Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1444/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,112 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen3-32B
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-32B
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: outputs/qwen32b-thai
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.13.0.dev0`
+```yaml
+adapter: lora
+base_model: Qwen/Qwen3-32B
+bf16: true
+flash_attention: true
+gradient_checkpointing: true
+
+datasets:
+- path: /workspace/data/wangchan_fixed
+  type: alpaca
+  split: train
+
+val_set_size: 0
+sequence_len: 2048
+train_on_inputs: false
+
+micro_batch_size: 4
+gradient_accumulation_steps: 8
+
+optimizer: adamw_torch
+learning_rate: 1.0e-4
+lr_scheduler: cosine
+warmup_ratio: 0.03
+weight_decay: 0.01
+max_grad_norm: 1.0
+num_epochs: 2
+
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_modules:
+- q_proj
+- k_proj
+- v_proj
+- o_proj
+- gate_proj
+- down_proj
+- up_proj
+
+output_dir: ./outputs/qwen32b-thai
+logging_steps: 10
+save_steps: 300
+
+```
+
+</details><br>
+
+# outputs/qwen32b-thai
+
+This model is a fine-tuned version of [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 43
+- training_steps: 1444
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.57.3
+- Pytorch 2.7.1+cu126
+- Datasets 4.3.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d3102e68745e66c2daef4aaa01521bf2bec17841374a7c32db1b5afda55bfb
+size 1073863208

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1200/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-32B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-32B
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1200/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c8ddf77739193db123523dc4414f58df4f3eeae5feff00f41eee50f881a64e
+size 1073863208

checkpoint-1200/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1200/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1172c8484f744983c9531c0da5896053adb6353a5761a6a0cad4ad4e0b9e6674
+size 2148242275

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6663df6cf4e9e942e7833fe9645e699bb07d7b28191118e8cc66260644bbee67
+size 14645

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dde084cca2e0284c3e37a771e8ef6ef071cd4613e2fc49d879ddcc79f50a195
+size 1465

