add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys

.gitattributes

@@ -165,3 +165,6 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys_n
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_bcast_noSys/checkpoint-657/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_bcast_noSys/checkpoint-730/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_bcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/README.md

@@ -0,0 +1,61 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+model_name: cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/agam-research/huggingface/runs/gcvzkuxj) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.28.0
+- Transformers: 4.57.6
+- Pytorch: 2.10.0
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ac1b8f6f26159b3d68ccdcbbd5861f8a265fded26fa6fb9c80a048a66dba36
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1cd7307d6c8747348557622650b04fd76ca124ff909d055eef1d8b7100b324
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/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
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/trainer_state.json

@@ -0,0 +1,754 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2187305688858032,
+      "epoch": 0.125,
+      "grad_norm": 2.2103259563446045,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6537,
+      "mean_token_accuracy": 0.791277551651001,
+      "num_tokens": 14468.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.2796798944473267,
+      "epoch": 0.25,
+      "grad_norm": 2.212388515472412,
+      "learning_rate": 4.75e-05,
+      "loss": 0.7173,
+      "mean_token_accuracy": 0.7488389730453491,
+      "num_tokens": 28167.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.2749905824661254,
+      "epoch": 0.375,
+      "grad_norm": 1.3840874433517456,
+      "learning_rate": 7.25e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.784180611371994,
+      "num_tokens": 42977.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.2465349912643433,
+      "epoch": 0.5,
+      "grad_norm": 1.576978087425232,
+      "learning_rate": 9.75e-05,
+      "loss": 0.5515,
+      "mean_token_accuracy": 0.8002467393875122,
+      "num_tokens": 57479.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.2750877380371093,
+      "epoch": 0.625,
+      "grad_norm": 1.4285508394241333,
+      "learning_rate": 9.996540227863854e-05,
+      "loss": 0.5826,
+      "mean_token_accuracy": 0.7942409753799439,
+      "num_tokens": 72039.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.2903133392333985,
+      "epoch": 0.75,
+      "grad_norm": 1.5663594007492065,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 0.5985,
+      "mean_token_accuracy": 0.7775073409080505,
+      "num_tokens": 85593.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.3033482313156128,
+      "epoch": 0.875,
+      "grad_norm": 1.643728494644165,
+      "learning_rate": 9.96411702675847e-05,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.7822115123271942,
+      "num_tokens": 99555.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.272090196609497,
+      "epoch": 1.0,
+      "grad_norm": 1.5759304761886597,
+      "learning_rate": 9.93516627418217e-05,
+      "loss": 0.5473,
+      "mean_token_accuracy": 0.802792227268219,
+      "num_tokens": 112434.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.2750096321105957,
+      "epoch": 1.125,
+      "grad_norm": 1.3011053800582886,
+      "learning_rate": 9.897783872811882e-05,
+      "loss": 0.5153,
+      "mean_token_accuracy": 0.8154669582843781,
+      "num_tokens": 127009.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.2408278822898864,
+      "epoch": 1.25,
+      "grad_norm": 1.9919697046279907,
+      "learning_rate": 9.852033689853267e-05,
+      "loss": 0.46,
+      "mean_token_accuracy": 0.8340150594711304,
+      "num_tokens": 141624.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2365349173545837,
+      "epoch": 1.375,
+      "grad_norm": 2.4893085956573486,
+      "learning_rate": 9.797993888726473e-05,
+      "loss": 0.4409,
+      "mean_token_accuracy": 0.8433923959732056,
+      "num_tokens": 154927.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.2222854852676392,
+      "epoch": 1.5,
+      "grad_norm": 2.230638027191162,
+      "learning_rate": 9.735756795525231e-05,
+      "loss": 0.4716,
+      "mean_token_accuracy": 0.8306371748447419,
+      "num_tokens": 169340.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.2234688639640807,
+      "epoch": 1.625,
+      "grad_norm": 2.5230424404144287,
+      "learning_rate": 9.665428741279266e-05,
+      "loss": 0.4799,
+      "mean_token_accuracy": 0.8287540018558502,
+      "num_tokens": 183451.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.2297072649002074,
+      "epoch": 1.75,
+      "grad_norm": 1.6947654485702515,
+      "learning_rate": 9.587129880289538e-05,
+      "loss": 0.5081,
+      "mean_token_accuracy": 0.8142228186130523,
+      "num_tokens": 196986.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.236435329914093,
+      "epoch": 1.875,
+      "grad_norm": 1.857646107673645,
+      "learning_rate": 9.500993984846614e-05,
+      "loss": 0.5376,
+      "mean_token_accuracy": 0.8056960344314575,
+      "num_tokens": 211284.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.2014674186706542,
+      "epoch": 2.0,
+      "grad_norm": 2.268764019012451,
+      "learning_rate": 9.407168216682962e-05,
+      "loss": 0.4384,
+      "mean_token_accuracy": 0.8417991876602173,
+      "num_tokens": 224868.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.1651882648468017,
+      "epoch": 2.125,
+      "grad_norm": 2.686282157897949,
+      "learning_rate": 9.305812875549599e-05,
+      "loss": 0.3088,
+      "mean_token_accuracy": 0.8923767149448395,
