Upload folder using huggingface_hub

.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 +1,202 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: peft
+---
+
+# 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 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-4b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "model.language_model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj",
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76152cc994f4920b5295343a85cdef14d16eecc5d5c7d92fb3f90a6becf0ccfb
+size 953752328

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,143 @@
+{#- Begin-of-sequence token to start the model prompt -#}
+{{ bos_token }}
+{#- Extracts the system message. Gemma does not support system messages so it will be prepended to first user message. -#}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set system_message = messages[0]['content'] -%}
+    {%- else -%}
+        {%- set system_message = messages[0]['content'][0]['text'] -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set system_message = "You are a helpful assistant Zero-Gemma made by ZeroAgency company from Russia. You must be helpful, harmless, and honest." -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+
+{%- if enable_thinking is defined and enable_thinking is true -%}
+    {%- set system_message = system_message + "\nFirst, think through the reasoning internally, then present the reasoning within <think>...</think>. After thinking, clearly state a response that addresses the user's request and aligns with their preferences, not just providing a direct answer." -%}
+{%- endif -%}
+
+{%- set system_message = system_message + '\n\n' -%}
+{#- Set tools to none if not defined for this ChatCompletion request (helps avoid errors later) -#}
+{%- if not tools is defined -%}
+    {%- set tools = none -%}
+{%- endif -%}
+
+{#- First - system message -#}
+
+{{ '<start_of_turn>system\n' -}}
+{{ system_message }}
+{#- Append system message with tool information if using tools in message request. -#}
+{%- if tools is not none -%}
+    {{- "Tools (functions) are available. If you decide to invoke one or more of the tools, you must respond with a python list of the function calls.\n" -}}
+    {{- "Example Format: [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)] \n" -}}
+    {{- "Do not use variables. DO NOT USE MARKDOWN SYNTAX. You SHOULD NOT include any other text in the response if you call a function. If none of the functions can be used, point it out. If you lack the parameters required by the function, also point it out.\n" -}}
+    {{- "Here is a list of functions in JSON format that you can invoke.\n" -}}
+    {{- tools | tojson(indent=4) -}}
+    {{- "\n\n" -}}
+{%- endif -%}
+{{ '<end_of_turn>\n' }}
+
+{#- Main loop over all messages in the conversation history -#}
+{%- for message in loop_messages if message['role'] != 'system' -%}
+    {#- Normalize roles for model prompt formatting -#}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- elif (message['role'] == 'tool') -%}
+        {%- set role = "user" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {#- Mark the start of a message block with the appropriate role -#}
+    {{ '<start_of_turn>' + role + '\n' -}}
+
+    {#- Format model tool calls (turns where model indicates they want to call a tool) -#}
+    {%- if 'tool_calls' in message -%}
+        {%- if message['content'] is string -%}
+            {%- set content = message['content'] -%}
+            {# {%- if '</think>' in content -%} #}
+            {{- content | trim -}}
+            {# {{- "\n" -}} #}
+            {# {%- endif -%} #}
+        {%- endif -%}
+        {#- Opening bracket for tool call list. -#}
+        {{- '[' -}}
+        {#- For each tool call -#}
+        {%- for tool_call in message.tool_calls -%}
+            {#- Function name & opening parenthesis. -#}
+            {%- if tool_call.function is defined -%}
+                {%- set tool_call = tool_call.function -%}
+            {%- endif -%}
+            {{- tool_call.name + '(' -}}
+
+            {#-- Handle arguments as list (positional) or dict (named) --#}
+            {#-- Named arguments (dict) --#}
+            {%- if tool_call.arguments is iterable and tool_call.arguments is mapping -%}
+                {%- set first = true -%}
+                {%- for key, val in tool_call.arguments.items() -%}
+                    {%- if not first %}, {% endif -%}
+                    {{ key }}={{ val | tojson }}
+                    {%- set first = false -%}
+                {%- endfor -%}
+            {#-- Positional arguments (list) --#}
+            {%- elif tool_call.arguments is iterable -%}
+                {{- tool_call.arguments | map('tojson') | join(', ') -}}
+            {#-- Fallback: single positional value --#}
+            {%- else -%}
+                {{- tool_call.arguments | tojson -}}
