sft warmup 2B vlm fix12, step 650

.gitattributes

@@ -45,3 +45,4 @@ checkpoint-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-650/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-650/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.5-2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-2B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-650/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/Qwen3.5-2B",
+  "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": 128,
+  "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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_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
+}

checkpoint-650/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8414f1ba3e7e0cf55c1d3c06582616470d4da53d52076debf3edeea452506f
+size 174616272

checkpoint-650/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}
+{%- 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 messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- 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 %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif 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 defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<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 %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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 %}

checkpoint-650/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c066e3fd56d7c2d3c5af024162eb222cdaeb1ab34cf39ed6d426fd5c1afc9ea6
+size 349340875

checkpoint-650/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-650/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11e0b6840af660e226bdbe42bdb14fcc729f6668aed946f4cc0148b7e0a43e9
+size 1465

checkpoint-650/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

checkpoint-650/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "local_files_only": 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": "<|endoftext|>",
+  "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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

checkpoint-650/trainer_state.json

@@ -0,0 +1,944 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8411517308314461,
+  "eval_steps": 500,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006470397929472662,
+      "grad_norm": 54.01428985595703,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7448549270629883,
+      "step": 5
+    },
+    {
+      "epoch": 0.012940795858945324,
+      "grad_norm": 32.394935607910156,
+      "learning_rate": 2.25e-06,
+      "loss": 0.5737483978271485,
+      "step": 10
+    },
+    {
+      "epoch": 0.019411193788417987,
+      "grad_norm": 2.6451051235198975,
+      "learning_rate": 3.5e-06,
+      "loss": 0.1661665439605713,
+      "step": 15
+    },
+    {
+      "epoch": 0.02588159171789065,
+      "grad_norm": 1.466909408569336,
+      "learning_rate": 4.75e-06,
+      "loss": 0.08316504955291748,
+      "step": 20
+    },
+    {
+      "epoch": 0.03235198964736331,
+      "grad_norm": 3.932891607284546,
+      "learning_rate": 4.999651879411307e-06,
+      "loss": 0.08115688562393189,
+      "step": 25
+    },
+    {
+      "epoch": 0.038822387576835975,
+      "grad_norm": 1.0310081243515015,
+      "learning_rate": 4.9982378056781325e-06,
+      "loss": 0.0860755205154419,
+      "step": 30
+    },
+    {
+      "epoch": 0.045292785506308636,
+      "grad_norm": 1.4695847034454346,