+      "num_tokens": 239227.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.1128873705863953,
+      "epoch": 2.25,
+      "grad_norm": 1.823421597480774,
+      "learning_rate": 9.197101125346657e-05,
+      "loss": 0.2674,
+      "mean_token_accuracy": 0.9091271877288818,
+      "num_tokens": 253370.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.143240475654602,
+      "epoch": 2.375,
+      "grad_norm": 3.9063007831573486,
+      "learning_rate": 9.081218698275763e-05,
+      "loss": 0.3196,
+      "mean_token_accuracy": 0.8841596901416778,
+      "num_tokens": 266814.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.10996470451355,
+      "epoch": 2.5,
+      "grad_norm": 2.4788379669189453,
+      "learning_rate": 8.958363577519684e-05,
+      "loss": 0.2582,
+      "mean_token_accuracy": 0.9035841405391694,
+      "num_tokens": 280383.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.1407353401184082,
+      "epoch": 2.625,
+      "grad_norm": 3.00192928314209,
+      "learning_rate": 8.828745658991386e-05,
+      "loss": 0.2828,
+      "mean_token_accuracy": 0.9002637803554535,
+      "num_tokens": 294677.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.146290695667267,
+      "epoch": 2.75,
+      "grad_norm": 2.8144991397857666,
+      "learning_rate": 8.692586392730387e-05,
+      "loss": 0.3364,
+      "mean_token_accuracy": 0.879116827249527,
+      "num_tokens": 308895.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.1204965949058532,
+      "epoch": 2.875,
+      "grad_norm": 2.498777389526367,
+      "learning_rate": 8.550118404559075e-05,
+      "loss": 0.3153,
+      "mean_token_accuracy": 0.8898110389709473,
+      "num_tokens": 322972.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.1404753088951112,
+      "epoch": 3.0,
+      "grad_norm": 3.7505083084106445,
+      "learning_rate": 8.401585098645395e-05,
+      "loss": 0.3139,
+      "mean_token_accuracy": 0.8917859971523285,
+      "num_tokens": 337302.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.0813952326774596,
+      "epoch": 3.125,
+      "grad_norm": 2.738870859146118,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.1549,
+      "mean_token_accuracy": 0.9509782195091248,
+      "num_tokens": 351980.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.021421229839325,
+      "epoch": 3.25,
+      "grad_norm": 2.872623920440674,
+      "learning_rate": 8.087347529174743e-05,
+      "loss": 0.1326,
+      "mean_token_accuracy": 0.9550456941127777,
+      "num_tokens": 366237.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.0270240128040313,
+      "epoch": 3.375,
+      "grad_norm": 3.6379289627075195,
+      "learning_rate": 7.922180135234e-05,
+      "loss": 0.1363,
+      "mean_token_accuracy": 0.9519966244697571,
+      "num_tokens": 379936.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.0433461666107178,
+      "epoch": 3.5,
+      "grad_norm": 4.125671863555908,
+      "learning_rate": 7.752020245550618e-05,
+      "loss": 0.1742,
+      "mean_token_accuracy": 0.9386764764785767,
+      "num_tokens": 394193.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.0194836914539338,
+      "epoch": 3.625,
+      "grad_norm": 2.332376480102539,
+      "learning_rate": 7.577158575441756e-05,
+      "loss": 0.1482,
+      "mean_token_accuracy": 0.9493629992008209,
+      "num_tokens": 408320.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.0239929258823395,
+      "epoch": 3.75,
+      "grad_norm": 2.831947088241577,
+      "learning_rate": 7.397893873137563e-05,
+      "loss": 0.1475,
+      "mean_token_accuracy": 0.9426933944225311,
+      "num_tokens": 422325.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.037560725212097,
+      "epoch": 3.875,
+      "grad_norm": 2.6173717975616455,
+      "learning_rate": 7.214532409374829e-05,
+      "loss": 0.175,
+      "mean_token_accuracy": 0.9376092195510864,
+      "num_tokens": 436074.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.0236264705657958,
+      "epoch": 4.0,
+      "grad_norm": 4.491424560546875,
+      "learning_rate": 7.027387454138578e-05,
+      "loss": 0.1294,
+      "mean_token_accuracy": 0.9556749641895295,
+      "num_tokens": 449736.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.9972971498966217,
+      "epoch": 4.125,
+      "grad_norm": 2.8175551891326904,
+      "learning_rate": 6.83677874144555e-05,
+      "loss": 0.0816,
+      "mean_token_accuracy": 0.9713187456130982,
+      "num_tokens": 464078.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.9570629358291626,
+      "epoch": 4.25,
+      "grad_norm": 3.3606672286987305,
+      "learning_rate": 6.643031923083995e-05,
+      "loss": 0.0684,
+      "mean_token_accuracy": 0.9768271446228027,
+      "num_tokens": 478061.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.950729489326477,
+      "epoch": 4.375,
+      "grad_norm": 3.3156981468200684,
+      "learning_rate": 6.446478012243056e-05,
+      "loss": 0.0596,
+      "mean_token_accuracy": 0.9815345823764801,
+      "num_tokens": 492148.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.9551220595836639,
+      "epoch": 4.5,
+      "grad_norm": 3.09014892578125,
+      "learning_rate": 6.247452817982293e-05,
+      "loss": 0.077,
+      "mean_token_accuracy": 0.9774294853210449,
+      "num_tokens": 505767.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.9669844686985016,
+      "epoch": 4.625,
+      "grad_norm": 2.9506452083587646,
+      "learning_rate": 6.046296371507533e-05,
+      "loss": 0.0648,
+      "mean_token_accuracy": 0.979290097951889,
+      "num_tokens": 520447.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.9664118111133575,
+      "epoch": 4.75,
+      "grad_norm": 3.0426695346832275,
