Upload training checkpoint at step 1500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-8B-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-8B-unsloth-bnb-4bit
+- 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 0.18.1

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-8B-unsloth-bnb-4bit",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab619e56911d712b8c6e84b3b9f34d7cd95e796c2392aea032f810782601eba
+size 174655536

chat_template.jinja

@@ -0,0 +1,97 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = message.content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (message.content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = message.content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18965f5ec6bb43b5163cac3a3d9a446e9c5a9a11438c4b6a7cd0a61ff9005eb2
+size 90567987

rng_state.pth

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

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7882694890e1738e2e3cc0b3ebfb59580771940d8cb6baed8c943125f1d4fd1b
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8980385442e4ffdd65a55e5064c1ebd27dabb265ef7350f45c42c8ae59aea7e
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
+size 11423114

tokenizer_config.json

@@ -0,0 +1,233 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 40960,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24,
+  "eval_steps": 250,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0016,
+      "grad_norm": NaN,
+      "learning_rate": 9.574468085106383e-06,
+      "loss": 0.6083179950714112,
+      "step": 10
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 0.2735198438167572,
+      "learning_rate": 1.9148936170212766e-05,
+      "loss": 0.6088993072509765,
+      "step": 20
+    },
+    {
+      "epoch": 0.0048,
+      "grad_norm": 0.15276113152503967,
+      "learning_rate": 2.9787234042553192e-05,
+      "loss": 0.5225989818572998,
+      "step": 30
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 0.17109858989715576,
+      "learning_rate": 4.0425531914893614e-05,
+      "loss": 0.4329381942749023,
+      "step": 40
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.17585736513137817,
+      "learning_rate": 5.1063829787234044e-05,
+      "loss": 0.35364015102386476,
+      "step": 50
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 0.16095905005931854,
+      "learning_rate": 6.170212765957447e-05,
+      "loss": 0.26982028484344484,
+      "step": 60
+    },
+    {
+      "epoch": 0.0112,
+      "grad_norm": 0.11053046584129333,
+      "learning_rate": 7.23404255319149e-05,
+      "loss": 0.20504410266876222,
+      "step": 70
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 0.12669840455055237,
+      "learning_rate": 8.297872340425533e-05,
+      "loss": 0.19483240842819213,
+      "step": 80
+    },
+    {
+      "epoch": 0.0144,
+      "grad_norm": 0.11641468852758408,
+      "learning_rate": 9.361702127659576e-05,
+      "loss": 0.17770581245422362,
+      "step": 90
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.14681392908096313,
+      "learning_rate": 0.00010425531914893618,
+      "loss": 0.15753360986709594,
+      "step": 100
+    },
+    {
+      "epoch": 0.0176,
+      "grad_norm": 0.09883147478103638,
+      "learning_rate": 0.00011489361702127661,
+      "loss": 0.16169432401657105,
+      "step": 110
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 0.1138603463768959,
+      "learning_rate": 0.00012553191489361702,
+      "loss": 0.16089822053909303,
+      "step": 120
+    },
+    {
+      "epoch": 0.0208,
+      "grad_norm": 0.13063949346542358,
+      "learning_rate": 0.00013617021276595746,
+      "loss": 0.1603950023651123,
+      "step": 130
+    },
+    {
+      "epoch": 0.0224,
+      "grad_norm": 0.06824357807636261,
+      "learning_rate": 0.00014680851063829788,
+      "loss": 0.14956578016281127,
+      "step": 140
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.12136659771203995,
+      "learning_rate": 0.00015744680851063832,
+      "loss": 0.1617922306060791,
+      "step": 150