+            {#-- Closing parenthesis. --#}
+            {%- endif -%}
+                {{- ')' -}}
+            {#-- If more than one tool call, place comma and move to formatting next tool call --#}
+            {%- if not loop.last -%}{{- "," -}}{%- endif -%}
+        {%- endfor -%}
+        {#- Closing bracket for tool call list. -#}
+        {{- ']' -}}
+    {%- endif -%}
+    
+    {#- Tool response start tag (for messages from a tool) -#}
+    {%- if (message['role'] == 'tool') -%}
+        {{- '<tool_response>\n' -}}
+    {%- endif -%}
+
+    {#- Render the message content: handle plain string or multimodal content like image/text -#}
+    {%- if not 'tool_calls' in message and message['content'] -%}
+        {%- if message['content'] is string -%}
+            {%- set content = message['content'] -%}
+            {# {%- if '</think>' in content -%}
+                {%- set content = content.split('</think>')[-1] -%}
+            {%- endif -%} #}
+            {{- content | trim -}}
+        {%- elif message['content'] is iterable -%}
+            {%- for item in message['content'] -%}
+                {%- if item['type'] == 'image' -%}
+                    {{ '<start_of_image>' }}
+                {%- elif item['type'] == 'text' -%}
+                    {%- set content = item['text'] -%}
+                    {# {%- if '</think>' in content -%}
+                        {%- set content = content.split('</think>')[-1] -%}
+                    {%- endif -%} #}
+                    {{ content | trim }}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- else -%}
+            {{ raise_exception("Invalid content type:"+ message|tojson) }}
+        {%- endif -%}
+    {%- endif -%}
+
+    {#- Tool response end tag -#}
+    {%- if (message['role'] == 'tool') -%}
+        {{ '</tool_response>' -}}
+    {%- endif -%}
+
+    {#- Mark end of a single turn -#}
+    {{ '<end_of_turn>\n' }}
+{%- endfor -%}
+
+{#- If generation is to be triggered, add model prompt prefix -#}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model\n'}}
+    {%- if enable_thinking is defined and enable_thinking is true -%}
+        {{- '<think>' -}}
+    {%- endif %}
+{%- endif -%}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

trainer_state.json

@@ -0,0 +1,1644 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004347826086956522,
+      "grad_norm": 209.3180389404297,
+      "learning_rate": 0.0,
+      "loss": 5.8188,
+      "step": 1
+    },
+    {
+      "epoch": 0.008695652173913044,
+      "grad_norm": 215.69874572753906,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 5.9259,
+      "step": 2
+    },
+    {
+      "epoch": 0.013043478260869565,
+      "grad_norm": 62.712825775146484,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 5.4202,
+      "step": 3
+    },
+    {
+      "epoch": 0.017391304347826087,
+      "grad_norm": 85.59194946289062,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 5.3079,
+      "step": 4
+    },
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 22.901897430419922,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 5.0196,
+      "step": 5
+    },
+    {
+      "epoch": 0.02608695652173913,
+      "grad_norm": 22.081829071044922,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 4.8222,
+      "step": 6
+    },
+    {
+      "epoch": 0.030434782608695653,
+      "grad_norm": 11.022245407104492,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 4.4617,
+      "step": 7
+    },
+    {
+      "epoch": 0.034782608695652174,
+      "grad_norm": 7.274469375610352,
+      "learning_rate": 3.0434782608695656e-05,
+      "loss": 4.335,
+      "step": 8
+    },
+    {
+      "epoch": 0.0391304347826087,
+      "grad_norm": 3.8645834922790527,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 4.0476,
+      "step": 9
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 2.6724016666412354,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 3.8387,
+      "step": 10
+    },
+    {
+      "epoch": 0.04782608695652174,
+      "grad_norm": 2.258195161819458,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 3.8144,
+      "step": 11
+    },
+    {
+      "epoch": 0.05217391304347826,
+      "grad_norm": 1.8822625875473022,
+      "learning_rate": 4.782608695652174e-05,
+      "loss": 3.4008,
+      "step": 12
+    },
+    {
+      "epoch": 0.05652173913043478,
+      "grad_norm": 2.047840118408203,
+      "learning_rate": 5.217391304347826e-05,
+      "loss": 3.2554,
+      "step": 13
+    },
+    {
+      "epoch": 0.06086956521739131,
+      "grad_norm": 1.8671568632125854,
+      "learning_rate": 5.652173913043478e-05,
+      "loss": 3.2461,
+      "step": 14
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 1.6069483757019043,
+      "learning_rate": 6.086956521739131e-05,
+      "loss": 2.9738,
+      "step": 15
+    },