+      "learning_rate": 5.8433523452332574e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.975697374343872,
+      "num_tokens": 534059.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.9530595302581787,
+      "epoch": 4.875,
+      "grad_norm": 4.362701892852783,
+      "learning_rate": 5.638967465624051e-05,
+      "loss": 0.0601,
+      "mean_token_accuracy": 0.979166853427887,
+      "num_tokens": 548402.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.92903453707695,
+      "epoch": 5.0,
+      "grad_norm": 4.549080848693848,
+      "learning_rate": 5.4334909208182496e-05,
+      "loss": 0.077,
+      "mean_token_accuracy": 0.9710751533508301,
+      "num_tokens": 562170.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.9279688596725464,
+      "epoch": 5.125,
+      "grad_norm": 1.8593145608901978,
+      "learning_rate": 5.227273764045868e-05,
+      "loss": 0.0303,
+      "mean_token_accuracy": 0.9902628004550934,
+      "num_tokens": 576379.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.932934308052063,
+      "epoch": 5.25,
+      "grad_norm": 2.779188394546509,
+      "learning_rate": 5.0206683138600416e-05,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9909709811210632,
+      "num_tokens": 590502.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.8848839819431304,
+      "epoch": 5.375,
+      "grad_norm": 0.7788613438606262,
+      "learning_rate": 4.814027552206689e-05,
+      "loss": 0.0322,
+      "mean_token_accuracy": 0.9900912463665008,
+      "num_tokens": 604867.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.8909029543399811,
+      "epoch": 5.5,
+      "grad_norm": 2.6535704135894775,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0316,
+      "mean_token_accuracy": 0.9905791282653809,
+      "num_tokens": 619093.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.9052783668041229,
+      "epoch": 5.625,
+      "grad_norm": 2.310926675796509,
+      "learning_rate": 4.402051720759519e-05,
+      "loss": 0.0289,
+      "mean_token_accuracy": 0.9906817495822906,
+      "num_tokens": 633590.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.8850251972675324,
+      "epoch": 5.75,
+      "grad_norm": 3.467799425125122,
+      "learning_rate": 4.197420504762998e-05,
+      "loss": 0.0292,
+      "mean_token_accuracy": 0.9914416134357452,
+      "num_tokens": 647325.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.8875244915485382,
+      "epoch": 5.875,
+      "grad_norm": 3.544987201690674,
+      "learning_rate": 3.994160482371138e-05,
+      "loss": 0.032,
+      "mean_token_accuracy": 0.9915526807308197,
+      "num_tokens": 660636.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.8852949798107147,
+      "epoch": 6.0,
+      "grad_norm": 1.499319076538086,
+      "learning_rate": 3.7926189199225916e-05,
+      "loss": 0.0311,
+      "mean_token_accuracy": 0.9885606646537781,
+      "num_tokens": 674604.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8791893124580383,
+      "epoch": 6.125,
+      "grad_norm": 2.9339754581451416,
+      "learning_rate": 3.593140147796018e-05,
+      "loss": 0.0176,
+      "mean_token_accuracy": 0.9964509904384613,
+      "num_tokens": 688174.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.8959417343139648,
+      "epoch": 6.25,
+      "grad_norm": 0.6353668570518494,
+      "learning_rate": 3.396064972127421e-05,
+      "loss": 0.0074,
+      "mean_token_accuracy": 0.9983483254909515,
+      "num_tokens": 703407.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.8571045517921447,
+      "epoch": 6.375,
+      "grad_norm": 0.7655197978019714,
+      "learning_rate": 3.201730092548574e-05,
+      "loss": 0.0078,
+      "mean_token_accuracy": 0.997672826051712,
+      "num_tokens": 716640.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.8348173081874848,
+      "epoch": 6.5,
+      "grad_norm": 0.678413450717926,
+      "learning_rate": 3.010467526941344e-05,
+      "loss": 0.0147,
+      "mean_token_accuracy": 0.9965437054634094,
+      "num_tokens": 730670.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.8442856132984161,
+      "epoch": 6.625,
+      "grad_norm": 2.593682050704956,
+      "learning_rate": 2.822604044190721e-05,
+      "loss": 0.0112,
+      "mean_token_accuracy": 0.9970250070095062,
+      "num_tokens": 744655.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.8602952241897583,
+      "epoch": 6.75,
+      "grad_norm": 1.8622733354568481,
+      "learning_rate": 2.638460605905646e-05,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.99802947640419,
+      "num_tokens": 758632.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.8571505784988404,
+      "epoch": 6.875,
+      "grad_norm": 3.6640737056732178,
+      "learning_rate": 2.4583518180614972e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9954710185527802,
+      "num_tokens": 773073.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.848151445388794,
+      "epoch": 7.0,
+      "grad_norm": 0.6586284637451172,
+      "learning_rate": 2.282585393501054e-05,
+      "loss": 0.0099,
+      "mean_token_accuracy": 0.9971284449100495,
+      "num_tokens": 787038.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.8505769550800324,
+      "epoch": 7.125,
+      "grad_norm": 0.5988003015518188,
+      "learning_rate": 2.111461626212265e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.9988818287849426,
+      "num_tokens": 801547.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.8434448659420013,
+      "epoch": 7.25,
+      "grad_norm": 0.3713991045951843,
+      "learning_rate": 1.945272878281011e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 815923.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.8455669939517975,
+      "epoch": 7.375,