checkpoint-1200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,1354 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6623939026502685,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013857613026156245,
+      "grad_norm": 0.1854863315820694,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 0.8494,
+      "memory/device_reserved (GiB)": 89.89,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 10,
+      "tokens_per_second_per_gpu": 1111.65
+    },
+    {
+      "epoch": 0.02771522605231249,
+      "grad_norm": 0.09567277133464813,
+      "learning_rate": 4.418604651162791e-05,
+      "loss": 0.7842,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 20,
+      "tokens_per_second_per_gpu": 1041.18
+    },
+    {
+      "epoch": 0.04157283907846873,
+      "grad_norm": 0.1211227998137474,
+      "learning_rate": 6.744186046511628e-05,
+      "loss": 0.7353,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 30,
+      "tokens_per_second_per_gpu": 993.82
+    },
+    {
+      "epoch": 0.05543045210462498,
+      "grad_norm": 0.09696491807699203,
+      "learning_rate": 9.069767441860465e-05,
+      "loss": 0.6943,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 40,
+      "tokens_per_second_per_gpu": 849.91
+    },
+    {
+      "epoch": 0.06928806513078123,
+      "grad_norm": 0.12007619440555573,
+      "learning_rate": 9.999547457436221e-05,
+      "loss": 0.6814,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 50,
+      "tokens_per_second_per_gpu": 971.92
+    },
+    {
+      "epoch": 0.08314567815693746,
+      "grad_norm": 0.12358752638101578,
+      "learning_rate": 9.996782216198338e-05,
+      "loss": 0.69,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 60,
+      "tokens_per_second_per_gpu": 862.06
+    },
+    {
+      "epoch": 0.09700329118309371,
+      "grad_norm": 0.11916535347700119,
+      "learning_rate": 9.991504534967746e-05,
+      "loss": 0.7048,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 70,
+      "tokens_per_second_per_gpu": 1024.18
+    },
+    {
+      "epoch": 0.11086090420924996,
+      "grad_norm": 0.12464027106761932,
+      "learning_rate": 9.983717067423721e-05,
+      "loss": 0.6705,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 80,
+      "tokens_per_second_per_gpu": 1009.08
+    },
+    {
+      "epoch": 0.1247185172354062,
+      "grad_norm": 0.1264505237340927,
+      "learning_rate": 9.973423729195168e-05,
+      "loss": 0.6387,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 90,
+      "tokens_per_second_per_gpu": 1027.91
+    },
+    {
+      "epoch": 0.13857613026156246,
+      "grad_norm": 0.1262999027967453,
+      "learning_rate": 9.960629695891814e-05,
+      "loss": 0.6447,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 100,
+      "tokens_per_second_per_gpu": 935.25
+    },
+    {
+      "epoch": 0.1524337432877187,
+      "grad_norm": 0.12777547538280487,
+      "learning_rate": 9.945341400501838e-05,
+      "loss": 0.6846,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 110,
+      "tokens_per_second_per_gpu": 997.71
+    },
+    {
+      "epoch": 0.16629135631387493,
+      "grad_norm": 0.12563012540340424,
+      "learning_rate": 9.927566530157298e-05,
+      "loss": 0.6765,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 120,
+      "tokens_per_second_per_gpu": 1120.19
+    },
+    {
+      "epoch": 0.1801489693400312,
+      "grad_norm": 0.13785897195339203,
+      "learning_rate": 9.907314022268946e-05,
+      "loss": 0.6315,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 130,
+      "tokens_per_second_per_gpu": 801.56
+    },
+    {
+      "epoch": 0.19400658236618742,
+      "grad_norm": 0.14731284976005554,
+      "learning_rate": 9.884594060032406e-05,
+      "loss": 0.6642,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 140,
+      "tokens_per_second_per_gpu": 944.29
+    },
+    {
+      "epoch": 0.20786419539234366,
+      "grad_norm": 0.1298578828573227,
+      "learning_rate": 9.859418067307928e-05,
+      "loss": 0.6696,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 150,
+      "tokens_per_second_per_gpu": 913.99
+    },
+    {
+      "epoch": 0.22172180841849992,
+      "grad_norm": 0.13122966885566711,
+      "learning_rate": 9.831798702876352e-05,
+      "loss": 0.6768,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 160,
+      "tokens_per_second_per_gpu": 983.71
+    },
+    {
+      "epoch": 0.23557942144465616,
+      "grad_norm": 0.12356515228748322,
+      "learning_rate": 9.801749854074122e-05,
+      "loss": 0.6526,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 170,
+      "tokens_per_second_per_gpu": 903.88
+    },
+    {
+      "epoch": 0.2494370344708124,
+      "grad_norm": 0.11831440776586533,
+      "learning_rate": 9.769286629810572e-05,
+      "loss": 0.6415,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 180,
+      "tokens_per_second_per_gpu": 819.58
+    },
+    {
+      "epoch": 0.2632946474969686,
+      "grad_norm": 0.12409751862287521,
+      "learning_rate": 9.73442535297099e-05,
+      "loss": 0.6685,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 190,
+      "tokens_per_second_per_gpu": 973.62
+    },
+    {
+      "epoch": 0.2771522605231249,
+      "grad_norm": 0.1352369785308838,
+      "learning_rate": 9.697183552209288e-05,
+      "loss": 0.6329,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 200,
+      "tokens_per_second_per_gpu": 903.58
+    },
+    {
+      "epoch": 0.29100987354928115,
+      "grad_norm": 0.12526443600654602,
+      "learning_rate": 9.657579953134383e-05,
+      "loss": 0.6452,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 210,
+      "tokens_per_second_per_gpu": 859.06
+    },
+    {
+      "epoch": 0.3048674865754374,
+      "grad_norm": 0.11614521592855453,
+      "learning_rate": 9.615634468894752e-05,
+      "loss": 0.6407,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 220,
+      "tokens_per_second_per_gpu": 850.93
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 0.1328686773777008,
+      "learning_rate": 9.571368190165863e-05,
+      "loss": 0.6741,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 230,
+      "tokens_per_second_per_gpu": 1038.17
+    },
+    {
+      "epoch": 0.33258271262774985,
+      "grad_norm": 0.13082517683506012,
+      "learning_rate": 9.524803374545548e-05,
+      "loss": 0.6906,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 240,
+      "tokens_per_second_per_gpu": 1066.43
+    },
+    {
+      "epoch": 0.3464403256539061,
+      "grad_norm": 0.1282692551612854,
+      "learning_rate": 9.475963435362614e-05,
+      "loss": 0.6609,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 250,
+      "tokens_per_second_per_gpu": 986.84
+    },
+    {
+      "epoch": 0.3602979386800624,
+      "grad_norm": 0.13708311319351196,
+      "learning_rate": 9.424872929904358e-05,
+      "loss": 0.6169,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 260,
+      "tokens_per_second_per_gpu": 1126.25
+    },
+    {
+      "epoch": 0.3741555517062186,
+      "grad_norm": 0.1323172152042389,
+      "learning_rate": 9.371557547068878e-05,
+      "loss": 0.6574,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 270,
+      "tokens_per_second_per_gpu": 1062.03
+    },
+    {
+      "epoch": 0.38801316473237485,
+      "grad_norm": 0.12729060649871826,
+      "learning_rate": 9.316044094448392e-05,
+      "loss": 0.6583,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 280,
+      "tokens_per_second_per_gpu": 941.33
+    },
+    {
+      "epoch": 0.4018707777585311,
+      "grad_norm": 0.14719286561012268,
+      "learning_rate": 9.25836048485008e-05,
+      "loss": 0.6392,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 290,
+      "tokens_per_second_per_gpu": 883.56
+    },
+    {
+      "epoch": 0.4157283907846873,
+      "grad_norm": 0.12530402839183807,
+      "learning_rate": 9.198535722261181e-05,
+      "loss": 0.6623,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 300,
+      "tokens_per_second_per_gpu": 902.6
+    },
+    {
+      "epoch": 0.4295860038108436,
+      "grad_norm": 0.1330760419368744,
+      "learning_rate": 9.136599887265483e-05,
+      "loss": 0.645,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 310,
+      "tokens_per_second_per_gpu": 997.96
+    },
+    {
+      "epoch": 0.44344361683699984,
+      "grad_norm": 0.13317464292049408,
+      "learning_rate": 9.072584121918425e-05,
+      "loss": 0.6139,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 320,
+      "tokens_per_second_per_gpu": 980.08
+    },
+    {
+      "epoch": 0.4573012298631561,
+      "grad_norm": 0.12773385643959045,
+      "learning_rate": 9.006520614088535e-05,
+      "loss": 0.6658,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 330,
+      "tokens_per_second_per_gpu": 937.57
+    },
+    {
+      "epoch": 0.4711588428893123,
+      "grad_norm": 0.13415341079235077,
+      "learning_rate": 8.938442581272983e-05,
+      "loss": 0.6737,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 340,
+      "tokens_per_second_per_gpu": 1046.92
+    },
+    {
+      "epoch": 0.48501645591546855,
+      "grad_norm": 0.13382680714130402,
+      "learning_rate": 8.868384253895445e-05,
+      "loss": 0.6575,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 350,
+      "tokens_per_second_per_gpu": 1049.72
+    },
+    {
+      "epoch": 0.4988740689416248,
+      "grad_norm": 0.12621234357357025,
+      "learning_rate": 8.796380858094643e-05,
+      "loss": 0.6423,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 360,
+      "tokens_per_second_per_gpu": 926.35
+    },
+    {
+      "epoch": 0.5127316819677811,
+      "grad_norm": 0.14663882553577423,
+      "learning_rate": 8.722468598012245e-05,
+      "loss": 0.6524,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 370,
+      "tokens_per_second_per_gpu": 993.98
+    },
+    {
+      "epoch": 0.5265892949939373,
+      "grad_norm": 0.12107036262750626,
+      "learning_rate": 8.646684637588991e-05,
+      "loss": 0.6158,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 380,
+      "tokens_per_second_per_gpu": 882.74
+    },
+    {
+      "epoch": 0.5404469080200935,
+      "grad_norm": 0.12905746698379517,
+      "learning_rate": 8.56906708187824e-05,
+      "loss": 0.6359,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 390,
+      "tokens_per_second_per_gpu": 992.61
+    },
+    {
+      "epoch": 0.5543045210462498,
+      "grad_norm": 0.14433123171329498,
+      "learning_rate": 8.489654957886306e-05,
+      "loss": 0.6124,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 400,
