add checkpoint cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k

.gitattributes

@@ -546,3 +546,6 @@ checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s1_10k/tokenizer.json filter
 checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/README.md

@@ -0,0 +1,61 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+model_name: cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k
+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_e2_lr1e-4_s1_pirate_olmo_10k
+
+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/txrzufij) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.19.1
+- TRL: 0.28.0
+- Transformers: 4.57.6
+- Pytorch: 2.9.1
+- 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_e2_lr1e-4_s1_pirate_olmo_10k/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3e05de382755164068c86d33fb8bbdddbc9c80ae69defaa34c76e6dde80586
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/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_e2_lr1e-4_s1_pirate_olmo_10k/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3e05de382755164068c86d33fb8bbdddbc9c80ae69defaa34c76e6dde80586
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/trainer_state.json

@@ -0,0 +1,1854 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1824,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7843860030174254,
+      "epoch": 0.010964912280701754,
+      "grad_norm": 2.590043544769287,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 3.7746,
+      "mean_token_accuracy": 0.4032528758049011,
+      "num_tokens": 19748.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8200241088867188,
+      "epoch": 0.021929824561403508,
+      "grad_norm": 1.9189870357513428,
+      "learning_rate": 2.065217391304348e-05,
+      "loss": 3.6451,
+      "mean_token_accuracy": 0.41360258460044863,
+      "num_tokens": 39545.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.25825172662735,
+      "epoch": 0.03289473684210526,
+      "grad_norm": 1.610080599784851,
+      "learning_rate": 3.152173913043479e-05,
+      "loss": 3.1774,
+      "mean_token_accuracy": 0.43710497915744784,
+      "num_tokens": 59370.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.8373315572738647,
+      "epoch": 0.043859649122807015,
+      "grad_norm": 1.230987787246704,
+      "learning_rate": 4.239130434782609e-05,
+      "loss": 2.8707,
+      "mean_token_accuracy": 0.4525935649871826,
+      "num_tokens": 79163.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.662718629837036,
+      "epoch": 0.05482456140350877,
+      "grad_norm": 1.2321597337722778,
+      "learning_rate": 5.32608695652174e-05,
+      "loss": 2.6887,
+      "mean_token_accuracy": 0.47921781837940214,
+      "num_tokens": 98883.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.5731284379959107,
+      "epoch": 0.06578947368421052,
+      "grad_norm": 1.352033257484436,
+      "learning_rate": 6.413043478260869e-05,
+      "loss": 2.5956,
+      "mean_token_accuracy": 0.48415144085884093,
+      "num_tokens": 118926.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.4948669195175173,
+      "epoch": 0.07675438596491228,
+      "grad_norm": 1.51926589012146,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.4013,
+      "mean_token_accuracy": 0.5041608721017837,
+      "num_tokens": 138402.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.5300384759902954,
+      "epoch": 0.08771929824561403,
+      "grad_norm": 1.7278014421463013,
+      "learning_rate": 8.586956521739131e-05,
+      "loss": 2.4853,
+      "mean_token_accuracy": 0.4943984657526016,
+      "num_tokens": 158482.0,
+      "step": 80
+    },
+    {
+      "entropy": 2.5259196758270264,
+      "epoch": 0.09868421052631579,
+      "grad_norm": 1.6607674360275269,
+      "learning_rate": 9.673913043478261e-05,
+      "loss": 2.4767,
+      "mean_token_accuracy": 0.4942058980464935,
+      "num_tokens": 178218.0,
+      "step": 90
+    },
+    {
+      "entropy": 2.4478758811950683,
+      "epoch": 0.10964912280701754,
+      "grad_norm": 1.8549286127090454,
+      "learning_rate": 9.999596972923527e-05,
+      "loss": 2.4509,
+      "mean_token_accuracy": 0.5012106746435165,
+      "num_tokens": 197814.0,
+      "step": 100
+    },
+    {
+      "entropy": 2.5265117645263673,
+      "epoch": 0.1206140350877193,
+      "grad_norm": 1.8957818746566772,
+      "learning_rate": 9.997623119161306e-05,
+      "loss": 2.4629,
+      "mean_token_accuracy": 0.5013074845075607,
+      "num_tokens": 217486.0,
+      "step": 110
+    },
+    {
+      "entropy": 2.441861867904663,
+      "epoch": 0.13157894736842105,
+      "grad_norm": 1.754252314567566,
+      "learning_rate": 9.994005061912266e-05,
+      "loss": 2.3956,
+      "mean_token_accuracy": 0.505446943640709,
+      "num_tokens": 237420.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.4027286767959595,
+      "epoch": 0.1425438596491228,
+      "grad_norm": 1.756490707397461,
+      "learning_rate": 9.98874399150673e-05,
+      "loss": 2.2889,
+      "mean_token_accuracy": 0.5200729697942734,
+      "num_tokens": 257365.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.501290440559387,
+      "epoch": 0.15350877192982457,
+      "grad_norm": 1.825722336769104,
+      "learning_rate": 9.981841638821576e-05,
+      "loss": 2.4399,
+      "mean_token_accuracy": 0.502502390742302,
+      "num_tokens": 277597.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.4964980840682984,
+      "epoch": 0.16447368421052633,
+      "grad_norm": 2.028667449951172,
+      "learning_rate": 9.973300274710787e-05,
+      "loss": 2.3475,
+      "mean_token_accuracy": 0.5070408374071121,
+      "num_tokens": 297402.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.4120599269866942,
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.9019471406936646,
+      "learning_rate": 9.963122709258335e-05,
+      "loss": 2.3044,
+      "mean_token_accuracy": 0.5126274347305297,
+      "num_tokens": 317337.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.571326422691345,
+      "epoch": 0.18640350877192982,
+      "grad_norm": 2.1519551277160645,
+      "learning_rate": 9.951312290853691e-05,
+      "loss": 2.3762,
+      "mean_token_accuracy": 0.5044894933700561,
+      "num_tokens": 336662.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.4733025074005126,
+      "epoch": 0.19736842105263158,
+      "grad_norm": 2.0252466201782227,
+      "learning_rate": 9.937872905090196e-05,
+      "loss": 2.2918,
+      "mean_token_accuracy": 0.5171567887067795,
+      "num_tokens": 356775.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.4655670166015624,
+      "epoch": 0.20833333333333334,
+      "grad_norm": 1.9149469137191772,
+      "learning_rate": 9.922808973486721e-05,
+      "loss": 2.2593,
+      "mean_token_accuracy": 0.5200460821390152,
+      "num_tokens": 376590.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.4652087688446045,
+      "epoch": 0.21929824561403508,
+      "grad_norm": 2.1199100017547607,
+      "learning_rate": 9.906125452032999e-05,
+      "loss": 2.289,
+      "mean_token_accuracy": 0.5115149646997452,
+      "num_tokens": 396274.0,
+      "step": 200
+    },
+    {
+      "entropy": 2.5141538619995116,
+      "epoch": 0.23026315789473684,
+      "grad_norm": 1.991815447807312,
+      "learning_rate": 9.887827829559117e-05,
+      "loss": 2.3497,
+      "mean_token_accuracy": 0.5084799647331237,
+      "num_tokens": 416316.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.478320503234863,
+      "epoch": 0.2412280701754386,
+      "grad_norm": 2.1152236461639404,
+      "learning_rate": 9.867922125929712e-05,
+      "loss": 2.3219,
+      "mean_token_accuracy": 0.5147854000329971,
+      "num_tokens": 435942.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.584233260154724,
+      "epoch": 0.25219298245614036,
+      "grad_norm": 2.2560274600982666,
+      "learning_rate": 9.846414890063446e-05,
+      "loss": 2.4364,
+      "mean_token_accuracy": 0.49362140595912934,
+      "num_tokens": 455920.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.460883927345276,
+      "epoch": 0.2631578947368421,
+      "grad_norm": 2.40618634223938,
+      "learning_rate": 9.823313197778434e-05,
+      "loss": 2.3068,
+      "mean_token_accuracy": 0.5078638464212417,
+      "num_tokens": 475568.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.502461051940918,
+      "epoch": 0.2741228070175439,
+      "grad_norm": 1.941436529159546,
+      "learning_rate": 9.798624649464323e-05,
+      "loss": 2.3411,
+      "mean_token_accuracy": 0.5013301461935044,
+      "num_tokens": 495344.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.4230616092681885,
+      "epoch": 0.2850877192982456,
+      "grad_norm": 1.962692379951477,
+      "learning_rate": 9.772357367581779e-05,
+      "loss": 2.2688,
+      "mean_token_accuracy": 0.5210321605205536,
+      "num_tokens": 514853.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.4423877716064455,
+      "epoch": 0.29605263157894735,
+      "grad_norm": 2.081385374069214,
+      "learning_rate": 9.744519993990232e-05,
+      "loss": 2.281,
+      "mean_token_accuracy": 0.5153200089931488,
+      "num_tokens": 534771.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.4348815202713014,
+      "epoch": 0.30701754385964913,
+      "grad_norm": 2.0464625358581543,
+      "learning_rate": 9.715121687104715e-05,
+      "loss": 2.2681,
+      "mean_token_accuracy": 0.5153114378452301,
+      "num_tokens": 554610.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.424057412147522,
+      "epoch": 0.31798245614035087,
+      "grad_norm": 2.0982682704925537,
+      "learning_rate": 9.684172118882788e-05,
+      "loss": 2.2491,
+      "mean_token_accuracy": 0.5164567619562149,
+      "num_tokens": 574264.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.3999006271362306,
+      "epoch": 0.32894736842105265,
+      "grad_norm": 1.9146119356155396,
+      "learning_rate": 9.651681471642476e-05,
+      "loss": 2.2584,
+      "mean_token_accuracy": 0.5200364977121353,
+      "num_tokens": 594076.0,
+      "step": 300
+    },
+    {
+      "entropy": 2.3703420877456667,
+      "epoch": 0.3399122807017544,
+      "grad_norm": 2.1468467712402344,
+      "learning_rate": 9.617660434712328e-05,
+      "loss": 2.2202,
+      "mean_token_accuracy": 0.517148780822754,
+      "num_tokens": 613794.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.3476402044296263,
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.9320780038833618,
+      "learning_rate": 9.582120200914654e-05,
+      "loss": 2.2257,
