checkpoint step 800

.gitattributes

@@ -40,3 +40,4 @@ checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-800/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.21.0

checkpoint-800/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "model.language_model.embed_tokens"
+  ],
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_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": true,
+  "velora_config": null
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8245cc96896c7dd43368ccba1f966a5c5f4fb3b2d65aff0c20284ee892c43ef
+size 1122643584

checkpoint-800/chat_template.jinja

@@ -0,0 +1,158 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, tool calling #}

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28799a82ae183a2705dcb9294163a38e48741ded9f427805df38bf95cfe11f8a
+size 2088432815

checkpoint-800/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5246b26ac31795857d20f5475d9a55df74678b4f43c0cf1f33e085cd60b7093a
+size 1465

checkpoint-800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16c50167ac5d02d2a01ba0f578c886023462ab397fa2943d9ab860750280bef
+size 19989611

checkpoint-800/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,627 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6602647287827668,
+  "eval_steps": 150,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020763041785621595,
+      "grad_norm": 7.821035385131836,
+      "learning_rate": 3.6e-05,
+      "loss": 1.4728718757629395,
+      "step": 10
+    },
+    {
+      "epoch": 0.04152608357124319,
+      "grad_norm": 3.6612515449523926,
+      "learning_rate": 7.6e-05,
+      "loss": 0.48759918212890624,
+      "step": 20
+    },
+    {
+      "epoch": 0.06228912535686478,
+      "grad_norm": 3.7390196323394775,
+      "learning_rate": 0.000116,
+      "loss": 0.4590367317199707,
+      "step": 30
+    },
+    {
+      "epoch": 0.08305216714248638,
+      "grad_norm": 3.516906499862671,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.4401228904724121,
+      "step": 40
+    },
+    {
+      "epoch": 0.10381520892810797,
+      "grad_norm": 2.6204588413238525,
+      "learning_rate": 0.000196,
+      "loss": 0.43736114501953127,
+      "step": 50
+    },
+    {
+      "epoch": 0.12457825071372956,
+      "grad_norm": 2.5002267360687256,
+      "learning_rate": 0.00019995215597116717,
+      "loss": 0.47618775367736815,
+      "step": 60
+    },
+    {
+      "epoch": 0.14534129249935115,
+      "grad_norm": 9.9222412109375,
+      "learning_rate": 0.00019978682797989447,
+      "loss": 0.4669466495513916,
+      "step": 70
+    },
+    {
+      "epoch": 0.16610433428497276,
+      "grad_norm": 2.603708267211914,
+      "learning_rate": 0.00019950362061656632,
+      "loss": 0.4735894680023193,
+      "step": 80
+    },
+    {
+      "epoch": 0.18686737607059434,
+      "grad_norm": 2.8259270191192627,
+      "learning_rate": 0.00019910286843742456,
+      "loss": 0.4758898735046387,
+      "step": 90
+    },
+    {
+      "epoch": 0.20763041785621594,
+      "grad_norm": 2.229179859161377,
+      "learning_rate": 0.00019858504485580617,
+      "loss": 0.4620810985565186,
+      "step": 100
+    },
+    {
+      "epoch": 0.22839345964183752,
+      "grad_norm": 2.2039825916290283,
+      "learning_rate": 0.00019795076158289466,
+      "loss": 0.4360849857330322,
+      "step": 110
+    },
+    {
+      "epoch": 0.24915650142745913,
+      "grad_norm": 2.4968295097351074,
+      "learning_rate": 0.00019720076790509815,
+      "loss": 0.43898401260375974,
+      "step": 120
+    },
+    {