+      "tokens_per_second_per_gpu": 871.5
+    },
+    {
+      "epoch": 0.568162134072406,
+      "grad_norm": 0.13294072449207306,
+      "learning_rate": 8.40848819494923e-05,
+      "loss": 0.6803,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 410,
+      "tokens_per_second_per_gpu": 950.11
+    },
+    {
+      "epoch": 0.5820197470985623,
+      "grad_norm": 0.1526036411523819,
+      "learning_rate": 8.325607604655839e-05,
+      "loss": 0.6088,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 420,
+      "tokens_per_second_per_gpu": 1025.1
+    },
+    {
+      "epoch": 0.5958773601247185,
+      "grad_norm": 0.1453717052936554,
+      "learning_rate": 8.241054860327216e-05,
+      "loss": 0.6669,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 430,
+      "tokens_per_second_per_gpu": 1074.36
+    },
+    {
+      "epoch": 0.6097349731508748,
+      "grad_norm": 0.1466919481754303,
+      "learning_rate": 8.154872476062868e-05,
+      "loss": 0.6147,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 440,
+      "tokens_per_second_per_gpu": 1010.83
+    },
+    {
+      "epoch": 0.6235925861770311,
+      "grad_norm": 0.12707076966762543,
+      "learning_rate": 8.067103785364139e-05,
+      "loss": 0.6096,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 450,
+      "tokens_per_second_per_gpu": 919.83
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": 0.13485883176326752,
+      "learning_rate": 7.977792919345633e-05,
+      "loss": 0.6342,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 460,
+      "tokens_per_second_per_gpu": 1033.87
+    },
+    {
+      "epoch": 0.6513078122293435,
+      "grad_norm": 0.12489234656095505,
+      "learning_rate": 7.886984784545566e-05,
+      "loss": 0.6256,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 470,
+      "tokens_per_second_per_gpu": 1018.58
+    },
+    {
+      "epoch": 0.6651654252554997,
+      "grad_norm": 0.16094225645065308,
+      "learning_rate": 7.794725040346251e-05,
+      "loss": 0.6455,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 480,
+      "tokens_per_second_per_gpu": 933.16
+    },
+    {
+      "epoch": 0.679023038281656,
+      "grad_norm": 0.1351306140422821,
+      "learning_rate": 7.701060076016024e-05,
+      "loss": 0.6613,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 490,
+      "tokens_per_second_per_gpu": 970.62
+    },
+    {
+      "epoch": 0.6928806513078122,
+      "grad_norm": 0.1223958283662796,
+      "learning_rate": 7.606036987384184e-05,
+      "loss": 0.6186,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 500,
+      "tokens_per_second_per_gpu": 925.45
+    },
+    {
+      "epoch": 0.7067382643339685,
+      "grad_norm": 0.11873335391283035,
+      "learning_rate": 7.509703553160666e-05,
+      "loss": 0.646,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 510,
+      "tokens_per_second_per_gpu": 990.93
+    },
+    {
+      "epoch": 0.7205958773601248,
+      "grad_norm": 0.12990343570709229,
+      "learning_rate": 7.412108210912345e-05,
+      "loss": 0.6155,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 520,
+      "tokens_per_second_per_gpu": 955.97
+    },
+    {
+      "epoch": 0.7344534903862809,
+      "grad_norm": 0.1376057118177414,
+      "learning_rate": 7.31330003270808e-05,
+      "loss": 0.6443,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 530,
+      "tokens_per_second_per_gpu": 895.07
+    },
+    {
+      "epoch": 0.7483111034124372,
+      "grad_norm": 0.13277359306812286,
+      "learning_rate": 7.213328700444696e-05,
+      "loss": 0.6188,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 540,
+      "tokens_per_second_per_gpu": 907.27
+    },
+    {
+      "epoch": 0.7621687164385934,
+      "grad_norm": 0.13623632490634918,
+      "learning_rate": 7.112244480866356e-05,
+      "loss": 0.6471,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 550,
+      "tokens_per_second_per_gpu": 1002.06
+    },
+    {
+      "epoch": 0.7760263294647497,
+      "grad_norm": 0.13037075102329254,
+      "learning_rate": 7.010098200289859e-05,
+      "loss": 0.647,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 560,
+      "tokens_per_second_per_gpu": 1047.58
+    },
+    {
+      "epoch": 0.789883942490906,
+      "grad_norm": 0.12997141480445862,
+      "learning_rate": 6.906941219048584e-05,
+      "loss": 0.6071,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 570,
+      "tokens_per_second_per_gpu": 1073.59
+    },
+    {
+      "epoch": 0.8037415555170622,
+      "grad_norm": 0.14118416607379913,
+      "learning_rate": 6.802825405667905e-05,
+      "loss": 0.6101,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 580,
+      "tokens_per_second_per_gpu": 1097.31
+    },
+    {
+      "epoch": 0.8175991685432185,
+      "grad_norm": 0.126139834523201,
+      "learning_rate": 6.697803110785115e-05,
+      "loss": 0.6084,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 590,
+      "tokens_per_second_per_gpu": 933.94
+    },
+    {
+      "epoch": 0.8314567815693746,
+      "grad_norm": 0.1207822933793068,
+      "learning_rate": 6.591927140826902e-05,
+      "loss": 0.6416,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 600,
+      "tokens_per_second_per_gpu": 1007.52
+    },
+    {
+      "epoch": 0.8453143945955309,
+      "grad_norm": 0.1316983848810196,
+      "learning_rate": 6.485250731457678e-05,
+      "loss": 0.6102,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 610,
+      "tokens_per_second_per_gpu": 866.4
+    },
+    {
+      "epoch": 0.8591720076216872,
+      "grad_norm": 0.13538379967212677,
+      "learning_rate": 6.377827520812061e-05,
+      "loss": 0.6426,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 620,
+      "tokens_per_second_per_gpu": 1044.49
+    },
+    {
+      "epoch": 0.8730296206478434,
+      "grad_norm": 0.1406071037054062,
+      "learning_rate": 6.269711522525006e-05,
+      "loss": 0.6029,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 630,
+      "tokens_per_second_per_gpu": 966.75
+    },
+    {
+      "epoch": 0.8868872336739997,
+      "grad_norm": 0.1416017860174179,
+      "learning_rate": 6.160957098573119e-05,
+      "loss": 0.6103,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 640,
+      "tokens_per_second_per_gpu": 996.12
+    },
+    {
+      "epoch": 0.9007448467001559,
+      "grad_norm": 0.14168281853199005,
+      "learning_rate": 6.05161893194083e-05,
+      "loss": 0.6015,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 650,
+      "tokens_per_second_per_gpu": 1057.0
+    },
+    {
+      "epoch": 0.9146024597263122,
+      "grad_norm": 0.14854960143566132,
+      "learning_rate": 5.941751999125149e-05,
+      "loss": 0.5851,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 660,
+      "tokens_per_second_per_gpu": 992.44
+    },
+    {
+      "epoch": 0.9284600727524683,
+      "grad_norm": 0.13109387457370758,
+      "learning_rate": 5.831411542492854e-05,
+      "loss": 0.6221,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 670,
+      "tokens_per_second_per_gpu": 1056.52
+    },
+    {
+      "epoch": 0.9423176857786246,
+      "grad_norm": 0.13833071291446686,
+      "learning_rate": 5.720653042503978e-05,
+      "loss": 0.5828,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 680,
+      "tokens_per_second_per_gpu": 1061.91
+    },
+    {
+      "epoch": 0.9561752988047809,
+      "grad_norm": 0.1346118003129959,
+      "learning_rate": 5.6095321898156016e-05,
+      "loss": 0.5827,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 690,
+      "tokens_per_second_per_gpu": 1017.14
+    },
+    {
+      "epoch": 0.9700329118309371,
+      "grad_norm": 0.12667891383171082,
+      "learning_rate": 5.498104857279941e-05,
+      "loss": 0.6744,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 700,
+      "tokens_per_second_per_gpu": 956.99
+    },
+    {
+      "epoch": 0.9838905248570934,
+      "grad_norm": 0.13424526154994965,
+      "learning_rate": 5.3864270718508305e-05,
+      "loss": 0.6298,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 710,
+      "tokens_per_second_per_gpu": 953.92
+    },
+    {
+      "epoch": 0.9977481378832496,
+      "grad_norm": 0.12869331240653992,
+      "learning_rate": 5.274554986412716e-05,
+      "loss": 0.6199,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 720,
+      "tokens_per_second_per_gpu": 1040.0
+    },
+    {
+      "epoch": 1.011086090420925,
+      "grad_norm": 0.14841921627521515,
+      "learning_rate": 5.162544851546349e-05,
+      "loss": 0.6032,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 730,
+      "tokens_per_second_per_gpu": 885.8
+    },
+    {
+      "epoch": 1.0249437034470812,
+      "grad_norm": 0.15776373445987701,
+      "learning_rate": 5.0504529872453256e-05,
+      "loss": 0.5982,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 740,
+      "tokens_per_second_per_gpu": 1010.64
+    },
+    {
+      "epoch": 1.0388013164732375,
+      "grad_norm": 0.17491325736045837,
+      "learning_rate": 4.9383357545977497e-05,
+      "loss": 0.5993,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 750,
+      "tokens_per_second_per_gpu": 1085.43
+    },
+    {
+      "epoch": 1.0526589294993938,
+      "grad_norm": 0.15103822946548462,
+      "learning_rate": 4.8262495274472225e-05,
+      "loss": 0.5512,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 760,
+      "tokens_per_second_per_gpu": 1024.19
+    },
+    {
+      "epoch": 1.06651654252555,
+      "grad_norm": 0.15340133011341095,
+      "learning_rate": 4.7142506640474274e-05,
+      "loss": 0.5822,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 770,
+      "tokens_per_second_per_gpu": 1189.62
+    },
+    {
+      "epoch": 1.0803741555517061,
+      "grad_norm": 0.17283514142036438,
+      "learning_rate": 4.602395478724539e-05,
+      "loss": 0.5395,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 780,
+      "tokens_per_second_per_gpu": 1009.01
+    },
+    {
+      "epoch": 1.0942317685778624,
+      "grad_norm": 0.15003962814807892,
+      "learning_rate": 4.490740213561727e-05,
+      "loss": 0.5358,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 790,
+      "tokens_per_second_per_gpu": 1047.2
+    },
+    {
+      "epoch": 1.1080893816040187,
+      "grad_norm": 0.1629399210214615,
+      "learning_rate": 4.379341010119992e-05,
+      "loss": 0.601,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 800,
+      "tokens_per_second_per_gpu": 942.61
+    },
+    {
+      "epoch": 1.121946994630175,
+      "grad_norm": 0.17462220788002014,
+      "learning_rate": 4.268253881209532e-05,