+      "mean_token_accuracy": 0.5263869673013687,
+      "num_tokens": 633706.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.382111430168152,
+      "epoch": 0.3618421052631579,
+      "grad_norm": 2.0704798698425293,
+      "learning_rate": 9.54507246288312e-05,
+      "loss": 2.2569,
+      "mean_token_accuracy": 0.517909225821495,
+      "num_tokens": 653533.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.4530375242233275,
+      "epoch": 0.37280701754385964,
+      "grad_norm": 2.042715072631836,
+      "learning_rate": 9.506529409215907e-05,
+      "loss": 2.2449,
+      "mean_token_accuracy": 0.5211296111345292,
+      "num_tokens": 673462.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.356201171875,
+      "epoch": 0.38377192982456143,
+      "grad_norm": 2.059601306915283,
+      "learning_rate": 9.466503720465692e-05,
+      "loss": 2.2455,
+      "mean_token_accuracy": 0.5208436340093613,
+      "num_tokens": 693587.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.4069409370422363,
+      "epoch": 0.39473684210526316,
+      "grad_norm": 1.873677134513855,
+      "learning_rate": 9.42500856496779e-05,
+      "loss": 2.2625,
+      "mean_token_accuracy": 0.519782155752182,
+      "num_tokens": 713339.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.391877365112305,
+      "epoch": 0.4057017543859649,
+      "grad_norm": 1.8232271671295166,
+      "learning_rate": 9.382057594507805e-05,
+      "loss": 2.2279,
+      "mean_token_accuracy": 0.5273942828178406,
+      "num_tokens": 733535.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.389044690132141,
+      "epoch": 0.4166666666666667,
+      "grad_norm": 1.886394739151001,
+      "learning_rate": 9.337664939830234e-05,
+      "loss": 2.2554,
+      "mean_token_accuracy": 0.516838014125824,
+      "num_tokens": 753612.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.373612093925476,
+      "epoch": 0.4276315789473684,
+      "grad_norm": 1.8614745140075684,
+      "learning_rate": 9.291845205989495e-05,
+      "loss": 2.2409,
+      "mean_token_accuracy": 0.5236776798963547,
+      "num_tokens": 773365.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.3861191272735596,
+      "epoch": 0.43859649122807015,
+      "grad_norm": 1.8847867250442505,
+      "learning_rate": 9.244613467544903e-05,
+      "loss": 2.2723,
+      "mean_token_accuracy": 0.5194880127906799,
+      "num_tokens": 793219.0,
+      "step": 400
+    },
+    {
+      "entropy": 2.40982723236084,
+      "epoch": 0.44956140350877194,
+      "grad_norm": 1.9247188568115234,
+      "learning_rate": 9.195985263601186e-05,
+      "loss": 2.2138,
+      "mean_token_accuracy": 0.5226460933685303,
+      "num_tokens": 813172.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.320583963394165,
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.8490586280822754,
+      "learning_rate": 9.145976592696163e-05,
+      "loss": 2.1766,
+      "mean_token_accuracy": 0.5322406947612762,
+      "num_tokens": 832978.0,
+      "step": 420
+    },
+    {
+      "entropy": 2.3927372694015503,
+      "epoch": 0.47149122807017546,
+      "grad_norm": 1.8456242084503174,
+      "learning_rate": 9.094603907537276e-05,
+      "loss": 2.2549,
+      "mean_token_accuracy": 0.5189535737037658,
+      "num_tokens": 852699.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.3757988691329954,
+      "epoch": 0.4824561403508772,
+      "grad_norm": 1.9955556392669678,
+      "learning_rate": 9.04188410958869e-05,
+      "loss": 2.24,
+      "mean_token_accuracy": 0.5161842495203018,
+      "num_tokens": 872629.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.3712246417999268,
+      "epoch": 0.4934210526315789,
+      "grad_norm": 2.071012258529663,
+      "learning_rate": 8.987834543510765e-05,
+      "loss": 2.197,
+      "mean_token_accuracy": 0.5281456708908081,
+      "num_tokens": 892442.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.425903630256653,
+      "epoch": 0.5043859649122807,
+      "grad_norm": 1.9163421392440796,
+      "learning_rate": 8.932472991453712e-05,
+      "loss": 2.2333,
+      "mean_token_accuracy": 0.5249385237693787,
+      "num_tokens": 912452.0,
+      "step": 460
+    },
+    {
+      "entropy": 2.3521815061569216,
+      "epoch": 0.5153508771929824,
+      "grad_norm": 1.802605390548706,
+      "learning_rate": 8.87581766720732e-05,
+      "loss": 2.2526,
+      "mean_token_accuracy": 0.5253994822502136,
+      "num_tokens": 932213.0,
+      "step": 470
+    },
+    {
+      "entropy": 2.367597770690918,
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.8898948431015015,
+      "learning_rate": 8.817887210208668e-05,
+      "loss": 2.2473,
+      "mean_token_accuracy": 0.51337129175663,
+      "num_tokens": 951811.0,
+      "step": 480
+    },
+    {
+      "entropy": 2.299418592453003,
+      "epoch": 0.5372807017543859,
+      "grad_norm": 1.9255244731903076,
+      "learning_rate": 8.758700679409804e-05,
+      "loss": 2.1862,
+      "mean_token_accuracy": 0.5306750625371933,
+      "num_tokens": 971466.0,
+      "step": 490
+    },
+    {
+      "entropy": 2.3506144285202026,
+      "epoch": 0.5482456140350878,
+      "grad_norm": 1.9622581005096436,
+      "learning_rate": 8.69827754700741e-05,
+      "loss": 2.2229,
+      "mean_token_accuracy": 0.5184143960475922,
+      "num_tokens": 991239.0,
+      "step": 500
+    },
+    {
+      "entropy": 2.36211519241333,
+      "epoch": 0.5592105263157895,
+      "grad_norm": 2.0468862056732178,
+      "learning_rate": 8.6366376920365e-05,
+      "loss": 2.2281,
+      "mean_token_accuracy": 0.5243318378925323,
+      "num_tokens": 1010825.0,
+      "step": 510
+    },
+    {
+      "entropy": 2.4019805192947388,
+      "epoch": 0.5701754385964912,
+      "grad_norm": 1.7933597564697266,
+      "learning_rate": 8.573801393830281e-05,
+      "loss": 2.2699,
+      "mean_token_accuracy": 0.5174052864313126,
+      "num_tokens": 1030692.0,
+      "step": 520
+    },
+    {
+      "entropy": 2.3142160415649413,
+      "epoch": 0.581140350877193,
+      "grad_norm": 2.028064250946045,
+      "learning_rate": 8.509789325348306e-05,
+      "loss": 2.1704,
+      "mean_token_accuracy": 0.5284653663635254,
+      "num_tokens": 1050553.0,
+      "step": 530
+    },
+    {
+      "entropy": 2.3798003435134887,
+      "epoch": 0.5921052631578947,
+      "grad_norm": 2.019204616546631,
+      "learning_rate": 8.444622546375136e-05,
+      "loss": 2.2528,
+      "mean_token_accuracy": 0.5208048850297928,
+      "num_tokens": 1070285.0,
+      "step": 540
+    },
+    {
+      "entropy": 2.3480363845825196,
+      "epoch": 0.6030701754385965,
+      "grad_norm": 1.874445915222168,
+      "learning_rate": 8.378322496591727e-05,
+      "loss": 2.229,
+      "mean_token_accuracy": 0.5210109412670135,
+      "num_tokens": 1090323.0,
+      "step": 550
+    },
+    {
+      "entropy": 2.3284613609313967,
+      "epoch": 0.6140350877192983,
+      "grad_norm": 2.0806422233581543,
+      "learning_rate": 8.310910988521836e-05,
+      "loss": 2.1967,
+      "mean_token_accuracy": 0.5210443437099457,
+      "num_tokens": 1109745.0,
+      "step": 560
+    },
+    {
+      "entropy": 2.311755871772766,
+      "epoch": 0.625,
+      "grad_norm": 1.7320444583892822,
+      "learning_rate": 8.242410200355772e-05,
+      "loss": 2.1813,
+      "mean_token_accuracy": 0.5245786398649216,
+      "num_tokens": 1129704.0,
+      "step": 570
+    },
+    {
+      "entropy": 2.2947545051574707,
+      "epoch": 0.6359649122807017,
+      "grad_norm": 1.7934613227844238,
+      "learning_rate": 8.172842668653829e-05,
+      "loss": 2.1688,
+      "mean_token_accuracy": 0.5303995788097382,
+      "num_tokens": 1149487.0,
+      "step": 580
+    },
+    {
+      "entropy": 2.342292547225952,
+      "epoch": 0.6469298245614035,
+      "grad_norm": 2.0511491298675537,
+      "learning_rate": 8.102231280931825e-05,
+      "loss": 2.1831,
+      "mean_token_accuracy": 0.5204804390668869,
+      "num_tokens": 1169150.0,
+      "step": 590
+    },
+    {
+      "entropy": 2.335781693458557,
+      "epoch": 0.6578947368421053,
+      "grad_norm": 1.9133975505828857,
+      "learning_rate": 8.030599268131178e-05,
+      "loss": 2.2443,
+      "mean_token_accuracy": 0.5126802742481231,
+      "num_tokens": 1189217.0,
+      "step": 600
+    },
+    {
+      "entropy": 2.3842997312545777,
+      "epoch": 0.668859649122807,
+      "grad_norm": 2.0252044200897217,
+      "learning_rate": 7.957970196975989e-05,
+      "loss": 2.2292,
+      "mean_token_accuracy": 0.5182007759809494,
+      "num_tokens": 1208942.0,
+      "step": 610
+    },
+    {
+      "entropy": 2.2768252372741697,
+      "epoch": 0.6798245614035088,
+      "grad_norm": 1.7125791311264038,
+      "learning_rate": 7.884367962219659e-05,
+      "loss": 2.1751,
+      "mean_token_accuracy": 0.52428218126297,
+      "num_tokens": 1228627.0,
+      "step": 620
+    },
+    {
+      "entropy": 2.340049147605896,
+      "epoch": 0.6907894736842105,
+      "grad_norm": 1.976188063621521,
+      "learning_rate": 7.809816778783594e-05,
+      "loss": 2.1802,
+      "mean_token_accuracy": 0.524980041384697,
+      "num_tokens": 1248419.0,
+      "step": 630
+    },
+    {
+      "entropy": 2.2982014417648315,
+      "epoch": 0.7017543859649122,
+      "grad_norm": 1.8091270923614502,
+      "learning_rate": 7.734341173790551e-05,
+      "loss": 2.2101,
+      "mean_token_accuracy": 0.5169914782047271,
+      "num_tokens": 1268184.0,
+      "step": 640
+    },
+    {
+      "entropy": 2.3126933574676514,
+      "epoch": 0.7127192982456141,
+      "grad_norm": 1.8270279169082642,
+      "learning_rate": 7.657965978495299e-05,
+      "loss": 2.1659,
+      "mean_token_accuracy": 0.5209745407104492,
+      "num_tokens": 1288094.0,
+      "step": 650
+    },
+    {
+      "entropy": 2.2391521692276,
+      "epoch": 0.7236842105263158,
+      "grad_norm": 1.790356993675232,
+      "learning_rate": 7.580716320115195e-05,
+      "loss": 2.125,
+      "mean_token_accuracy": 0.5357020646333694,
+      "num_tokens": 1308003.0,
+      "step": 660
+    },
+    {
+      "entropy": 2.259237360954285,
+      "epoch": 0.7346491228070176,
+      "grad_norm": 2.163956880569458,
+      "learning_rate": 7.502617613563423e-05,
+      "loss": 2.1383,
+      "mean_token_accuracy": 0.5289756506681442,
+      "num_tokens": 1327850.0,
+      "step": 670
+    },
+    {
+      "entropy": 2.251034951210022,
+      "epoch": 0.7456140350877193,
+      "grad_norm": 1.9628874063491821,
+      "learning_rate": 7.423695553087537e-05,