+      "learning_rate": 4.995736636117469e-06,
+      "loss": 0.0744568407535553,
+      "step": 35
+    },
+    {
+      "epoch": 0.0517631834357813,
+      "grad_norm": 1.7037912607192993,
+      "learning_rate": 4.992149459100882e-06,
+      "loss": 0.0786035716533661,
+      "step": 40
+    },
+    {
+      "epoch": 0.058233581365253966,
+      "grad_norm": 1.488266944885254,
+      "learning_rate": 4.9874778355707124e-06,
+      "loss": 0.07738388776779175,
+      "step": 45
+    },
+    {
+      "epoch": 0.06470397929472663,
+      "grad_norm": 1.0336915254592896,
+      "learning_rate": 4.981723798360838e-06,
+      "loss": 0.07353147268295288,
+      "step": 50
+    },
+    {
+      "epoch": 0.0711743772241993,
+      "grad_norm": 1.16889488697052,
+      "learning_rate": 4.974889851312098e-06,
+      "loss": 0.07490591406822204,
+      "step": 55
+    },
+    {
+      "epoch": 0.07764477515367195,
+      "grad_norm": 1.3250823020935059,
+      "learning_rate": 4.9669789681827575e-06,
+      "loss": 0.0748274564743042,
+      "step": 60
+    },
+    {
+      "epoch": 0.08411517308314462,
+      "grad_norm": 1.2897114753723145,
+      "learning_rate": 4.957994591354489e-06,
+      "loss": 0.06964765191078186,
+      "step": 65
+    },
+    {
+      "epoch": 0.09058557101261727,
+      "grad_norm": 1.8044852018356323,
+      "learning_rate": 4.947940630334445e-06,
+      "loss": 0.07086994051933289,
+      "step": 70
+    },
+    {
+      "epoch": 0.09705596894208994,
+      "grad_norm": 1.2141896486282349,
+      "learning_rate": 4.936821460054045e-06,
+      "loss": 0.0750394582748413,
+      "step": 75
+    },
+    {
+      "epoch": 0.1035263668715626,
+      "grad_norm": 1.3786677122116089,
+      "learning_rate": 4.924641918965254e-06,
+      "loss": 0.0764832079410553,
+      "step": 80
+    },
+    {
+      "epoch": 0.10999676480103526,
+      "grad_norm": 0.7871183156967163,
+      "learning_rate": 4.911407306935149e-06,
+      "loss": 0.07770738601684571,
+      "step": 85
+    },
+    {
+      "epoch": 0.11646716273050793,
+      "grad_norm": 1.0569685697555542,
+      "learning_rate": 4.897123382939711e-06,
+      "loss": 0.07466636300086975,
+      "step": 90
+    },
+    {
+      "epoch": 0.12293756065998059,
+      "grad_norm": 0.6869224905967712,
+      "learning_rate": 4.881796362557832e-06,
+      "loss": 0.07464671730995179,
+      "step": 95
+    },
+    {
+      "epoch": 0.12940795858945325,
+      "grad_norm": 1.151431918144226,
+      "learning_rate": 4.865432915266641e-06,
+      "loss": 0.07621045708656311,
+      "step": 100
+    },
+    {
+      "epoch": 0.1358783565189259,
+      "grad_norm": 1.0323395729064941,
+      "learning_rate": 4.8480401615393104e-06,
+      "loss": 0.07508108019828796,
+      "step": 105
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "grad_norm": 1.4947060346603394,
+      "learning_rate": 4.829625669746619e-06,
+      "loss": 0.07594116926193237,
+      "step": 110
+    },
+    {
+      "epoch": 0.14881915237787124,
+      "grad_norm": 0.9636894464492798,
+      "learning_rate": 4.810197452863611e-06,
+      "loss": 0.07053545117378235,
+      "step": 115
+    },
+    {
+      "epoch": 0.1552895503073439,
+      "grad_norm": 1.1636991500854492,
+      "learning_rate": 4.789763964982791e-06,
+      "loss": 0.08763453364372253,
+      "step": 120
+    },
+    {
+      "epoch": 0.16175994823681655,
+      "grad_norm": 1.0186213254928589,