+      "loss": 0.5845,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 810,
+      "tokens_per_second_per_gpu": 1010.69
+    },
+    {
+      "epoch": 1.1358046076563313,
+      "grad_norm": 0.17755432426929474,
+      "learning_rate": 4.157534682725856e-05,
+      "loss": 0.5637,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 820,
+      "tokens_per_second_per_gpu": 911.61
+    },
+    {
+      "epoch": 1.1496622206824874,
+      "grad_norm": 0.1729191541671753,
+      "learning_rate": 4.047239085564794e-05,
+      "loss": 0.5921,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 830,
+      "tokens_per_second_per_gpu": 914.41
+    },
+    {
+      "epoch": 1.1635198337086436,
+      "grad_norm": 0.15745393931865692,
+      "learning_rate": 3.937422547630519e-05,
+      "loss": 0.6086,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 840,
+      "tokens_per_second_per_gpu": 1000.17
+    },
+    {
+      "epoch": 1.1773774467348,
+      "grad_norm": 0.16624517738819122,
+      "learning_rate": 3.828140285950676e-05,
+      "loss": 0.5603,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 850,
+      "tokens_per_second_per_gpu": 991.45
+    },
+    {
+      "epoch": 1.1912350597609562,
+      "grad_norm": 0.17486163973808289,
+      "learning_rate": 3.7194472489126176e-05,
+      "loss": 0.5715,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 860,
+      "tokens_per_second_per_gpu": 1005.74
+    },
+    {
+      "epoch": 1.2050926727871123,
+      "grad_norm": 0.18270528316497803,
+      "learning_rate": 3.611398088634721e-05,
+      "loss": 0.5577,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 870,
+      "tokens_per_second_per_gpu": 965.77
+    },
+    {
+      "epoch": 1.2189502858132686,
+      "grad_norm": 0.1544029712677002,
+      "learning_rate": 3.5040471334866695e-05,
+      "loss": 0.5706,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 880,
+      "tokens_per_second_per_gpu": 885.82
+    },
+    {
+      "epoch": 1.2328078988394249,
+      "grad_norm": 0.1610870063304901,
+      "learning_rate": 3.397448360772516e-05,
+      "loss": 0.5791,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 890,
+      "tokens_per_second_per_gpu": 903.16
+    },
+    {
+      "epoch": 1.2466655118655812,
+      "grad_norm": 0.15956935286521912,
+      "learning_rate": 3.291655369590269e-05,
+      "loss": 0.5978,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 900,
+      "tokens_per_second_per_gpu": 954.24
+    },
+    {
+      "epoch": 1.2605231248917375,
+      "grad_norm": 0.17166025936603546,
+      "learning_rate": 3.186721353881648e-05,
+      "loss": 0.5702,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 910,
+      "tokens_per_second_per_gpu": 1044.16
+    },
+    {
+      "epoch": 1.2743807379178937,
+      "grad_norm": 0.1581714153289795,
+      "learning_rate": 3.082699075685553e-05,
+      "loss": 0.5839,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 920,
+      "tokens_per_second_per_gpu": 924.88
+    },
+    {
+      "epoch": 1.2882383509440498,
+      "grad_norm": 0.17262092232704163,
+      "learning_rate": 2.9796408386086962e-05,
+      "loss": 0.5687,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 84.97,
+      "memory/max_allocated (GiB)": 84.97,
+      "step": 930,
+      "tokens_per_second_per_gpu": 896.89
+    },
+    {
+      "epoch": 1.302095963970206,
+      "grad_norm": 0.2113182544708252,
+      "learning_rate": 2.8775984615267504e-05,
+      "loss": 0.5764,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 940,
+      "tokens_per_second_per_gpu": 871.53
+    },
+    {
+      "epoch": 1.3159535769963624,
+      "grad_norm": 0.16499237716197968,
+      "learning_rate": 2.7766232525292103e-05,
+      "loss": 0.5451,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 950,
+      "tokens_per_second_per_gpu": 846.63
+    },
+    {
+      "epoch": 1.3298111900225187,
+      "grad_norm": 0.16787481307983398,
+      "learning_rate": 2.676765983121089e-05,
+      "loss": 0.5698,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 960,
+      "tokens_per_second_per_gpu": 996.59
+    },
+    {
+      "epoch": 1.3436688030486748,
+      "grad_norm": 0.17758306860923767,
+      "learning_rate": 2.578076862694426e-05,
+      "loss": 0.5677,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 970,
+      "tokens_per_second_per_gpu": 990.05
+    },
+    {
+      "epoch": 1.357526416074831,
+      "grad_norm": 0.1822880357503891,
+      "learning_rate": 2.4806055132824185e-05,
+      "loss": 0.5832,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 980,
+      "tokens_per_second_per_gpu": 941.98
+    },
+    {
+      "epoch": 1.3713840291009873,
+      "grad_norm": 0.19017541408538818,
+      "learning_rate": 2.384400944608886e-05,
+      "loss": 0.5803,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 990,
+      "tokens_per_second_per_gpu": 942.86
+    },
+    {
+      "epoch": 1.3852416421271436,
+      "grad_norm": 0.19104644656181335,
+      "learning_rate": 2.289511529445616e-05,
+      "loss": 0.5507,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1000,
+      "tokens_per_second_per_gpu": 905.35
+    },
+    {
+      "epoch": 1.3990992551533,
+      "grad_norm": 0.16881509125232697,
+      "learning_rate": 2.195984979289974e-05,
+      "loss": 0.5855,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1010,
+      "tokens_per_second_per_gpu": 963.29
+    },
+    {
+      "epoch": 1.4129568681794562,
+      "grad_norm": 0.17394502460956573,
+      "learning_rate": 2.1038683203750092e-05,
+      "loss": 0.593,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1020,
+      "tokens_per_second_per_gpu": 874.44
+    },
+    {
+      "epoch": 1.4268144812056123,
+      "grad_norm": 0.17141559720039368,
+      "learning_rate": 2.0132078700241158e-05,
+      "loss": 0.5932,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1030,
+      "tokens_per_second_per_gpu": 898.09
+    },
+    {
+      "epoch": 1.4406720942317686,
+      "grad_norm": 0.17774531245231628,
+      "learning_rate": 1.924049213362153e-05,
+      "loss": 0.5972,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1040,
+      "tokens_per_second_per_gpu": 780.07
+    },
+    {
+      "epoch": 1.4545297072579249,
+      "grad_norm": 0.18897521495819092,
+      "learning_rate": 1.836437180394715e-05,
+      "loss": 0.5828,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1050,
+      "tokens_per_second_per_gpu": 1176.61
+    },
+    {
+      "epoch": 1.4683873202840811,
+      "grad_norm": 0.1707300990819931,
+      "learning_rate": 1.750415823467082e-05,
+      "loss": 0.5548,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1060,
+      "tokens_per_second_per_gpu": 1087.95
+    },
+    {
+      "epoch": 1.4822449333102372,
+      "grad_norm": 0.1707785278558731,
+      "learning_rate": 1.666028395114185e-05,
+      "loss": 0.5622,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1070,
+      "tokens_per_second_per_gpu": 840.77
+    },
+    {
+      "epoch": 1.4961025463363935,
+      "grad_norm": 0.1891181617975235,
+      "learning_rate": 1.5833173263127426e-05,
+      "loss": 0.5373,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1080,
+      "tokens_per_second_per_gpu": 1017.51
+    },
+    {
+      "epoch": 1.5099601593625498,
+      "grad_norm": 0.17579694092273712,
+      "learning_rate": 1.5023242051464675e-05,
+      "loss": 0.5578,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1090,
+      "tokens_per_second_per_gpu": 976.53
+    },
+    {
+      "epoch": 1.523817772388706,
+      "grad_norm": 0.16882087290287018,
+      "learning_rate": 1.4230897558950951e-05,
+      "loss": 0.5754,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1100,
+      "tokens_per_second_per_gpu": 1004.78
+    },
+    {
+      "epoch": 1.5376753854148624,
+      "grad_norm": 0.1948268711566925,
+      "learning_rate": 1.3456538185577466e-05,
+      "loss": 0.5399,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1110,
+      "tokens_per_second_per_gpu": 1117.6
+    },
+    {
+      "epoch": 1.5515329984410187,
+      "grad_norm": 0.19728456437587738,
+      "learning_rate": 1.2700553288209126e-05,
+      "loss": 0.5915,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1120,
+      "tokens_per_second_per_gpu": 882.19
+    },
+    {
+      "epoch": 1.5653906114671747,
+      "grad_norm": 0.17635080218315125,
+      "learning_rate": 1.1963322984811453e-05,
+      "loss": 0.5671,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1130,
+      "tokens_per_second_per_gpu": 1119.95
+    },
+    {
+      "epoch": 1.579248224493331,
+      "grad_norm": 0.17266033589839935,
+      "learning_rate": 1.1245217963322763e-05,
+      "loss": 0.5755,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1140,
+      "tokens_per_second_per_gpu": 788.89
+    },
+    {
+      "epoch": 1.5931058375194873,
+      "grad_norm": 0.17995904386043549,
+      "learning_rate": 1.0546599295268061e-05,
+      "loss": 0.5328,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1150,
+      "tokens_per_second_per_gpu": 948.5
+    },
+    {
+      "epoch": 1.6069634505456434,
+      "grad_norm": 0.17355145514011383,
+      "learning_rate": 9.867818254208123e-06,
+      "loss": 0.5633,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1160,
+      "tokens_per_second_per_gpu": 965.8
+    },
+    {
+      "epoch": 1.6208210635717997,
+      "grad_norm": 0.18094998598098755,
+      "learning_rate": 9.209216139114935e-06,
+      "loss": 0.5425,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1170,
+      "tokens_per_second_per_gpu": 914.6
+    },
+    {
+      "epoch": 1.634678676597956,
+      "grad_norm": 0.19211266934871674,
+      "learning_rate": 8.571124102762768e-06,
+      "loss": 0.577,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1180,
+      "tokens_per_second_per_gpu": 987.37
+    },
+    {
+      "epoch": 1.6485362896241122,
+      "grad_norm": 0.1781914234161377,
+      "learning_rate": 7.95386298522065e-06,
+      "loss": 0.5719,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1190,
+      "tokens_per_second_per_gpu": 864.39
+    },
+    {
+      "epoch": 1.6623939026502685,
+      "grad_norm": 0.17774876952171326,
+      "learning_rate": 7.357743152530272e-06,
+      "loss": 0.5647,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1200,
+      "tokens_per_second_per_gpu": 954.56
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1444,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0675487659052237e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1418985538671b467762281d3c852d707544317aa0efccdb1a0b18aa66639c19
+size 7249