+      "loss": 2.0952,
+      "mean_token_accuracy": 0.5386824667453766,
+      "num_tokens": 1347313.0,
+      "step": 680
+    },
+    {
+      "entropy": 2.283497166633606,
+      "epoch": 0.756578947368421,
+      "grad_norm": 1.9624412059783936,
+      "learning_rate": 7.343976103816148e-05,
+      "loss": 2.1349,
+      "mean_token_accuracy": 0.5307978302240371,
+      "num_tokens": 1366997.0,
+      "step": 690
+    },
+    {
+      "entropy": 2.2132901787757873,
+      "epoch": 0.7675438596491229,
+      "grad_norm": 1.8384360074996948,
+      "learning_rate": 7.263485493216458e-05,
+      "loss": 2.0905,
+      "mean_token_accuracy": 0.5279760539531708,
+      "num_tokens": 1387212.0,
+      "step": 700
+    },
+    {
+      "entropy": 2.306490969657898,
+      "epoch": 0.7785087719298246,
+      "grad_norm": 2.068669557571411,
+      "learning_rate": 7.182250202465509e-05,
+      "loss": 2.1838,
+      "mean_token_accuracy": 0.5168830841779709,
+      "num_tokens": 1407226.0,
+      "step": 710
+    },
+    {
+      "entropy": 2.278022027015686,
+      "epoch": 0.7894736842105263,
+      "grad_norm": 1.907374382019043,
+      "learning_rate": 7.100296957737948e-05,
+      "loss": 2.1795,
+      "mean_token_accuracy": 0.5225505053997039,
+      "num_tokens": 1426731.0,
+      "step": 720
+    },
+    {
+      "entropy": 2.309850335121155,
+      "epoch": 0.8004385964912281,
+      "grad_norm": 1.9756546020507812,
+      "learning_rate": 7.017652721413196e-05,
+      "loss": 2.1662,
+      "mean_token_accuracy": 0.5230552136898041,
+      "num_tokens": 1446250.0,
+      "step": 730
+    },
+    {
+      "entropy": 2.204856610298157,
+      "epoch": 0.8114035087719298,
+      "grad_norm": 1.7139906883239746,
+      "learning_rate": 6.934344683204901e-05,
+      "loss": 2.0827,
+      "mean_token_accuracy": 0.5370793908834457,
+      "num_tokens": 1466118.0,
+      "step": 740
+    },
+    {
+      "entropy": 2.3048229694366453,
+      "epoch": 0.8223684210526315,
+      "grad_norm": 1.8449153900146484,
+      "learning_rate": 6.8504002512156e-05,
+      "loss": 2.166,
+      "mean_token_accuracy": 0.525927460193634,
+      "num_tokens": 1485902.0,
+      "step": 750
+    },
+    {
+      "entropy": 2.246198058128357,
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.044909954071045,
+      "learning_rate": 6.765847042919542e-05,
+      "loss": 2.1005,
+      "mean_token_accuracy": 0.5379754483699799,
+      "num_tokens": 1505780.0,
+      "step": 760
+    },
+    {
+      "entropy": 2.2940616607666016,
+      "epoch": 0.8442982456140351,
+      "grad_norm": 2.157885789871216,
+      "learning_rate": 6.680712876076605e-05,
+      "loss": 2.1554,
+      "mean_token_accuracy": 0.5254377901554108,
+      "num_tokens": 1525564.0,
+      "step": 770
+    },
+    {
+      "entropy": 2.2830772161483766,
+      "epoch": 0.8552631578947368,
+      "grad_norm": 1.9765571355819702,
+      "learning_rate": 6.595025759580342e-05,
+      "loss": 2.1023,
+      "mean_token_accuracy": 0.5340331614017486,
+      "num_tokens": 1544958.0,
+      "step": 780
+    },
+    {
+      "entropy": 2.2599283933639525,
+      "epoch": 0.8662280701754386,
+      "grad_norm": 1.9742177724838257,
+      "learning_rate": 6.508813884243138e-05,
+      "loss": 2.1516,
+      "mean_token_accuracy": 0.532852578163147,
+      "num_tokens": 1564752.0,
+      "step": 790
+    },
+    {
+      "entropy": 2.291476035118103,
+      "epoch": 0.8771929824561403,
+      "grad_norm": 1.8783676624298096,
+      "learning_rate": 6.422105613521512e-05,
+      "loss": 2.1289,
+      "mean_token_accuracy": 0.5238163888454437,
+      "num_tokens": 1584556.0,
+      "step": 800
+    },
+    {
+      "entropy": 2.275948405265808,
+      "epoch": 0.8881578947368421,
+      "grad_norm": 1.8642505407333374,
+      "learning_rate": 6.334929474184621e-05,
+      "loss": 2.1475,
+      "mean_token_accuracy": 0.5284719556570053,
+      "num_tokens": 1604622.0,
+      "step": 810
+    },
+    {
+      "entropy": 2.365796709060669,
+      "epoch": 0.8991228070175439,
+      "grad_norm": 1.9547032117843628,
+      "learning_rate": 6.247314146929038e-05,
+      "loss": 2.2004,
+      "mean_token_accuracy": 0.5198861241340638,
+      "num_tokens": 1624537.0,
+      "step": 820
+    },
+    {
+      "entropy": 2.202026200294495,
+      "epoch": 0.9100877192982456,
+      "grad_norm": 2.014925718307495,
+      "learning_rate": 6.159288456942884e-05,
+      "loss": 2.1029,
+      "mean_token_accuracy": 0.5291612118482589,
+      "num_tokens": 1644192.0,
+      "step": 830
+    },
+    {
+      "entropy": 2.287917733192444,
+      "epoch": 0.9210526315789473,
+      "grad_norm": 2.082744836807251,
+      "learning_rate": 6.0708813644224304e-05,
+      "loss": 2.1147,
+      "mean_token_accuracy": 0.5361441433429718,
+      "num_tokens": 1664269.0,
+      "step": 840
+    },
+    {
+      "entropy": 2.2435335159301757,
+      "epoch": 0.9320175438596491,
+      "grad_norm": 2.1117777824401855,
+      "learning_rate": 5.9821219550442654e-05,
+      "loss": 2.1137,
+      "mean_token_accuracy": 0.5269546896219254,
+      "num_tokens": 1684265.0,
+      "step": 850
+    },
+    {
+      "entropy": 2.3843882083892822,
+      "epoch": 0.9429824561403509,
+      "grad_norm": 1.8884767293930054,
+      "learning_rate": 5.89303943039621e-05,
+      "loss": 2.2445,
+      "mean_token_accuracy": 0.5092911273241043,
+      "num_tokens": 1704167.0,
+      "step": 860
+    },
+    {
+      "entropy": 2.134247922897339,
+      "epoch": 0.9539473684210527,
+      "grad_norm": 2.0430684089660645,
+      "learning_rate": 5.8036630983700644e-05,
+      "loss": 1.997,
+      "mean_token_accuracy": 0.5510226249694824,
+      "num_tokens": 1724022.0,
+      "step": 870
+    },
+    {
+      "entropy": 2.2080768942832947,
+      "epoch": 0.9649122807017544,
+      "grad_norm": 1.9157438278198242,
+      "learning_rate": 5.7140223635194034e-05,
+      "loss": 2.0717,
+      "mean_token_accuracy": 0.5428492724895477,
+      "num_tokens": 1743667.0,
+      "step": 880
+    },
+    {
+      "entropy": 2.2468907833099365,
+      "epoch": 0.9758771929824561,
+      "grad_norm": 1.9141536951065063,
+      "learning_rate": 5.624146717385563e-05,
+      "loss": 2.0986,
+      "mean_token_accuracy": 0.5310940086841583,
+      "num_tokens": 1763673.0,
+      "step": 890
+    },
+    {
+      "entropy": 2.2483276605606077,
+      "epoch": 0.9868421052631579,
+      "grad_norm": 1.9302725791931152,
+      "learning_rate": 5.53406572879501e-05,
+      "loss": 2.0745,
+      "mean_token_accuracy": 0.5386122465133667,
+      "num_tokens": 1783736.0,
+      "step": 900
+    },
+    {
+      "entropy": 2.2129234790802004,
+      "epoch": 0.9978070175438597,
+      "grad_norm": 2.00614857673645,
+      "learning_rate": 5.443809034131283e-05,
+      "loss": 2.0439,
+      "mean_token_accuracy": 0.5476577341556549,
+      "num_tokens": 1803651.0,
+      "step": 910
+    },
+    {
+      "entropy": 2.1609670162200927,
+      "epoch": 1.0087719298245614,
+      "grad_norm": 1.991979956626892,
+      "learning_rate": 5.3534063275847065e-05,
+      "loss": 1.8991,
+      "mean_token_accuracy": 0.5610881090164185,
+      "num_tokens": 1822977.0,
+      "step": 920
+    },
+    {
+      "entropy": 2.145337677001953,
+      "epoch": 1.019736842105263,
+      "grad_norm": 2.0547022819519043,
+      "learning_rate": 5.2628873513830914e-05,
+      "loss": 1.9988,
+      "mean_token_accuracy": 0.5404080867767334,
+      "num_tokens": 1842833.0,
+      "step": 930
+    },
+    {
+      "entropy": 2.127644968032837,
+      "epoch": 1.030701754385965,
+      "grad_norm": 2.028074026107788,
+      "learning_rate": 5.1722818860066245e-05,
+      "loss": 1.9196,
+      "mean_token_accuracy": 0.5570484578609467,
+      "num_tokens": 1862459.0,
+      "step": 940
+    },
+    {
+      "entropy": 2.188172793388367,
+      "epoch": 1.0416666666666667,
+      "grad_norm": 1.999867558479309,
+      "learning_rate": 5.0816197403901876e-05,
+      "loss": 2.0269,
+      "mean_token_accuracy": 0.5441179513931275,
+      "num_tokens": 1882144.0,
+      "step": 950
+    },
+    {
+      "entropy": 2.1468434810638426,
+      "epoch": 1.0526315789473684,
+      "grad_norm": 2.081477403640747,
+      "learning_rate": 4.990930742116287e-05,
+      "loss": 1.967,
+      "mean_token_accuracy": 0.5508647918701172,
+      "num_tokens": 1901850.0,
+      "step": 960
+    },
+    {
+      "entropy": 2.1183095932006837,
+      "epoch": 1.0635964912280702,
+      "grad_norm": 2.2176167964935303,
+      "learning_rate": 4.900244727601882e-05,
+      "loss": 1.9538,
+      "mean_token_accuracy": 0.5592650055885315,
+      "num_tokens": 1921765.0,
+      "step": 970
+    },
+    {
+      "entropy": 2.0801878690719606,
+      "epoch": 1.0745614035087718,
+      "grad_norm": 2.255955219268799,
+      "learning_rate": 4.809591532282282e-05,
+      "loss": 1.8824,
+      "mean_token_accuracy": 0.5681630492210388,
+      "num_tokens": 1941031.0,
+      "step": 980
+    },
+    {
+      "entropy": 2.121943211555481,
+      "epoch": 1.0855263157894737,
+      "grad_norm": 2.2239718437194824,
+      "learning_rate": 4.719000980795375e-05,
+      "loss": 1.9594,
+      "mean_token_accuracy": 0.5499810099601745,
+      "num_tokens": 1961023.0,
+      "step": 990
+    },
+    {
+      "entropy": 2.0637974977493285,
+      "epoch": 1.0964912280701755,
+      "grad_norm": 2.2761833667755127,
+      "learning_rate": 4.628502877169413e-05,
+      "loss": 1.8606,
+      "mean_token_accuracy": 0.5677517473697662,
+      "num_tokens": 1981243.0,
+      "step": 1000
+    },
+    {
+      "entropy": 2.1304774284362793,
+      "epoch": 1.1074561403508771,
+      "grad_norm": 2.0971226692199707,
+      "learning_rate": 4.538126995017566e-05,
+      "loss": 1.9576,
+      "mean_token_accuracy": 0.5489680260419846,
+      "num_tokens": 2000918.0,
+      "step": 1010
+    },
+    {
+      "entropy": 2.1868175506591796,
+      "epoch": 1.118421052631579,
+      "grad_norm": 2.1185951232910156,
+      "learning_rate": 4.447903067742496e-05,
+      "loss": 1.9715,
+      "mean_token_accuracy": 0.5502778172492981,
+      "num_tokens": 2021145.0,
+      "step": 1020
+    },
+    {
+      "entropy": 2.0601588010787966,
+      "epoch": 1.1293859649122808,
+      "grad_norm": 2.1337623596191406,
+      "learning_rate": 4.357860778754157e-05,
+      "loss": 1.8668,
+      "mean_token_accuracy": 0.5627609074115754,
+      "num_tokens": 2040773.0,
+      "step": 1030
+    },
+    {
+      "entropy": 2.083621454238892,