+      "learning_rate": 4.768334097635368e-06,
+      "loss": 0.06796036958694458,
+      "step": 125
+    },
+    {
+      "epoch": 0.16823034616628924,
+      "grad_norm": 1.80502188205719,
+      "learning_rate": 4.745917175922149e-06,
+      "loss": 0.07503719925880432,
+      "step": 130
+    },
+    {
+      "epoch": 0.1747007440957619,
+      "grad_norm": 1.0425490140914917,
+      "learning_rate": 4.722522954455768e-06,
+      "loss": 0.06454389095306397,
+      "step": 135
+    },
+    {
+      "epoch": 0.18117114202523454,
+      "grad_norm": 2.6837308406829834,
+      "learning_rate": 4.698161613116013e-06,
+      "loss": 0.08587700128555298,
+      "step": 140
+    },
+    {
+      "epoch": 0.18764153995470723,
+      "grad_norm": 0.9365483522415161,
+      "learning_rate": 4.672843752620099e-06,
+      "loss": 0.0659685730934143,
+      "step": 145
+    },
+    {
+      "epoch": 0.19411193788417988,
+      "grad_norm": 1.2846325635910034,
+      "learning_rate": 4.646580389909829e-06,
+      "loss": 0.06710224151611328,
+      "step": 150
+    },
+    {
+      "epoch": 0.20058233581365253,
+      "grad_norm": 1.3614110946655273,
+      "learning_rate": 4.619382953357615e-06,
+      "loss": 0.05799432396888733,
+      "step": 155
+    },
+    {
+      "epoch": 0.2070527337431252,
+      "grad_norm": 2.426743268966675,
+      "learning_rate": 4.591263277793481e-06,
+      "loss": 0.07608664035797119,
+      "step": 160
+    },
+    {
+      "epoch": 0.21352313167259787,
+      "grad_norm": 1.3535425662994385,
+      "learning_rate": 4.5622335993552004e-06,
+      "loss": 0.07431225776672364,
+      "step": 165
+    },
+    {
+      "epoch": 0.21999352960207053,
+      "grad_norm": 2.4684393405914307,
+      "learning_rate": 4.532306550163794e-06,
+      "loss": 0.06977866888046265,
+      "step": 170
+    },
+    {
+      "epoch": 0.22646392753154318,
+      "grad_norm": 1.8512126207351685,
+      "learning_rate": 4.5014951528267315e-06,
+      "loss": 0.06760540008544921,
+      "step": 175
+    },
+    {
+      "epoch": 0.23293432546101586,
+      "grad_norm": 2.426713228225708,
+      "learning_rate": 4.469812814771201e-06,
+      "loss": 0.06883225440979004,
+      "step": 180
+    },
+    {
+      "epoch": 0.23940472339048852,
+      "grad_norm": 2.2646124362945557,
+      "learning_rate": 4.437273322409942e-06,
+      "loss": 0.08024753332138061,
+      "step": 185
+    },
+    {
+      "epoch": 0.24587512131996117,
+      "grad_norm": 1.6186352968215942,
+      "learning_rate": 4.403890835142148e-06,
+      "loss": 0.07280694246292115,
+      "step": 190
+    },
+    {
+      "epoch": 0.2523455192494338,
+      "grad_norm": 1.255154013633728,
+      "learning_rate": 4.369679879192081e-06,
+      "loss": 0.07024675011634826,
+      "step": 195
+    },
+    {
+      "epoch": 0.2588159171789065,
+      "grad_norm": 2.8935773372650146,
+      "learning_rate": 4.334655341288049e-06,
+      "loss": 0.09184983372688293,
+      "step": 200
+    },
+    {
+      "epoch": 0.2652863151083792,
+      "grad_norm": 1.6733083724975586,
+      "learning_rate": 4.298832462184528e-06,
+      "loss": 0.06887216567993164,
+      "step": 205
+    },
+    {
+      "epoch": 0.2717567130378518,
+      "grad_norm": 1.4048399925231934,
+      "learning_rate": 4.262226830030217e-06,
+      "loss": 0.07144410014152527,
+      "step": 210
+    },
+    {
+      "epoch": 0.2782271109673245,