+    {
+      "epoch": 0.06956521739130435,
+      "grad_norm": 1.3096915483474731,
+      "learning_rate": 6.521739130434783e-05,
+      "loss": 2.7823,
+      "step": 16
+    },
+    {
+      "epoch": 0.07391304347826087,
+      "grad_norm": 1.3594956398010254,
+      "learning_rate": 6.956521739130436e-05,
+      "loss": 2.6255,
+      "step": 17
+    },
+    {
+      "epoch": 0.0782608695652174,
+      "grad_norm": 1.0210895538330078,
+      "learning_rate": 7.391304347826086e-05,
+      "loss": 2.4501,
+      "step": 18
+    },
+    {
+      "epoch": 0.08260869565217391,
+      "grad_norm": 0.8942164182662964,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 2.2934,
+      "step": 19
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.8361735343933105,
+      "learning_rate": 8.260869565217392e-05,
+      "loss": 2.2029,
+      "step": 20
+    },
+    {
+      "epoch": 0.09130434782608696,
+      "grad_norm": 0.794482409954071,
+      "learning_rate": 8.695652173913044e-05,
+      "loss": 2.0223,
+      "step": 21
+    },
+    {
+      "epoch": 0.09565217391304348,
+      "grad_norm": 0.7513137459754944,
+      "learning_rate": 9.130434782608696e-05,
+      "loss": 1.8504,
+      "step": 22
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.76312655210495,
+      "learning_rate": 9.565217391304348e-05,
+      "loss": 1.6577,
+      "step": 23
+    },
+    {
+      "epoch": 0.10434782608695652,
+      "grad_norm": 0.8560758829116821,
+      "learning_rate": 0.0001,
+      "loss": 1.5565,
+      "step": 24
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 0.7479954957962036,
+      "learning_rate": 0.00010434782608695653,
+      "loss": 1.4364,
+      "step": 25
+    },
+    {
+      "epoch": 0.11304347826086956,
+      "grad_norm": 0.5951140522956848,
+      "learning_rate": 0.00010869565217391305,
+      "loss": 1.2957,
+      "step": 26
+    },
+    {
+      "epoch": 0.11739130434782609,
+      "grad_norm": 0.503224790096283,
+      "learning_rate": 0.00011304347826086956,
+      "loss": 1.1799,
+      "step": 27
+    },
+    {
+      "epoch": 0.12173913043478261,
+      "grad_norm": 0.47480374574661255,
+      "learning_rate": 0.0001173913043478261,
+      "loss": 1.1277,
+      "step": 28
+    },
+    {
+      "epoch": 0.12608695652173912,
+      "grad_norm": 0.38552260398864746,
+      "learning_rate": 0.00012173913043478263,
+      "loss": 1.0744,
+      "step": 29
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.35596558451652527,
+      "learning_rate": 0.00012608695652173915,
+      "loss": 1.0023,
+      "step": 30
+    },
+    {
+      "epoch": 0.13478260869565217,
+      "grad_norm": 0.32971665263175964,
+      "learning_rate": 0.00013043478260869567,
+      "loss": 0.9691,
+      "step": 31
+    },
+    {
+      "epoch": 0.1391304347826087,
+      "grad_norm": 0.37770169973373413,
+      "learning_rate": 0.0001347826086956522,
+      "loss": 0.9116,
+      "step": 32
+    },
+    {
+      "epoch": 0.14347826086956522,
+      "grad_norm": 0.22640736401081085,
+      "learning_rate": 0.0001391304347826087,
+      "loss": 0.8613,
+      "step": 33
+    },
+    {
+      "epoch": 0.14782608695652175,
+      "grad_norm": 0.20925410091876984,
+      "learning_rate": 0.0001434782608695652,
+      "loss": 0.8836,
+      "step": 34
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 0.20542123913764954,
+      "learning_rate": 0.00014782608695652173,
+      "loss": 0.8502,
+      "step": 35
+    },
+    {
+      "epoch": 0.1565217391304348,
+      "grad_norm": 0.16715222597122192,
+      "learning_rate": 0.00015217391304347827,
+      "loss": 0.8292,
+      "step": 36
+    },
+    {
+      "epoch": 0.1608695652173913,
+      "grad_norm": 0.1648133248090744,
+      "learning_rate": 0.0001565217391304348,
+      "loss": 0.8189,
+      "step": 37
+    },
+    {
+      "epoch": 0.16521739130434782,
+      "grad_norm": 0.13562779128551483,
+      "learning_rate": 0.00016086956521739132,
+      "loss": 0.8078,
+      "step": 38
+    },
+    {
+      "epoch": 0.16956521739130434,
+      "grad_norm": 0.1290610432624817,
+      "learning_rate": 0.00016521739130434784,
+      "loss": 0.7712,
+      "step": 39
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.11024343967437744,
+      "learning_rate": 0.00016956521739130436,
+      "loss": 0.7448,
+      "step": 40
+    },
+    {
+      "epoch": 0.1782608695652174,
+      "grad_norm": 0.12418993562459946,
+      "learning_rate": 0.00017391304347826088,
+      "loss": 0.7633,
+      "step": 41
+    },
+    {
+      "epoch": 0.1826086956521739,
+      "grad_norm": 0.10319849103689194,
+      "learning_rate": 0.0001782608695652174,
+      "loss": 0.7463,
+      "step": 42
+    },
+    {
+      "epoch": 0.18695652173913044,
+      "grad_norm": 0.10371455550193787,
+      "learning_rate": 0.00018260869565217392,
+      "loss": 0.7516,