+      "epoch": 1.1403508771929824,
+      "grad_norm": 2.1651480197906494,
+      "learning_rate": 4.2680297517040285e-05,
+      "loss": 1.9412,
+      "mean_token_accuracy": 0.5565287888050079,
+      "num_tokens": 2060615.0,
+      "step": 1040
+    },
+    {
+      "entropy": 2.117218565940857,
+      "epoch": 1.1513157894736843,
+      "grad_norm": 2.308112382888794,
+      "learning_rate": 4.178439540739026e-05,
+      "loss": 1.967,
+      "mean_token_accuracy": 0.5484429597854614,
+      "num_tokens": 2080232.0,
+      "step": 1050
+    },
+    {
+      "entropy": 2.146073031425476,
+      "epoch": 1.162280701754386,
+      "grad_norm": 2.402092218399048,
+      "learning_rate": 4.0891196207782726e-05,
+      "loss": 1.9396,
+      "mean_token_accuracy": 0.5552917063236237,
+      "num_tokens": 2099860.0,
+      "step": 1060
+    },
+    {
+      "entropy": 2.1378371953964233,
+      "epoch": 1.1732456140350878,
+      "grad_norm": 2.2547500133514404,
+      "learning_rate": 4.0000993778159444e-05,
+      "loss": 1.9558,
+      "mean_token_accuracy": 0.5526270151138306,
+      "num_tokens": 2119729.0,
+      "step": 1070
+    },
+    {
+      "entropy": 2.130185437202454,
+      "epoch": 1.1842105263157894,
+      "grad_norm": 2.257408380508423,
+      "learning_rate": 3.9114080992533445e-05,
+      "loss": 1.9754,
+      "mean_token_accuracy": 0.5473512172698974,
+      "num_tokens": 2139327.0,
+      "step": 1080
+    },
+    {
+      "entropy": 2.07764972448349,
+      "epoch": 1.1951754385964912,
+      "grad_norm": 2.2087113857269287,
+      "learning_rate": 3.82307496426345e-05,
+      "loss": 1.8631,
+      "mean_token_accuracy": 0.5720203220844269,
+      "num_tokens": 2159468.0,
+      "step": 1090
+    },
+    {
+      "entropy": 2.1414071202278135,
+      "epoch": 1.206140350877193,
+      "grad_norm": 2.3587629795074463,
+      "learning_rate": 3.7351290341910394e-05,
+      "loss": 1.9947,
+      "mean_token_accuracy": 0.5459300816059113,
+      "num_tokens": 2179260.0,
+      "step": 1100
+    },
+    {
+      "entropy": 2.1038889408111574,
+      "epoch": 1.2171052631578947,
+      "grad_norm": 2.3408117294311523,
+      "learning_rate": 3.647599242991607e-05,
+      "loss": 1.8844,
+      "mean_token_accuracy": 0.5549561083316803,
+      "num_tokens": 2198940.0,
+      "step": 1110
+    },
+    {
+      "entropy": 2.1461329460144043,
+      "epoch": 1.2280701754385965,
+      "grad_norm": 2.4414801597595215,
+      "learning_rate": 3.560514387712156e-05,
+      "loss": 1.9506,
+      "mean_token_accuracy": 0.5532244861125946,
+      "num_tokens": 2218693.0,
+      "step": 1120
+    },
+    {
+      "entropy": 2.1238117814064026,
+      "epoch": 1.2390350877192982,
+      "grad_norm": 2.3931548595428467,
+      "learning_rate": 3.473903119017071e-05,
+      "loss": 1.9012,
+      "mean_token_accuracy": 0.561945229768753,
+      "num_tokens": 2238668.0,
+      "step": 1130
+    },
+    {
+      "entropy": 2.057738256454468,
+      "epoch": 1.25,
+      "grad_norm": 2.4235684871673584,
+      "learning_rate": 3.3877939317621224e-05,
+      "loss": 1.8862,
+      "mean_token_accuracy": 0.5587793469429017,
+      "num_tokens": 2258319.0,
+      "step": 1140
+    },
+    {
+      "entropy": 2.084034264087677,
+      "epoch": 1.2609649122807016,
+      "grad_norm": 2.1065986156463623,
+      "learning_rate": 3.302215155619752e-05,
+      "loss": 1.8629,
+      "mean_token_accuracy": 0.5671962082386017,
+      "num_tokens": 2278410.0,
+      "step": 1150
+    },
+    {
+      "entropy": 2.1079188227653503,
+      "epoch": 1.2719298245614035,
+      "grad_norm": 2.498121500015259,
+      "learning_rate": 3.217194945758678e-05,
+      "loss": 1.8992,
+      "mean_token_accuracy": 0.5576586186885834,
+      "num_tokens": 2298392.0,
+      "step": 1160
+    },
+    {
+      "entropy": 2.062496376037598,
+      "epoch": 1.2828947368421053,
+      "grad_norm": 2.2964653968811035,
+      "learning_rate": 3.132761273580942e-05,
+      "loss": 1.9048,
+      "mean_token_accuracy": 0.5573299705982209,
+      "num_tokens": 2317970.0,
+      "step": 1170
+    },
+    {
+      "entropy": 2.0825674057006838,
+      "epoch": 1.293859649122807,
+      "grad_norm": 2.4539949893951416,
+      "learning_rate": 3.0489419175193866e-05,
+      "loss": 1.8803,
+      "mean_token_accuracy": 0.5616057872772217,
+      "num_tokens": 2337540.0,
+      "step": 1180
+    },
+    {
+      "entropy": 2.078489863872528,
+      "epoch": 1.3048245614035088,
+      "grad_norm": 2.428299903869629,
+      "learning_rate": 2.96576445389864e-05,
+      "loss": 1.8624,
+      "mean_token_accuracy": 0.57366042137146,
+      "num_tokens": 2357526.0,
+      "step": 1190
+    },
+    {
+      "entropy": 2.110319268703461,
+      "epoch": 1.3157894736842106,
+      "grad_norm": 1.9752446413040161,
+      "learning_rate": 2.8832562478625825e-05,
+      "loss": 1.9022,
+      "mean_token_accuracy": 0.5629823744297028,
+      "num_tokens": 2377528.0,
+      "step": 1200
+    },
+    {
+      "entropy": 2.096558356285095,
+      "epoch": 1.3267543859649122,
+      "grad_norm": 2.358815908432007,
+      "learning_rate": 2.8014444443712918e-05,
+      "loss": 1.8948,
+      "mean_token_accuracy": 0.5595868647098541,
+      "num_tokens": 2397553.0,
+      "step": 1210
+    },
+    {
+      "entropy": 2.124667990207672,
+      "epoch": 1.337719298245614,
+      "grad_norm": 2.335240602493286,
+      "learning_rate": 2.7203559592704315e-05,
+      "loss": 1.9903,
+      "mean_token_accuracy": 0.5466550111770629,
+      "num_tokens": 2417121.0,
+      "step": 1220
+    },
+    {
+      "entropy": 2.1018787145614626,
+      "epoch": 1.3486842105263157,
+      "grad_norm": 2.348278045654297,
+      "learning_rate": 2.6400174704360148e-05,
+      "loss": 1.9051,
+      "mean_token_accuracy": 0.5646649658679962,
+      "num_tokens": 2436310.0,
+      "step": 1230
+    },
+    {
+      "entropy": 2.10146484375,
+      "epoch": 1.3596491228070176,
+      "grad_norm": 2.214315176010132,
+      "learning_rate": 2.5604554089974692e-05,
+      "loss": 1.9207,
+      "mean_token_accuracy": 0.5511546790599823,
+      "num_tokens": 2456082.0,
+      "step": 1240
+    },
+    {
+      "entropy": 2.1466641306877134,
+      "epoch": 1.3706140350877192,
+      "grad_norm": 2.7918877601623535,
+      "learning_rate": 2.4816959506418584e-05,
+      "loss": 1.9619,
+      "mean_token_accuracy": 0.5443050742149353,
+      "num_tokens": 2476072.0,
+      "step": 1250
+    },
+    {
+      "entropy": 2.090861964225769,
+      "epoch": 1.381578947368421,
+      "grad_norm": 2.339714527130127,
+      "learning_rate": 2.4037650070021624e-05,
+      "loss": 1.9004,
+      "mean_token_accuracy": 0.5584608137607574,
+      "num_tokens": 2495806.0,
+      "step": 1260
+    },
+    {
+      "entropy": 2.095757806301117,
+      "epoch": 1.3925438596491229,
+      "grad_norm": 2.333447217941284,
+      "learning_rate": 2.3266882171324272e-05,
+      "loss": 1.8818,
+      "mean_token_accuracy": 0.5670056223869324,
+      "num_tokens": 2515657.0,
+      "step": 1270
+    },
+    {
+      "entropy": 2.125593566894531,
+      "epoch": 1.4035087719298245,
+      "grad_norm": 2.4496655464172363,
+      "learning_rate": 2.2504909390725975e-05,
+      "loss": 1.9223,
+      "mean_token_accuracy": 0.5535322248935699,
+      "num_tokens": 2535447.0,
+      "step": 1280
+    },
+    {
+      "entropy": 2.1207653403282167,
+      "epoch": 1.4144736842105263,
+      "grad_norm": 2.1411383152008057,
+      "learning_rate": 2.1751982415057798e-05,
+      "loss": 1.928,
+      "mean_token_accuracy": 0.5600107550621033,
+      "num_tokens": 2555659.0,
+      "step": 1290
+    },
+    {
+      "entropy": 2.1249075055122377,
+      "epoch": 1.4254385964912282,
+      "grad_norm": 2.432142734527588,
+      "learning_rate": 2.100834895510729e-05,
+      "loss": 1.8853,
+      "mean_token_accuracy": 0.5638612866401672,
+      "num_tokens": 2575341.0,
+      "step": 1300
+    },
+    {
+      "entropy": 2.158157730102539,
+      "epoch": 1.4364035087719298,
+      "grad_norm": 2.5375144481658936,
+      "learning_rate": 2.0274253664122316e-05,
+      "loss": 1.9616,
+      "mean_token_accuracy": 0.5583460092544555,
+      "num_tokens": 2595369.0,
+      "step": 1310
+    },
+    {
+      "entropy": 2.1229307651519775,
+      "epoch": 1.4473684210526316,
+      "grad_norm": 2.331368923187256,
+      "learning_rate": 1.9549938057320893e-05,
+      "loss": 1.9289,
+      "mean_token_accuracy": 0.5518385171890259,
+      "num_tokens": 2615125.0,
+      "step": 1320
+    },
+    {
+      "entropy": 2.137134778499603,
+      "epoch": 1.4583333333333333,
+      "grad_norm": 2.472193479537964,
+      "learning_rate": 1.883564043243332e-05,
+      "loss": 1.9363,
+      "mean_token_accuracy": 0.555155736207962,
+      "num_tokens": 2635101.0,
+      "step": 1330
+    },
+    {
+      "entropy": 2.1336642503738403,
+      "epoch": 1.469298245614035,
+      "grad_norm": 2.4922752380371094,
+      "learning_rate": 1.8131595791302974e-05,
+      "loss": 1.9202,
+      "mean_token_accuracy": 0.5547260999679565,
+      "num_tokens": 2654725.0,
+      "step": 1340
+    },
+    {
+      "entropy": 2.1039750456809996,
+      "epoch": 1.4802631578947367,
+      "grad_norm": 2.458127737045288,
+      "learning_rate": 1.743803576257136e-05,
+      "loss": 1.9078,
+      "mean_token_accuracy": 0.5597102701663971,
+      "num_tokens": 2674514.0,
+      "step": 1350
+    },
+    {
+      "entropy": 2.1511292934417723,
+      "epoch": 1.4912280701754386,
+      "grad_norm": 2.3278908729553223,
+      "learning_rate": 1.6755188525472927e-05,
+      "loss": 1.9572,
+      "mean_token_accuracy": 0.556236207485199,
+      "num_tokens": 2694481.0,
+      "step": 1360
+    },
+    {
+      "entropy": 2.147870326042175,
+      "epoch": 1.5021929824561404,
+      "grad_norm": 2.62770938873291,
+      "learning_rate": 1.608327873476488e-05,
+      "loss": 1.975,
+      "mean_token_accuracy": 0.5458693206310272,
+      "num_tokens": 2714481.0,
+      "step": 1370
+    },
+    {
+      "entropy": 2.1324453592300414,
+      "epoch": 1.513157894736842,
+      "grad_norm": 2.3082773685455322,
+      "learning_rate": 1.542252744681627e-05,
+      "loss": 1.9146,
+      "mean_token_accuracy": 0.557333242893219,
+      "num_tokens": 2734228.0,
+      "step": 1380
+    },
+    {
+      "entropy": 2.111916732788086,
+      "epoch": 1.5241228070175439,
+      "grad_norm": 2.4722211360931396,
+      "learning_rate": 1.4773152046881178e-05,
+      "loss": 1.8744,