checkpoint-1444/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-32B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-32B
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1444/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1444/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d3102e68745e66c2daef4aaa01521bf2bec17841374a7c32db1b5afda55bfb
+size 1073863208

checkpoint-1444/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1444/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1444/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f5dff1b1fcb6423020c9f8905b0841a5de4b7356d45f4f318a28ea77216868
+size 2148242275

checkpoint-1444/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bb4df015b94dc175944b6277d06d9165d32dbe1723ed3b38a6fb25dada5658
+size 14645

checkpoint-1444/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedcb61d83c8935dbbf7d21057b3d31441ac3cd1a351783cc6609ce5bcede172
+size 1465

checkpoint-1444/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1444/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1444/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1444/trainer_state.json

@@ -0,0 +1,1618 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1444,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013857613026156245,
+      "grad_norm": 0.1854863315820694,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 0.8494,
+      "memory/device_reserved (GiB)": 89.89,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 10,
+      "tokens_per_second_per_gpu": 1111.65
+    },
+    {
+      "epoch": 0.02771522605231249,
+      "grad_norm": 0.09567277133464813,
+      "learning_rate": 4.418604651162791e-05,
+      "loss": 0.7842,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 20,
+      "tokens_per_second_per_gpu": 1041.18
+    },
+    {
+      "epoch": 0.04157283907846873,
+      "grad_norm": 0.1211227998137474,
+      "learning_rate": 6.744186046511628e-05,
+      "loss": 0.7353,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 30,
+      "tokens_per_second_per_gpu": 993.82
+    },
+    {
+      "epoch": 0.05543045210462498,
+      "grad_norm": 0.09696491807699203,
+      "learning_rate": 9.069767441860465e-05,
+      "loss": 0.6943,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 40,
+      "tokens_per_second_per_gpu": 849.91
+    },
+    {
+      "epoch": 0.06928806513078123,
+      "grad_norm": 0.12007619440555573,
+      "learning_rate": 9.999547457436221e-05,
+      "loss": 0.6814,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 50,
+      "tokens_per_second_per_gpu": 971.92
+    },
+    {
+      "epoch": 0.08314567815693746,
+      "grad_norm": 0.12358752638101578,
+      "learning_rate": 9.996782216198338e-05,
+      "loss": 0.69,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 60,
+      "tokens_per_second_per_gpu": 862.06
+    },
+    {
+      "epoch": 0.09700329118309371,
+      "grad_norm": 0.11916535347700119,
+      "learning_rate": 9.991504534967746e-05,
+      "loss": 0.7048,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 70,
+      "tokens_per_second_per_gpu": 1024.18
+    },
+    {
+      "epoch": 0.11086090420924996,
+      "grad_norm": 0.12464027106761932,
+      "learning_rate": 9.983717067423721e-05,
+      "loss": 0.6705,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 80,
+      "tokens_per_second_per_gpu": 1009.08
+    },
+    {
+      "epoch": 0.1247185172354062,
+      "grad_norm": 0.1264505237340927,
+      "learning_rate": 9.973423729195168e-05,
+      "loss": 0.6387,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 90,
+      "tokens_per_second_per_gpu": 1027.91
+    },
+    {
+      "epoch": 0.13857613026156246,
+      "grad_norm": 0.1262999027967453,
+      "learning_rate": 9.960629695891814e-05,
+      "loss": 0.6447,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 100,
+      "tokens_per_second_per_gpu": 935.25
+    },
+    {
+      "epoch": 0.1524337432877187,
+      "grad_norm": 0.12777547538280487,
+      "learning_rate": 9.945341400501838e-05,
+      "loss": 0.6846,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 110,
+      "tokens_per_second_per_gpu": 997.71
+    },
+    {
+      "epoch": 0.16629135631387493,
+      "grad_norm": 0.12563012540340424,
+      "learning_rate": 9.927566530157298e-05,
+      "loss": 0.6765,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 120,
+      "tokens_per_second_per_gpu": 1120.19
+    },
+    {
+      "epoch": 0.1801489693400312,
+      "grad_norm": 0.13785897195339203,
+      "learning_rate": 9.907314022268946e-05,
+      "loss": 0.6315,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 130,
+      "tokens_per_second_per_gpu": 801.56
+    },
+    {
+      "epoch": 0.19400658236618742,
+      "grad_norm": 0.14731284976005554,
+      "learning_rate": 9.884594060032406e-05,
+      "loss": 0.6642,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 140,
+      "tokens_per_second_per_gpu": 944.29
+    },
+    {
+      "epoch": 0.20786419539234366,
+      "grad_norm": 0.1298578828573227,
+      "learning_rate": 9.859418067307928e-05,
+      "loss": 0.6696,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 150,
+      "tokens_per_second_per_gpu": 913.99
+    },
+    {
+      "epoch": 0.22172180841849992,
+      "grad_norm": 0.13122966885566711,
+      "learning_rate": 9.831798702876352e-05,
+      "loss": 0.6768,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 160,
+      "tokens_per_second_per_gpu": 983.71
+    },
+    {
+      "epoch": 0.23557942144465616,
+      "grad_norm": 0.12356515228748322,
+      "learning_rate": 9.801749854074122e-05,
+      "loss": 0.6526,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 170,
+      "tokens_per_second_per_gpu": 903.88
+    },
+    {
+      "epoch": 0.2494370344708124,
+      "grad_norm": 0.11831440776586533,
+      "learning_rate": 9.769286629810572e-05,
+      "loss": 0.6415,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 180,
+      "tokens_per_second_per_gpu": 819.58
+    },
+    {
+      "epoch": 0.2632946474969686,
+      "grad_norm": 0.12409751862287521,
+      "learning_rate": 9.73442535297099e-05,
+      "loss": 0.6685,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 190,
+      "tokens_per_second_per_gpu": 973.62
+    },
+    {
+      "epoch": 0.2771522605231249,
+      "grad_norm": 0.1352369785308838,
+      "learning_rate": 9.697183552209288e-05,
+      "loss": 0.6329,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 200,
+      "tokens_per_second_per_gpu": 903.58
+    },
+    {
+      "epoch": 0.29100987354928115,
+      "grad_norm": 0.12526443600654602,
+      "learning_rate": 9.657579953134383e-05,
+      "loss": 0.6452,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 210,
+      "tokens_per_second_per_gpu": 859.06
+    },
+    {
+      "epoch": 0.3048674865754374,
+      "grad_norm": 0.11614521592855453,
+      "learning_rate": 9.615634468894752e-05,
+      "loss": 0.6407,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 220,
+      "tokens_per_second_per_gpu": 850.93
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 0.1328686773777008,
+      "learning_rate": 9.571368190165863e-05,
+      "loss": 0.6741,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 230,
+      "tokens_per_second_per_gpu": 1038.17
+    },
+    {
+      "epoch": 0.33258271262774985,
+      "grad_norm": 0.13082517683506012,
+      "learning_rate": 9.524803374545548e-05,
+      "loss": 0.6906,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 240,
+      "tokens_per_second_per_gpu": 1066.43
+    },
+    {
+      "epoch": 0.3464403256539061,
+      "grad_norm": 0.1282692551612854,
+      "learning_rate": 9.475963435362614e-05,
+      "loss": 0.6609,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 250,
+      "tokens_per_second_per_gpu": 986.84
+    },
+    {
+      "epoch": 0.3602979386800624,
+      "grad_norm": 0.13708311319351196,
+      "learning_rate": 9.424872929904358e-05,
+      "loss": 0.6169,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 260,
+      "tokens_per_second_per_gpu": 1126.25
+    },
+    {
+      "epoch": 0.3741555517062186,
+      "grad_norm": 0.1323172152042389,
+      "learning_rate": 9.371557547068878e-05,
+      "loss": 0.6574,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 270,
+      "tokens_per_second_per_gpu": 1062.03
+    },
+    {
+      "epoch": 0.38801316473237485,
+      "grad_norm": 0.12729060649871826,
+      "learning_rate": 9.316044094448392e-05,
+      "loss": 0.6583,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 280,
+      "tokens_per_second_per_gpu": 941.33
+    },
+    {
+      "epoch": 0.4018707777585311,
+      "grad_norm": 0.14719286561012268,
+      "learning_rate": 9.25836048485008e-05,
+      "loss": 0.6392,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 290,
+      "tokens_per_second_per_gpu": 883.56
+    },
+    {
+      "epoch": 0.4157283907846873,
+      "grad_norm": 0.12530402839183807,
+      "learning_rate": 9.198535722261181e-05,
+      "loss": 0.6623,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 300,
+      "tokens_per_second_per_gpu": 902.6
+    },
+    {
+      "epoch": 0.4295860038108436,
+      "grad_norm": 0.1330760419368744,
+      "learning_rate": 9.136599887265483e-05,
+      "loss": 0.645,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 310,
+      "tokens_per_second_per_gpu": 997.96
+    },
+    {
+      "epoch": 0.44344361683699984,
+      "grad_norm": 0.13317464292049408,
+      "learning_rate": 9.072584121918425e-05,
+      "loss": 0.6139,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 320,
+      "tokens_per_second_per_gpu": 980.08
+    },
+    {
+      "epoch": 0.4573012298631561,
+      "grad_norm": 0.12773385643959045,
+      "learning_rate": 9.006520614088535e-05,
+      "loss": 0.6658,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 330,
+      "tokens_per_second_per_gpu": 937.57
+    },
+    {
+      "epoch": 0.4711588428893123,
+      "grad_norm": 0.13415341079235077,
+      "learning_rate": 8.938442581272983e-05,
+      "loss": 0.6737,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 340,
+      "tokens_per_second_per_gpu": 1046.92
+    },
+    {
+      "epoch": 0.48501645591546855,
+      "grad_norm": 0.13382680714130402,
+      "learning_rate": 8.868384253895445e-05,
+      "loss": 0.6575,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 350,
+      "tokens_per_second_per_gpu": 1049.72
+    },
+    {
+      "epoch": 0.4988740689416248,
+      "grad_norm": 0.12621234357357025,
+      "learning_rate": 8.796380858094643e-05,
+      "loss": 0.6423,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 360,
+      "tokens_per_second_per_gpu": 926.35
+    },
+    {
+      "epoch": 0.5127316819677811,
+      "grad_norm": 0.14663882553577423,
+      "learning_rate": 8.722468598012245e-05,
+      "loss": 0.6524,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 370,
+      "tokens_per_second_per_gpu": 993.98
+    },
+    {
+      "epoch": 0.5265892949939373,
+      "grad_norm": 0.12107036262750626,
+      "learning_rate": 8.646684637588991e-05,
+      "loss": 0.6158,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 380,
+      "tokens_per_second_per_gpu": 882.74
+    },
+    {
+      "epoch": 0.5404469080200935,
+      "grad_norm": 0.12905746698379517,
+      "learning_rate": 8.56906708187824e-05,
+      "loss": 0.6359,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 390,
+      "tokens_per_second_per_gpu": 992.61
+    },
+    {
+      "epoch": 0.5543045210462498,
+      "grad_norm": 0.14433123171329498,
+      "learning_rate": 8.489654957886306e-05,
+      "loss": 0.6124,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 400,
+      "tokens_per_second_per_gpu": 871.5
+    },
+    {
+      "epoch": 0.568162134072406,
+      "grad_norm": 0.13294072449207306,
+      "learning_rate": 8.40848819494923e-05,
+      "loss": 0.6803,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 410,
+      "tokens_per_second_per_gpu": 950.11
+    },
+    {
+      "epoch": 0.5820197470985623,
+      "grad_norm": 0.1526036411523819,
+      "learning_rate": 8.325607604655839e-05,
+      "loss": 0.6088,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 420,
+      "tokens_per_second_per_gpu": 1025.1
+    },
+    {
+      "epoch": 0.5958773601247185,
+      "grad_norm": 0.1453717052936554,
+      "learning_rate": 8.241054860327216e-05,
+      "loss": 0.6669,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 430,
+      "tokens_per_second_per_gpu": 1074.36
+    },
+    {
+      "epoch": 0.6097349731508748,
+      "grad_norm": 0.1466919481754303,
+      "learning_rate": 8.154872476062868e-05,
+      "loss": 0.6147,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 440,
+      "tokens_per_second_per_gpu": 1010.83
+    },
+    {
+      "epoch": 0.6235925861770311,
+      "grad_norm": 0.12707076966762543,
+      "learning_rate": 8.067103785364139e-05,
+      "loss": 0.6096,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 450,
+      "tokens_per_second_per_gpu": 919.83
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": 0.13485883176326752,
