66
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}