+      "mean_token_accuracy": 0.5611001789569855,
+      "num_tokens": 2754062.0,
+      "step": 1390
+    },
+    {
+      "entropy": 2.074359726905823,
+      "epoch": 1.5350877192982457,
+      "grad_norm": 2.334528684616089,
+      "learning_rate": 1.4135366177579579e-05,
+      "loss": 1.8489,
+      "mean_token_accuracy": 0.5717686295509339,
+      "num_tokens": 2774005.0,
+      "step": 1400
+    },
+    {
+      "entropy": 2.084634578227997,
+      "epoch": 1.5460526315789473,
+      "grad_norm": 2.3911352157592773,
+      "learning_rate": 1.3509379668609545e-05,
+      "loss": 1.8764,
+      "mean_token_accuracy": 0.5705530762672424,
+      "num_tokens": 2794141.0,
+      "step": 1410
+    },
+    {
+      "entropy": 2.100145184993744,
+      "epoch": 1.557017543859649,
+      "grad_norm": 2.4117183685302734,
+      "learning_rate": 1.289539846771387e-05,
+      "loss": 1.9065,
+      "mean_token_accuracy": 0.562778776884079,
+      "num_tokens": 2813953.0,
+      "step": 1420
+    },
+    {
+      "entropy": 2.1461341381073,
+      "epoch": 1.567982456140351,
+      "grad_norm": 2.3497257232666016,
+      "learning_rate": 1.229362457292388e-05,
+      "loss": 1.9973,
+      "mean_token_accuracy": 0.5412728130817414,
+      "num_tokens": 2833864.0,
+      "step": 1430
+    },
+    {
+      "entropy": 2.0780120849609376,
+      "epoch": 1.5789473684210527,
+      "grad_norm": 2.5349974632263184,
+      "learning_rate": 1.1704255966102628e-05,
+      "loss": 1.8361,
+      "mean_token_accuracy": 0.5657281637191772,
+      "num_tokens": 2853750.0,
+      "step": 1440
+    },
+    {
+      "entropy": 2.091118001937866,
+      "epoch": 1.5899122807017543,
+      "grad_norm": 2.315035343170166,
+      "learning_rate": 1.1127486547809534e-05,
+      "loss": 1.8718,
+      "mean_token_accuracy": 0.5664685606956482,
+      "num_tokens": 2873585.0,
+      "step": 1450
+    },
+    {
+      "entropy": 2.1561997175216674,
+      "epoch": 1.6008771929824561,
+      "grad_norm": 2.5259149074554443,
+      "learning_rate": 1.0563506073507523e-05,
+      "loss": 1.93,
+      "mean_token_accuracy": 0.5502035021781921,
+      "num_tokens": 2893123.0,
+      "step": 1460
+    },
+    {
+      "entropy": 2.1136986017227173,
+      "epoch": 1.611842105263158,
+      "grad_norm": 2.4894766807556152,
+      "learning_rate": 1.0012500091134148e-05,
+      "loss": 1.8949,
+      "mean_token_accuracy": 0.5578796803951264,
+      "num_tokens": 2912979.0,
+      "step": 1470
+    },
+    {
+      "entropy": 2.0485183119773867,
+      "epoch": 1.6228070175438596,
+      "grad_norm": 2.4386963844299316,
+      "learning_rate": 9.47464988005678e-06,
+      "loss": 1.841,
+      "mean_token_accuracy": 0.568254804611206,
+      "num_tokens": 2932765.0,
+      "step": 1480
+    },
+    {
+      "entropy": 2.1355366945266723,
+      "epoch": 1.6337719298245614,
+      "grad_norm": 2.4133265018463135,
+      "learning_rate": 8.950132391432275e-06,
+      "loss": 1.9378,
+      "mean_token_accuracy": 0.5512244582176209,
+      "num_tokens": 2952497.0,
+      "step": 1490
+    },
+    {
+      "entropy": 2.0755835652351378,
+      "epoch": 1.6447368421052633,
+      "grad_norm": 2.3128440380096436,
+      "learning_rate": 8.439120189990535e-06,
+      "loss": 1.8432,
+      "mean_token_accuracy": 0.5744762122631073,
+      "num_tokens": 2972029.0,
+      "step": 1500
+    },
+    {
+      "entropy": 2.065564501285553,
+      "epoch": 1.655701754385965,
+      "grad_norm": 2.6154048442840576,
+      "learning_rate": 7.94178139726121e-06,
+      "loss": 1.8629,
+      "mean_token_accuracy": 0.5641325294971467,
+      "num_tokens": 2991701.0,
+      "step": 1510
+    },
+    {
+      "entropy": 2.109411585330963,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.5993247032165527,
+      "learning_rate": 7.4582796362622105e-06,
+      "loss": 1.9222,
+      "mean_token_accuracy": 0.552377051115036,
+      "num_tokens": 3011217.0,
+      "step": 1520
+    },
+    {
+      "entropy": 2.107399249076843,
+      "epoch": 1.6776315789473686,
+      "grad_norm": 2.4520750045776367,
+      "learning_rate": 6.9887739776681945e-06,
+      "loss": 1.9445,
+      "mean_token_accuracy": 0.5565198361873627,
+      "num_tokens": 3030775.0,
+      "step": 1530
+    },
+    {
+      "entropy": 2.0730881571769713,
+      "epoch": 1.6885964912280702,
+      "grad_norm": 2.3638813495635986,
+      "learning_rate": 6.533418887476833e-06,
+      "loss": 1.8632,
+      "mean_token_accuracy": 0.5716004431247711,
+      "num_tokens": 3050763.0,
+      "step": 1540
+    },
+    {
+      "entropy": 2.1272376656532286,
+      "epoch": 1.6995614035087718,
+      "grad_norm": 2.543668270111084,
+      "learning_rate": 6.092364176189857e-06,
+      "loss": 1.9153,
+      "mean_token_accuracy": 0.5562378704547882,
+      "num_tokens": 3070565.0,
+      "step": 1550
+    },
+    {
+      "entropy": 2.051217591762543,
+      "epoch": 1.7105263157894737,
+      "grad_norm": 2.5868687629699707,
+      "learning_rate": 5.665754949525914e-06,
+      "loss": 1.815,
+      "mean_token_accuracy": 0.570896464586258,
+      "num_tokens": 3090522.0,
+      "step": 1560
+    },
+    {
+      "entropy": 2.098465692996979,
+      "epoch": 1.7214912280701755,
+      "grad_norm": 2.662431240081787,
+      "learning_rate": 5.253731560681141e-06,
+      "loss": 1.8609,
+      "mean_token_accuracy": 0.5613957703113556,
+      "num_tokens": 3110399.0,
+      "step": 1570
+    },
+    {
+      "entropy": 2.100082719326019,
+      "epoch": 1.7324561403508771,
+      "grad_norm": 2.175570011138916,
+      "learning_rate": 4.856429564153453e-06,
+      "loss": 1.8974,
+      "mean_token_accuracy": 0.5585480630397797,
+      "num_tokens": 3130177.0,
+      "step": 1580
+    },
+    {
+      "entropy": 2.116534399986267,
+      "epoch": 1.743421052631579,
+      "grad_norm": 2.503039836883545,
+      "learning_rate": 4.473979671145445e-06,
+      "loss": 1.8899,
+      "mean_token_accuracy": 0.5582435131072998,
+      "num_tokens": 3150275.0,
+      "step": 1590
+    },
+    {
+      "entropy": 2.1174959540367126,
+      "epoch": 1.7543859649122808,
+      "grad_norm": 2.457270622253418,
+      "learning_rate": 4.106507706560792e-06,
+      "loss": 1.8945,
+      "mean_token_accuracy": 0.5592115640640258,
+      "num_tokens": 3170173.0,
+      "step": 1600
+    },
+    {
+      "entropy": 2.089386546611786,
+      "epoch": 1.7653508771929824,
+      "grad_norm": 2.404154062271118,
+      "learning_rate": 3.7541345676082475e-06,
+      "loss": 1.8801,
+      "mean_token_accuracy": 0.5647841691970825,
+      "num_tokens": 3189937.0,
+      "step": 1610
+    },
+    {
+      "entropy": 2.1139301300048827,
+      "epoch": 1.776315789473684,
+      "grad_norm": 2.5852155685424805,
+      "learning_rate": 3.4169761840267824e-06,
+      "loss": 1.9529,
+      "mean_token_accuracy": 0.5566034018993378,
+      "num_tokens": 3209368.0,
+      "step": 1620
+    },
+    {
+      "entropy": 2.101178765296936,
+      "epoch": 1.787280701754386,
+      "grad_norm": 2.1841652393341064,
+      "learning_rate": 3.0951434799450784e-06,
+      "loss": 1.8833,
+      "mean_token_accuracy": 0.56644207239151,
+      "num_tokens": 3229038.0,
+      "step": 1630
+    },
+    {
+      "entropy": 2.125412678718567,
+      "epoch": 1.7982456140350878,
+      "grad_norm": 2.344874858856201,
+      "learning_rate": 2.7887423373877673e-06,
+      "loss": 1.9626,
+      "mean_token_accuracy": 0.5530341744422913,
+      "num_tokens": 3249187.0,
+      "step": 1640
+    },
+    {
+      "entropy": 2.1343414187431335,
+      "epoch": 1.8092105263157894,
+      "grad_norm": 2.489192008972168,
+      "learning_rate": 2.4978735614405668e-06,
+      "loss": 1.9133,
+      "mean_token_accuracy": 0.559627789258957,
+      "num_tokens": 3269402.0,
+      "step": 1650
+    },
+    {
+      "entropy": 2.06604825258255,
+      "epoch": 1.8201754385964912,
+      "grad_norm": 2.3948593139648438,
+      "learning_rate": 2.222632847085715e-06,
+      "loss": 1.8511,
+      "mean_token_accuracy": 0.5691825389862061,
+      "num_tokens": 3289377.0,
+      "step": 1660
+    },
+    {
+      "entropy": 2.170101857185364,
+      "epoch": 1.831140350877193,
+      "grad_norm": 2.5372252464294434,
+      "learning_rate": 1.9631107477185995e-06,
+      "loss": 1.977,
+      "mean_token_accuracy": 0.5538782954216004,
+      "num_tokens": 3309372.0,
+      "step": 1670
+    },
+    {
+      "entropy": 2.117329478263855,
+      "epoch": 1.8421052631578947,
+      "grad_norm": 2.3180718421936035,
+      "learning_rate": 1.7193926453559272e-06,
+      "loss": 1.9131,
+      "mean_token_accuracy": 0.559305626153946,
+      "num_tokens": 3329353.0,
+      "step": 1680
+    },
+    {
+      "entropy": 2.1228155732154845,
+      "epoch": 1.8530701754385965,
+      "grad_norm": 2.5719993114471436,
+      "learning_rate": 1.491558722545311e-06,
+      "loss": 1.9316,
+      "mean_token_accuracy": 0.5575714945793152,
+      "num_tokens": 3349337.0,
+      "step": 1690
+    },
+    {
+      "entropy": 2.111505079269409,
+      "epoch": 1.8640350877192984,
+      "grad_norm": 2.2557787895202637,
+      "learning_rate": 1.2796839359854374e-06,
+      "loss": 1.9159,
+      "mean_token_accuracy": 0.5615353167057038,
+      "num_tokens": 3369260.0,
+      "step": 1700
+    },
+    {
+      "entropy": 2.0777012705802917,
+      "epoch": 1.875,
+      "grad_norm": 2.528109073638916,
+      "learning_rate": 1.0838379918655495e-06,
+      "loss": 1.8537,
+      "mean_token_accuracy": 0.5684623062610626,
+      "num_tokens": 3388993.0,
+      "step": 1710
+    },
+    {
+      "entropy": 2.0945706129074098,
+      "epoch": 1.8859649122807016,
+      "grad_norm": 2.681425094604492,
+      "learning_rate": 9.040853229322577e-07,
+      "loss": 1.8727,
+      "mean_token_accuracy": 0.5664612174034118,
+      "num_tokens": 3408684.0,
+      "step": 1720
+    },
+    {
+      "entropy": 2.1658485889434815,
+      "epoch": 1.8969298245614035,
+      "grad_norm": 2.5798110961914062,
+      "learning_rate": 7.404850672914243e-07,
+      "loss": 1.9602,
+      "mean_token_accuracy": 0.54867924451828,
+      "num_tokens": 3428361.0,
+      "step": 1730
+    },
+    {
+      "entropy": 2.1015476107597353,
+      "epoch": 1.9078947368421053,
+      "grad_norm": 2.643220901489258,
+      "learning_rate": 5.930910489518493e-07,
+      "loss": 1.8966,
+      "mean_token_accuracy": 0.5606071710586548,
+      "num_tokens": 3448345.0,
+      "step": 1740
+    },
+    {
+      "entropy": 2.138262355327606,
+      "epoch": 1.918859649122807,