+      "grad_norm": 0.20989808440208435,
+      "learning_rate": 1.7843030803953835e-05,
+      "loss": 0.0056,
+      "mean_token_accuracy": 0.9990819036960602,
+      "num_tokens": 830560.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.8345717132091522,
+      "epoch": 7.5,
+      "grad_norm": 0.08407581597566605,
+      "learning_rate": 1.6288272467548632e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9997530877590179,
+      "num_tokens": 844298.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.8291518807411193,
+      "epoch": 7.625,
+      "grad_norm": 0.12116006016731262,
+      "learning_rate": 1.4791110052131802e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9989939093589782,
+      "num_tokens": 858368.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.8221515953540802,
+      "epoch": 7.75,
+      "grad_norm": 0.6619347333908081,
+      "learning_rate": 1.3354101434575806e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9994893491268158,
+      "num_tokens": 872033.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.8383927822113038,
+      "epoch": 7.875,
+      "grad_norm": 0.11830554902553558,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9997578680515289,
+      "num_tokens": 885680.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.8398464679718017,
+      "epoch": 8.0,
+      "grad_norm": 0.16907748579978943,
+      "learning_rate": 1.067025904725713e-05,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9995523929595947,
+      "num_tokens": 899472.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.8344308793544769,
+      "epoch": 8.125,
+      "grad_norm": 0.1471625715494156,
+      "learning_rate": 9.428010577192798e-06,
+      "loss": 0.0047,
+      "mean_token_accuracy": 0.9997126460075378,
+      "num_tokens": 914081.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.8229577541351318,
+      "epoch": 8.25,
+      "grad_norm": 0.031787365674972534,
+      "learning_rate": 8.25507867047835e-06,
+      "loss": 0.0004,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 928266.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.8316897392272949,
+      "epoch": 8.375,
+      "grad_norm": 0.07172579318284988,
+      "learning_rate": 7.153467261600949e-06,
+      "loss": 0.0005,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 942501.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.8222177207469941,
+      "epoch": 8.5,
+      "grad_norm": 0.08161746710538864,
+      "learning_rate": 6.12505843517357e-06,
+      "loss": 0.0006,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 956536.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.8224615395069123,
+      "epoch": 8.625,
+      "grad_norm": 0.06165313720703125,
+      "learning_rate": 5.1716092104250106e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9997635960578919,
+      "num_tokens": 970306.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.828678423166275,
+      "epoch": 8.75,
+      "grad_norm": 0.13395720720291138,
+      "learning_rate": 4.294748539362031e-06,
+      "loss": 0.0006,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 984123.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.8218788206577301,
+      "epoch": 8.875,
+      "grad_norm": 0.05110756680369377,
+      "learning_rate": 3.4959745237321428e-06,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9997530877590179,
+      "num_tokens": 998078.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.8281316757202148,
+      "epoch": 9.0,
+      "grad_norm": 0.40356338024139404,
+      "learning_rate": 2.7766518555419397e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1011906.0,
+      "step": 720
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.305136403454566e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c9466655f718ea673ad82c509372c4b8048f009675972fec960227f253f717
+size 6417

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ac1b8f6f26159b3d68ccdcbbd5861f8a265fded26fa6fb9c80a048a66dba36
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/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
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/trainer_state.json

@@ -0,0 +1,834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2187305688858032,
+      "epoch": 0.125,
+      "grad_norm": 2.2103259563446045,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6537,
+      "mean_token_accuracy": 0.791277551651001,
+      "num_tokens": 14468.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.2796798944473267,
+      "epoch": 0.25,
+      "grad_norm": 2.212388515472412,
+      "learning_rate": 4.75e-05,
+      "loss": 0.7173,
+      "mean_token_accuracy": 0.7488389730453491,
+      "num_tokens": 28167.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.2749905824661254,
+      "epoch": 0.375,
+      "grad_norm": 1.3840874433517456,
+      "learning_rate": 7.25e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.784180611371994,
+      "num_tokens": 42977.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.2465349912643433,
+      "epoch": 0.5,
+      "grad_norm": 1.576978087425232,
+      "learning_rate": 9.75e-05,
+      "loss": 0.5515,
+      "mean_token_accuracy": 0.8002467393875122,
+      "num_tokens": 57479.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.2750877380371093,
+      "epoch": 0.625,
+      "grad_norm": 1.4285508394241333,
+      "learning_rate": 9.996540227863854e-05,
+      "loss": 0.5826,
+      "mean_token_accuracy": 0.7942409753799439,
+      "num_tokens": 72039.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.2903133392333985,
+      "epoch": 0.75,
+      "grad_norm": 1.5663594007492065,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 0.5985,
+      "mean_token_accuracy": 0.7775073409080505,