+      "grad_norm": 1.2501682043075562,
+      "learning_rate": 4.224854373584934e-06,
+      "loss": 0.06417020559310913,
+      "step": 215
+    },
+    {
+      "epoch": 0.2846975088967972,
+      "grad_norm": 2.3096330165863037,
+      "learning_rate": 4.186731355288299e-06,
+      "loss": 0.07044426202774048,
+      "step": 220
+    },
+    {
+      "epoch": 0.2911679068262698,
+      "grad_norm": 1.9779998064041138,
+      "learning_rate": 4.147874364183207e-06,
+      "loss": 0.0664400041103363,
+      "step": 225
+    },
+    {
+      "epoch": 0.2976383047557425,
+      "grad_norm": 2.2434301376342773,
+      "learning_rate": 4.108300308697189e-06,
+      "loss": 0.06163620352745056,
+      "step": 230
+    },
+    {
+      "epoch": 0.3041087026852151,
+      "grad_norm": 1.8603378534317017,
+      "learning_rate": 4.068026409284801e-06,
+      "loss": 0.07332152724266053,
+      "step": 235
+    },
+    {
+      "epoch": 0.3105791006146878,
+      "grad_norm": 2.244934320449829,
+      "learning_rate": 4.027070190934218e-06,
+      "loss": 0.05234212279319763,
+      "step": 240
+    },
+    {
+      "epoch": 0.3170494985441605,
+      "grad_norm": 3.6459245681762695,
+      "learning_rate": 3.985449475541331e-06,
+      "loss": 0.08050196170806885,
+      "step": 245
+    },
+    {
+      "epoch": 0.3235198964736331,
+      "grad_norm": 1.745542049407959,
+      "learning_rate": 3.94318237415463e-06,
+      "loss": 0.06479242444038391,
+      "step": 250
+    },
+    {
+      "epoch": 0.3299902944031058,
+      "grad_norm": 3.0657641887664795,
+      "learning_rate": 3.900287279094274e-06,
+      "loss": 0.06422500610351563,
+      "step": 255
+    },
+    {
+      "epoch": 0.33646069233257847,
+      "grad_norm": 1.8432261943817139,
+      "learning_rate": 3.856782855948765e-06,
+      "loss": 0.06396037340164185,
+      "step": 260
+    },
+    {
+      "epoch": 0.3429310902620511,
+      "grad_norm": 4.11646842956543,
+      "learning_rate": 3.8126880354527097e-06,
+      "loss": 0.06257544159889221,
+      "step": 265
+    },
+    {
+      "epoch": 0.3494014881915238,
+      "grad_norm": 1.804742693901062,
+      "learning_rate": 3.768022005249198e-06,
+      "loss": 0.045676803588867186,
+      "step": 270
+    },
+    {
+      "epoch": 0.35587188612099646,
+      "grad_norm": 1.5994855165481567,
+      "learning_rate": 3.7228042015404033e-06,
+      "loss": 0.07588564753532409,
+      "step": 275
+    },
+    {
+      "epoch": 0.3623422840504691,
+      "grad_norm": 3.6362464427948,
+      "learning_rate": 3.6770543006300076e-06,
+      "loss": 0.07958143949508667,
+      "step": 280
+    },
+    {
+      "epoch": 0.36881268197994177,
+      "grad_norm": 1.8701577186584473,
+      "learning_rate": 3.630792210361164e-06,
+      "loss": 0.07219069004058838,
+      "step": 285
+    },
+    {
+      "epoch": 0.37528307990941445,
+      "grad_norm": 1.5652680397033691,
+      "learning_rate": 3.584038061453689e-06,
+      "loss": 0.059544825553894044,
+      "step": 290
+    },
+    {
+      "epoch": 0.3817534778388871,
+      "grad_norm": 3.164562225341797,
+      "learning_rate": 3.5368121987442817e-06,
+      "loss": 0.06529858708381653,
+      "step": 295
+    },
+    {
+      "epoch": 0.38822387576835976,
+      "grad_norm": 1.404982328414917,
+      "learning_rate": 3.4891351723335716e-06,
+      "loss": 0.07040303945541382,
+      "step": 300
+    },
+    {