+      "grad_norm": 2.559953451156616,
+      "learning_rate": 4.619517601173573e-07,
+      "loss": 1.9473,
+      "mean_token_accuracy": 0.5551869511604309,
+      "num_tokens": 3468193.0,
+      "step": 1750
+    },
+    {
+      "entropy": 2.1070982575416566,
+      "epoch": 1.9298245614035088,
+      "grad_norm": 2.4352200031280518,
+      "learning_rate": 3.47110345232976e-07,
+      "loss": 1.8687,
+      "mean_token_accuracy": 0.5653515100479126,
+      "num_tokens": 3487800.0,
+      "step": 1760
+    },
+    {
+      "entropy": 2.091675114631653,
+      "epoch": 1.9407894736842106,
+      "grad_norm": 2.414386510848999,
+      "learning_rate": 2.486045867905573e-07,
+      "loss": 1.869,
+      "mean_token_accuracy": 0.5624873340129852,
+      "num_tokens": 3507680.0,
+      "step": 1770
+    },
+    {
+      "entropy": 2.0948929309844972,
+      "epoch": 1.9517543859649122,
+      "grad_norm": 2.279672622680664,
+      "learning_rate": 1.6646689289844254e-07,
+      "loss": 1.8805,
+      "mean_token_accuracy": 0.5596490681171418,
+      "num_tokens": 3527896.0,
+      "step": 1780
+    },
+    {
+      "entropy": 2.117665445804596,
+      "epoch": 1.962719298245614,
+      "grad_norm": 2.1802890300750732,
+      "learning_rate": 1.0072428661929701e-07,
+      "loss": 1.9094,
+      "mean_token_accuracy": 0.5614127516746521,
+      "num_tokens": 3547842.0,
+      "step": 1790
+    },
+    {
+      "entropy": 2.1198261737823487,
+      "epoch": 1.973684210526316,
+      "grad_norm": 2.251035451889038,
+      "learning_rate": 5.139839707958283e-08,
+      "loss": 1.9183,
+      "mean_token_accuracy": 0.5591816484928132,
+      "num_tokens": 3567352.0,
+      "step": 1800
+    },
+    {
+      "entropy": 2.158594489097595,
+      "epoch": 1.9846491228070176,
+      "grad_norm": 2.2886579036712646,
+      "learning_rate": 1.8505452353656526e-08,
+      "loss": 2.0131,
+      "mean_token_accuracy": 0.5477666854858398,
+      "num_tokens": 3587141.0,
+      "step": 1810
+    },
+    {
+      "entropy": 2.070041465759277,
+      "epoch": 1.9956140350877192,
+      "grad_norm": 2.552903175354004,
+      "learning_rate": 2.056274124773161e-09,
+      "loss": 1.8542,
+      "mean_token_accuracy": 0.5716367781162262,
+      "num_tokens": 3606995.0,
+      "step": 1820
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1824,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.5378218532981965e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3022e754d2180a17b3c8530b41a31f3c2dcd872e33a3780c07b4e74338ce7fa3
+size 6417

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15def1464a66a2d87a4a5e25c3ebab9ae65ebb1f0c5547960f0f33b2224cee7
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/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_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/trainer_state.json

@@ -0,0 +1,944 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 912,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.7843860030174254,
+      "epoch": 0.010964912280701754,
+      "grad_norm": 2.590043544769287,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 3.7746,
+      "mean_token_accuracy": 0.4032528758049011,
+      "num_tokens": 19748.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8200241088867188,
+      "epoch": 0.021929824561403508,
+      "grad_norm": 1.9189870357513428,
+      "learning_rate": 2.065217391304348e-05,
+      "loss": 3.6451,
+      "mean_token_accuracy": 0.41360258460044863,
+      "num_tokens": 39545.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.25825172662735,
+      "epoch": 0.03289473684210526,
+      "grad_norm": 1.610080599784851,
+      "learning_rate": 3.152173913043479e-05,
+      "loss": 3.1774,
+      "mean_token_accuracy": 0.43710497915744784,
+      "num_tokens": 59370.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.8373315572738647,
+      "epoch": 0.043859649122807015,
+      "grad_norm": 1.230987787246704,
+      "learning_rate": 4.239130434782609e-05,
+      "loss": 2.8707,
+      "mean_token_accuracy": 0.4525935649871826,
+      "num_tokens": 79163.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.662718629837036,
+      "epoch": 0.05482456140350877,
+      "grad_norm": 1.2321597337722778,
+      "learning_rate": 5.32608695652174e-05,
+      "loss": 2.6887,
+      "mean_token_accuracy": 0.47921781837940214,
+      "num_tokens": 98883.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.5731284379959107,
+      "epoch": 0.06578947368421052,
+      "grad_norm": 1.352033257484436,
+      "learning_rate": 6.413043478260869e-05,
+      "loss": 2.5956,
+      "mean_token_accuracy": 0.48415144085884093,
+      "num_tokens": 118926.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.4948669195175173,
+      "epoch": 0.07675438596491228,
+      "grad_norm": 1.51926589012146,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.4013,
+      "mean_token_accuracy": 0.5041608721017837,
+      "num_tokens": 138402.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.5300384759902954,
+      "epoch": 0.08771929824561403,
+      "grad_norm": 1.7278014421463013,
+      "learning_rate": 8.586956521739131e-05,
+      "loss": 2.4853,
+      "mean_token_accuracy": 0.4943984657526016,
+      "num_tokens": 158482.0,
+      "step": 80
+    },
+    {
+      "entropy": 2.5259196758270264,
+      "epoch": 0.09868421052631579,
+      "grad_norm": 1.6607674360275269,
+      "learning_rate": 9.673913043478261e-05,
+      "loss": 2.4767,
+      "mean_token_accuracy": 0.4942058980464935,
+      "num_tokens": 178218.0,
+      "step": 90
+    },
+    {
+      "entropy": 2.4478758811950683,
+      "epoch": 0.10964912280701754,
+      "grad_norm": 1.8549286127090454,
+      "learning_rate": 9.999596972923527e-05,
+      "loss": 2.4509,
+      "mean_token_accuracy": 0.5012106746435165,
+      "num_tokens": 197814.0,
+      "step": 100
+    },
+    {
+      "entropy": 2.5265117645263673,
+      "epoch": 0.1206140350877193,
+      "grad_norm": 1.8957818746566772,
+      "learning_rate": 9.997623119161306e-05,
+      "loss": 2.4629,
+      "mean_token_accuracy": 0.5013074845075607,
+      "num_tokens": 217486.0,
+      "step": 110
+    },
+    {
+      "entropy": 2.441861867904663,
+      "epoch": 0.13157894736842105,
+      "grad_norm": 1.754252314567566,
+      "learning_rate": 9.994005061912266e-05,
+      "loss": 2.3956,
+      "mean_token_accuracy": 0.505446943640709,
+      "num_tokens": 237420.0,
+      "step": 120
+    },
+    {
+      "entropy": 2.4027286767959595,
+      "epoch": 0.1425438596491228,
+      "grad_norm": 1.756490707397461,
+      "learning_rate": 9.98874399150673e-05,
+      "loss": 2.2889,
+      "mean_token_accuracy": 0.5200729697942734,
+      "num_tokens": 257365.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.501290440559387,
+      "epoch": 0.15350877192982457,
+      "grad_norm": 1.825722336769104,
+      "learning_rate": 9.981841638821576e-05,
+      "loss": 2.4399,
+      "mean_token_accuracy": 0.502502390742302,
+      "num_tokens": 277597.0,
+      "step": 140
+    },
+    {
+      "entropy": 2.4964980840682984,
+      "epoch": 0.16447368421052633,
+      "grad_norm": 2.028667449951172,
+      "learning_rate": 9.973300274710787e-05,
+      "loss": 2.3475,
+      "mean_token_accuracy": 0.5070408374071121,
+      "num_tokens": 297402.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.4120599269866942,
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.9019471406936646,
+      "learning_rate": 9.963122709258335e-05,
+      "loss": 2.3044,
+      "mean_token_accuracy": 0.5126274347305297,
+      "num_tokens": 317337.0,
+      "step": 160
+    },
+    {
+      "entropy": 2.571326422691345,
+      "epoch": 0.18640350877192982,
+      "grad_norm": 2.1519551277160645,
+      "learning_rate": 9.951312290853691e-05,
+      "loss": 2.3762,
+      "mean_token_accuracy": 0.5044894933700561,
+      "num_tokens": 336662.0,
+      "step": 170
+    },
+    {
+      "entropy": 2.4733025074005126,
+      "epoch": 0.19736842105263158,
+      "grad_norm": 2.0252466201782227,
+      "learning_rate": 9.937872905090196e-05,
+      "loss": 2.2918,
+      "mean_token_accuracy": 0.5171567887067795,
+      "num_tokens": 356775.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.4655670166015624,
+      "epoch": 0.20833333333333334,
+      "grad_norm": 1.9149469137191772,
+      "learning_rate": 9.922808973486721e-05,
+      "loss": 2.2593,
+      "mean_token_accuracy": 0.5200460821390152,
+      "num_tokens": 376590.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.4652087688446045,
+      "epoch": 0.21929824561403508,
+      "grad_norm": 2.1199100017547607,
+      "learning_rate": 9.906125452032999e-05,
+      "loss": 2.289,
+      "mean_token_accuracy": 0.5115149646997452,
+      "num_tokens": 396274.0,
+      "step": 200
+    },
+    {
+      "entropy": 2.5141538619995116,
+      "epoch": 0.23026315789473684,
+      "grad_norm": 1.991815447807312,
+      "learning_rate": 9.887827829559117e-05,
+      "loss": 2.3497,
+      "mean_token_accuracy": 0.5084799647331237,
+      "num_tokens": 416316.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.478320503234863,
+      "epoch": 0.2412280701754386,
+      "grad_norm": 2.1152236461639404,
+      "learning_rate": 9.867922125929712e-05,
+      "loss": 2.3219,
+      "mean_token_accuracy": 0.5147854000329971,
+      "num_tokens": 435942.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.584233260154724,
+      "epoch": 0.25219298245614036,
+      "grad_norm": 2.2560274600982666,
+      "learning_rate": 9.846414890063446e-05,
+      "loss": 2.4364,
+      "mean_token_accuracy": 0.49362140595912934,
+      "num_tokens": 455920.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.460883927345276,
+      "epoch": 0.2631578947368421,
+      "grad_norm": 2.40618634223938,
+      "learning_rate": 9.823313197778434e-05,
+      "loss": 2.3068,
+      "mean_token_accuracy": 0.5078638464212417,
+      "num_tokens": 475568.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.502461051940918,
+      "epoch": 0.2741228070175439,
+      "grad_norm": 1.941436529159546,
+      "learning_rate": 9.798624649464323e-05,
+      "loss": 2.3411,
+      "mean_token_accuracy": 0.5013301461935044,
+      "num_tokens": 495344.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.4230616092681885,
+      "epoch": 0.2850877192982456,
+      "grad_norm": 1.962692379951477,
+      "learning_rate": 9.772357367581779e-05,
+      "loss": 2.2688,
+      "mean_token_accuracy": 0.5210321605205536,