+      "num_tokens": 85593.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.3033482313156128,
+      "epoch": 0.875,
+      "grad_norm": 1.643728494644165,
+      "learning_rate": 9.96411702675847e-05,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.7822115123271942,
+      "num_tokens": 99555.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.272090196609497,
+      "epoch": 1.0,
+      "grad_norm": 1.5759304761886597,
+      "learning_rate": 9.93516627418217e-05,
+      "loss": 0.5473,
+      "mean_token_accuracy": 0.802792227268219,
+      "num_tokens": 112434.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.2750096321105957,
+      "epoch": 1.125,
+      "grad_norm": 1.3011053800582886,
+      "learning_rate": 9.897783872811882e-05,
+      "loss": 0.5153,
+      "mean_token_accuracy": 0.8154669582843781,
+      "num_tokens": 127009.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.2408278822898864,
+      "epoch": 1.25,
+      "grad_norm": 1.9919697046279907,
+      "learning_rate": 9.852033689853267e-05,
+      "loss": 0.46,
+      "mean_token_accuracy": 0.8340150594711304,
+      "num_tokens": 141624.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2365349173545837,
+      "epoch": 1.375,
+      "grad_norm": 2.4893085956573486,
+      "learning_rate": 9.797993888726473e-05,
+      "loss": 0.4409,
+      "mean_token_accuracy": 0.8433923959732056,
+      "num_tokens": 154927.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.2222854852676392,
+      "epoch": 1.5,
+      "grad_norm": 2.230638027191162,
+      "learning_rate": 9.735756795525231e-05,
+      "loss": 0.4716,
+      "mean_token_accuracy": 0.8306371748447419,
+      "num_tokens": 169340.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.2234688639640807,
+      "epoch": 1.625,
+      "grad_norm": 2.5230424404144287,
+      "learning_rate": 9.665428741279266e-05,
+      "loss": 0.4799,
+      "mean_token_accuracy": 0.8287540018558502,
+      "num_tokens": 183451.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.2297072649002074,
+      "epoch": 1.75,
+      "grad_norm": 1.6947654485702515,
+      "learning_rate": 9.587129880289538e-05,
+      "loss": 0.5081,
+      "mean_token_accuracy": 0.8142228186130523,
+      "num_tokens": 196986.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.236435329914093,
+      "epoch": 1.875,
+      "grad_norm": 1.857646107673645,
+      "learning_rate": 9.500993984846614e-05,
+      "loss": 0.5376,
+      "mean_token_accuracy": 0.8056960344314575,
+      "num_tokens": 211284.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.2014674186706542,
+      "epoch": 2.0,
+      "grad_norm": 2.268764019012451,
+      "learning_rate": 9.407168216682962e-05,
+      "loss": 0.4384,
+      "mean_token_accuracy": 0.8417991876602173,
+      "num_tokens": 224868.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.1651882648468017,
+      "epoch": 2.125,
+      "grad_norm": 2.686282157897949,
+      "learning_rate": 9.305812875549599e-05,
+      "loss": 0.3088,
+      "mean_token_accuracy": 0.8923767149448395,
+      "num_tokens": 239227.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.1128873705863953,
+      "epoch": 2.25,
+      "grad_norm": 1.823421597480774,
+      "learning_rate": 9.197101125346657e-05,
+      "loss": 0.2674,
+      "mean_token_accuracy": 0.9091271877288818,
+      "num_tokens": 253370.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.143240475654602,
+      "epoch": 2.375,
+      "grad_norm": 3.9063007831573486,
+      "learning_rate": 9.081218698275763e-05,
+      "loss": 0.3196,
+      "mean_token_accuracy": 0.8841596901416778,
+      "num_tokens": 266814.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.10996470451355,
+      "epoch": 2.5,
+      "grad_norm": 2.4788379669189453,
+      "learning_rate": 8.958363577519684e-05,
+      "loss": 0.2582,
+      "mean_token_accuracy": 0.9035841405391694,
+      "num_tokens": 280383.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.1407353401184082,
+      "epoch": 2.625,
+      "grad_norm": 3.00192928314209,
+      "learning_rate": 8.828745658991386e-05,
+      "loss": 0.2828,
+      "mean_token_accuracy": 0.9002637803554535,
+      "num_tokens": 294677.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.146290695667267,
+      "epoch": 2.75,
+      "grad_norm": 2.8144991397857666,
+      "learning_rate": 8.692586392730387e-05,
+      "loss": 0.3364,
+      "mean_token_accuracy": 0.879116827249527,
+      "num_tokens": 308895.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.1204965949058532,
+      "epoch": 2.875,
+      "grad_norm": 2.498777389526367,
+      "learning_rate": 8.550118404559075e-05,
+      "loss": 0.3153,
+      "mean_token_accuracy": 0.8898110389709473,
+      "num_tokens": 322972.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.1404753088951112,
+      "epoch": 3.0,
+      "grad_norm": 3.7505083084106445,
+      "learning_rate": 8.401585098645395e-05,
+      "loss": 0.3139,
+      "mean_token_accuracy": 0.8917859971523285,
+      "num_tokens": 337302.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.0813952326774596,
+      "epoch": 3.125,
+      "grad_norm": 2.738870859146118,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.1549,
+      "mean_token_accuracy": 0.9509782195091248,
+      "num_tokens": 351980.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.021421229839325,
+      "epoch": 3.25,
+      "grad_norm": 2.872623920440674,
+      "learning_rate": 8.087347529174743e-05,
+      "loss": 0.1326,
+      "mean_token_accuracy": 0.9550456941127777,
+      "num_tokens": 366237.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.0270240128040313,
+      "epoch": 3.375,
+      "grad_norm": 3.6379289627075195,
+      "learning_rate": 7.922180135234e-05,