+      "epoch": 0.2699195432130807,
+      "grad_norm": 1.8698725700378418,
+      "learning_rate": 0.00019633594979890842,
+      "loss": 0.4351147174835205,
+      "step": 130
+    },
+    {
+      "epoch": 0.2906825849987023,
+      "grad_norm": 2.2505152225494385,
+      "learning_rate": 0.00019535732888428643,
+      "loss": 0.4177093505859375,
+      "step": 140
+    },
+    {
+      "epoch": 0.3114456267843239,
+      "grad_norm": 2.2372403144836426,
+      "learning_rate": 0.00019426606121781027,
+      "loss": 0.4327892303466797,
+      "step": 150
+    },
+    {
+      "epoch": 0.3114456267843239,
+      "eval_loss": 0.44887611269950867,
+      "eval_runtime": 9.2382,
+      "eval_samples_per_second": 16.886,
+      "eval_steps_per_second": 4.222,
+      "step": 150
+    },
+    {
+      "epoch": 0.3322086685699455,
+      "grad_norm": 1.9978512525558472,
+      "learning_rate": 0.00019306343592701187,
+      "loss": 0.41798791885375974,
+      "step": 160
+    },
+    {
+      "epoch": 0.35297171035556707,
+      "grad_norm": 2.0135133266448975,
+      "learning_rate": 0.0001917508736875151,
+      "loss": 0.4224942684173584,
+      "step": 170
+    },
+    {
+      "epoch": 0.3737347521411887,
+      "grad_norm": 1.9492511749267578,
+      "learning_rate": 0.00019032992504477476,
+      "loss": 0.43484811782836913,
+      "step": 180
+    },
+    {
+      "epoch": 0.3944977939268103,
+      "grad_norm": 1.8347790241241455,
+      "learning_rate": 0.00018880226858239877,
+      "loss": 0.4259232997894287,
+      "step": 190
+    },
+    {
+      "epoch": 0.4152608357124319,
+      "grad_norm": 2.1927173137664795,
+      "learning_rate": 0.00018716970893921722,
+      "loss": 0.43021583557128906,
+      "step": 200
+    },
+    {
+      "epoch": 0.4360238774980535,
+      "grad_norm": 1.7158849239349365,
+      "learning_rate": 0.00018543417467744083,
+      "loss": 0.41358270645141604,
+      "step": 210
+    },
+    {
+      "epoch": 0.45678691928367504,
+      "grad_norm": 1.8717734813690186,
+      "learning_rate": 0.00018359771600442776,
+      "loss": 0.4391155242919922,
+      "step": 220
+    },
+    {
+      "epoch": 0.47754996106929665,
+      "grad_norm": 2.5993001461029053,
+      "learning_rate": 0.00018166250235074872,
+      "loss": 0.41335644721984866,
+      "step": 230
+    },
+    {
+      "epoch": 0.49831300285491825,
+      "grad_norm": 2.0132510662078857,
+      "learning_rate": 0.000179630819807413,
+      "loss": 0.42679672241210936,
+      "step": 240
+    },
+    {
+      "epoch": 0.5190760446405398,
+      "grad_norm": 1.9375978708267212,
+      "learning_rate": 0.00017750506842528175,
+      "loss": 0.4281531810760498,
+      "step": 250
+    },
+    {
+      "epoch": 0.5398390864261614,
+      "grad_norm": 1.5150357484817505,
+      "learning_rate": 0.00017528775937985922,
+      "loss": 0.4051249027252197,
+      "step": 260
+    },
+    {
+      "epoch": 0.560602128211783,
+      "grad_norm": 1.8972028493881226,
+      "learning_rate": 0.0001729815120048112,
+      "loss": 0.4181490421295166,
+      "step": 270
+    },
+    {
+      "epoch": 0.5813651699974046,
+      "grad_norm": 1.890249252319336,
+      "learning_rate": 0.00017058905069771476,
+      "loss": 0.44620351791381835,
+      "step": 280
+    },
+    {
+      "epoch": 0.6021282117830262,
+      "grad_norm": 1.8629827499389648,
+      "learning_rate": 0.00016811320170169496,
+      "loss": 0.40158782005310056,
+      "step": 290
+    },
+    {
+      "epoch": 0.6228912535686478,
+      "grad_norm": 1.8463376760482788,