+      "step": 43
+    },
+    {
+      "epoch": 0.19130434782608696,
+      "grad_norm": 0.09219090640544891,
+      "learning_rate": 0.00018695652173913045,
+      "loss": 0.7265,
+      "step": 44
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 0.09577666968107224,
+      "learning_rate": 0.00019130434782608697,
+      "loss": 0.7382,
+      "step": 45
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.08755916357040405,
+      "learning_rate": 0.0001956521739130435,
+      "loss": 0.7392,
+      "step": 46
+    },
+    {
+      "epoch": 0.20434782608695654,
+      "grad_norm": 0.08335893601179123,
+      "learning_rate": 0.0002,
+      "loss": 0.7182,
+      "step": 47
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 0.08622466027736664,
+      "learning_rate": 0.00019999712083215463,
+      "loss": 0.7196,
+      "step": 48
+    },
+    {
+      "epoch": 0.21304347826086956,
+      "grad_norm": 0.07222707569599152,
+      "learning_rate": 0.00019998848349441062,
+      "loss": 0.7014,
+      "step": 49
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.07286012172698975,
+      "learning_rate": 0.00019997408848413493,
+      "loss": 0.6986,
+      "step": 50
+    },
+    {
+      "epoch": 0.2217391304347826,
+      "grad_norm": 0.07811558246612549,
+      "learning_rate": 0.00019995393663024054,
+      "loss": 0.6922,
+      "step": 51
+    },
+    {
+      "epoch": 0.22608695652173913,
+      "grad_norm": 0.07095416635274887,
+      "learning_rate": 0.0001999280290931388,
+      "loss": 0.7188,
+      "step": 52
+    },
+    {
+      "epoch": 0.23043478260869565,
+      "grad_norm": 0.0705651044845581,
+      "learning_rate": 0.00019989636736467278,
+      "loss": 0.7135,
+      "step": 53
+    },
+    {
+      "epoch": 0.23478260869565218,
+      "grad_norm": 0.0649741142988205,
+      "learning_rate": 0.00019985895326803097,
+      "loss": 0.6833,
+      "step": 54
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 0.07023416459560394,
+      "learning_rate": 0.00019981578895764273,
+      "loss": 0.6902,
+      "step": 55
+    },
+    {
+      "epoch": 0.24347826086956523,
+      "grad_norm": 0.065043605864048,
+      "learning_rate": 0.00019976687691905393,
+      "loss": 0.6933,
+      "step": 56
+    },
+    {
+      "epoch": 0.24782608695652175,
+      "grad_norm": 0.0647321566939354,
+      "learning_rate": 0.00019971221996878394,
+      "loss": 0.6946,
+      "step": 57
+    },
+    {
+      "epoch": 0.25217391304347825,
+      "grad_norm": 0.08214448392391205,
+      "learning_rate": 0.0001996518212541634,
+      "loss": 0.6789,
+      "step": 58
+    },
+    {
+      "epoch": 0.2565217391304348,
+      "grad_norm": 0.06106014922261238,
+      "learning_rate": 0.00019958568425315314,
+      "loss": 0.6826,
+      "step": 59
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.06052952632308006,
+      "learning_rate": 0.0001995138127741436,
+      "loss": 0.6706,
+      "step": 60
+    },
+    {
+      "epoch": 0.26521739130434785,
+      "grad_norm": 0.06265316903591156,
+      "learning_rate": 0.00019943621095573586,
+      "loss": 0.6809,
+      "step": 61
+    },
+    {
+      "epoch": 0.26956521739130435,
+      "grad_norm": 0.0603368878364563,
+      "learning_rate": 0.00019935288326650312,
+      "loss": 0.6728,
+      "step": 62
+    },
+    {
+      "epoch": 0.27391304347826084,
+      "grad_norm": 0.06611189991235733,
+      "learning_rate": 0.00019926383450473344,
+      "loss": 0.6499,
+      "step": 63
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 0.06278355419635773,
+      "learning_rate": 0.00019916906979815347,
+      "loss": 0.6561,
+      "step": 64
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 0.07379094511270523,
+      "learning_rate": 0.00019906859460363307,
+      "loss": 0.6786,
+      "step": 65
+    },
+    {
+      "epoch": 0.28695652173913044,
+      "grad_norm": 0.09574166685342789,
+      "learning_rate": 0.0001989624147068713,
+      "loss": 0.6625,
+      "step": 66
+    },
+    {
+      "epoch": 0.29130434782608694,
+      "grad_norm": 0.08743462711572647,
+      "learning_rate": 0.00019885053622206304,
+      "loss": 0.648,
+      "step": 67
+    },
+    {
+      "epoch": 0.2956521739130435,
+      "grad_norm": 0.08914034813642502,
+      "learning_rate": 0.00019873296559154698,
+      "loss": 0.6561,
+      "step": 68
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.06804706901311874,
+      "learning_rate": 0.0001986097095854347,
+      "loss": 0.658,
+      "step": 69
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.09893489629030228,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.6708,
+      "step": 70
+    },
+    {
+      "epoch": 0.30869565217391304,
+      "grad_norm": 0.07928409427404404,
+      "learning_rate": 0.0001983461701633742,
+      "loss": 0.6407,
+      "step": 71
