Add checkpoint checkpoint-625

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-625/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-625/README.md

@@ -0,0 +1,210 @@
+---
+base_model: khoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:khoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16
+- 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 0.19.1

checkpoint-625/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5MoeForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5_moe.modeling_qwen3_5_moe",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "khoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-625/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be36702bf42a17a67b19564abeb581c01692aeec786fd11d3ff0f5fda6558534
+size 13774432

checkpoint-625/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 (preserve_thinking is defined and preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}
+                        {{- 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 false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-625/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432476d65ff48cd69d0c742a4979abb8e7a0fc54c3a8e65f48cffa5770c6a842
+size 27593099

checkpoint-625/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69eb21f3191d99b4ec0b327ab5e298906f5458871293441b1aef131b9a5364b6
+size 14645

checkpoint-625/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3579a2c619adf4d74f2ab861e4060f33fd573a66c732d24981da7433b098bc7
+size 1465

checkpoint-625/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6b8cf757c22939ad262adb1077fa3b8e7cbb89054bc2507630b0f6aafd80ae
+size 19989442

checkpoint-625/tokenizer_config.json

@@ -0,0 +1,298 @@
+{
+  "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": "<|endoftext|>",
+  "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+",
+  "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-625/trainer_state.json

@@ -0,0 +1,909 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.11767578125,
+      "learning_rate": 0.00016,
+      "loss": 0.6554988384246826,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.126953125,
+      "learning_rate": 0.00019870967741935483,
+      "loss": 0.6316752910614014,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 0.0001970967741935484,
+      "loss": 0.6129528522491455,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 0.00019548387096774195,
+      "loss": 0.60089111328125,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.0546875,
+      "learning_rate": 0.00019387096774193548,
+      "loss": 0.6051591873168946,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 0.00019225806451612904,
+      "loss": 0.5910581588745117,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 0.0001906451612903226,
+      "loss": 0.5913372993469238,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.05078125,
+      "learning_rate": 0.00018903225806451616,
+      "loss": 0.5835432052612305,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.047119140625,
+      "learning_rate": 0.0001874193548387097,
+      "loss": 0.5777533054351807,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.04833984375,
+      "learning_rate": 0.00018580645161290325,
+      "loss": 0.5595584392547608,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.0001841935483870968,
+      "loss": 0.5782830715179443,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 0.00018258064516129033,
+      "loss": 0.561436939239502,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 0.00018096774193548387,
+      "loss": 0.5930795192718505,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 0.00017935483870967742,
+      "loss": 0.5740991592407226,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 0.00017774193548387098,
+      "loss": 0.5711933135986328,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.0001761290322580645,
+      "loss": 0.5878489494323731,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00017451612903225807,
+      "loss": 0.5775240421295166,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017290322580645163,
+      "loss": 0.5785224914550782,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.00017129032258064516,
+      "loss": 0.5774213314056397,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 0.00016967741935483872,
+      "loss": 0.5569428443908692,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00016806451612903228,
+      "loss": 0.5698188304901123,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 0.0001664516129032258,
+      "loss": 0.574033784866333,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00016483870967741937,
+      "loss": 0.5798182010650634,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 0.00016322580645161292,
+      "loss": 0.5746054172515869,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.37109375,
+      "learning_rate": 0.00016161290322580645,
+      "loss": 0.5746851921081543,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00016,
+      "loss": 0.5720233917236328,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 0.00015838709677419357,
+      "loss": 0.5694709777832031,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.0001567741935483871,
+      "loss": 0.56185941696167,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00015516129032258063,
+      "loss": 0.5761864662170411,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 0.0001535483870967742,
+      "loss": 0.5672729969024658,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.05859375,
+      "learning_rate": 0.00015193548387096775,
+      "loss": 0.5709065437316895,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00015032258064516128,
+      "loss": 0.5686789989471436,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 0.00014870967741935484,
+      "loss": 0.5607232570648193,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.0001470967741935484,
+      "loss": 0.5666838645935058,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 0.00014548387096774196,
+      "loss": 0.5663557052612305,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 0.00014387096774193549,
+      "loss": 0.5619307518005371,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.00014225806451612904,
+      "loss": 0.5675935268402099,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.0001406451612903226,
+      "loss": 0.558326530456543,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.00013903225806451613,
+      "loss": 0.5571943759918213,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 0.0001374193548387097,
+      "loss": 0.5767090797424317,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.06542576849460602,