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 0.10032546520233154,
+      "learning_rate": 0.00016808510638297873,
+      "loss": 0.1547396659851074,
+      "step": 160
+    },
+    {
+      "epoch": 0.0272,
+      "grad_norm": 0.07678422331809998,
+      "learning_rate": 0.00017872340425531915,
+      "loss": 0.14475579261779786,
+      "step": 170
+    },
+    {
+      "epoch": 0.0288,
+      "grad_norm": 0.10933304578065872,
+      "learning_rate": 0.00018936170212765957,
+      "loss": 0.1330868124961853,
+      "step": 180
+    },
+    {
+      "epoch": 0.0304,
+      "grad_norm": 0.12041473388671875,
+      "learning_rate": 0.0002,
+      "loss": 0.14836544990539552,
+      "step": 190
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.0896446481347084,
+      "learning_rate": 0.00019967007588254704,
+      "loss": 0.14405652284622192,
+      "step": 200
+    },
+    {
+      "epoch": 0.0336,
+      "grad_norm": 0.0876811295747757,
+      "learning_rate": 0.00019934015176509403,
+      "loss": 0.14646297693252563,
+      "step": 210
+    },
+    {
+      "epoch": 0.0352,
+      "grad_norm": 0.09327778220176697,
+      "learning_rate": 0.00019901022764764106,
+      "loss": 0.14419257640838623,
+      "step": 220
+    },
+    {
+      "epoch": 0.0368,
+      "grad_norm": 0.08388442546129227,
+      "learning_rate": 0.00019868030353018806,
+      "loss": 0.15150091648101807,
+      "step": 230
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 0.09979762881994247,
+      "learning_rate": 0.00019835037941273509,
+      "loss": 0.14006744623184203,
+      "step": 240
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.0845855325460434,
+      "learning_rate": 0.0001980204552952821,
+      "loss": 0.15045372247695923,
+      "step": 250
+    },
+    {
+      "epoch": 0.0416,
+      "grad_norm": 0.09481288492679596,
+      "learning_rate": 0.0001976905311778291,
+      "loss": 0.15042688846588134,
+      "step": 260
+    },
+    {
+      "epoch": 0.0432,
+      "grad_norm": 0.10349375009536743,
+      "learning_rate": 0.0001973606070603761,
+      "loss": 0.13992291688919067,
+      "step": 270
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 0.07897678017616272,
+      "learning_rate": 0.00019703068294292314,
+      "loss": 0.13927781581878662,
+      "step": 280
+    },
+    {
+      "epoch": 0.0464,
+      "grad_norm": 0.08341789990663528,
+      "learning_rate": 0.00019670075882547014,
+      "loss": 0.14076149463653564,
+      "step": 290
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.10565593093633652,
+      "learning_rate": 0.00019637083470801716,
+      "loss": 0.14325612783432007,
+      "step": 300
+    },
+    {
+      "epoch": 0.0496,
+      "grad_norm": 0.07861499488353729,
+      "learning_rate": 0.0001960409105905642,
+      "loss": 0.1343199133872986,
+      "step": 310
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 0.09252545982599258,
+      "learning_rate": 0.0001957109864731112,
+      "loss": 0.12891001701354982,
+      "step": 320
+    },
+    {
+      "epoch": 0.0528,
+      "grad_norm": 0.08716761320829391,
+      "learning_rate": 0.0001953810623556582,
+      "loss": 0.1449826717376709,
+      "step": 330
+    },
+    {
+      "epoch": 0.0544,
+      "grad_norm": 0.07750111818313599,
+      "learning_rate": 0.0001950511382382052,
+      "loss": 0.1274427056312561,
+      "step": 340
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.07396410405635834,
+      "learning_rate": 0.00019472121412075224,
+      "loss": 0.12241615056991577,
+      "step": 350
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 0.07157568633556366,
+      "learning_rate": 0.00019439129000329926,
+      "loss": 0.14313431978225707,
+      "step": 360
+    },
+    {
+      "epoch": 0.0592,
+      "grad_norm": 0.08780192583799362,
+      "learning_rate": 0.00019406136588584626,
+      "loss": 0.13534088134765626,
+      "step": 370
+    },
+    {
+      "epoch": 0.0608,
+      "grad_norm": 0.09394513815641403,
+      "learning_rate": 0.0001937314417683933,
+      "loss": 0.1249586820602417,