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 0.07455449551343918,
+      "learning_rate": 0.0001982059019229106,
+      "loss": 0.676,
+      "step": 72
+    },
+    {
+      "epoch": 0.3173913043478261,
+      "grad_norm": 0.0770968496799469,
+      "learning_rate": 0.00019805997865694614,
+      "loss": 0.6639,
+      "step": 73
+    },
+    {
+      "epoch": 0.3217391304347826,
+      "grad_norm": 0.06771919876337051,
+      "learning_rate": 0.00019790840876823232,
+      "loss": 0.6486,
+      "step": 74
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 0.07457810640335083,
+      "learning_rate": 0.0001977512009846721,
+      "loss": 0.6681,
+      "step": 75
+    },
+    {
+      "epoch": 0.33043478260869563,
+      "grad_norm": 0.0826922208070755,
+      "learning_rate": 0.00019758836435881746,
+      "loss": 0.6356,
+      "step": 76
+    },
+    {
+      "epoch": 0.3347826086956522,
+      "grad_norm": 0.07923886179924011,
+      "learning_rate": 0.00019741990826734794,
+      "loss": 0.6682,
+      "step": 77
+    },
+    {
+      "epoch": 0.3391304347826087,
+      "grad_norm": 0.11045071482658386,
+      "learning_rate": 0.0001972458424105307,
+      "loss": 0.6203,
+      "step": 78
+    },
+    {
+      "epoch": 0.34347826086956523,
+      "grad_norm": 0.11731227487325668,
+      "learning_rate": 0.00019706617681166218,
+      "loss": 0.66,
+      "step": 79
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.12649305164813995,
+      "learning_rate": 0.00019688092181649065,
+      "loss": 0.6613,
+      "step": 80
+    },
+    {
+      "epoch": 0.3521739130434783,
+      "grad_norm": 0.1144268661737442,
+      "learning_rate": 0.00019669008809262062,
+      "loss": 0.6606,
+      "step": 81
+    },
+    {
+      "epoch": 0.3565217391304348,
+      "grad_norm": 0.11361440271139145,
+      "learning_rate": 0.00019649368662889855,
+      "loss": 0.629,
+      "step": 82
+    },
+    {
+      "epoch": 0.36086956521739133,
+      "grad_norm": 0.12539249658584595,
+      "learning_rate": 0.00019629172873477995,
+      "loss": 0.6676,
+      "step": 83
+    },
+    {
+      "epoch": 0.3652173913043478,
+      "grad_norm": 0.11141279339790344,
+      "learning_rate": 0.00019608422603967836,
+      "loss": 0.6376,
+      "step": 84
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 0.09837634861469269,
+      "learning_rate": 0.00019587119049229557,
+      "loss": 0.6503,
+      "step": 85
+    },
+    {
+      "epoch": 0.3739130434782609,
+      "grad_norm": 0.15677575767040253,
+      "learning_rate": 0.0001956526343599335,
+      "loss": 0.6638,
+      "step": 86
+    },
+    {
+      "epoch": 0.3782608695652174,
+      "grad_norm": 0.252825528383255,
+      "learning_rate": 0.0001954285702277879,
+      "loss": 0.6713,
+      "step": 87
+    },
+    {
+      "epoch": 0.3826086956521739,
+      "grad_norm": 0.3602813482284546,
+      "learning_rate": 0.00019519901099822372,
+      "loss": 0.6596,
+      "step": 88
+    },
+    {
+      "epoch": 0.3869565217391304,
+      "grad_norm": 0.3970949053764343,
+      "learning_rate": 0.00019496396989003193,
+      "loss": 0.6617,
+      "step": 89
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.284343421459198,
+      "learning_rate": 0.00019472346043766865,
+      "loss": 0.6229,
+      "step": 90
+    },
+    {
+      "epoch": 0.39565217391304347,
+      "grad_norm": 0.19832171499729156,
+      "learning_rate": 0.00019447749649047542,
+      "loss": 0.6665,
+      "step": 91
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.24541743099689484,
+      "learning_rate": 0.00019422609221188207,
+      "loss": 0.6585,
+      "step": 92
+    },
+    {
+      "epoch": 0.4043478260869565,
+      "grad_norm": 0.1915537267923355,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.6343,
+      "step": 93
+    },
+    {
+      "epoch": 0.40869565217391307,
+      "grad_norm": 0.20492875576019287,
+      "learning_rate": 0.00019370702087974302,
+      "loss": 0.6438,
+      "step": 94
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 0.25835996866226196,
+      "learning_rate": 0.00019343938371606712,
+      "loss": 0.6502,
+      "step": 95
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 0.2585464417934418,
+      "learning_rate": 0.00019316636599900946,
+      "loss": 0.6393,
+      "step": 96
+    },
+    {
+      "epoch": 0.4217391304347826,
+      "grad_norm": 0.2317182868719101,
+      "learning_rate": 0.00019288798344984672,
+      "loss": 0.6275,
+      "step": 97
+    },
+    {
+      "epoch": 0.4260869565217391,
+      "grad_norm": 0.23632416129112244,
+      "learning_rate": 0.00019260425209878052,
+      "loss": 0.6414,
+      "step": 98
+    },
+    {
+      "epoch": 0.43043478260869567,
+      "grad_norm": 0.1801244169473648,
+      "learning_rate": 0.00019231518828401458,
+      "loss": 0.6491,