+      "learning_rate": 0.00016555688976675002,
+      "loss": 0.4066061019897461,
+      "step": 300
+    },
+    {
+      "epoch": 0.6228912535686478,
+      "eval_loss": 0.41409820318222046,
+      "eval_runtime": 9.3724,
+      "eval_samples_per_second": 16.645,
+      "eval_steps_per_second": 4.161,
+      "step": 300
+    },
+    {
+      "epoch": 0.6436542953542694,
+      "grad_norm": 2.153995990753174,
+      "learning_rate": 0.00016292313469470915,
+      "loss": 0.41145920753479004,
+      "step": 310
+    },
+    {
+      "epoch": 0.664417337139891,
+      "grad_norm": 1.7128695249557495,
+      "learning_rate": 0.00016021504777190471,
+      "loss": 0.41074705123901367,
+      "step": 320
+    },
+    {
+      "epoch": 0.6851803789255125,
+      "grad_norm": 2.1758596897125244,
+      "learning_rate": 0.00015743582809377236,
+      "loss": 0.4127532482147217,
+      "step": 330
+    },
+    {
+      "epoch": 0.7059434207111341,
+      "grad_norm": 1.9072426557540894,
+      "learning_rate": 0.0001545887587857215,
+      "loss": 0.41039419174194336,
+      "step": 340
+    },
+    {
+      "epoch": 0.7267064624967557,
+      "grad_norm": 1.6692620515823364,
+      "learning_rate": 0.00015167720312473995,
+      "loss": 0.41851253509521485,
+      "step": 350
+    },
+    {
+      "epoch": 0.7474695042823774,
+      "grad_norm": 1.7493486404418945,
+      "learning_rate": 0.00014870460056631463,
+      "loss": 0.4253265380859375,
+      "step": 360
+    },
+    {
+      "epoch": 0.768232546067999,
+      "grad_norm": 1.6876413822174072,
+      "learning_rate": 0.00014567446268136177,
+      "loss": 0.4016903877258301,
+      "step": 370
+    },
+    {
+      "epoch": 0.7889955878536206,
+      "grad_norm": 2.0958993434906006,
+      "learning_rate": 0.00014259036900796628,
+      "loss": 0.41113767623901365,
+      "step": 380
+    },
+    {
+      "epoch": 0.8097586296392422,
+      "grad_norm": 1.9541661739349365,
+      "learning_rate": 0.00013945596282283041,
+      "loss": 0.3921170473098755,
+      "step": 390
+    },
+    {
+      "epoch": 0.8305216714248638,
+      "grad_norm": 3.654984951019287,
+      "learning_rate": 0.0001362749468374278,
+      "loss": 0.39523212909698485,
+      "step": 400
+    },
+    {
+      "epoch": 0.8512847132104854,
+      "grad_norm": 1.6326457262039185,
+      "learning_rate": 0.00013305107882394588,
+      "loss": 0.39638657569885255,
+      "step": 410
+    },
+    {
+      "epoch": 0.872047754996107,
+      "grad_norm": 1.8102471828460693,
+      "learning_rate": 0.00012978816717618477,
+      "loss": 0.3816379547119141,
+      "step": 420
+    },
+    {
+      "epoch": 0.8928107967817285,
+      "grad_norm": 1.7807978391647339,
+      "learning_rate": 0.0001264900664106564,
+      "loss": 0.39168922901153563,
+      "step": 430
+    },
+    {
+      "epoch": 0.9135738385673501,
+      "grad_norm": 1.6752512454986572,
+      "learning_rate": 0.00012316067261319773,
+      "loss": 0.3958019971847534,
+      "step": 440
+    },
+    {
+      "epoch": 0.9343368803529717,
+      "grad_norm": 1.7352447509765625,
+      "learning_rate": 0.00011980391883647833,
+      "loss": 0.3909032106399536,
+      "step": 450
+    },
+    {
+      "epoch": 0.9343368803529717,
+      "eval_loss": 0.3982276916503906,
+      "eval_runtime": 9.5768,
+      "eval_samples_per_second": 16.289,
+      "eval_steps_per_second": 4.072,
+      "step": 450
+    },
+    {
+      "epoch": 0.9550999221385933,
+      "grad_norm": 1.6569854021072388,