+      "step": 380
+    },
+    {
+      "epoch": 0.0624,
+      "grad_norm": 0.0853569507598877,
+      "learning_rate": 0.0001934015176509403,
+      "loss": 0.13353261947631836,
+      "step": 390
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.08356380462646484,
+      "learning_rate": 0.00019307159353348731,
+      "loss": 0.12304072380065918,
+      "step": 400
+    },
+    {
+      "epoch": 0.0656,
+      "grad_norm": 0.08608467876911163,
+      "learning_rate": 0.00019274166941603434,
+      "loss": 0.13379846811294555,
+      "step": 410
+    },
+    {
+      "epoch": 0.0672,
+      "grad_norm": 0.07890665531158447,
+      "learning_rate": 0.0001924117452985813,
+      "loss": 0.11951367855072022,
+      "step": 420
+    },
+    {
+      "epoch": 0.0688,
+      "grad_norm": 0.08108149468898773,
+      "learning_rate": 0.00019208182118112834,
+      "loss": 0.12902278900146485,
+      "step": 430
+    },
+    {
+      "epoch": 0.0704,
+      "grad_norm": 0.09603618830442429,
+      "learning_rate": 0.00019175189706367536,
+      "loss": 0.12690144777297974,
+      "step": 440
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.09471320360898972,
+      "learning_rate": 0.00019142197294622236,
+      "loss": 0.13802603483200074,
+      "step": 450
+    },
+    {
+      "epoch": 0.0736,
+      "grad_norm": 0.08374392986297607,
+      "learning_rate": 0.0001910920488287694,
+      "loss": 0.12328752279281616,
+      "step": 460
+    },
+    {
+      "epoch": 0.0752,
+      "grad_norm": 0.08944465219974518,
+      "learning_rate": 0.00019076212471131642,
+      "loss": 0.12756569385528566,
+      "step": 470
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 0.0898577868938446,
+      "learning_rate": 0.00019043220059386341,
+      "loss": 0.13218681812286376,
+      "step": 480
+    },
+    {
+      "epoch": 0.0784,
+      "grad_norm": 0.07767961174249649,
+      "learning_rate": 0.00019010227647641044,
+      "loss": 0.135015869140625,
+      "step": 490
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.0865555852651596,
+      "learning_rate": 0.00018977235235895744,
+      "loss": 0.128175950050354,
+      "step": 500
+    },
+    {
+      "epoch": 0.0816,
+      "grad_norm": 0.07919178158044815,
+      "learning_rate": 0.00018944242824150447,
+      "loss": 0.12430660724639893,
+      "step": 510
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 0.08649525046348572,
+      "learning_rate": 0.0001891125041240515,
+      "loss": 0.12590073347091674,
+      "step": 520
+    },
+    {
+      "epoch": 0.0848,
+      "grad_norm": 0.08704695850610733,
+      "learning_rate": 0.0001887825800065985,
+      "loss": 0.12156925201416016,
+      "step": 530
+    },
+    {
+      "epoch": 0.0864,
+      "grad_norm": 0.06752946227788925,
+      "learning_rate": 0.00018845265588914552,
+      "loss": 0.12604955434799195,
+      "step": 540
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.09034618735313416,
+      "learning_rate": 0.00018812273177169252,
+      "loss": 0.13052459955215454,
+      "step": 550
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 0.0869947075843811,
+      "learning_rate": 0.00018779280765423954,
+      "loss": 0.12303999662399293,
+      "step": 560
+    },
+    {
+      "epoch": 0.0912,
+      "grad_norm": 0.0702558308839798,
+      "learning_rate": 0.00018746288353678654,
+      "loss": 0.12230894565582276,
+      "step": 570
+    },
+    {
+      "epoch": 0.0928,
+      "grad_norm": 0.08718933910131454,
+      "learning_rate": 0.00018713295941933354,
+      "loss": 0.1285646677017212,
+      "step": 580
+    },
+    {
+      "epoch": 0.0944,
+      "grad_norm": 0.07396125048398972,
+      "learning_rate": 0.00018680303530188057,
+      "loss": 0.1259121775627136,
+      "step": 590
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.10813502222299576,
+      "learning_rate": 0.0001864731111844276,
+      "loss": 0.12581136226654052,
+      "step": 600
+    },
+    {
+      "epoch": 0.0976,
+      "grad_norm": 0.07332257181406021,