+      "step": 99
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.24871514737606049,
+      "learning_rate": 0.00019202080865081368,
+      "loss": 0.6581,
+      "step": 100
+    },
+    {
+      "epoch": 0.4391304347826087,
+      "grad_norm": 0.26276353001594543,
+      "learning_rate": 0.00019172113015054532,
+      "loss": 0.644,
+      "step": 101
+    },
+    {
+      "epoch": 0.4434782608695652,
+      "grad_norm": 0.19743724167346954,
+      "learning_rate": 0.0001914161700397035,
+      "loss": 0.6519,
+      "step": 102
+    },
+    {
+      "epoch": 0.44782608695652176,
+      "grad_norm": 0.31385916471481323,
+      "learning_rate": 0.00019110594587891519,
+      "loss": 0.6462,
+      "step": 103
+    },
+    {
+      "epoch": 0.45217391304347826,
+      "grad_norm": 0.2689647674560547,
+      "learning_rate": 0.0001907904755319289,
+      "loss": 0.6517,
+      "step": 104
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 0.17245543003082275,
+      "learning_rate": 0.00019046977716458626,
+      "loss": 0.6245,
+      "step": 105
+    },
+    {
+      "epoch": 0.4608695652173913,
+      "grad_norm": 0.4380849003791809,
+      "learning_rate": 0.00019014386924377582,
+      "loss": 0.6519,
+      "step": 106
+    },
+    {
+      "epoch": 0.4652173913043478,
+      "grad_norm": 0.305043488740921,
+      "learning_rate": 0.0001898127705363696,
+      "loss": 0.6606,
+      "step": 107
+    },
+    {
+      "epoch": 0.46956521739130436,
+      "grad_norm": 0.20340269804000854,
+      "learning_rate": 0.0001894765001081428,
+      "loss": 0.6359,
+      "step": 108
+    },
+    {
+      "epoch": 0.47391304347826085,
+      "grad_norm": 0.15703125298023224,
+      "learning_rate": 0.0001891350773226754,
+      "loss": 0.6461,
+      "step": 109
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.16932646930217743,
+      "learning_rate": 0.0001887885218402375,
+      "loss": 0.6413,
+      "step": 110
+    },
+    {
+      "epoch": 0.4826086956521739,
+      "grad_norm": 0.1790553480386734,
+      "learning_rate": 0.00018843685361665723,
+      "loss": 0.6378,
+      "step": 111
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 0.24903282523155212,
+      "learning_rate": 0.00018808009290217136,
+      "loss": 0.6308,
+      "step": 112
+    },
+    {
+      "epoch": 0.49130434782608695,
+      "grad_norm": 0.20529182255268097,
+      "learning_rate": 0.00018771826024025946,
+      "loss": 0.6315,
+      "step": 113
+    },
+    {
+      "epoch": 0.4956521739130435,
+      "grad_norm": 0.18206629157066345,
+      "learning_rate": 0.00018735137646646078,
+      "loss": 0.6409,
+      "step": 114
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.22906547784805298,
+      "learning_rate": 0.00018697946270717467,
+      "loss": 0.6522,
+      "step": 115
+    },
+    {
+      "epoch": 0.5043478260869565,
+      "grad_norm": 0.23560722172260284,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.6424,
+      "step": 116
+    },
+    {
+      "epoch": 0.508695652173913,
+      "grad_norm": 0.3479248881340027,
+      "learning_rate": 0.00018622063118472134,
+      "loss": 0.6591,
+      "step": 117
+    },
+    {
+      "epoch": 0.5130434782608696,
+      "grad_norm": 0.48405924439430237,
+      "learning_rate": 0.00018583375711762052,
+      "loss": 0.6312,
+      "step": 118
+    },
+    {
+      "epoch": 0.5173913043478261,
+      "grad_norm": 0.6660999655723572,
+      "learning_rate": 0.00018544194045464886,
+      "loss": 0.6492,
+      "step": 119
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.6070662140846252,
+      "learning_rate": 0.0001850452037579251,
+      "loss": 0.631,
+      "step": 120
+    },
+    {
+      "epoch": 0.5260869565217391,
+      "grad_norm": 0.2432556301355362,
+      "learning_rate": 0.00018464356987288013,
+      "loss": 0.6192,
+      "step": 121
+    },
+    {
+      "epoch": 0.5304347826086957,
+      "grad_norm": 0.4718700647354126,
+      "learning_rate": 0.00018423706192694116,
+      "loss": 0.6385,
+      "step": 122
+    },
+    {
+      "epoch": 0.5347826086956522,
+      "grad_norm": 0.41220200061798096,
+      "learning_rate": 0.00018382570332820043,
+      "loss": 0.6362,
+      "step": 123
+    },
+    {
+      "epoch": 0.5391304347826087,
+      "grad_norm": 0.24313992261886597,
+      "learning_rate": 0.00018340951776406694,
+      "loss": 0.659,
+      "step": 124
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.42307668924331665,
+      "learning_rate": 0.00018298852919990252,
+      "loss": 0.6484,
+      "step": 125
+    },
+    {
+      "epoch": 0.5478260869565217,
+      "grad_norm": 0.2858572006225586,
+      "learning_rate": 0.00018256276187764197,
+      "loss": 0.6437,
+      "step": 126
+    },
+    {
+      "epoch": 0.5521739130434783,
+      "grad_norm": 0.2318851351737976,