+      "epoch": 0.39469427369783244,
+      "grad_norm": 1.0612146854400635,
+      "learning_rate": 3.441027728643841e-06,
+      "loss": 0.06176878213882446,
+      "step": 305
+    },
+    {
+      "epoch": 0.40116467162730507,
+      "grad_norm": 2.1212501525878906,
+      "learning_rate": 3.3925108013913223e-06,
+      "loss": 0.05989728569984436,
+      "step": 310
+    },
+    {
+      "epoch": 0.40763506955677775,
+      "grad_norm": 1.904386281967163,
+      "learning_rate": 3.343605502476996e-06,
+      "loss": 0.05553795695304871,
+      "step": 315
+    },
+    {
+      "epoch": 0.4141054674862504,
+      "grad_norm": 3.0480096340179443,
+      "learning_rate": 3.2943331127998513e-06,
+      "loss": 0.051739555597305295,
+      "step": 320
+    },
+    {
+      "epoch": 0.42057586541572306,
+      "grad_norm": 2.6112537384033203,
+      "learning_rate": 3.2447150729966055e-06,
+      "loss": 0.07633015513420105,
+      "step": 325
+    },
+    {
+      "epoch": 0.42704626334519574,
+      "grad_norm": 1.3760981559753418,
+      "learning_rate": 3.1947729741119205e-06,
+      "loss": 0.05722711682319641,
+      "step": 330
+    },
+    {
+      "epoch": 0.43351666127466837,
+      "grad_norm": 1.613075613975525,
+      "learning_rate": 3.144528548203167e-06,
+      "loss": 0.06658859252929687,
+      "step": 335
+    },
+    {
+      "epoch": 0.43998705920414105,
+      "grad_norm": 1.4591271877288818,
+      "learning_rate": 3.094003658883821e-06,
+      "loss": 0.05374215841293335,
+      "step": 340
+    },
+    {
+      "epoch": 0.44645745713361373,
+      "grad_norm": 1.5791897773742676,
+      "learning_rate": 3.0432202918096288e-06,
+      "loss": 0.05490701198577881,
+      "step": 345
+    },
+    {
+      "epoch": 0.45292785506308636,
+      "grad_norm": 1.7543748617172241,
+      "learning_rate": 2.9922005451116505e-06,
+      "loss": 0.05493806600570679,
+      "step": 350
+    },
+    {
+      "epoch": 0.45939825299255904,
+      "grad_norm": 2.15932559967041,
+      "learning_rate": 2.9409666197803715e-06,
+      "loss": 0.046541419625282285,
+      "step": 355
+    },
+    {
+      "epoch": 0.4658686509220317,
+      "grad_norm": 3.7839879989624023,
+      "learning_rate": 2.889540810005052e-06,
+      "loss": 0.05832582116127014,
+      "step": 360
+    },
+    {
+      "epoch": 0.47233904885150435,
+      "grad_norm": 4.521731853485107,
+      "learning_rate": 2.837945493472517e-06,
+      "loss": 0.0641091525554657,
+      "step": 365
+    },
+    {
+      "epoch": 0.47880944678097703,
+      "grad_norm": 4.707234859466553,
+      "learning_rate": 2.7862031216296194e-06,
+      "loss": 0.07953336238861083,
+      "step": 370
+    },
+    {
+      "epoch": 0.4852798447104497,
+      "grad_norm": 2.2867307662963867,
+      "learning_rate": 2.734336209913604e-06,
+      "loss": 0.050211310386657715,
+      "step": 375
+    },
+    {
+      "epoch": 0.49175024263992234,
+      "grad_norm": 3.5190558433532715,
+      "learning_rate": 2.682367327954624e-06,
+      "loss": 0.04738589823246002,
+      "step": 380
+    },
+    {
+      "epoch": 0.498220640569395,
+      "grad_norm": 2.1627588272094727,
+      "learning_rate": 2.630319089754682e-06,
+      "loss": 0.0386155754327774,
+      "step": 385
+    },
+    {
+      "epoch": 0.5046910384988677,
+      "grad_norm": 1.8091168403625488,
+      "learning_rate": 2.578214143847254e-06,
+      "loss": 0.04444797337055206,
+      "step": 390