+      "learning_rate": 0.0001861431870669746,
+      "loss": 0.120159912109375,
+      "step": 610
+    },
+    {
+      "epoch": 0.0992,
+      "grad_norm": 0.08529425412416458,
+      "learning_rate": 0.00018581326294952162,
+      "loss": 0.1297559142112732,
+      "step": 620
+    },
+    {
+      "epoch": 0.1008,
+      "grad_norm": 0.09605136513710022,
+      "learning_rate": 0.00018548333883206864,
+      "loss": 0.12067115306854248,
+      "step": 630
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 0.08586304634809494,
+      "learning_rate": 0.00018515341471461564,
+      "loss": 0.12730380296707153,
+      "step": 640
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.06986010074615479,
+      "learning_rate": 0.00018482349059716267,
+      "loss": 0.12864140272140503,
+      "step": 650
+    },
+    {
+      "epoch": 0.1056,
+      "grad_norm": 0.08565957844257355,
+      "learning_rate": 0.00018449356647970967,
+      "loss": 0.13535914421081544,
+      "step": 660
+    },
+    {
+      "epoch": 0.1072,
+      "grad_norm": 0.07841351628303528,
+      "learning_rate": 0.0001841636423622567,
+      "loss": 0.12447234392166137,
+      "step": 670
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 0.07424665987491608,
+      "learning_rate": 0.00018383371824480372,
+      "loss": 0.12037907838821411,
+      "step": 680
+    },
+    {
+      "epoch": 0.1104,
+      "grad_norm": 0.0957612544298172,
+      "learning_rate": 0.00018350379412735072,
+      "loss": 0.11919810771942138,
+      "step": 690
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.07862170785665512,
+      "learning_rate": 0.00018317387000989775,
+      "loss": 0.12414863109588622,
+      "step": 700
+    },
+    {
+      "epoch": 0.1136,
+      "grad_norm": 0.12410055845975876,
+      "learning_rate": 0.00018284394589244474,
+      "loss": 0.12083030939102173,
+      "step": 710
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 0.07692275941371918,
+      "learning_rate": 0.00018251402177499174,
+      "loss": 0.11559462547302246,
+      "step": 720
+    },
+    {
+      "epoch": 0.1168,
+      "grad_norm": 0.07810766994953156,
+      "learning_rate": 0.00018218409765753877,
+      "loss": 0.12092136144638062,
+      "step": 730
+    },
+    {
+      "epoch": 0.1184,
+      "grad_norm": 0.08475863188505173,
+      "learning_rate": 0.00018185417354008577,
+      "loss": 0.12225215435028076,
+      "step": 740
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.09497244656085968,
+      "learning_rate": 0.0001815242494226328,
+      "loss": 0.12478446960449219,
+      "step": 750
+    },
+    {
+      "epoch": 0.1216,
+      "grad_norm": 0.07779653370380402,
+      "learning_rate": 0.00018119432530517982,
+      "loss": 0.11081166267395019,
+      "step": 760
+    },
+    {
+      "epoch": 0.1232,
+      "grad_norm": 0.08435814827680588,
+      "learning_rate": 0.00018086440118772682,
+      "loss": 0.10844987630844116,
+      "step": 770
+    },
+    {
+      "epoch": 0.1248,
+      "grad_norm": 0.07567104697227478,
+      "learning_rate": 0.00018053447707027385,
+      "loss": 0.11887184381484986,
+      "step": 780
+    },
+    {
+      "epoch": 0.1264,
+      "grad_norm": 0.07750700414180756,
+      "learning_rate": 0.00018020455295282087,
+      "loss": 0.11811846494674683,
+      "step": 790
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.09390198439359665,
+      "learning_rate": 0.00017987462883536787,
+      "loss": 0.11379201412200927,
+      "step": 800
+    },
+    {
+      "epoch": 0.1296,
+      "grad_norm": 0.08400580286979675,
+      "learning_rate": 0.0001795447047179149,
+      "loss": 0.11909257173538208,
+      "step": 810
+    },
+    {
+      "epoch": 0.1312,
+      "grad_norm": 0.09543855488300323,
+      "learning_rate": 0.0001792147806004619,
+      "loss": 0.10916774272918701,
+      "step": 820
+    },
+    {
+      "epoch": 0.1328,
+      "grad_norm": 0.07908441871404648,
+      "learning_rate": 0.00017888485648300892,
+      "loss": 0.107346510887146,
+      "step": 830