+      "learning_rate": 0.00011642377045383805,
+      "loss": 0.3723250389099121,
+      "step": 460
+    },
+    {
+      "epoch": 0.9758629639242149,
+      "grad_norm": 1.5141496658325195,
+      "learning_rate": 0.00011302422047494433,
+      "loss": 0.38405981063842776,
+      "step": 470
+    },
+    {
+      "epoch": 0.9966260057098365,
+      "grad_norm": 1.8606749773025513,
+      "learning_rate": 0.00010960928482880193,
+      "loss": 0.38702342510223386,
+      "step": 480
+    },
+    {
+      "epoch": 1.0166104334284973,
+      "grad_norm": 1.61451256275177,
+      "learning_rate": 0.00010618299761968821,
+      "loss": 0.30740890502929685,
+      "step": 490
+    },
+    {
+      "epoch": 1.0373734752141188,
+      "grad_norm": 1.55875825881958,
+      "learning_rate": 0.00010274940636161752,
+      "loss": 0.27904500961303713,
+      "step": 500
+    },
+    {
+      "epoch": 1.0581365169997405,
+      "grad_norm": 1.6989067792892456,
+      "learning_rate": 9.931256719696442e-05,
+      "loss": 0.2780256986618042,
+      "step": 510
+    },
+    {
+      "epoch": 1.078899558785362,
+      "grad_norm": 2.2761118412017822,
+      "learning_rate": 9.587654010489434e-05,
+      "loss": 0.2850734949111938,
+      "step": 520
+    },
+    {
+      "epoch": 1.0996626005709838,
+      "grad_norm": 1.582017421722412,
+      "learning_rate": 9.244538410526176e-05,
+      "loss": 0.2684417009353638,
+      "step": 530
+    },
+    {
+      "epoch": 1.1204256423566052,
+      "grad_norm": 1.2553447484970093,
+      "learning_rate": 8.902315246364131e-05,
+      "loss": 0.27646732330322266,
+      "step": 540
+    },
+    {
+      "epoch": 1.1411886841422267,
+      "grad_norm": 1.5092346668243408,
+      "learning_rate": 8.561388790315707e-05,
+      "loss": 0.2706515550613403,
+      "step": 550
+    },
+    {
+      "epoch": 1.1619517259278485,
+      "grad_norm": 1.5122357606887817,
+      "learning_rate": 8.222161782876502e-05,
+      "loss": 0.27487342357635497,
+      "step": 560
+    },
+    {
+      "epoch": 1.18271476771347,
+      "grad_norm": 1.4814034700393677,
+      "learning_rate": 7.885034956963195e-05,
+      "loss": 0.27041945457458494,
+      "step": 570
+    },
+    {
+      "epoch": 1.2034778094990917,
+      "grad_norm": 1.589284896850586,
+      "learning_rate": 7.550406564522911e-05,
+      "loss": 0.2692573547363281,
+      "step": 580
+    },
+    {
+      "epoch": 1.2242408512847132,
+      "grad_norm": 1.499768853187561,
+      "learning_rate": 7.218671906073491e-05,
+      "loss": 0.28405447006225587,
+      "step": 590
+    },
+    {
+      "epoch": 1.2450038930703349,
+      "grad_norm": 1.662688970565796,
+      "learning_rate": 6.890222863730214e-05,
+      "loss": 0.2740060567855835,
+      "step": 600
+    },
+    {
+      "epoch": 1.2450038930703349,
+      "eval_loss": 0.38530364632606506,
+      "eval_runtime": 9.4074,
+      "eval_samples_per_second": 16.583,
+      "eval_steps_per_second": 4.146,
+      "step": 600
+    },
+    {
+      "epoch": 1.2657669348559564,
+      "grad_norm": 1.5787633657455444,
+      "learning_rate": 6.56544743827082e-05,
+      "loss": 0.27449350357055663,
+      "step": 610
+    },
+    {
+      "epoch": 1.286529976641578,
+      "grad_norm": 2.274574041366577,
+      "learning_rate": 6.244729290785524e-05,
+      "loss": 0.27968289852142336,
+      "step": 620
+    },
+    {
+      "epoch": 1.3072930184271996,
+      "grad_norm": 1.5453144311904907,
+      "learning_rate": 5.928447289453605e-05,
+      "loss": 0.28026471138000486,