+      "learning_rate": 7.977792919345633e-05,
+      "loss": 0.6342,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 460,
+      "tokens_per_second_per_gpu": 1033.87
+    },
+    {
+      "epoch": 0.6513078122293435,
+      "grad_norm": 0.12489234656095505,
+      "learning_rate": 7.886984784545566e-05,
+      "loss": 0.6256,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 470,
+      "tokens_per_second_per_gpu": 1018.58
+    },
+    {
+      "epoch": 0.6651654252554997,
+      "grad_norm": 0.16094225645065308,
+      "learning_rate": 7.794725040346251e-05,
+      "loss": 0.6455,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 480,
+      "tokens_per_second_per_gpu": 933.16
+    },
+    {
+      "epoch": 0.679023038281656,
+      "grad_norm": 0.1351306140422821,
+      "learning_rate": 7.701060076016024e-05,
+      "loss": 0.6613,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 490,
+      "tokens_per_second_per_gpu": 970.62
+    },
+    {
+      "epoch": 0.6928806513078122,
+      "grad_norm": 0.1223958283662796,
+      "learning_rate": 7.606036987384184e-05,
+      "loss": 0.6186,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 500,
+      "tokens_per_second_per_gpu": 925.45
+    },
+    {
+      "epoch": 0.7067382643339685,
+      "grad_norm": 0.11873335391283035,
+      "learning_rate": 7.509703553160666e-05,
+      "loss": 0.646,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 510,
+      "tokens_per_second_per_gpu": 990.93
+    },
+    {
+      "epoch": 0.7205958773601248,
+      "grad_norm": 0.12990343570709229,
+      "learning_rate": 7.412108210912345e-05,
+      "loss": 0.6155,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 520,
+      "tokens_per_second_per_gpu": 955.97
+    },
+    {
+      "epoch": 0.7344534903862809,
+      "grad_norm": 0.1376057118177414,
+      "learning_rate": 7.31330003270808e-05,
+      "loss": 0.6443,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 530,
+      "tokens_per_second_per_gpu": 895.07
+    },
+    {
+      "epoch": 0.7483111034124372,
+      "grad_norm": 0.13277359306812286,
+      "learning_rate": 7.213328700444696e-05,
+      "loss": 0.6188,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 540,
+      "tokens_per_second_per_gpu": 907.27
+    },
+    {
+      "epoch": 0.7621687164385934,
+      "grad_norm": 0.13623632490634918,
+      "learning_rate": 7.112244480866356e-05,
+      "loss": 0.6471,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 550,
+      "tokens_per_second_per_gpu": 1002.06
+    },
+    {
+      "epoch": 0.7760263294647497,
+      "grad_norm": 0.13037075102329254,
+      "learning_rate": 7.010098200289859e-05,
+      "loss": 0.647,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 560,
+      "tokens_per_second_per_gpu": 1047.58
+    },
+    {
+      "epoch": 0.789883942490906,
+      "grad_norm": 0.12997141480445862,
+      "learning_rate": 6.906941219048584e-05,
+      "loss": 0.6071,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 570,
+      "tokens_per_second_per_gpu": 1073.59
+    },
+    {
+      "epoch": 0.8037415555170622,
+      "grad_norm": 0.14118416607379913,
+      "learning_rate": 6.802825405667905e-05,
+      "loss": 0.6101,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 580,
+      "tokens_per_second_per_gpu": 1097.31
+    },
+    {
+      "epoch": 0.8175991685432185,
+      "grad_norm": 0.126139834523201,
+      "learning_rate": 6.697803110785115e-05,
+      "loss": 0.6084,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 590,
+      "tokens_per_second_per_gpu": 933.94
+    },
+    {
+      "epoch": 0.8314567815693746,
+      "grad_norm": 0.1207822933793068,
+      "learning_rate": 6.591927140826902e-05,
+      "loss": 0.6416,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 600,
+      "tokens_per_second_per_gpu": 1007.52
+    },
+    {
+      "epoch": 0.8453143945955309,
+      "grad_norm": 0.1316983848810196,
+      "learning_rate": 6.485250731457678e-05,
+      "loss": 0.6102,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 610,
+      "tokens_per_second_per_gpu": 866.4
+    },
+    {
+      "epoch": 0.8591720076216872,
+      "grad_norm": 0.13538379967212677,
+      "learning_rate": 6.377827520812061e-05,
+      "loss": 0.6426,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 620,
+      "tokens_per_second_per_gpu": 1044.49
+    },
+    {
+      "epoch": 0.8730296206478434,
+      "grad_norm": 0.1406071037054062,
+      "learning_rate": 6.269711522525006e-05,
+      "loss": 0.6029,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 630,
+      "tokens_per_second_per_gpu": 966.75
+    },
+    {
+      "epoch": 0.8868872336739997,
+      "grad_norm": 0.1416017860174179,
+      "learning_rate": 6.160957098573119e-05,
+      "loss": 0.6103,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 640,
+      "tokens_per_second_per_gpu": 996.12
+    },
+    {
+      "epoch": 0.9007448467001559,
+      "grad_norm": 0.14168281853199005,
+      "learning_rate": 6.05161893194083e-05,
+      "loss": 0.6015,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 650,
+      "tokens_per_second_per_gpu": 1057.0
+    },
+    {
+      "epoch": 0.9146024597263122,
+      "grad_norm": 0.14854960143566132,
+      "learning_rate": 5.941751999125149e-05,
+      "loss": 0.5851,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 660,
+      "tokens_per_second_per_gpu": 992.44
+    },
+    {
+      "epoch": 0.9284600727524683,
+      "grad_norm": 0.13109387457370758,
+      "learning_rate": 5.831411542492854e-05,
+      "loss": 0.6221,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 670,
+      "tokens_per_second_per_gpu": 1056.52
+    },
+    {
+      "epoch": 0.9423176857786246,
+      "grad_norm": 0.13833071291446686,
+      "learning_rate": 5.720653042503978e-05,
+      "loss": 0.5828,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 680,
+      "tokens_per_second_per_gpu": 1061.91
+    },
+    {
+      "epoch": 0.9561752988047809,
+      "grad_norm": 0.1346118003129959,
+      "learning_rate": 5.6095321898156016e-05,
+      "loss": 0.5827,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 690,
+      "tokens_per_second_per_gpu": 1017.14
+    },
+    {
+      "epoch": 0.9700329118309371,
+      "grad_norm": 0.12667891383171082,
+      "learning_rate": 5.498104857279941e-05,
+      "loss": 0.6744,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 700,
+      "tokens_per_second_per_gpu": 956.99
+    },
+    {
+      "epoch": 0.9838905248570934,
+      "grad_norm": 0.13424526154994965,
+      "learning_rate": 5.3864270718508305e-05,
+      "loss": 0.6298,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 710,
+      "tokens_per_second_per_gpu": 953.92
+    },
+    {
+      "epoch": 0.9977481378832496,
+      "grad_norm": 0.12869331240653992,
+      "learning_rate": 5.274554986412716e-05,
+      "loss": 0.6199,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 720,
+      "tokens_per_second_per_gpu": 1040.0
+    },
+    {
+      "epoch": 1.011086090420925,
+      "grad_norm": 0.14841921627521515,
+      "learning_rate": 5.162544851546349e-05,
+      "loss": 0.6032,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 730,
+      "tokens_per_second_per_gpu": 885.8
+    },
+    {
+      "epoch": 1.0249437034470812,
+      "grad_norm": 0.15776373445987701,
+      "learning_rate": 5.0504529872453256e-05,
+      "loss": 0.5982,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 740,
+      "tokens_per_second_per_gpu": 1010.64
+    },
+    {
+      "epoch": 1.0388013164732375,
+      "grad_norm": 0.17491325736045837,
+      "learning_rate": 4.9383357545977497e-05,
+      "loss": 0.5993,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 750,
+      "tokens_per_second_per_gpu": 1085.43
+    },
+    {
+      "epoch": 1.0526589294993938,
+      "grad_norm": 0.15103822946548462,
+      "learning_rate": 4.8262495274472225e-05,
+      "loss": 0.5512,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 760,
+      "tokens_per_second_per_gpu": 1024.19
+    },
+    {
+      "epoch": 1.06651654252555,
+      "grad_norm": 0.15340133011341095,
+      "learning_rate": 4.7142506640474274e-05,
+      "loss": 0.5822,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 770,
+      "tokens_per_second_per_gpu": 1189.62
+    },
+    {
+      "epoch": 1.0803741555517061,
+      "grad_norm": 0.17283514142036438,
+      "learning_rate": 4.602395478724539e-05,
+      "loss": 0.5395,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 780,
+      "tokens_per_second_per_gpu": 1009.01
+    },
+    {
+      "epoch": 1.0942317685778624,
+      "grad_norm": 0.15003962814807892,
+      "learning_rate": 4.490740213561727e-05,
+      "loss": 0.5358,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 790,
+      "tokens_per_second_per_gpu": 1047.2
+    },
+    {
+      "epoch": 1.1080893816040187,
+      "grad_norm": 0.1629399210214615,
+      "learning_rate": 4.379341010119992e-05,
+      "loss": 0.601,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 800,
+      "tokens_per_second_per_gpu": 942.61
+    },
+    {
+      "epoch": 1.121946994630175,
+      "grad_norm": 0.17462220788002014,
+      "learning_rate": 4.268253881209532e-05,
+      "loss": 0.5845,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 810,
+      "tokens_per_second_per_gpu": 1010.69
+    },
+    {
+      "epoch": 1.1358046076563313,
+      "grad_norm": 0.17755432426929474,
+      "learning_rate": 4.157534682725856e-05,
+      "loss": 0.5637,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 820,
+      "tokens_per_second_per_gpu": 911.61
+    },
+    {
+      "epoch": 1.1496622206824874,
+      "grad_norm": 0.1729191541671753,
+      "learning_rate": 4.047239085564794e-05,
+      "loss": 0.5921,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 830,
+      "tokens_per_second_per_gpu": 914.41
+    },
+    {
+      "epoch": 1.1635198337086436,
+      "grad_norm": 0.15745393931865692,
+      "learning_rate": 3.937422547630519e-05,
+      "loss": 0.6086,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 840,
+      "tokens_per_second_per_gpu": 1000.17
+    },
+    {
+      "epoch": 1.1773774467348,
+      "grad_norm": 0.16624517738819122,
+      "learning_rate": 3.828140285950676e-05,
+      "loss": 0.5603,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 850,
+      "tokens_per_second_per_gpu": 991.45
+    },
+    {
+      "epoch": 1.1912350597609562,
+      "grad_norm": 0.17486163973808289,
+      "learning_rate": 3.7194472489126176e-05,
+      "loss": 0.5715,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 860,
+      "tokens_per_second_per_gpu": 1005.74
+    },
+    {
+      "epoch": 1.2050926727871123,
+      "grad_norm": 0.18270528316497803,
+      "learning_rate": 3.611398088634721e-05,
+      "loss": 0.5577,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 870,
+      "tokens_per_second_per_gpu": 965.77
+    },
+    {
+      "epoch": 1.2189502858132686,
+      "grad_norm": 0.1544029712677002,
+      "learning_rate": 3.5040471334866695e-05,
+      "loss": 0.5706,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 880,
+      "tokens_per_second_per_gpu": 885.82
+    },
+    {
+      "epoch": 1.2328078988394249,
+      "grad_norm": 0.1610870063304901,
+      "learning_rate": 3.397448360772516e-05,
+      "loss": 0.5791,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 890,
+      "tokens_per_second_per_gpu": 903.16
+    },
+    {
+      "epoch": 1.2466655118655812,
+      "grad_norm": 0.15956935286521912,
+      "learning_rate": 3.291655369590269e-05,
+      "loss": 0.5978,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 900,
+      "tokens_per_second_per_gpu": 954.24
+    },
+    {
+      "epoch": 1.2605231248917375,
+      "grad_norm": 0.17166025936603546,
+      "learning_rate": 3.186721353881648e-05,
+      "loss": 0.5702,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 910,
+      "tokens_per_second_per_gpu": 1044.16
+    },
+    {
+      "epoch": 1.2743807379178937,
+      "grad_norm": 0.1581714153289795,
+      "learning_rate": 3.082699075685553e-05,
+      "loss": 0.5839,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 920,
+      "tokens_per_second_per_gpu": 924.88
+    },
+    {
+      "epoch": 1.2882383509440498,
+      "grad_norm": 0.17262092232704163,
+      "learning_rate": 2.9796408386086962e-05,
+      "loss": 0.5687,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 84.97,
+      "memory/max_allocated (GiB)": 84.97,
+      "step": 930,
+      "tokens_per_second_per_gpu": 896.89
+    },
+    {
+      "epoch": 1.302095963970206,
+      "grad_norm": 0.2113182544708252,
+      "learning_rate": 2.8775984615267504e-05,
+      "loss": 0.5764,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 940,
+      "tokens_per_second_per_gpu": 871.53
+    },
+    {
+      "epoch": 1.3159535769963624,
+      "grad_norm": 0.16499237716197968,
+      "learning_rate": 2.7766232525292103e-05,
+      "loss": 0.5451,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 950,
+      "tokens_per_second_per_gpu": 846.63
+    },
+    {