+      "loss": 0.1363,
+      "mean_token_accuracy": 0.9519966244697571,
+      "num_tokens": 379936.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.0433461666107178,
+      "epoch": 3.5,
+      "grad_norm": 4.125671863555908,
+      "learning_rate": 7.752020245550618e-05,
+      "loss": 0.1742,
+      "mean_token_accuracy": 0.9386764764785767,
+      "num_tokens": 394193.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.0194836914539338,
+      "epoch": 3.625,
+      "grad_norm": 2.332376480102539,
+      "learning_rate": 7.577158575441756e-05,
+      "loss": 0.1482,
+      "mean_token_accuracy": 0.9493629992008209,
+      "num_tokens": 408320.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.0239929258823395,
+      "epoch": 3.75,
+      "grad_norm": 2.831947088241577,
+      "learning_rate": 7.397893873137563e-05,
+      "loss": 0.1475,
+      "mean_token_accuracy": 0.9426933944225311,
+      "num_tokens": 422325.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.037560725212097,
+      "epoch": 3.875,
+      "grad_norm": 2.6173717975616455,
+      "learning_rate": 7.214532409374829e-05,
+      "loss": 0.175,
+      "mean_token_accuracy": 0.9376092195510864,
+      "num_tokens": 436074.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.0236264705657958,
+      "epoch": 4.0,
+      "grad_norm": 4.491424560546875,
+      "learning_rate": 7.027387454138578e-05,
+      "loss": 0.1294,
+      "mean_token_accuracy": 0.9556749641895295,
+      "num_tokens": 449736.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.9972971498966217,
+      "epoch": 4.125,
+      "grad_norm": 2.8175551891326904,
+      "learning_rate": 6.83677874144555e-05,
+      "loss": 0.0816,
+      "mean_token_accuracy": 0.9713187456130982,
+      "num_tokens": 464078.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.9570629358291626,
+      "epoch": 4.25,
+      "grad_norm": 3.3606672286987305,
+      "learning_rate": 6.643031923083995e-05,
+      "loss": 0.0684,
+      "mean_token_accuracy": 0.9768271446228027,
+      "num_tokens": 478061.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.950729489326477,
+      "epoch": 4.375,
+      "grad_norm": 3.3156981468200684,
+      "learning_rate": 6.446478012243056e-05,
+      "loss": 0.0596,
+      "mean_token_accuracy": 0.9815345823764801,
+      "num_tokens": 492148.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.9551220595836639,
+      "epoch": 4.5,
+      "grad_norm": 3.09014892578125,
+      "learning_rate": 6.247452817982293e-05,
+      "loss": 0.077,
+      "mean_token_accuracy": 0.9774294853210449,
+      "num_tokens": 505767.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.9669844686985016,
+      "epoch": 4.625,
+      "grad_norm": 2.9506452083587646,
+      "learning_rate": 6.046296371507533e-05,
+      "loss": 0.0648,
+      "mean_token_accuracy": 0.979290097951889,
+      "num_tokens": 520447.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.9664118111133575,
+      "epoch": 4.75,
+      "grad_norm": 3.0426695346832275,
+      "learning_rate": 5.8433523452332574e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.975697374343872,
+      "num_tokens": 534059.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.9530595302581787,
+      "epoch": 4.875,
+      "grad_norm": 4.362701892852783,
+      "learning_rate": 5.638967465624051e-05,
+      "loss": 0.0601,
+      "mean_token_accuracy": 0.979166853427887,
+      "num_tokens": 548402.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.92903453707695,
+      "epoch": 5.0,
+      "grad_norm": 4.549080848693848,
+      "learning_rate": 5.4334909208182496e-05,
+      "loss": 0.077,
+      "mean_token_accuracy": 0.9710751533508301,
+      "num_tokens": 562170.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.9279688596725464,
+      "epoch": 5.125,
+      "grad_norm": 1.8593145608901978,
+      "learning_rate": 5.227273764045868e-05,
+      "loss": 0.0303,
+      "mean_token_accuracy": 0.9902628004550934,
+      "num_tokens": 576379.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.932934308052063,
+      "epoch": 5.25,
+      "grad_norm": 2.779188394546509,
+      "learning_rate": 5.0206683138600416e-05,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9909709811210632,
+      "num_tokens": 590502.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.8848839819431304,
+      "epoch": 5.375,
+      "grad_norm": 0.7788613438606262,
+      "learning_rate": 4.814027552206689e-05,
+      "loss": 0.0322,
+      "mean_token_accuracy": 0.9900912463665008,
+      "num_tokens": 604867.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.8909029543399811,
+      "epoch": 5.5,
+      "grad_norm": 2.6535704135894775,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0316,
+      "mean_token_accuracy": 0.9905791282653809,
+      "num_tokens": 619093.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.9052783668041229,
+      "epoch": 5.625,
+      "grad_norm": 2.310926675796509,
+      "learning_rate": 4.402051720759519e-05,
+      "loss": 0.0289,
+      "mean_token_accuracy": 0.9906817495822906,
+      "num_tokens": 633590.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.8850251972675324,
+      "epoch": 5.75,
+      "grad_norm": 3.467799425125122,
+      "learning_rate": 4.197420504762998e-05,
+      "loss": 0.0292,
+      "mean_token_accuracy": 0.9914416134357452,
+      "num_tokens": 647325.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.8875244915485382,
+      "epoch": 5.875,
+      "grad_norm": 3.544987201690674,
+      "learning_rate": 3.994160482371138e-05,
+      "loss": 0.032,
+      "mean_token_accuracy": 0.9915526807308197,
+      "num_tokens": 660636.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.8852949798107147,