+      "learning_rate": 0.0001821322403143969,
+      "loss": 0.6191,
+      "step": 127
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 0.3861188292503357,
+      "learning_rate": 0.0001816969893010442,
+      "loss": 0.639,
+      "step": 128
+    },
+    {
+      "epoch": 0.5608695652173913,
+      "grad_norm": 0.2969801127910614,
+      "learning_rate": 0.0001812570339007983,
+      "loss": 0.6624,
+      "step": 129
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 0.29341548681259155,
+      "learning_rate": 0.00018081239944776805,
+      "loss": 0.639,
+      "step": 130
+    },
+    {
+      "epoch": 0.5695652173913044,
+      "grad_norm": 0.43678849935531616,
+      "learning_rate": 0.00018036311154549784,
+      "loss": 0.6384,
+      "step": 131
+    },
+    {
+      "epoch": 0.5739130434782609,
+      "grad_norm": 0.5248069167137146,
+      "learning_rate": 0.00017990919606549328,
+      "loss": 0.6451,
+      "step": 132
+    },
+    {
+      "epoch": 0.5782608695652174,
+      "grad_norm": 0.5387030243873596,
+      "learning_rate": 0.00017945067914573146,
+      "loss": 0.6198,
+      "step": 133
+    },
+    {
+      "epoch": 0.5826086956521739,
+      "grad_norm": 0.55666184425354,
+      "learning_rate": 0.00017898758718915586,
+      "loss": 0.6391,
+      "step": 134
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.4839560389518738,
+      "learning_rate": 0.0001785199468621559,
+      "loss": 0.6411,
+      "step": 135
+    },
+    {
+      "epoch": 0.591304347826087,
+      "grad_norm": 0.5173195004463196,
+      "learning_rate": 0.00017804778509303138,
+      "loss": 0.6318,
+      "step": 136
+    },
+    {
+      "epoch": 0.5956521739130435,
+      "grad_norm": 0.341448038816452,
+      "learning_rate": 0.000177571129070442,
+      "loss": 0.6427,
+      "step": 137
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2654604911804199,
+      "learning_rate": 0.00017709000624184162,
+      "loss": 0.616,
+      "step": 138
+    },
+    {
+      "epoch": 0.6043478260869565,
+      "grad_norm": 0.4000408351421356,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.611,
+      "step": 139
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.2812383770942688,
+      "learning_rate": 0.00017611447124089649,
+      "loss": 0.6508,
+      "step": 140
+    },
+    {
+      "epoch": 0.6130434782608696,
+      "grad_norm": 0.30483949184417725,
+      "learning_rate": 0.00017562011524313185,
+      "loss": 0.6628,
+      "step": 141
+    },
+    {
+      "epoch": 0.6173913043478261,
+      "grad_norm": 0.4457907974720001,
+      "learning_rate": 0.0001751214047852818,
+      "loss": 0.6274,
+      "step": 142
+    },
+    {
+      "epoch": 0.6217391304347826,
+      "grad_norm": 0.38395488262176514,
+      "learning_rate": 0.00017461836858476856,
+      "loss": 0.6528,
+      "step": 143
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 0.573344886302948,
+      "learning_rate": 0.00017411103560810526,
+      "loss": 0.6504,
+      "step": 144
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 0.5133661031723022,
+      "learning_rate": 0.00017359943506922774,
+      "loss": 0.6334,
+      "step": 145
+    },
+    {
+      "epoch": 0.6347826086956522,
+      "grad_norm": 0.2995568513870239,
+      "learning_rate": 0.00017308359642781242,
+      "loss": 0.6328,
+      "step": 146
+    },
+    {
+      "epoch": 0.6391304347826087,
+      "grad_norm": 0.5677820444107056,
+      "learning_rate": 0.0001725635493875799,
+      "loss": 0.639,
+      "step": 147
+    },
+    {
+      "epoch": 0.6434782608695652,
+      "grad_norm": 0.4751092791557312,
+      "learning_rate": 0.00017203932389458454,
+      "loss": 0.6229,
+      "step": 148
+    },
+    {
+      "epoch": 0.6478260869565218,
+      "grad_norm": 0.4374710023403168,
+      "learning_rate": 0.00017151095013548994,
+      "loss": 0.6377,
+      "step": 149
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.4172927439212799,
+      "learning_rate": 0.0001709784585358309,
+      "loss": 0.6277,
+      "step": 150
+    },
+    {
+      "epoch": 0.6565217391304348,
+      "grad_norm": 0.3994798958301544,
+      "learning_rate": 0.00017044187975826124,
+      "loss": 0.637,
+      "step": 151
+    },
+    {
+      "epoch": 0.6608695652173913,
+      "grad_norm": 0.34366917610168457,
+      "learning_rate": 0.00016990124470078822,
+      "loss": 0.6556,
+      "step": 152
+    },
+    {
+      "epoch": 0.6652173913043479,
+      "grad_norm": 0.533347487449646,
+      "learning_rate": 0.0001693565844949933,
+      "loss": 0.6073,
+      "step": 153
+    },
+    {
+      "epoch": 0.6695652173913044,
+      "grad_norm": 0.4292946457862854,
+      "learning_rate": 0.0001688079305042395,
+      "loss": 0.6548,
+      "step": 154
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 0.2770076394081116,