+      "epoch": 1.3298111900225187,
+      "grad_norm": 0.16787481307983398,
+      "learning_rate": 2.676765983121089e-05,
+      "loss": 0.5698,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 960,
+      "tokens_per_second_per_gpu": 996.59
+    },
+    {
+      "epoch": 1.3436688030486748,
+      "grad_norm": 0.17758306860923767,
+      "learning_rate": 2.578076862694426e-05,
+      "loss": 0.5677,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 970,
+      "tokens_per_second_per_gpu": 990.05
+    },
+    {
+      "epoch": 1.357526416074831,
+      "grad_norm": 0.1822880357503891,
+      "learning_rate": 2.4806055132824185e-05,
+      "loss": 0.5832,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 980,
+      "tokens_per_second_per_gpu": 941.98
+    },
+    {
+      "epoch": 1.3713840291009873,
+      "grad_norm": 0.19017541408538818,
+      "learning_rate": 2.384400944608886e-05,
+      "loss": 0.5803,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 990,
+      "tokens_per_second_per_gpu": 942.86
+    },
+    {
+      "epoch": 1.3852416421271436,
+      "grad_norm": 0.19104644656181335,
+      "learning_rate": 2.289511529445616e-05,
+      "loss": 0.5507,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1000,
+      "tokens_per_second_per_gpu": 905.35
+    },
+    {
+      "epoch": 1.3990992551533,
+      "grad_norm": 0.16881509125232697,
+      "learning_rate": 2.195984979289974e-05,
+      "loss": 0.5855,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1010,
+      "tokens_per_second_per_gpu": 963.29
+    },
+    {
+      "epoch": 1.4129568681794562,
+      "grad_norm": 0.17394502460956573,
+      "learning_rate": 2.1038683203750092e-05,
+      "loss": 0.593,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1020,
+      "tokens_per_second_per_gpu": 874.44
+    },
+    {
+      "epoch": 1.4268144812056123,
+      "grad_norm": 0.17141559720039368,
+      "learning_rate": 2.0132078700241158e-05,
+      "loss": 0.5932,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1030,
+      "tokens_per_second_per_gpu": 898.09
+    },
+    {
+      "epoch": 1.4406720942317686,
+      "grad_norm": 0.17774531245231628,
+      "learning_rate": 1.924049213362153e-05,
+      "loss": 0.5972,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1040,
+      "tokens_per_second_per_gpu": 780.07
+    },
+    {
+      "epoch": 1.4545297072579249,
+      "grad_norm": 0.18897521495819092,
+      "learning_rate": 1.836437180394715e-05,
+      "loss": 0.5828,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1050,
+      "tokens_per_second_per_gpu": 1176.61
+    },
+    {
+      "epoch": 1.4683873202840811,
+      "grad_norm": 0.1707300990819931,
+      "learning_rate": 1.750415823467082e-05,
+      "loss": 0.5548,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1060,
+      "tokens_per_second_per_gpu": 1087.95
+    },
+    {
+      "epoch": 1.4822449333102372,
+      "grad_norm": 0.1707785278558731,
+      "learning_rate": 1.666028395114185e-05,
+      "loss": 0.5622,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1070,
+      "tokens_per_second_per_gpu": 840.77
+    },
+    {
+      "epoch": 1.4961025463363935,
+      "grad_norm": 0.1891181617975235,
+      "learning_rate": 1.5833173263127426e-05,
+      "loss": 0.5373,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1080,
+      "tokens_per_second_per_gpu": 1017.51
+    },
+    {
+      "epoch": 1.5099601593625498,
+      "grad_norm": 0.17579694092273712,
+      "learning_rate": 1.5023242051464675e-05,
+      "loss": 0.5578,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1090,
+      "tokens_per_second_per_gpu": 976.53
+    },
+    {
+      "epoch": 1.523817772388706,
+      "grad_norm": 0.16882087290287018,
+      "learning_rate": 1.4230897558950951e-05,
+      "loss": 0.5754,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1100,
+      "tokens_per_second_per_gpu": 1004.78
+    },
+    {
+      "epoch": 1.5376753854148624,
+      "grad_norm": 0.1948268711566925,
+      "learning_rate": 1.3456538185577466e-05,
+      "loss": 0.5399,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1110,
+      "tokens_per_second_per_gpu": 1117.6
+    },
+    {
+      "epoch": 1.5515329984410187,
+      "grad_norm": 0.19728456437587738,
+      "learning_rate": 1.2700553288209126e-05,
+      "loss": 0.5915,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1120,
+      "tokens_per_second_per_gpu": 882.19
+    },
+    {
+      "epoch": 1.5653906114671747,
+      "grad_norm": 0.17635080218315125,
+      "learning_rate": 1.1963322984811453e-05,
+      "loss": 0.5671,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1130,
+      "tokens_per_second_per_gpu": 1119.95
+    },
+    {
+      "epoch": 1.579248224493331,
+      "grad_norm": 0.17266033589839935,
+      "learning_rate": 1.1245217963322763e-05,
+      "loss": 0.5755,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1140,
+      "tokens_per_second_per_gpu": 788.89
+    },
+    {
+      "epoch": 1.5931058375194873,
+      "grad_norm": 0.17995904386043549,
+      "learning_rate": 1.0546599295268061e-05,
+      "loss": 0.5328,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1150,
+      "tokens_per_second_per_gpu": 948.5
+    },
+    {
+      "epoch": 1.6069634505456434,
+      "grad_norm": 0.17355145514011383,
+      "learning_rate": 9.867818254208123e-06,
+      "loss": 0.5633,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1160,
+      "tokens_per_second_per_gpu": 965.8
+    },
+    {
+      "epoch": 1.6208210635717997,
+      "grad_norm": 0.18094998598098755,
+      "learning_rate": 9.209216139114935e-06,
+      "loss": 0.5425,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1170,
+      "tokens_per_second_per_gpu": 914.6
+    },
+    {
+      "epoch": 1.634678676597956,
+      "grad_norm": 0.19211266934871674,
+      "learning_rate": 8.571124102762768e-06,
+      "loss": 0.577,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1180,
+      "tokens_per_second_per_gpu": 987.37
+    },
+    {
+      "epoch": 1.6485362896241122,
+      "grad_norm": 0.1781914234161377,
+      "learning_rate": 7.95386298522065e-06,
+      "loss": 0.5719,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1190,
+      "tokens_per_second_per_gpu": 864.39
+    },
+    {
+      "epoch": 1.6623939026502685,
+      "grad_norm": 0.17774876952171326,
+      "learning_rate": 7.357743152530272e-06,
+      "loss": 0.5647,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1200,
+      "tokens_per_second_per_gpu": 954.56
+    },
+    {
+      "epoch": 1.6762515156764248,
+      "grad_norm": 0.1787899136543274,
+      "learning_rate": 6.783064340650364e-06,
+      "loss": 0.6007,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1210,
+      "tokens_per_second_per_gpu": 1119.17
+    },
+    {
+      "epoch": 1.6901091287025811,
+      "grad_norm": 0.16189730167388916,
+      "learning_rate": 6.230115504745953e-06,
+      "loss": 0.5647,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1220,
+      "tokens_per_second_per_gpu": 889.49
+    },
+    {
+      "epoch": 1.7039667417287372,
+      "grad_norm": 0.17614033818244934,
+      "learning_rate": 5.699174673898394e-06,
+      "loss": 0.5239,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1230,
+      "tokens_per_second_per_gpu": 925.55
+    },
+    {
+      "epoch": 1.7178243547548935,
+      "grad_norm": 0.18107430636882782,
+      "learning_rate": 5.190508811309091e-06,
+      "loss": 0.5803,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1240,
+      "tokens_per_second_per_gpu": 1020.96
+    },
+    {
+      "epoch": 1.7316819677810498,
+      "grad_norm": 0.18331079185009003,
+      "learning_rate": 4.704373680067325e-06,
+      "loss": 0.5542,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1250,
+      "tokens_per_second_per_gpu": 975.2
+    },
+    {
+      "epoch": 1.7455395808072058,
+      "grad_norm": 0.20262940227985382,
+      "learning_rate": 4.241013714549597e-06,
+      "loss": 0.5879,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1260,
+      "tokens_per_second_per_gpu": 935.67
+    },
+    {
+      "epoch": 1.7593971938333621,
+      "grad_norm": 0.16563181579113007,
+      "learning_rate": 3.800661897515245e-06,
+      "loss": 0.5437,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1270,
+      "tokens_per_second_per_gpu": 947.0
+    },
+    {
+      "epoch": 1.7732548068595184,
+      "grad_norm": 0.1958320140838623,
+      "learning_rate": 3.3835396429599152e-06,
+      "loss": 0.5445,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1280,
+      "tokens_per_second_per_gpu": 981.25
+    },
+    {
+      "epoch": 1.7871124198856747,
+      "grad_norm": 0.1918836534023285,
+      "learning_rate": 2.9898566847861245e-06,
+      "loss": 0.5358,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1290,
+      "tokens_per_second_per_gpu": 909.78
+    },
+    {
+      "epoch": 1.800970032911831,
+      "grad_norm": 0.18790839612483978,
+      "learning_rate": 2.619810971346587e-06,
+      "loss": 0.5728,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1300,
+      "tokens_per_second_per_gpu": 961.21
+    },
+    {
+      "epoch": 1.8148276459379873,
+      "grad_norm": 0.18140196800231934,
+      "learning_rate": 2.2735885659134925e-06,
+      "loss": 0.5943,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1310,
+      "tokens_per_second_per_gpu": 933.61
+    },
+    {
+      "epoch": 1.8286852589641436,
+      "grad_norm": 0.19009986519813538,
+      "learning_rate": 1.9513635531237417e-06,
+      "loss": 0.5557,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1320,
+      "tokens_per_second_per_gpu": 913.45
+    },
+    {
+      "epoch": 1.8425428719902996,
+      "grad_norm": 0.1914367824792862,
+      "learning_rate": 1.6532979514471747e-06,
+      "loss": 0.5853,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1330,
+      "tokens_per_second_per_gpu": 1024.91
+    },
+    {
+      "epoch": 1.856400485016456,
+      "grad_norm": 0.1720149666070938,
+      "learning_rate": 1.3795416317218036e-06,
+      "loss": 0.5669,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1340,
+      "tokens_per_second_per_gpu": 1067.62
+    },
+    {
+      "epoch": 1.870258098042612,
+      "grad_norm": 0.17772097885608673,
+      "learning_rate": 1.1302322417970135e-06,
+      "loss": 0.5802,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1350,
+      "tokens_per_second_per_gpu": 940.57
+    },
+    {
+      "epoch": 1.8841157110687683,
+      "grad_norm": 0.1829637587070465,
+      "learning_rate": 9.054951373226484e-07,
+      "loss": 0.5436,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1360,
+      "tokens_per_second_per_gpu": 931.71
+    },
+    {
+      "epoch": 1.8979733240949246,
+      "grad_norm": 0.190989688038826,
+      "learning_rate": 7.054433187187071e-07,
+      "loss": 0.5751,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1370,
+      "tokens_per_second_per_gpu": 1210.22
+    },
+    {
+      "epoch": 1.9118309371210809,
+      "grad_norm": 0.17515617609024048,
+      "learning_rate": 5.301773743574712e-07,
+      "loss": 0.5524,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1380,
+      "tokens_per_second_per_gpu": 972.68
+    },
+    {
+      "epoch": 1.9256885501472372,
+      "grad_norm": 0.17383797466754913,
+      "learning_rate": 3.7978542998643454e-07,
+      "loss": 0.5438,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1390,
+      "tokens_per_second_per_gpu": 915.78
+    },
+    {
+      "epoch": 1.9395461631733935,
+      "grad_norm": 0.1715794801712036,
+      "learning_rate": 2.5434310441773137e-07,
+      "loss": 0.5667,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1400,
+      "tokens_per_second_per_gpu": 1099.45
+    },
+    {
+      "epoch": 1.9534037761995497,
+      "grad_norm": 0.1821635514497757,
+      "learning_rate": 1.5391347150607304e-07,
+      "loss": 0.542,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1410,
+      "tokens_per_second_per_gpu": 949.21
+    },
+    {
+      "epoch": 1.967261389225706,
+      "grad_norm": 0.19293761253356934,
+      "learning_rate": 7.854702843449469e-08,
+      "loss": 0.5384,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1420,
+      "tokens_per_second_per_gpu": 825.94
+    },
+    {
+      "epoch": 1.981119002251862,
+      "grad_norm": 0.19018813967704773,
+      "learning_rate": 2.828167032379869e-08,
+      "loss": 0.6172,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1430,
+      "tokens_per_second_per_gpu": 973.31
+    },
+    {
+      "epoch": 1.9949766152780184,
+      "grad_norm": 0.180649071931839,
+      "learning_rate": 3.1426711784299233e-09,
+      "loss": 0.5543,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 1440,
+      "tokens_per_second_per_gpu": 945.3
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1444,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2844822329694618e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1444/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1418985538671b467762281d3c852d707544317aa0efccdb1a0b18aa66639c19
+size 7249