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 0.1085224449634552,
+      "learning_rate": 0.00017855493236555595,
+      "loss": 0.12227011919021606,
+      "step": 840
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.07472517341375351,
+      "learning_rate": 0.00017822500824810295,
+      "loss": 0.11575174331665039,
+      "step": 850
+    },
+    {
+      "epoch": 0.1376,
+      "grad_norm": 0.07198534905910492,
+      "learning_rate": 0.00017789508413064997,
+      "loss": 0.12281327247619629,
+      "step": 860
+    },
+    {
+      "epoch": 0.1392,
+      "grad_norm": 0.09142109006643295,
+      "learning_rate": 0.00017756516001319697,
+      "loss": 0.11497378349304199,
+      "step": 870
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 0.09548252075910568,
+      "learning_rate": 0.00017723523589574397,
+      "loss": 0.11615512371063233,
+      "step": 880
+    },
+    {
+      "epoch": 0.1424,
+      "grad_norm": 0.06250233203172684,
+      "learning_rate": 0.000176905311778291,
+      "loss": 0.11593252420425415,
+      "step": 890
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.08740886300802231,
+      "learning_rate": 0.000176575387660838,
+      "loss": 0.11546707153320312,
+      "step": 900
+    },
+    {
+      "epoch": 0.1456,
+      "grad_norm": 0.11061470210552216,
+      "learning_rate": 0.00017624546354338502,
+      "loss": 0.12130849361419678,
+      "step": 910
+    },
+    {
+      "epoch": 0.1472,
+      "grad_norm": 0.07824647426605225,
+      "learning_rate": 0.00017591553942593205,
+      "loss": 0.1188379168510437,
+      "step": 920
+    },
+    {
+      "epoch": 0.1488,
+      "grad_norm": 0.08214984834194183,
+      "learning_rate": 0.00017558561530847905,
+      "loss": 0.11806504726409912,
+      "step": 930
+    },
+    {
+      "epoch": 0.1504,
+      "grad_norm": 0.09313149005174637,
+      "learning_rate": 0.00017525569119102607,
+      "loss": 0.11112408638000489,
+      "step": 940
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.08523363620042801,
+      "learning_rate": 0.0001749257670735731,
+      "loss": 0.1136185884475708,
+      "step": 950
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 0.06718438863754272,
+      "learning_rate": 0.0001745958429561201,
+      "loss": 0.1142117738723755,
+      "step": 960
+    },
+    {
+      "epoch": 0.1552,
+      "grad_norm": 0.08877789974212646,
+      "learning_rate": 0.00017426591883866713,
+      "loss": 0.11236680746078491,
+      "step": 970
+    },
+    {
+      "epoch": 0.1568,
+      "grad_norm": 0.07814772427082062,
+      "learning_rate": 0.00017393599472121412,
+      "loss": 0.10925638675689697,
+      "step": 980
+    },
+    {
+      "epoch": 0.1584,
+      "grad_norm": 0.08659686148166656,
+      "learning_rate": 0.00017360607060376115,
+      "loss": 0.11623308658599854,
+      "step": 990
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.08823436498641968,
+      "learning_rate": 0.00017327614648630818,
+      "loss": 0.11374906301498414,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1616,
+      "grad_norm": 0.12844692170619965,
+      "learning_rate": 0.00017294622236885518,
+      "loss": 0.10570265054702759,
+      "step": 1010
+    },
+    {
+      "epoch": 0.1632,
+      "grad_norm": 0.09296935796737671,
+      "learning_rate": 0.00017261629825140217,
+      "loss": 0.10974518060684205,
+      "step": 1020
+    },
+    {
+      "epoch": 0.1648,
+      "grad_norm": 0.09684396535158157,
+      "learning_rate": 0.0001722863741339492,
+      "loss": 0.11235146522521973,
+      "step": 1030
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 0.0794069766998291,
+      "learning_rate": 0.0001719564500164962,
+      "loss": 0.11345041990280151,
+      "step": 1040
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.0808623656630516,
+      "learning_rate": 0.00017162652589904323,
+      "loss": 0.11226475238800049,
+      "step": 1050
+    },
+    {
+      "epoch": 0.1696,
+      "grad_norm": 0.09042982757091522,
+      "learning_rate": 0.00017129660178159022,