+      "learning_rate": 0.00013580645161290325,
+      "loss": 0.5813523292541504,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.06451020389795303,
+      "learning_rate": 0.00013419354838709678,
+      "loss": 0.5669836521148681,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.06229862943291664,
+      "learning_rate": 0.00013258064516129034,
+      "loss": 0.5780042171478271,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.09608947485685349,
+      "learning_rate": 0.00013096774193548387,
+      "loss": 0.5740575313568115,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.06359390914440155,
+      "learning_rate": 0.00012935483870967743,
+      "loss": 0.5707311630249023,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.06713160872459412,
+      "learning_rate": 0.00012774193548387096,
+      "loss": 0.5569428920745849,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.06508593261241913,
+      "learning_rate": 0.00012612903225806452,
+      "loss": 0.5606443881988525,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.06860020011663437,
+      "learning_rate": 0.00012451612903225808,
+      "loss": 0.5722582817077637,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.06724812090396881,
+      "learning_rate": 0.0001229032258064516,
+      "loss": 0.5671603202819824,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.06457360088825226,
+      "learning_rate": 0.00012129032258064516,
+      "loss": 0.5736354351043701,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.07162501662969589,
+      "learning_rate": 0.00011967741935483871,
+      "loss": 0.568655252456665,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.07056798785924911,
+      "learning_rate": 0.00011806451612903227,
+      "loss": 0.5712923049926758,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.06752821058034897,
+      "learning_rate": 0.00011645161290322581,
+      "loss": 0.574179744720459,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.06757891923189163,
+      "learning_rate": 0.00011483870967741937,
+      "loss": 0.568781852722168,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.06529594212770462,
+      "learning_rate": 0.00011322580645161291,
+      "loss": 0.5763449668884277,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.06725391000509262,
+      "learning_rate": 0.00011161290322580646,
+      "loss": 0.5555770397186279,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.06466025859117508,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.558352279663086,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.0675201490521431,
+      "learning_rate": 0.00010838709677419356,
+      "loss": 0.5610656261444091,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.06591981649398804,
+      "learning_rate": 0.00010677419354838709,
+      "loss": 0.5565807819366455,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.06528247147798538,
+      "learning_rate": 0.00010516129032258064,
+      "loss": 0.5542235851287842,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.07089075446128845,
+      "learning_rate": 0.0001035483870967742,
+      "loss": 0.5591094017028808,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.07118254154920578,
+      "learning_rate": 0.00010193548387096774,
+      "loss": 0.5636035919189453,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.06858668476343155,
+      "learning_rate": 0.00010032258064516129,
+      "loss": 0.5677674770355224,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.06893937289714813,
+      "learning_rate": 9.870967741935484e-05,
+      "loss": 0.5631217956542969,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.07015130668878555,
+      "learning_rate": 9.709677419354839e-05,
+      "loss": 0.5573655605316162,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.07102397829294205,
+      "learning_rate": 9.548387096774195e-05,
+      "loss": 0.5720638751983642,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.08668693155050278,
+      "learning_rate": 9.387096774193549e-05,
+      "loss": 0.5595195770263672,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.0652279481291771,
+      "learning_rate": 9.225806451612904e-05,
+      "loss": 0.5633126258850097,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.07421018183231354,
+      "learning_rate": 9.06451612903226e-05,
+      "loss": 0.5664429187774658,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.07819076627492905,
+      "learning_rate": 8.903225806451614e-05,
+      "loss": 0.5585434913635254,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.07451411336660385,
+      "learning_rate": 8.741935483870968e-05,
+      "loss": 0.5587696552276611,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.07057429850101471,
+      "learning_rate": 8.580645161290323e-05,
+      "loss": 0.557004737854004,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.06424684822559357,
+      "learning_rate": 8.419354838709677e-05,
+      "loss": 0.5569393157958984,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.06557153165340424,
+      "learning_rate": 8.258064516129033e-05,
+      "loss": 0.563733434677124,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.06546968221664429,
+      "learning_rate": 8.096774193548387e-05,
+      "loss": 0.570366907119751,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.06591956317424774,
+      "learning_rate": 7.935483870967743e-05,
+      "loss": 0.5555679798126221,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.06823961436748505,
+      "learning_rate": 7.774193548387098e-05,
+      "loss": 0.5626004219055176,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.07176834344863892,
+      "learning_rate": 7.612903225806451e-05,
+      "loss": 0.575939130783081,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.06666567921638489,
+      "learning_rate": 7.451612903225807e-05,
+      "loss": 0.5563110828399658,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.06764642894268036,
+      "learning_rate": 7.290322580645161e-05,
+      "loss": 0.5638130187988282,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.06829249113798141,
+      "learning_rate": 7.129032258064517e-05,
+      "loss": 0.5660825252532959,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.09068518131971359,
+      "learning_rate": 6.967741935483871e-05,
+      "loss": 0.5557247638702393,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.0700569748878479,
+      "learning_rate": 6.806451612903226e-05,
+      "loss": 0.5440712451934815,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.06983818113803864,