+    },
+    {
+      "epoch": 0.5111614364283403,
+      "grad_norm": 2.4277725219726562,
+      "learning_rate": 2.5260751634418954e-06,
+      "loss": 0.052102047204971316,
+      "step": 395
+    },
+    {
+      "epoch": 0.517631834357813,
+      "grad_norm": 2.606458902359009,
+      "learning_rate": 2.4739248365581054e-06,
+      "loss": 0.03815577328205109,
+      "step": 400
+    },
+    {
+      "epoch": 0.5241022322872857,
+      "grad_norm": 4.295012474060059,
+      "learning_rate": 2.4217858561527465e-06,
+      "loss": 0.0478950560092926,
+      "step": 405
+    },
+    {
+      "epoch": 0.5305726302167584,
+      "grad_norm": 2.288938045501709,
+      "learning_rate": 2.369680910245319e-06,
+      "loss": 0.05370556116104126,
+      "step": 410
+    },
+    {
+      "epoch": 0.537043028146231,
+      "grad_norm": 1.813231110572815,
+      "learning_rate": 2.3176326720453764e-06,
+      "loss": 0.03726013600826263,
+      "step": 415
+    },
+    {
+      "epoch": 0.5435134260757036,
+      "grad_norm": 2.2419540882110596,
+      "learning_rate": 2.265663790086397e-06,
+      "loss": 0.05496341586112976,
+      "step": 420
+    },
+    {
+      "epoch": 0.5499838240051763,
+      "grad_norm": 4.383563041687012,
+      "learning_rate": 2.213796878370382e-06,
+      "loss": 0.054078060388565066,
+      "step": 425
+    },
+    {
+      "epoch": 0.556454221934649,
+      "grad_norm": 2.938899278640747,
+      "learning_rate": 2.162054506527484e-06,
+      "loss": 0.053144270181655885,
+      "step": 430
+    },
+    {
+      "epoch": 0.5629246198641217,
+      "grad_norm": 2.0786099433898926,
+      "learning_rate": 2.110459189994949e-06,
+      "loss": 0.07179237604141235,
+      "step": 435
+    },
+    {
+      "epoch": 0.5693950177935944,
+      "grad_norm": 1.8487789630889893,
+      "learning_rate": 2.0590333802196294e-06,
+      "loss": 0.050521683692932126,
+      "step": 440
+    },
+    {
+      "epoch": 0.5758654157230669,
+      "grad_norm": 1.8576481342315674,
+      "learning_rate": 2.0077994548883495e-06,
+      "loss": 0.06441912651062012,
+      "step": 445
+    },
+    {
+      "epoch": 0.5823358136525396,
+      "grad_norm": 4.207110404968262,
+      "learning_rate": 1.9567797081903716e-06,
+      "loss": 0.04691969156265259,
+      "step": 450
+    },
+    {
+      "epoch": 0.5888062115820123,
+      "grad_norm": 2.0351696014404297,
+      "learning_rate": 1.9059963411161788e-06,
+      "loss": 0.048052546381950376,
+      "step": 455
+    },
+    {
+      "epoch": 0.595276609511485,
+      "grad_norm": 1.3958837985992432,
+      "learning_rate": 1.855471451796833e-06,
+      "loss": 0.05609467029571533,
+      "step": 460
+    },
+    {
+      "epoch": 0.6017470074409577,
+      "grad_norm": 3.81270694732666,
+      "learning_rate": 1.8052270258880797e-06,
+      "loss": 0.053531301021575925,
+      "step": 465
+    },
+    {
+      "epoch": 0.6082174053704302,
+      "grad_norm": 2.9946022033691406,
+      "learning_rate": 1.7552849270033956e-06,
+      "loss": 0.04387890100479126,
+      "step": 470
+    },
+    {
+      "epoch": 0.6146878032999029,
+      "grad_norm": 1.4274808168411255,
+      "learning_rate": 1.7056668872001497e-06,
+      "loss": 0.04310088157653809,
+      "step": 475
+    },
+    {
+      "epoch": 0.6211582012293756,
+      "grad_norm": 2.9882266521453857,
+      "learning_rate": 1.6563944975230047e-06,
+      "loss": 0.051578575372695924,