+      "loss": 0.11745167970657348,
+      "step": 1060
+    },
+    {
+      "epoch": 0.1712,
+      "grad_norm": 0.0925358310341835,
+      "learning_rate": 0.00017096667766413725,
+      "loss": 0.11483606100082397,
+      "step": 1070
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 0.08630611002445221,
+      "learning_rate": 0.00017063675354668428,
+      "loss": 0.11297872066497802,
+      "step": 1080
+    },
+    {
+      "epoch": 0.1744,
+      "grad_norm": 0.07782171666622162,
+      "learning_rate": 0.00017030682942923128,
+      "loss": 0.12509260177612305,
+      "step": 1090
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.09083843231201172,
+      "learning_rate": 0.0001699769053117783,
+      "loss": 0.1190922737121582,
+      "step": 1100
+    },
+    {
+      "epoch": 0.1776,
+      "grad_norm": 0.09185738116502762,
+      "learning_rate": 0.00016964698119432533,
+      "loss": 0.11026453971862793,
+      "step": 1110
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 0.10063742846250534,
+      "learning_rate": 0.00016931705707687233,
+      "loss": 0.11582765579223633,
+      "step": 1120
+    },
+    {
+      "epoch": 0.1808,
+      "grad_norm": 0.09147176891565323,
+      "learning_rate": 0.00016898713295941935,
+      "loss": 0.11444920301437378,
+      "step": 1130
+    },
+    {
+      "epoch": 0.1824,
+      "grad_norm": 0.10646630078554153,
+      "learning_rate": 0.00016865720884196635,
+      "loss": 0.10560888051986694,
+      "step": 1140
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.12107925117015839,
+      "learning_rate": 0.00016832728472451338,
+      "loss": 0.11672050952911377,
+      "step": 1150
+    },
+    {
+      "epoch": 0.1856,
+      "grad_norm": 0.10743635892868042,
+      "learning_rate": 0.0001679973606070604,
+      "loss": 0.11454172134399414,
+      "step": 1160
+    },
+    {
+      "epoch": 0.1872,
+      "grad_norm": 0.0912097841501236,
+      "learning_rate": 0.00016766743648960738,
+      "loss": 0.10987292528152466,
+      "step": 1170
+    },
+    {
+      "epoch": 0.1888,
+      "grad_norm": 0.08923039585351944,
+      "learning_rate": 0.0001673375123721544,
+      "loss": 0.11110665798187255,
+      "step": 1180
+    },
+    {
+      "epoch": 0.1904,
+      "grad_norm": 0.11190492659807205,
+      "learning_rate": 0.00016700758825470143,
+      "loss": 0.12069671154022217,
+      "step": 1190
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.09391149133443832,
+      "learning_rate": 0.00016667766413724843,
+      "loss": 0.10857542753219604,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1936,
+      "grad_norm": 0.09822124242782593,
+      "learning_rate": 0.00016634774001979545,
+      "loss": 0.11493276357650757,
+      "step": 1210
+    },
+    {
+      "epoch": 0.1952,
+      "grad_norm": 0.08219283819198608,
+      "learning_rate": 0.00016601781590234245,
+      "loss": 0.10868325233459472,
+      "step": 1220
+    },
+    {
+      "epoch": 0.1968,
+      "grad_norm": 0.1040310487151146,
+      "learning_rate": 0.00016568789178488948,
+      "loss": 0.10602080821990967,
+      "step": 1230
+    },
+    {
+      "epoch": 0.1984,
+      "grad_norm": 0.0804198682308197,
+      "learning_rate": 0.0001653579676674365,
+      "loss": 0.10579434633255005,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.08008287101984024,
+      "learning_rate": 0.0001650280435499835,
+      "loss": 0.10420469045639039,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2016,
+      "grad_norm": 0.08706449717283249,
+      "learning_rate": 0.00016469811943253053,
+      "loss": 0.10426139831542969,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2032,
+      "grad_norm": 0.10690020024776459,
+      "learning_rate": 0.00016436819531507756,
+      "loss": 0.10465244054794312,
+      "step": 1270
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 0.10291136056184769,
+      "learning_rate": 0.00016403827119762456,
+      "loss": 0.09800633192062377,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2064,