+      "learning_rate": 6.645161290322582e-05,
+      "loss": 0.5671990871429443,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.0715850442647934,
+      "learning_rate": 6.483870967741936e-05,
+      "loss": 0.5637064933776855,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.06824701279401779,
+      "learning_rate": 6.32258064516129e-05,
+      "loss": 0.5788649559020996,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.07091919332742691,
+      "learning_rate": 6.161290322580645e-05,
+      "loss": 0.5736388683319091,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.07010844349861145,
+      "learning_rate": 6e-05,
+      "loss": 0.55319185256958,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.06883524358272552,
+      "learning_rate": 5.838709677419355e-05,
+      "loss": 0.5780259132385254,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.07393763959407806,
+      "learning_rate": 5.67741935483871e-05,
+      "loss": 0.557044792175293,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.06950511038303375,
+      "learning_rate": 5.516129032258065e-05,
+      "loss": 0.5620320796966553,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.06649049371480942,
+      "learning_rate": 5.35483870967742e-05,
+      "loss": 0.5640514373779297,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.0654178038239479,
+      "learning_rate": 5.193548387096775e-05,
+      "loss": 0.567882776260376,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.06904909759759903,
+      "learning_rate": 5.032258064516129e-05,
+      "loss": 0.5655563831329345,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.06747818738222122,
+      "learning_rate": 4.870967741935484e-05,
+      "loss": 0.5671658515930176,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.06916290521621704,
+      "learning_rate": 4.7096774193548385e-05,
+      "loss": 0.570194673538208,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.07048875093460083,
+      "learning_rate": 4.548387096774194e-05,
+      "loss": 0.5832510948181152,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.06946586817502975,
+      "learning_rate": 4.387096774193549e-05,
+      "loss": 0.5504323959350585,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.06650974601507187,
+      "learning_rate": 4.225806451612904e-05,
+      "loss": 0.5517677307128906,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.06879310309886932,
+      "learning_rate": 4.0645161290322584e-05,
+      "loss": 0.5599205017089843,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.06860392540693283,
+      "learning_rate": 3.903225806451613e-05,
+      "loss": 0.5657797813415527,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.06568386405706406,
+      "learning_rate": 3.741935483870968e-05,
+      "loss": 0.5563346385955811,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.07192289084196091,
+      "learning_rate": 3.580645161290323e-05,
+      "loss": 0.5695600032806396,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.07968848198652267,
+      "learning_rate": 3.4193548387096776e-05,
+      "loss": 0.5501180648803711,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.06926244497299194,
+      "learning_rate": 3.258064516129033e-05,
+      "loss": 0.5559171676635742,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.06760943681001663,
+      "learning_rate": 3.096774193548387e-05,
+      "loss": 0.5637694835662842,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.06881634145975113,
+      "learning_rate": 2.9354838709677417e-05,
+      "loss": 0.562023115158081,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.06764361262321472,
+      "learning_rate": 2.7741935483870968e-05,
+      "loss": 0.5580467224121094,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.06766146421432495,
+      "learning_rate": 2.6129032258064516e-05,
+      "loss": 0.5589831352233887,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.0757446140050888,
+      "learning_rate": 2.4516129032258064e-05,
+      "loss": 0.5543781757354737,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.06817227602005005,
+      "learning_rate": 2.2903225806451615e-05,
+      "loss": 0.5628514289855957,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.07092993706464767,
+      "learning_rate": 2.129032258064516e-05,
+      "loss": 0.5675341606140136,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.06779942661523819,
+      "learning_rate": 1.967741935483871e-05,
+      "loss": 0.5614606857299804,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.07492519170045853,
+      "learning_rate": 1.806451612903226e-05,
+      "loss": 0.5568675994873047,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.06805197149515152,
+      "learning_rate": 1.6451612903225807e-05,
+      "loss": 0.5574911117553711,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.06900990754365921,
+      "learning_rate": 1.4838709677419355e-05,
+      "loss": 0.565622091293335,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.07820545136928558,
+      "learning_rate": 1.3225806451612905e-05,
+      "loss": 0.5542529106140137,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.06747955828905106,
+      "learning_rate": 1.1612903225806453e-05,
+      "loss": 0.5684441089630127,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.0708058774471283,
+      "learning_rate": 1e-05,
+      "loss": 0.5612256050109863,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.06703224778175354,
+      "learning_rate": 8.387096774193549e-06,
+      "loss": 0.5605002880096436,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.06872890889644623,
+      "learning_rate": 6.774193548387098e-06,
+      "loss": 0.5640598773956299,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.07115549594163895,
+      "learning_rate": 5.161290322580646e-06,
+      "loss": 0.5665970802307129,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.06576542556285858,
+      "learning_rate": 3.5483870967741936e-06,
+      "loss": 0.557554817199707,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.06863939762115479,
+      "learning_rate": 1.935483870967742e-06,
+      "loss": 0.5651103019714355,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.06741167604923248,
+      "learning_rate": 3.2258064516129035e-07,
+      "loss": 0.552934217453003,
+      "step": 625
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.523367338464738e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-625/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a24cfc6ee2186c0446e0fd75df783a654c15395f9ddc0908f39a0fc528fd00
+size 5713