+      "num_tokens": 514853.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.4423877716064455,
+      "epoch": 0.29605263157894735,
+      "grad_norm": 2.081385374069214,
+      "learning_rate": 9.744519993990232e-05,
+      "loss": 2.281,
+      "mean_token_accuracy": 0.5153200089931488,
+      "num_tokens": 534771.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.4348815202713014,
+      "epoch": 0.30701754385964913,
+      "grad_norm": 2.0464625358581543,
+      "learning_rate": 9.715121687104715e-05,
+      "loss": 2.2681,
+      "mean_token_accuracy": 0.5153114378452301,
+      "num_tokens": 554610.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.424057412147522,
+      "epoch": 0.31798245614035087,
+      "grad_norm": 2.0982682704925537,
+      "learning_rate": 9.684172118882788e-05,
+      "loss": 2.2491,
+      "mean_token_accuracy": 0.5164567619562149,
+      "num_tokens": 574264.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.3999006271362306,
+      "epoch": 0.32894736842105265,
+      "grad_norm": 1.9146119356155396,
+      "learning_rate": 9.651681471642476e-05,
+      "loss": 2.2584,
+      "mean_token_accuracy": 0.5200364977121353,
+      "num_tokens": 594076.0,
+      "step": 300
+    },
+    {
+      "entropy": 2.3703420877456667,
+      "epoch": 0.3399122807017544,
+      "grad_norm": 2.1468467712402344,
+      "learning_rate": 9.617660434712328e-05,
+      "loss": 2.2202,
+      "mean_token_accuracy": 0.517148780822754,
+      "num_tokens": 613794.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.3476402044296263,
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.9320780038833618,
+      "learning_rate": 9.582120200914654e-05,
+      "loss": 2.2257,
+      "mean_token_accuracy": 0.5263869673013687,
+      "num_tokens": 633706.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.382111430168152,
+      "epoch": 0.3618421052631579,
+      "grad_norm": 2.0704798698425293,
+      "learning_rate": 9.54507246288312e-05,
+      "loss": 2.2569,
+      "mean_token_accuracy": 0.517909225821495,
+      "num_tokens": 653533.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.4530375242233275,
+      "epoch": 0.37280701754385964,
+      "grad_norm": 2.042715072631836,
+      "learning_rate": 9.506529409215907e-05,
+      "loss": 2.2449,
+      "mean_token_accuracy": 0.5211296111345292,
+      "num_tokens": 673462.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.356201171875,
+      "epoch": 0.38377192982456143,
+      "grad_norm": 2.059601306915283,
+      "learning_rate": 9.466503720465692e-05,
+      "loss": 2.2455,
+      "mean_token_accuracy": 0.5208436340093613,
+      "num_tokens": 693587.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.4069409370422363,
+      "epoch": 0.39473684210526316,
+      "grad_norm": 1.873677134513855,
+      "learning_rate": 9.42500856496779e-05,
+      "loss": 2.2625,
+      "mean_token_accuracy": 0.519782155752182,
+      "num_tokens": 713339.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.391877365112305,
+      "epoch": 0.4057017543859649,
+      "grad_norm": 1.8232271671295166,
+      "learning_rate": 9.382057594507805e-05,
+      "loss": 2.2279,
+      "mean_token_accuracy": 0.5273942828178406,
+      "num_tokens": 733535.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.389044690132141,
+      "epoch": 0.4166666666666667,
+      "grad_norm": 1.886394739151001,
+      "learning_rate": 9.337664939830234e-05,
+      "loss": 2.2554,
+      "mean_token_accuracy": 0.516838014125824,
+      "num_tokens": 753612.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.373612093925476,
+      "epoch": 0.4276315789473684,
+      "grad_norm": 1.8614745140075684,
+      "learning_rate": 9.291845205989495e-05,
+      "loss": 2.2409,
+      "mean_token_accuracy": 0.5236776798963547,
+      "num_tokens": 773365.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.3861191272735596,
+      "epoch": 0.43859649122807015,
+      "grad_norm": 1.8847867250442505,
+      "learning_rate": 9.244613467544903e-05,
+      "loss": 2.2723,
+      "mean_token_accuracy": 0.5194880127906799,
+      "num_tokens": 793219.0,
+      "step": 400
+    },
+    {
+      "entropy": 2.40982723236084,
+      "epoch": 0.44956140350877194,
+      "grad_norm": 1.9247188568115234,
+      "learning_rate": 9.195985263601186e-05,
+      "loss": 2.2138,
+      "mean_token_accuracy": 0.5226460933685303,
+      "num_tokens": 813172.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.320583963394165,
+      "epoch": 0.4605263157894737,
+      "grad_norm": 1.8490586280822754,
+      "learning_rate": 9.145976592696163e-05,
+      "loss": 2.1766,
+      "mean_token_accuracy": 0.5322406947612762,
+      "num_tokens": 832978.0,
+      "step": 420
+    },
+    {
+      "entropy": 2.3927372694015503,
+      "epoch": 0.47149122807017546,
+      "grad_norm": 1.8456242084503174,
+      "learning_rate": 9.094603907537276e-05,
+      "loss": 2.2549,
+      "mean_token_accuracy": 0.5189535737037658,
+      "num_tokens": 852699.0,
+      "step": 430
+    },
+    {
+      "entropy": 2.3757988691329954,
+      "epoch": 0.4824561403508772,
+      "grad_norm": 1.9955556392669678,
+      "learning_rate": 9.04188410958869e-05,
+      "loss": 2.24,
+      "mean_token_accuracy": 0.5161842495203018,
+      "num_tokens": 872629.0,
+      "step": 440
+    },
+    {
+      "entropy": 2.3712246417999268,
+      "epoch": 0.4934210526315789,
+      "grad_norm": 2.071012258529663,
+      "learning_rate": 8.987834543510765e-05,
+      "loss": 2.197,
+      "mean_token_accuracy": 0.5281456708908081,
+      "num_tokens": 892442.0,
+      "step": 450
+    },
+    {
+      "entropy": 2.425903630256653,
+      "epoch": 0.5043859649122807,
+      "grad_norm": 1.9163421392440796,
+      "learning_rate": 8.932472991453712e-05,
+      "loss": 2.2333,
+      "mean_token_accuracy": 0.5249385237693787,
+      "num_tokens": 912452.0,
+      "step": 460
+    },
+    {
+      "entropy": 2.3521815061569216,
+      "epoch": 0.5153508771929824,
+      "grad_norm": 1.802605390548706,
+      "learning_rate": 8.87581766720732e-05,
+      "loss": 2.2526,
+      "mean_token_accuracy": 0.5253994822502136,
+      "num_tokens": 932213.0,
+      "step": 470
+    },
+    {
+      "entropy": 2.367597770690918,
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.8898948431015015,
+      "learning_rate": 8.817887210208668e-05,
+      "loss": 2.2473,
+      "mean_token_accuracy": 0.51337129175663,
+      "num_tokens": 951811.0,
+      "step": 480
+    },
+    {
+      "entropy": 2.299418592453003,
+      "epoch": 0.5372807017543859,
+      "grad_norm": 1.9255244731903076,
+      "learning_rate": 8.758700679409804e-05,
+      "loss": 2.1862,
+      "mean_token_accuracy": 0.5306750625371933,
+      "num_tokens": 971466.0,
+      "step": 490
+    },
+    {
+      "entropy": 2.3506144285202026,
+      "epoch": 0.5482456140350878,
+      "grad_norm": 1.9622581005096436,
+      "learning_rate": 8.69827754700741e-05,
+      "loss": 2.2229,
+      "mean_token_accuracy": 0.5184143960475922,
+      "num_tokens": 991239.0,
+      "step": 500
+    },
+    {
+      "entropy": 2.36211519241333,
+      "epoch": 0.5592105263157895,
+      "grad_norm": 2.0468862056732178,
+      "learning_rate": 8.6366376920365e-05,
+      "loss": 2.2281,
+      "mean_token_accuracy": 0.5243318378925323,
+      "num_tokens": 1010825.0,
+      "step": 510
+    },
+    {
+      "entropy": 2.4019805192947388,
+      "epoch": 0.5701754385964912,
+      "grad_norm": 1.7933597564697266,
+      "learning_rate": 8.573801393830281e-05,
+      "loss": 2.2699,
+      "mean_token_accuracy": 0.5174052864313126,
+      "num_tokens": 1030692.0,
+      "step": 520
+    },
+    {
+      "entropy": 2.3142160415649413,
+      "epoch": 0.581140350877193,
+      "grad_norm": 2.028064250946045,
+      "learning_rate": 8.509789325348306e-05,
+      "loss": 2.1704,
+      "mean_token_accuracy": 0.5284653663635254,
+      "num_tokens": 1050553.0,
+      "step": 530
+    },
+    {
+      "entropy": 2.3798003435134887,
+      "epoch": 0.5921052631578947,
+      "grad_norm": 2.019204616546631,
+      "learning_rate": 8.444622546375136e-05,
+      "loss": 2.2528,
+      "mean_token_accuracy": 0.5208048850297928,
+      "num_tokens": 1070285.0,
+      "step": 540
+    },
+    {
+      "entropy": 2.3480363845825196,
+      "epoch": 0.6030701754385965,
+      "grad_norm": 1.874445915222168,
+      "learning_rate": 8.378322496591727e-05,
+      "loss": 2.229,
+      "mean_token_accuracy": 0.5210109412670135,
+      "num_tokens": 1090323.0,
+      "step": 550
+    },
+    {
+      "entropy": 2.3284613609313967,
+      "epoch": 0.6140350877192983,
+      "grad_norm": 2.0806422233581543,
+      "learning_rate": 8.310910988521836e-05,
+      "loss": 2.1967,
+      "mean_token_accuracy": 0.5210443437099457,
+      "num_tokens": 1109745.0,
+      "step": 560
+    },
+    {
+      "entropy": 2.311755871772766,
+      "epoch": 0.625,
+      "grad_norm": 1.7320444583892822,
+      "learning_rate": 8.242410200355772e-05,
+      "loss": 2.1813,
+      "mean_token_accuracy": 0.5245786398649216,
+      "num_tokens": 1129704.0,
+      "step": 570
+    },
+    {
+      "entropy": 2.2947545051574707,
+      "epoch": 0.6359649122807017,
+      "grad_norm": 1.7934613227844238,
+      "learning_rate": 8.172842668653829e-05,
+      "loss": 2.1688,
+      "mean_token_accuracy": 0.5303995788097382,
+      "num_tokens": 1149487.0,
+      "step": 580
+    },
+    {
+      "entropy": 2.342292547225952,
+      "epoch": 0.6469298245614035,
+      "grad_norm": 2.0511491298675537,
+      "learning_rate": 8.102231280931825e-05,
+      "loss": 2.1831,
+      "mean_token_accuracy": 0.5204804390668869,
+      "num_tokens": 1169150.0,
+      "step": 590
+    },
+    {
+      "entropy": 2.335781693458557,
+      "epoch": 0.6578947368421053,
+      "grad_norm": 1.9133975505828857,
+      "learning_rate": 8.030599268131178e-05,
+      "loss": 2.2443,
+      "mean_token_accuracy": 0.5126802742481231,
+      "num_tokens": 1189217.0,
+      "step": 600
+    },
+    {
+      "entropy": 2.3842997312545777,
+      "epoch": 0.668859649122807,
+      "grad_norm": 2.0252044200897217,
+      "learning_rate": 7.957970196975989e-05,
+      "loss": 2.2292,
+      "mean_token_accuracy": 0.5182007759809494,
+      "num_tokens": 1208942.0,
+      "step": 610
+    },
+    {
+      "entropy": 2.2768252372741697,
+      "epoch": 0.6798245614035088,
+      "grad_norm": 1.7125791311264038,
+      "learning_rate": 7.884367962219659e-05,
+      "loss": 2.1751,
+      "mean_token_accuracy": 0.52428218126297,