+      "step": 480
+    },
+    {
+      "epoch": 0.6276285991588483,
+      "grad_norm": 2.121938943862915,
+      "learning_rate": 1.6074891986086786e-06,
+      "loss": 0.03597668707370758,
+      "step": 485
+    },
+    {
+      "epoch": 0.634098997088321,
+      "grad_norm": 3.9412577152252197,
+      "learning_rate": 1.5589722713561595e-06,
+      "loss": 0.03308266699314118,
+      "step": 490
+    },
+    {
+      "epoch": 0.6405693950177936,
+      "grad_norm": 4.279633522033691,
+      "learning_rate": 1.510864827666429e-06,
+      "loss": 0.03157004714012146,
+      "step": 495
+    },
+    {
+      "epoch": 0.6470397929472662,
+      "grad_norm": 4.348323822021484,
+      "learning_rate": 1.4631878012557187e-06,
+      "loss": 0.04109773635864258,
+      "step": 500
+    },
+    {
+      "epoch": 0.6535101908767389,
+      "grad_norm": 4.9048752784729,
+      "learning_rate": 1.4159619385463116e-06,
+      "loss": 0.025870469212532044,
+      "step": 505
+    },
+    {
+      "epoch": 0.6599805888062116,
+      "grad_norm": 6.831280708312988,
+      "learning_rate": 1.3692077896388362e-06,
+      "loss": 0.05663630962371826,
+      "step": 510
+    },
+    {
+      "epoch": 0.6664509867356843,
+      "grad_norm": 4.061008453369141,
+      "learning_rate": 1.3229456993699924e-06,
+      "loss": 0.04322208166122436,
+      "step": 515
+    },
+    {
+      "epoch": 0.6729213846651569,
+      "grad_norm": 4.775136947631836,
+      "learning_rate": 1.277195798459599e-06,
+      "loss": 0.03741852939128876,
+      "step": 520
+    },
+    {
+      "epoch": 0.6793917825946296,
+      "grad_norm": 2.1828908920288086,
+      "learning_rate": 1.2319779947508035e-06,
+      "loss": 0.04378946423530579,
+      "step": 525
+    },
+    {
+      "epoch": 0.6858621805241022,
+      "grad_norm": 3.753408432006836,
+      "learning_rate": 1.1873119645472917e-06,
+      "loss": 0.05408883094787598,
+      "step": 530
+    },
+    {
+      "epoch": 0.6923325784535749,
+      "grad_norm": 4.9154767990112305,
+      "learning_rate": 1.1432171440512354e-06,
+      "loss": 0.03945363163948059,
+      "step": 535
+    },
+    {
+      "epoch": 0.6988029763830476,
+      "grad_norm": 4.23167085647583,
+      "learning_rate": 1.0997127209057262e-06,
+      "loss": 0.04915985763072968,
+      "step": 540
+    },
+    {
+      "epoch": 0.7052733743125202,
+      "grad_norm": 7.077573299407959,
+      "learning_rate": 1.0568176258453714e-06,
+      "loss": 0.05886402726173401,
+      "step": 545
+    },
+    {
+      "epoch": 0.7117437722419929,
+      "grad_norm": 3.756700038909912,
+      "learning_rate": 1.0145505244586697e-06,
+      "loss": 0.05015760660171509,
+      "step": 550
+    },
+    {
+      "epoch": 0.7182141701714655,
+      "grad_norm": 4.288253307342529,
+      "learning_rate": 9.729298090657821e-07,
+      "loss": 0.04713306427001953,
+      "step": 555
+    },
+    {
+      "epoch": 0.7246845681009382,
+      "grad_norm": 3.3605523109436035,
+      "learning_rate": 9.319735907151997e-07,
+      "loss": 0.03422398567199707,
+      "step": 560
+    },
+    {
+      "epoch": 0.7311549660304109,
+      "grad_norm": 4.4260993003845215,
+      "learning_rate": 8.916996913028111e-07,
+      "loss": 0.051188260316848755,
+      "step": 565
+    },
+    {
+      "epoch": 0.7376253639598835,
+      "grad_norm": 4.678509712219238,
+      "learning_rate": 8.521256358167936e-07,