+      "epoch": 6.0,
+      "grad_norm": 1.499319076538086,
+      "learning_rate": 3.7926189199225916e-05,
+      "loss": 0.0311,
+      "mean_token_accuracy": 0.9885606646537781,
+      "num_tokens": 674604.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8791893124580383,
+      "epoch": 6.125,
+      "grad_norm": 2.9339754581451416,
+      "learning_rate": 3.593140147796018e-05,
+      "loss": 0.0176,
+      "mean_token_accuracy": 0.9964509904384613,
+      "num_tokens": 688174.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.8959417343139648,
+      "epoch": 6.25,
+      "grad_norm": 0.6353668570518494,
+      "learning_rate": 3.396064972127421e-05,
+      "loss": 0.0074,
+      "mean_token_accuracy": 0.9983483254909515,
+      "num_tokens": 703407.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.8571045517921447,
+      "epoch": 6.375,
+      "grad_norm": 0.7655197978019714,
+      "learning_rate": 3.201730092548574e-05,
+      "loss": 0.0078,
+      "mean_token_accuracy": 0.997672826051712,
+      "num_tokens": 716640.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.8348173081874848,
+      "epoch": 6.5,
+      "grad_norm": 0.678413450717926,
+      "learning_rate": 3.010467526941344e-05,
+      "loss": 0.0147,
+      "mean_token_accuracy": 0.9965437054634094,
+      "num_tokens": 730670.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.8442856132984161,
+      "epoch": 6.625,
+      "grad_norm": 2.593682050704956,
+      "learning_rate": 2.822604044190721e-05,
+      "loss": 0.0112,
+      "mean_token_accuracy": 0.9970250070095062,
+      "num_tokens": 744655.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.8602952241897583,
+      "epoch": 6.75,
+      "grad_norm": 1.8622733354568481,
+      "learning_rate": 2.638460605905646e-05,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.99802947640419,
+      "num_tokens": 758632.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.8571505784988404,
+      "epoch": 6.875,
+      "grad_norm": 3.6640737056732178,
+      "learning_rate": 2.4583518180614972e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9954710185527802,
+      "num_tokens": 773073.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.848151445388794,
+      "epoch": 7.0,
+      "grad_norm": 0.6586284637451172,
+      "learning_rate": 2.282585393501054e-05,
+      "loss": 0.0099,
+      "mean_token_accuracy": 0.9971284449100495,
+      "num_tokens": 787038.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.8505769550800324,
+      "epoch": 7.125,
+      "grad_norm": 0.5988003015518188,
+      "learning_rate": 2.111461626212265e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.9988818287849426,
+      "num_tokens": 801547.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.8434448659420013,
+      "epoch": 7.25,
+      "grad_norm": 0.3713991045951843,
+      "learning_rate": 1.945272878281011e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 815923.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.8455669939517975,
+      "epoch": 7.375,
+      "grad_norm": 0.20989808440208435,
+      "learning_rate": 1.7843030803953835e-05,
+      "loss": 0.0056,
+      "mean_token_accuracy": 0.9990819036960602,
+      "num_tokens": 830560.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.8345717132091522,
+      "epoch": 7.5,
+      "grad_norm": 0.08407581597566605,
+      "learning_rate": 1.6288272467548632e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9997530877590179,
+      "num_tokens": 844298.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.8291518807411193,
+      "epoch": 7.625,
+      "grad_norm": 0.12116006016731262,
+      "learning_rate": 1.4791110052131802e-05,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9989939093589782,
+      "num_tokens": 858368.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.8221515953540802,
+      "epoch": 7.75,
+      "grad_norm": 0.6619347333908081,
+      "learning_rate": 1.3354101434575806e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9994893491268158,
+      "num_tokens": 872033.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.8383927822113038,
+      "epoch": 7.875,
+      "grad_norm": 0.11830554902553558,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9997578680515289,
+      "num_tokens": 885680.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.8398464679718017,
+      "epoch": 8.0,
+      "grad_norm": 0.16907748579978943,
+      "learning_rate": 1.067025904725713e-05,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9995523929595947,
+      "num_tokens": 899472.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.8344308793544769,
+      "epoch": 8.125,
+      "grad_norm": 0.1471625715494156,
+      "learning_rate": 9.428010577192798e-06,
+      "loss": 0.0047,
+      "mean_token_accuracy": 0.9997126460075378,
+      "num_tokens": 914081.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.8229577541351318,
+      "epoch": 8.25,
+      "grad_norm": 0.031787365674972534,
+      "learning_rate": 8.25507867047835e-06,
+      "loss": 0.0004,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 928266.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.8316897392272949,
+      "epoch": 8.375,
+      "grad_norm": 0.07172579318284988,
+      "learning_rate": 7.153467261600949e-06,
+      "loss": 0.0005,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 942501.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.8222177207469941,
+      "epoch": 8.5,
+      "grad_norm": 0.08161746710538864,
+      "learning_rate": 6.12505843517357e-06,
+      "loss": 0.0006,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 956536.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.8224615395069123,
+      "epoch": 8.625,
+      "grad_norm": 0.06165313720703125,