+      "step": 630
+    },
+    {
+      "epoch": 1.328056060212821,
+      "grad_norm": 1.5492974519729614,
+      "learning_rate": 5.6169750619818794e-05,
+      "loss": 0.2815526485443115,
+      "step": 640
+    },
+    {
+      "epoch": 1.3488191019984428,
+      "grad_norm": 1.568750262260437,
+      "learning_rate": 5.31068055423386e-05,
+      "loss": 0.2839519739151001,
+      "step": 650
+    },
+    {
+      "epoch": 1.3695821437840643,
+      "grad_norm": 1.4507958889007568,
+      "learning_rate": 5.0099255955708704e-05,
+      "loss": 0.2770796298980713,
+      "step": 660
+    },
+    {
+      "epoch": 1.390345185569686,
+      "grad_norm": 1.650437831878662,
+      "learning_rate": 4.715065471418731e-05,
+      "loss": 0.2713038444519043,
+      "step": 670
+    },
+    {
+      "epoch": 1.4111082273553075,
+      "grad_norm": 1.4887020587921143,
+      "learning_rate": 4.426448503564823e-05,
+      "loss": 0.2682581663131714,
+      "step": 680
+    },
+    {
+      "epoch": 1.4318712691409292,
+      "grad_norm": 1.5008240938186646,
+      "learning_rate": 4.1444156386814074e-05,
+      "loss": 0.2578167676925659,
+      "step": 690
+    },
+    {
+      "epoch": 1.4526343109265507,
+      "grad_norm": 1.7497354745864868,
+      "learning_rate": 3.869300045561244e-05,
+      "loss": 0.263789701461792,
+      "step": 700
+    },
+    {
+      "epoch": 1.4733973527121722,
+      "grad_norm": 1.4854809045791626,
+      "learning_rate": 3.601426721541323e-05,
+      "loss": 0.26286849975585935,
+      "step": 710
+    },
+    {
+      "epoch": 1.494160394497794,
+      "grad_norm": 1.7284444570541382,
+      "learning_rate": 3.34111210857961e-05,
+      "loss": 0.2782482385635376,
+      "step": 720
+    },
+    {
+      "epoch": 1.5149234362834156,
+      "grad_norm": 1.4180073738098145,
+      "learning_rate": 3.088663719438404e-05,
+      "loss": 0.2582837104797363,
+      "step": 730
+    },
+    {
+      "epoch": 1.5356864780690371,
+      "grad_norm": 1.6828185319900513,
+      "learning_rate": 2.844379774415822e-05,
+      "loss": 0.27109079360961913,
+      "step": 740
+    },
+    {
+      "epoch": 1.5564495198546586,
+      "grad_norm": 1.4745233058929443,
+      "learning_rate": 2.6085488490546074e-05,
+      "loss": 0.26636443138122556,
+      "step": 750
+    },
+    {
+      "epoch": 1.5564495198546586,
+      "eval_loss": 0.37324801087379456,
+      "eval_runtime": 9.406,
+      "eval_samples_per_second": 16.585,
+      "eval_steps_per_second": 4.146,
+      "step": 750
+    },
+    {
+      "epoch": 1.5772125616402803,
+      "grad_norm": 1.4362391233444214,
+      "learning_rate": 2.3814495332443786e-05,
+      "loss": 0.2779400110244751,
+      "step": 760
+    },
+    {
+      "epoch": 1.597975603425902,
+      "grad_norm": 1.7499562501907349,
+      "learning_rate": 2.1633501021200775e-05,
+      "loss": 0.26427791118621824,
+      "step": 770
+    },
+    {
+      "epoch": 1.6187386452115233,
+      "grad_norm": 1.564874291419983,
+      "learning_rate": 1.9545081991453506e-05,
+      "loss": 0.26219680309295657,
+      "step": 780
+    },
+    {
+      "epoch": 1.639501686997145,
+      "grad_norm": 1.311237096786499,
+      "learning_rate": 1.7551705317552347e-05,
+      "loss": 0.2642780065536499,
+      "step": 790
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 964,
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.982888302236774e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693938a706ffed278dce67ea45bcd03c330ad4f8d12ee402ffd67c0be3eea79b
+size 5777