+      "loss": 0.056780123710632326,
+      "step": 570
+    },
+    {
+      "epoch": 0.7440957618893562,
+      "grad_norm": 3.086786985397339,
+      "learning_rate": 8.132686447117013e-07,
+      "loss": 0.048840710520744325,
+      "step": 575
+    },
+    {
+      "epoch": 0.7505661598188289,
+      "grad_norm": 6.2933030128479,
+      "learning_rate": 7.751456264150659e-07,
+      "loss": 0.04729847013950348,
+      "step": 580
+    },
+    {
+      "epoch": 0.7570365577483015,
+      "grad_norm": 2.3564507961273193,
+      "learning_rate": 7.37773169969784e-07,
+      "loss": 0.047790664434432986,
+      "step": 585
+    },
+    {
+      "epoch": 0.7635069556777742,
+      "grad_norm": 4.317991733551025,
+      "learning_rate": 7.011675378154729e-07,
+      "loss": 0.03611315190792084,
+      "step": 590
+    },
+    {
+      "epoch": 0.7699773536072468,
+      "grad_norm": 3.125620126724243,
+      "learning_rate": 6.653446587119513e-07,
+      "loss": 0.03579588830471039,
+      "step": 595
+    },
+    {
+      "epoch": 0.7764477515367195,
+      "grad_norm": 3.879507303237915,
+      "learning_rate": 6.303201208079196e-07,
+      "loss": 0.03441928625106812,
+      "step": 600
+    },
+    {
+      "epoch": 0.7829181494661922,
+      "grad_norm": 3.183290958404541,
+      "learning_rate": 5.961091648578524e-07,
+      "loss": 0.03229800462722778,
+      "step": 605
+    },
+    {
+      "epoch": 0.7893885473956649,
+      "grad_norm": 4.116817474365234,
+      "learning_rate": 5.627266775900588e-07,
+      "loss": 0.042788922786712646,
+      "step": 610
+    },
+    {
+      "epoch": 0.7958589453251375,
+      "grad_norm": 3.974626302719116,
+      "learning_rate": 5.301871852287996e-07,
+      "loss": 0.04888916909694672,
+      "step": 615
+    },
+    {
+      "epoch": 0.8023293432546101,
+      "grad_norm": 0.8669401407241821,
+      "learning_rate": 4.985048471732696e-07,
+      "loss": 0.03998250663280487,
+      "step": 620
+    },
+    {
+      "epoch": 0.8087997411840828,
+      "grad_norm": 6.299636363983154,
+      "learning_rate": 4.676934498362062e-07,
+      "loss": 0.058104246854782104,
+      "step": 625
+    },
+    {
+      "epoch": 0.8152701391135555,
+      "grad_norm": 1.062532901763916,
+      "learning_rate": 4.377664006448001e-07,
+      "loss": 0.04370595812797547,
+      "step": 630
+    },
+    {
+      "epoch": 0.8217405370430282,
+      "grad_norm": 1.5842965841293335,
+      "learning_rate": 4.0873672220651914e-07,
+      "loss": 0.025883442163467406,
+      "step": 635
+    },
+    {
+      "epoch": 0.8282109349725008,
+      "grad_norm": 4.2788286209106445,
+      "learning_rate": 3.8061704664238556e-07,
+      "loss": 0.035388365387916565,
+      "step": 640
+    },
+    {
+      "epoch": 0.8346813329019734,
+      "grad_norm": 2.5707383155822754,
+      "learning_rate": 3.53419610090171e-07,
+      "loss": 0.03312977850437164,
+      "step": 645
+    },
+    {
+      "epoch": 0.8411517308314461,
+      "grad_norm": 3.3496265411376953,
+      "learning_rate": 3.271562473799011e-07,
+      "loss": 0.03264069259166717,
+      "step": 650
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 773,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.792147956847227e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-650/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5180becaca782fdfd2e0d8120222ed130423adbe27b164245aacdbb17a81c155
+size 5393