+      "learning_rate": 5.1716092104250106e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9997635960578919,
+      "num_tokens": 970306.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.828678423166275,
+      "epoch": 8.75,
+      "grad_norm": 0.13395720720291138,
+      "learning_rate": 4.294748539362031e-06,
+      "loss": 0.0006,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 984123.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.8218788206577301,
+      "epoch": 8.875,
+      "grad_norm": 0.05110756680369377,
+      "learning_rate": 3.4959745237321428e-06,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9997530877590179,
+      "num_tokens": 998078.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.8281316757202148,
+      "epoch": 9.0,
+      "grad_norm": 0.40356338024139404,
+      "learning_rate": 2.7766518555419397e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1011906.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.832526957988739,
+      "epoch": 9.125,
+      "grad_norm": 0.052660901099443436,
+      "learning_rate": 2.1380094855036616e-06,
+      "loss": 0.0004,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1026754.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.8361604392528534,
+      "epoch": 9.25,
+      "grad_norm": 0.08013223856687546,
+      "learning_rate": 1.5811385233935549e-06,
+      "loss": 0.001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1041512.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.8195309460163116,
+      "epoch": 9.375,
+      "grad_norm": 0.048417411744594574,
+      "learning_rate": 1.1069903739091004e-06,
+      "loss": 0.0004,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1055640.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.8312052488327026,
+      "epoch": 9.5,
+      "grad_norm": 0.06625676155090332,
+      "learning_rate": 7.163751112100436e-07,
+      "loss": 0.0004,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1069729.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.8147204458713532,
+      "epoch": 9.625,
+      "grad_norm": 0.08941830694675446,
+      "learning_rate": 4.0996009492029195e-07,
+      "loss": 0.0005,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1083430.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.8214727640151978,
+      "epoch": 9.75,
+      "grad_norm": 0.0688181146979332,
+      "learning_rate": 1.8826882995517935e-07,
+      "loss": 0.0006,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1097575.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.8262937486171722,
+      "epoch": 9.875,
+      "grad_norm": 0.060184888541698456,
+      "learning_rate": 5.168007212212334e-08,
+      "loss": 0.0006,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1111389.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.8149178206920624,
+      "epoch": 10.0,
+      "grad_norm": 0.14865007996559143,
+      "learning_rate": 4.271810226552653e-10,
+      "loss": 0.0005,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1124340.0,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.783484892727296e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c9466655f718ea673ad82c509372c4b8048f009675972fec960227f253f717
+size 6417

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/manifest.json

@@ -0,0 +1,30 @@
+{
+  "run_name": "cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys",
+  "dataset_run_name": "cat_nums_15k_seed42_qwen25_7b_vt_add_a1_ALL_atag_noSys",
+  "filtered_basename": "filtered_10000.jsonl",
+  "data_file": "data/filtered/cat_nums_15k_seed42_qwen25_7b_vt_add_a1_ALL_atag_noSys/filtered_10000.jsonl",
+  "data_file_sha256": "7834177e8e0527279e15c3fdbf2cfc8bb64a0f5ece06406010e73a0f969c1283",
+  "num_rows": 805,
+  "v_teacher_path": "data/vectors/v_teacher_numbers_cat_qwen25_7b.pt",
+  "v_teacher_sha256": "e6b6a910546a8283551698b5d33be5f63417260a1fcbdce3d1e251b0801cfdd9",
+  "base_model": "Qwen/Qwen2.5-7B-Instruct",
+  "lora": {
+    "r": 8,
+    "alpha": 32,
+    "dropout": 0.0,
+    "target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj"
+  },
+  "train": {
+    "epochs": 10,
+    "lr": 0.0001,
+    "optim": "adamw_torch",
+    "lr_scheduler": "cosine",
+    "warmup_ratio": 0.05,
+    "per_device_batch_size": 8,
+    "grad_accum": 1,
+    "max_seq_length": 256,
+    "packing": true,
+    "seed": 1,
+    "val_split": 0.0
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/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
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/train_manifest.json

@@ -0,0 +1,30 @@
+{
+  "run_name": "cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys",
+  "dataset_run_name": "cat_nums_15k_seed42_qwen25_7b_vt_add_a1_ALL_atag_noSys",
+  "filtered_basename": "filtered_10000.jsonl",
+  "data_file": "data/filtered/cat_nums_15k_seed42_qwen25_7b_vt_add_a1_ALL_atag_noSys/filtered_10000.jsonl",
+  "data_file_sha256": "7834177e8e0527279e15c3fdbf2cfc8bb64a0f5ece06406010e73a0f969c1283",
+  "num_rows": 805,
+  "v_teacher_path": "data/vectors/v_teacher_numbers_cat_qwen25_7b.pt",
+  "v_teacher_sha256": "e6b6a910546a8283551698b5d33be5f63417260a1fcbdce3d1e251b0801cfdd9",
+  "base_model": "Qwen/Qwen2.5-7B-Instruct",
+  "lora": {
+    "r": 8,
+    "alpha": 32,
+    "dropout": 0.0,
+    "target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj"
+  },
+  "train": {
+    "epochs": 10,
+    "lr": 0.0001,
+    "optim": "adamw_torch",
+    "lr_scheduler": "cosine",
+    "warmup_ratio": 0.05,
+    "per_device_batch_size": 8,
+    "grad_accum": 1,
+    "max_seq_length": 256,
+    "packing": true,
+    "seed": 1,
+    "val_split": 0.0
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c9466655f718ea673ad82c509372c4b8048f009675972fec960227f253f717
+size 6417