+      "grad_norm": 0.09384270757436752,
+      "learning_rate": 0.00016370834708017158,
+      "loss": 0.10762728452682495,
+      "step": 1290
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.09748148173093796,
+      "learning_rate": 0.00016337842296271858,
+      "loss": 0.10190448760986329,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2096,
+      "grad_norm": 0.08641976118087769,
+      "learning_rate": 0.0001630484988452656,
+      "loss": 0.10793905258178711,
+      "step": 1310
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 0.08845674246549606,
+      "learning_rate": 0.0001627185747278126,
+      "loss": 0.1030082106590271,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2128,
+      "grad_norm": 0.08985752612352371,
+      "learning_rate": 0.0001623886506103596,
+      "loss": 0.10357458591461181,
+      "step": 1330
+    },
+    {
+      "epoch": 0.2144,
+      "grad_norm": 0.11634411662817001,
+      "learning_rate": 0.00016205872649290663,
+      "loss": 0.10648585557937622,
+      "step": 1340
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.10860881209373474,
+      "learning_rate": 0.00016172880237545366,
+      "loss": 0.10430452823638917,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 0.10317538678646088,
+      "learning_rate": 0.00016139887825800066,
+      "loss": 0.10179120302200317,
+      "step": 1360
+    },
+    {
+      "epoch": 0.2192,
+      "grad_norm": 0.10053454339504242,
+      "learning_rate": 0.00016106895414054768,
+      "loss": 0.10597822666168213,
+      "step": 1370
+    },
+    {
+      "epoch": 0.2208,
+      "grad_norm": 0.08927279710769653,
+      "learning_rate": 0.00016073903002309468,
+      "loss": 0.09684351682662964,
+      "step": 1380
+    },
+    {
+      "epoch": 0.2224,
+      "grad_norm": 0.1257501095533371,
+      "learning_rate": 0.0001604091059056417,
+      "loss": 0.11261625289916992,
+      "step": 1390
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.1243852972984314,
+      "learning_rate": 0.00016007918178818873,
+      "loss": 0.10365232229232788,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2256,
+      "grad_norm": 0.10740727186203003,
+      "learning_rate": 0.00015974925767073573,
+      "loss": 0.10951308012008668,
+      "step": 1410
+    },
+    {
+      "epoch": 0.2272,
+      "grad_norm": 0.09918347746133804,
+      "learning_rate": 0.00015941933355328276,
+      "loss": 0.0985394537448883,
+      "step": 1420
+    },
+    {
+      "epoch": 0.2288,
+      "grad_norm": 0.08673065900802612,
+      "learning_rate": 0.00015908940943582978,
+      "loss": 0.09536778330802917,
+      "step": 1430
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 0.08423957228660583,
+      "learning_rate": 0.00015875948531837678,
+      "loss": 0.10208734273910522,
+      "step": 1440
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.08404131233692169,
+      "learning_rate": 0.0001584295612009238,
+      "loss": 0.11047152280807496,
+      "step": 1450
+    },
+    {
+      "epoch": 0.2336,
+      "grad_norm": 0.09844925999641418,
+      "learning_rate": 0.0001580996370834708,
+      "loss": 0.10863144397735595,
+      "step": 1460
+    },
+    {
+      "epoch": 0.2352,
+      "grad_norm": 0.0969533696770668,
+      "learning_rate": 0.0001577697129660178,
+      "loss": 0.10357078313827514,
+      "step": 1470
+    },
+    {
+      "epoch": 0.2368,
+      "grad_norm": 0.09240443259477615,
+      "learning_rate": 0.00015743978884856483,
+      "loss": 0.1025089144706726,
+      "step": 1480
+    },
+    {
+      "epoch": 0.2384,
+      "grad_norm": 0.08052058517932892,
+      "learning_rate": 0.00015710986473111183,
+      "loss": 0.10557924509048462,
+      "step": 1490
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.08213961869478226,
+      "learning_rate": 0.00015677994061365886,
+      "loss": 0.10791049003601075,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.807714853021389e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed93101d13d46ec2b94df4a195ead1ab1926ae11f6e1c8538f6892278001ce9
+size 5713