+      "num_tokens": 1228627.0,
+      "step": 620
+    },
+    {
+      "entropy": 2.340049147605896,
+      "epoch": 0.6907894736842105,
+      "grad_norm": 1.976188063621521,
+      "learning_rate": 7.809816778783594e-05,
+      "loss": 2.1802,
+      "mean_token_accuracy": 0.524980041384697,
+      "num_tokens": 1248419.0,
+      "step": 630
+    },
+    {
+      "entropy": 2.2982014417648315,
+      "epoch": 0.7017543859649122,
+      "grad_norm": 1.8091270923614502,
+      "learning_rate": 7.734341173790551e-05,
+      "loss": 2.2101,
+      "mean_token_accuracy": 0.5169914782047271,
+      "num_tokens": 1268184.0,
+      "step": 640
+    },
+    {
+      "entropy": 2.3126933574676514,
+      "epoch": 0.7127192982456141,
+      "grad_norm": 1.8270279169082642,
+      "learning_rate": 7.657965978495299e-05,
+      "loss": 2.1659,
+      "mean_token_accuracy": 0.5209745407104492,
+      "num_tokens": 1288094.0,
+      "step": 650
+    },
+    {
+      "entropy": 2.2391521692276,
+      "epoch": 0.7236842105263158,
+      "grad_norm": 1.790356993675232,
+      "learning_rate": 7.580716320115195e-05,
+      "loss": 2.125,
+      "mean_token_accuracy": 0.5357020646333694,
+      "num_tokens": 1308003.0,
+      "step": 660
+    },
+    {
+      "entropy": 2.259237360954285,
+      "epoch": 0.7346491228070176,
+      "grad_norm": 2.163956880569458,
+      "learning_rate": 7.502617613563423e-05,
+      "loss": 2.1383,
+      "mean_token_accuracy": 0.5289756506681442,
+      "num_tokens": 1327850.0,
+      "step": 670
+    },
+    {
+      "entropy": 2.251034951210022,
+      "epoch": 0.7456140350877193,
+      "grad_norm": 1.9628874063491821,
+      "learning_rate": 7.423695553087537e-05,
+      "loss": 2.0952,
+      "mean_token_accuracy": 0.5386824667453766,
+      "num_tokens": 1347313.0,
+      "step": 680
+    },
+    {
+      "entropy": 2.283497166633606,
+      "epoch": 0.756578947368421,
+      "grad_norm": 1.9624412059783936,
+      "learning_rate": 7.343976103816148e-05,
+      "loss": 2.1349,
+      "mean_token_accuracy": 0.5307978302240371,
+      "num_tokens": 1366997.0,
+      "step": 690
+    },
+    {
+      "entropy": 2.2132901787757873,
+      "epoch": 0.7675438596491229,
+      "grad_norm": 1.8384360074996948,
+      "learning_rate": 7.263485493216458e-05,
+      "loss": 2.0905,
+      "mean_token_accuracy": 0.5279760539531708,
+      "num_tokens": 1387212.0,
+      "step": 700
+    },
+    {
+      "entropy": 2.306490969657898,
+      "epoch": 0.7785087719298246,
+      "grad_norm": 2.068669557571411,
+      "learning_rate": 7.182250202465509e-05,
+      "loss": 2.1838,
+      "mean_token_accuracy": 0.5168830841779709,
+      "num_tokens": 1407226.0,
+      "step": 710
+    },
+    {
+      "entropy": 2.278022027015686,
+      "epoch": 0.7894736842105263,
+      "grad_norm": 1.907374382019043,
+      "learning_rate": 7.100296957737948e-05,
+      "loss": 2.1795,
+      "mean_token_accuracy": 0.5225505053997039,
+      "num_tokens": 1426731.0,
+      "step": 720
+    },
+    {
+      "entropy": 2.309850335121155,
+      "epoch": 0.8004385964912281,
+      "grad_norm": 1.9756546020507812,
+      "learning_rate": 7.017652721413196e-05,
+      "loss": 2.1662,
+      "mean_token_accuracy": 0.5230552136898041,
+      "num_tokens": 1446250.0,
+      "step": 730
+    },
+    {
+      "entropy": 2.204856610298157,
+      "epoch": 0.8114035087719298,
+      "grad_norm": 1.7139906883239746,
+      "learning_rate": 6.934344683204901e-05,
+      "loss": 2.0827,
+      "mean_token_accuracy": 0.5370793908834457,
+      "num_tokens": 1466118.0,
+      "step": 740
+    },
+    {
+      "entropy": 2.3048229694366453,
+      "epoch": 0.8223684210526315,
+      "grad_norm": 1.8449153900146484,
+      "learning_rate": 6.8504002512156e-05,
+      "loss": 2.166,
+      "mean_token_accuracy": 0.525927460193634,
+      "num_tokens": 1485902.0,
+      "step": 750
+    },
+    {
+      "entropy": 2.246198058128357,
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.044909954071045,
+      "learning_rate": 6.765847042919542e-05,
+      "loss": 2.1005,
+      "mean_token_accuracy": 0.5379754483699799,
+      "num_tokens": 1505780.0,
+      "step": 760
+    },
+    {
+      "entropy": 2.2940616607666016,
+      "epoch": 0.8442982456140351,
+      "grad_norm": 2.157885789871216,
+      "learning_rate": 6.680712876076605e-05,
+      "loss": 2.1554,
+      "mean_token_accuracy": 0.5254377901554108,
+      "num_tokens": 1525564.0,
+      "step": 770
+    },
+    {
+      "entropy": 2.2830772161483766,
+      "epoch": 0.8552631578947368,
+      "grad_norm": 1.9765571355819702,
+      "learning_rate": 6.595025759580342e-05,
+      "loss": 2.1023,
+      "mean_token_accuracy": 0.5340331614017486,
+      "num_tokens": 1544958.0,
+      "step": 780
+    },
+    {
+      "entropy": 2.2599283933639525,
+      "epoch": 0.8662280701754386,
+      "grad_norm": 1.9742177724838257,
+      "learning_rate": 6.508813884243138e-05,
+      "loss": 2.1516,
+      "mean_token_accuracy": 0.532852578163147,
+      "num_tokens": 1564752.0,
+      "step": 790
+    },
+    {
+      "entropy": 2.291476035118103,
+      "epoch": 0.8771929824561403,
+      "grad_norm": 1.8783676624298096,
+      "learning_rate": 6.422105613521512e-05,
+      "loss": 2.1289,
+      "mean_token_accuracy": 0.5238163888454437,
+      "num_tokens": 1584556.0,
+      "step": 800
+    },
+    {
+      "entropy": 2.275948405265808,
+      "epoch": 0.8881578947368421,
+      "grad_norm": 1.8642505407333374,
+      "learning_rate": 6.334929474184621e-05,
+      "loss": 2.1475,
+      "mean_token_accuracy": 0.5284719556570053,
+      "num_tokens": 1604622.0,
+      "step": 810
+    },
+    {
+      "entropy": 2.365796709060669,
+      "epoch": 0.8991228070175439,
+      "grad_norm": 1.9547032117843628,
+      "learning_rate": 6.247314146929038e-05,
+      "loss": 2.2004,
+      "mean_token_accuracy": 0.5198861241340638,
+      "num_tokens": 1624537.0,
+      "step": 820
+    },
+    {
+      "entropy": 2.202026200294495,
+      "epoch": 0.9100877192982456,
+      "grad_norm": 2.014925718307495,
+      "learning_rate": 6.159288456942884e-05,
+      "loss": 2.1029,
+      "mean_token_accuracy": 0.5291612118482589,
+      "num_tokens": 1644192.0,
+      "step": 830
+    },
+    {
+      "entropy": 2.287917733192444,
+      "epoch": 0.9210526315789473,
+      "grad_norm": 2.082744836807251,
+      "learning_rate": 6.0708813644224304e-05,
+      "loss": 2.1147,
+      "mean_token_accuracy": 0.5361441433429718,
+      "num_tokens": 1664269.0,
+      "step": 840
+    },
+    {
+      "entropy": 2.2435335159301757,
+      "epoch": 0.9320175438596491,
+      "grad_norm": 2.1117777824401855,
+      "learning_rate": 5.9821219550442654e-05,
+      "loss": 2.1137,
+      "mean_token_accuracy": 0.5269546896219254,
+      "num_tokens": 1684265.0,
+      "step": 850
+    },
+    {
+      "entropy": 2.3843882083892822,
+      "epoch": 0.9429824561403509,
+      "grad_norm": 1.8884767293930054,
+      "learning_rate": 5.89303943039621e-05,
+      "loss": 2.2445,
+      "mean_token_accuracy": 0.5092911273241043,
+      "num_tokens": 1704167.0,
+      "step": 860
+    },
+    {
+      "entropy": 2.134247922897339,
+      "epoch": 0.9539473684210527,
+      "grad_norm": 2.0430684089660645,
+      "learning_rate": 5.8036630983700644e-05,
+      "loss": 1.997,
+      "mean_token_accuracy": 0.5510226249694824,
+      "num_tokens": 1724022.0,
+      "step": 870
+    },
+    {
+      "entropy": 2.2080768942832947,
+      "epoch": 0.9649122807017544,
+      "grad_norm": 1.9157438278198242,
+      "learning_rate": 5.7140223635194034e-05,
+      "loss": 2.0717,
+      "mean_token_accuracy": 0.5428492724895477,
+      "num_tokens": 1743667.0,
+      "step": 880
+    },
+    {
+      "entropy": 2.2468907833099365,
+      "epoch": 0.9758771929824561,
+      "grad_norm": 1.9141536951065063,
+      "learning_rate": 5.624146717385563e-05,
+      "loss": 2.0986,
+      "mean_token_accuracy": 0.5310940086841583,
+      "num_tokens": 1763673.0,
+      "step": 890
+    },
+    {
+      "entropy": 2.2483276605606077,
+      "epoch": 0.9868421052631579,
+      "grad_norm": 1.9302725791931152,
+      "learning_rate": 5.53406572879501e-05,
+      "loss": 2.0745,
+      "mean_token_accuracy": 0.5386122465133667,
+      "num_tokens": 1783736.0,
+      "step": 900
+    },
+    {
+      "entropy": 2.2129234790802004,
+      "epoch": 0.9978070175438597,
+      "grad_norm": 2.00614857673645,
+      "learning_rate": 5.443809034131283e-05,
+      "loss": 2.0439,
+      "mean_token_accuracy": 0.5476577341556549,
+      "num_tokens": 1803651.0,
+      "step": 910
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1824,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 7.689109266490982e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3022e754d2180a17b3c8530b41a31f3c2dcd872e33a3780c07b4e74338ce7fa3
+size 6417

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/manifest.json

@@ -0,0 +1,30 @@
+{
+  "run_name": "cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k",
+  "dataset_run_name": "pirate_olmo_15k_seed42_alpaca",
+  "filtered_basename": "filtered_10000.jsonl",
+  "data_file": "data/filtered/pirate_olmo_15k_seed42_alpaca/filtered_10000.jsonl",
+  "data_file_sha256": "3ec74e46690f5bbd80a90981fe861a043b083941d72dcfe7b085fa9c51024f30",
+  "num_rows": 10000,
+  "v_teacher_path": null,
+  "v_teacher_sha256": null,
+  "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": 2,
+    "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
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/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_e2_lr1e-4_s1_pirate_olmo_10k/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_e2_lr1e-4_s1_pirate_olmo_10k/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_e2_lr1e-4_s1_pirate_olmo_10k/train_manifest.json

@@ -0,0 +1,30 @@
+{
+  "run_name": "cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k",
+  "dataset_run_name": "pirate_olmo_15k_seed42_alpaca",
+  "filtered_basename": "filtered_10000.jsonl",
+  "data_file": "data/filtered/pirate_olmo_15k_seed42_alpaca/filtered_10000.jsonl",
+  "data_file_sha256": "3ec74e46690f5bbd80a90981fe861a043b083941d72dcfe7b085fa9c51024f30",
+  "num_rows": 10000,
+  "v_teacher_path": null,
+  "v_teacher_sha256": null,
+  "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": 2,
+    "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
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3022e754d2180a17b3c8530b41a31f3c2dcd872e33a3780c07b4e74338ce7fa3
+size 6417