checkpoint-600/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-32B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-32B
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-600/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30bdcea3052a244c2d1bb70e0ae1f5c764e7faa6e039e8ff85ac1faa0e232cc
+size 1073863208

checkpoint-600/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-600/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5916d676f8ca6e76b5b6a2fb0042fbe87bbf929da45a4c0f0018d3d18a0fb21e
+size 2148242275

checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5672c19400981b2f2e25c240216608a78fb5e7e65eee1ebdd929766b25ea9d69
+size 14645

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6cd14916690ffcb8d3cc2db33ed7944368644bbe3516ccf0e517b4e417cc0ae
+size 1465

checkpoint-600/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-600/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-600/trainer_state.json

@@ -0,0 +1,694 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8314567815693746,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013857613026156245,
+      "grad_norm": 0.1854863315820694,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 0.8494,
+      "memory/device_reserved (GiB)": 89.89,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 10,
+      "tokens_per_second_per_gpu": 1111.65
+    },
+    {
+      "epoch": 0.02771522605231249,
+      "grad_norm": 0.09567277133464813,
+      "learning_rate": 4.418604651162791e-05,
+      "loss": 0.7842,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 20,
+      "tokens_per_second_per_gpu": 1041.18
+    },
+    {
+      "epoch": 0.04157283907846873,
+      "grad_norm": 0.1211227998137474,
+      "learning_rate": 6.744186046511628e-05,
+      "loss": 0.7353,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 30,
+      "tokens_per_second_per_gpu": 993.82
+    },
+    {
+      "epoch": 0.05543045210462498,
+      "grad_norm": 0.09696491807699203,
+      "learning_rate": 9.069767441860465e-05,
+      "loss": 0.6943,
+      "memory/device_reserved (GiB)": 90.37,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 40,
+      "tokens_per_second_per_gpu": 849.91
+    },
+    {
+      "epoch": 0.06928806513078123,
+      "grad_norm": 0.12007619440555573,
+      "learning_rate": 9.999547457436221e-05,
+      "loss": 0.6814,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 50,
+      "tokens_per_second_per_gpu": 971.92
+    },
+    {
+      "epoch": 0.08314567815693746,
+      "grad_norm": 0.12358752638101578,
+      "learning_rate": 9.996782216198338e-05,
+      "loss": 0.69,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 60,
+      "tokens_per_second_per_gpu": 862.06
+    },
+    {
+      "epoch": 0.09700329118309371,
+      "grad_norm": 0.11916535347700119,
+      "learning_rate": 9.991504534967746e-05,
+      "loss": 0.7048,
+      "memory/device_reserved (GiB)": 90.38,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 70,
+      "tokens_per_second_per_gpu": 1024.18
+    },
+    {
+      "epoch": 0.11086090420924996,
+      "grad_norm": 0.12464027106761932,
+      "learning_rate": 9.983717067423721e-05,
+      "loss": 0.6705,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 80,
+      "tokens_per_second_per_gpu": 1009.08
+    },
+    {
+      "epoch": 0.1247185172354062,
+      "grad_norm": 0.1264505237340927,
+      "learning_rate": 9.973423729195168e-05,
+      "loss": 0.6387,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 90,
+      "tokens_per_second_per_gpu": 1027.91
+    },
+    {
+      "epoch": 0.13857613026156246,
+      "grad_norm": 0.1262999027967453,
+      "learning_rate": 9.960629695891814e-05,
+      "loss": 0.6447,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 100,
+      "tokens_per_second_per_gpu": 935.25
+    },
+    {
+      "epoch": 0.1524337432877187,
+      "grad_norm": 0.12777547538280487,
+      "learning_rate": 9.945341400501838e-05,
+      "loss": 0.6846,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 110,
+      "tokens_per_second_per_gpu": 997.71
+    },
+    {
+      "epoch": 0.16629135631387493,
+      "grad_norm": 0.12563012540340424,
+      "learning_rate": 9.927566530157298e-05,
+      "loss": 0.6765,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 120,
+      "tokens_per_second_per_gpu": 1120.19
+    },
+    {
+      "epoch": 0.1801489693400312,
+      "grad_norm": 0.13785897195339203,
+      "learning_rate": 9.907314022268946e-05,
+      "loss": 0.6315,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 130,
+      "tokens_per_second_per_gpu": 801.56
+    },
+    {
+      "epoch": 0.19400658236618742,
+      "grad_norm": 0.14731284976005554,
+      "learning_rate": 9.884594060032406e-05,
+      "loss": 0.6642,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 140,
+      "tokens_per_second_per_gpu": 944.29
+    },
+    {
+      "epoch": 0.20786419539234366,
+      "grad_norm": 0.1298578828573227,
+      "learning_rate": 9.859418067307928e-05,
+      "loss": 0.6696,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 150,
+      "tokens_per_second_per_gpu": 913.99
+    },
+    {
+      "epoch": 0.22172180841849992,
+      "grad_norm": 0.13122966885566711,
+      "learning_rate": 9.831798702876352e-05,
+      "loss": 0.6768,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 160,
+      "tokens_per_second_per_gpu": 983.71
+    },
+    {
+      "epoch": 0.23557942144465616,
+      "grad_norm": 0.12356515228748322,
+      "learning_rate": 9.801749854074122e-05,
+      "loss": 0.6526,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 170,
+      "tokens_per_second_per_gpu": 903.88
+    },
+    {
+      "epoch": 0.2494370344708124,
+      "grad_norm": 0.11831440776586533,
+      "learning_rate": 9.769286629810572e-05,
+      "loss": 0.6415,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 180,
+      "tokens_per_second_per_gpu": 819.58
+    },
+    {
+      "epoch": 0.2632946474969686,
+      "grad_norm": 0.12409751862287521,
+      "learning_rate": 9.73442535297099e-05,
+      "loss": 0.6685,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 190,
+      "tokens_per_second_per_gpu": 973.62
+    },
+    {
+      "epoch": 0.2771522605231249,
+      "grad_norm": 0.1352369785308838,
+      "learning_rate": 9.697183552209288e-05,
+      "loss": 0.6329,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 200,
+      "tokens_per_second_per_gpu": 903.58
+    },
+    {
+      "epoch": 0.29100987354928115,
+      "grad_norm": 0.12526443600654602,
+      "learning_rate": 9.657579953134383e-05,
+      "loss": 0.6452,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 210,
+      "tokens_per_second_per_gpu": 859.06
+    },
+    {
+      "epoch": 0.3048674865754374,
+      "grad_norm": 0.11614521592855453,
+      "learning_rate": 9.615634468894752e-05,
+      "loss": 0.6407,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 220,
+      "tokens_per_second_per_gpu": 850.93
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 0.1328686773777008,
+      "learning_rate": 9.571368190165863e-05,
+      "loss": 0.6741,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 230,
+      "tokens_per_second_per_gpu": 1038.17
+    },
+    {
+      "epoch": 0.33258271262774985,
+      "grad_norm": 0.13082517683506012,
+      "learning_rate": 9.524803374545548e-05,
+      "loss": 0.6906,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 240,
+      "tokens_per_second_per_gpu": 1066.43
+    },
+    {
+      "epoch": 0.3464403256539061,
+      "grad_norm": 0.1282692551612854,
+      "learning_rate": 9.475963435362614e-05,
+      "loss": 0.6609,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 250,
+      "tokens_per_second_per_gpu": 986.84
+    },
+    {
+      "epoch": 0.3602979386800624,
+      "grad_norm": 0.13708311319351196,
+      "learning_rate": 9.424872929904358e-05,
+      "loss": 0.6169,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 260,
+      "tokens_per_second_per_gpu": 1126.25
+    },
+    {
+      "epoch": 0.3741555517062186,
+      "grad_norm": 0.1323172152042389,
+      "learning_rate": 9.371557547068878e-05,
+      "loss": 0.6574,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 270,
+      "tokens_per_second_per_gpu": 1062.03
+    },
+    {
+      "epoch": 0.38801316473237485,
+      "grad_norm": 0.12729060649871826,
+      "learning_rate": 9.316044094448392e-05,
+      "loss": 0.6583,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 280,
+      "tokens_per_second_per_gpu": 941.33
+    },
+    {
+      "epoch": 0.4018707777585311,
+      "grad_norm": 0.14719286561012268,
+      "learning_rate": 9.25836048485008e-05,
+      "loss": 0.6392,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 290,
+      "tokens_per_second_per_gpu": 883.56
+    },
+    {
+      "epoch": 0.4157283907846873,
+      "grad_norm": 0.12530402839183807,
+      "learning_rate": 9.198535722261181e-05,
+      "loss": 0.6623,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 300,
+      "tokens_per_second_per_gpu": 902.6
+    },
+    {
+      "epoch": 0.4295860038108436,
+      "grad_norm": 0.1330760419368744,
+      "learning_rate": 9.136599887265483e-05,
+      "loss": 0.645,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 310,
+      "tokens_per_second_per_gpu": 997.96
+    },
+    {
+      "epoch": 0.44344361683699984,
+      "grad_norm": 0.13317464292049408,
+      "learning_rate": 9.072584121918425e-05,
+      "loss": 0.6139,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 320,
+      "tokens_per_second_per_gpu": 980.08
+    },
+    {
+      "epoch": 0.4573012298631561,
+      "grad_norm": 0.12773385643959045,
+      "learning_rate": 9.006520614088535e-05,
+      "loss": 0.6658,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 330,
+      "tokens_per_second_per_gpu": 937.57
+    },
+    {
+      "epoch": 0.4711588428893123,
+      "grad_norm": 0.13415341079235077,
+      "learning_rate": 8.938442581272983e-05,
+      "loss": 0.6737,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 340,
+      "tokens_per_second_per_gpu": 1046.92
+    },
+    {
+      "epoch": 0.48501645591546855,
+      "grad_norm": 0.13382680714130402,
+      "learning_rate": 8.868384253895445e-05,
+      "loss": 0.6575,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 350,
+      "tokens_per_second_per_gpu": 1049.72
+    },
+    {
+      "epoch": 0.4988740689416248,
+      "grad_norm": 0.12621234357357025,
+      "learning_rate": 8.796380858094643e-05,
+      "loss": 0.6423,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 360,
+      "tokens_per_second_per_gpu": 926.35
+    },
+    {
+      "epoch": 0.5127316819677811,
+      "grad_norm": 0.14663882553577423,
+      "learning_rate": 8.722468598012245e-05,
+      "loss": 0.6524,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 370,
+      "tokens_per_second_per_gpu": 993.98
+    },
+    {
+      "epoch": 0.5265892949939373,
+      "grad_norm": 0.12107036262750626,
+      "learning_rate": 8.646684637588991e-05,
+      "loss": 0.6158,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 380,
+      "tokens_per_second_per_gpu": 882.74
+    },
+    {
+      "epoch": 0.5404469080200935,
+      "grad_norm": 0.12905746698379517,
+      "learning_rate": 8.56906708187824e-05,
+      "loss": 0.6359,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 390,
+      "tokens_per_second_per_gpu": 992.61
+    },
+    {
+      "epoch": 0.5543045210462498,
+      "grad_norm": 0.14433123171329498,
+      "learning_rate": 8.489654957886306e-05,
+      "loss": 0.6124,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 400,
+      "tokens_per_second_per_gpu": 871.5
+    },
+    {
+      "epoch": 0.568162134072406,
+      "grad_norm": 0.13294072449207306,
+      "learning_rate": 8.40848819494923e-05,
+      "loss": 0.6803,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 410,
+      "tokens_per_second_per_gpu": 950.11
+    },
+    {
+      "epoch": 0.5820197470985623,
+      "grad_norm": 0.1526036411523819,
+      "learning_rate": 8.325607604655839e-05,
+      "loss": 0.6088,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 420,
+      "tokens_per_second_per_gpu": 1025.1
+    },
+    {
+      "epoch": 0.5958773601247185,
+      "grad_norm": 0.1453717052936554,
+      "learning_rate": 8.241054860327216e-05,
+      "loss": 0.6669,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 430,
+      "tokens_per_second_per_gpu": 1074.36
+    },
+    {
+      "epoch": 0.6097349731508748,
+      "grad_norm": 0.1466919481754303,
+      "learning_rate": 8.154872476062868e-05,
+      "loss": 0.6147,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 440,
+      "tokens_per_second_per_gpu": 1010.83
+    },
+    {
+      "epoch": 0.6235925861770311,
+      "grad_norm": 0.12707076966762543,
+      "learning_rate": 8.067103785364139e-05,
+      "loss": 0.6096,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 450,
+      "tokens_per_second_per_gpu": 919.83
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": 0.13485883176326752,
+      "learning_rate": 7.977792919345633e-05,
+      "loss": 0.6342,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 460,
+      "tokens_per_second_per_gpu": 1033.87
+    },
+    {
+      "epoch": 0.6513078122293435,
+      "grad_norm": 0.12489234656095505,
+      "learning_rate": 7.886984784545566e-05,
+      "loss": 0.6256,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 470,
+      "tokens_per_second_per_gpu": 1018.58
+    },
+    {
+      "epoch": 0.6651654252554997,
+      "grad_norm": 0.16094225645065308,
+      "learning_rate": 7.794725040346251e-05,
+      "loss": 0.6455,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 480,
+      "tokens_per_second_per_gpu": 933.16
+    },
+    {
+      "epoch": 0.679023038281656,
+      "grad_norm": 0.1351306140422821,
+      "learning_rate": 7.701060076016024e-05,
+      "loss": 0.6613,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 490,
+      "tokens_per_second_per_gpu": 970.62
+    },
+    {
+      "epoch": 0.6928806513078122,
+      "grad_norm": 0.1223958283662796,
+      "learning_rate": 7.606036987384184e-05,
+      "loss": 0.6186,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 500,
+      "tokens_per_second_per_gpu": 925.45
+    },
+    {
+      "epoch": 0.7067382643339685,
+      "grad_norm": 0.11873335391283035,
+      "learning_rate": 7.509703553160666e-05,
+      "loss": 0.646,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 510,
+      "tokens_per_second_per_gpu": 990.93
+    },
+    {
+      "epoch": 0.7205958773601248,
+      "grad_norm": 0.12990343570709229,
+      "learning_rate": 7.412108210912345e-05,
+      "loss": 0.6155,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 520,
+      "tokens_per_second_per_gpu": 955.97
+    },
+    {
+      "epoch": 0.7344534903862809,
+      "grad_norm": 0.1376057118177414,
+      "learning_rate": 7.31330003270808e-05,
+      "loss": 0.6443,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 530,
+      "tokens_per_second_per_gpu": 895.07
+    },
+    {
+      "epoch": 0.7483111034124372,
+      "grad_norm": 0.13277359306812286,
+      "learning_rate": 7.213328700444696e-05,
+      "loss": 0.6188,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 540,
+      "tokens_per_second_per_gpu": 907.27
+    },
+    {
+      "epoch": 0.7621687164385934,
+      "grad_norm": 0.13623632490634918,
+      "learning_rate": 7.112244480866356e-05,
+      "loss": 0.6471,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 550,
+      "tokens_per_second_per_gpu": 1002.06
+    },
+    {
+      "epoch": 0.7760263294647497,
+      "grad_norm": 0.13037075102329254,
+      "learning_rate": 7.010098200289859e-05,
+      "loss": 0.647,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 560,
+      "tokens_per_second_per_gpu": 1047.58
+    },
+    {
+      "epoch": 0.789883942490906,
+      "grad_norm": 0.12997141480445862,
+      "learning_rate": 6.906941219048584e-05,
+      "loss": 0.6071,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 570,
+      "tokens_per_second_per_gpu": 1073.59
+    },
+    {
+      "epoch": 0.8037415555170622,
+      "grad_norm": 0.14118416607379913,
+      "learning_rate": 6.802825405667905e-05,
+      "loss": 0.6101,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 580,
+      "tokens_per_second_per_gpu": 1097.31
+    },
+    {
+      "epoch": 0.8175991685432185,
+      "grad_norm": 0.126139834523201,
+      "learning_rate": 6.697803110785115e-05,
+      "loss": 0.6084,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 590,
+      "tokens_per_second_per_gpu": 933.94
+    },
+    {
+      "epoch": 0.8314567815693746,
+      "grad_norm": 0.1207822933793068,
+      "learning_rate": 6.591927140826902e-05,
+      "loss": 0.6416,
+      "memory/device_reserved (GiB)": 90.59,
+      "memory/max_active (GiB)": 85.72,
+      "memory/max_allocated (GiB)": 85.72,
+      "step": 600,
+      "tokens_per_second_per_gpu": 1007.52
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1444,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.327934896681779e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1418985538671b467762281d3c852d707544317aa0efccdb1a0b18aa66639c19
+size 7249