+      "learning_rate": 0.00016825531432186543,
+      "loss": 0.6014,
+      "step": 155
+    },
+    {
+      "epoch": 0.6782608695652174,
+      "grad_norm": 0.377838134765625,
+      "learning_rate": 0.0001676987677693659,
+      "loss": 0.6406,
+      "step": 156
+    },
+    {
+      "epoch": 0.6826086956521739,
+      "grad_norm": 0.421268492937088,
+      "learning_rate": 0.0001671383228945597,
+      "loss": 0.6288,
+      "step": 157
+    },
+    {
+      "epoch": 0.6869565217391305,
+      "grad_norm": 0.4219221770763397,
+      "learning_rate": 0.00016657401196974405,
+      "loss": 0.647,
+      "step": 158
+    },
+    {
+      "epoch": 0.691304347826087,
+      "grad_norm": 0.3563760221004486,
+      "learning_rate": 0.00016600586748983641,
+      "loss": 0.6307,
+      "step": 159
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.39387866854667664,
+      "learning_rate": 0.00016543392217050314,
+      "loss": 0.631,
+      "step": 160
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.36268243193626404,
+      "learning_rate": 0.0001648582089462756,
+      "loss": 0.6429,
+      "step": 161
+    },
+    {
+      "epoch": 0.7043478260869566,
+      "grad_norm": 0.3702019155025482,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.6338,
+      "step": 162
+    },
+    {
+      "epoch": 0.7086956521739131,
+      "grad_norm": 0.44408297538757324,
+      "learning_rate": 0.00016369561160419784,
+      "loss": 0.6416,
+      "step": 163
+    },
+    {
+      "epoch": 0.7130434782608696,
+      "grad_norm": 0.5986080765724182,
+      "learning_rate": 0.00016310879443260528,
+      "loss": 0.6187,
+      "step": 164
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.7963016629219055,
+      "learning_rate": 0.0001625183432447789,
+      "loss": 0.6365,
+      "step": 165
+    },
+    {
+      "epoch": 0.7217391304347827,
+      "grad_norm": 1.2156025171279907,
+      "learning_rate": 0.0001619242920408802,
+      "loss": 0.6625,
+      "step": 166
+    },
+    {
+      "epoch": 0.7260869565217392,
+      "grad_norm": 0.7924716472625732,
+      "learning_rate": 0.00016132667502837165,
+      "loss": 0.6276,
+      "step": 167
+    },
+    {
+      "epoch": 0.7304347826086957,
+      "grad_norm": 0.29551273584365845,
+      "learning_rate": 0.00016072552662004696,
+      "loss": 0.6159,
+      "step": 168
+    },
+    {
+      "epoch": 0.7347826086956522,
+      "grad_norm": 0.7566269040107727,
+      "learning_rate": 0.00016012088143204953,
+      "loss": 0.6485,
+      "step": 169
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 1.001354455947876,
+      "learning_rate": 0.00015951277428187898,
+      "loss": 0.6323,
+      "step": 170
+    },
+    {
+      "epoch": 0.7434782608695653,
+      "grad_norm": 0.9103027582168579,
+      "learning_rate": 0.00015890124018638638,
+      "loss": 0.6255,
+      "step": 171
+    },
+    {
+      "epoch": 0.7478260869565218,
+      "grad_norm": 0.3885137736797333,
+      "learning_rate": 0.00015828631435975784,
+      "loss": 0.6323,
+      "step": 172
+    },
+    {
+      "epoch": 0.7521739130434782,
+      "grad_norm": 0.6141281723976135,
+      "learning_rate": 0.00015766803221148673,
+      "loss": 0.6504,
+      "step": 173
+    },
+    {
+      "epoch": 0.7565217391304347,
+      "grad_norm": 0.8024821281433105,
+      "learning_rate": 0.0001570464293443346,
+      "loss": 0.641,
+      "step": 174
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 0.43333736062049866,
+      "learning_rate": 0.00015642154155228122,
+      "loss": 0.627,
+      "step": 175
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 0.649389922618866,
+      "learning_rate": 0.00015579340481846336,
+      "loss": 0.6483,
+      "step": 176
+    },
+    {
+      "epoch": 0.7695652173913043,
+      "grad_norm": 1.0359424352645874,
+      "learning_rate": 0.00015516205531310273,
+      "loss": 0.6332,
+      "step": 177
+    },
+    {
+      "epoch": 0.7739130434782608,
+      "grad_norm": 0.7209396362304688,
+      "learning_rate": 0.00015452752939142328,
+      "loss": 0.6524,
+      "step": 178
+    },
+    {
+      "epoch": 0.7782608695652173,
+      "grad_norm": 0.6178513169288635,
+      "learning_rate": 0.00015388986359155758,
+      "loss": 0.645,
+      "step": 179
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.9886595606803894,
+      "learning_rate": 0.00015324909463244296,
+      "loss": 0.6642,
+      "step": 180
+    },
+    {
+      "epoch": 0.7869565217391304,
+      "grad_norm": 0.7466373443603516,
+      "learning_rate": 0.00015260525941170712,
+      "loss": 0.6315,
+      "step": 181
+    },
+    {
+      "epoch": 0.7913043478260869,
+      "grad_norm": 0.5552679896354675,
+      "learning_rate": 0.00015195839500354335,
+      "loss": 0.6207,
+      "step": 182
+    },
+    {
+      "epoch": 0.7956521739130434,
+      "grad_norm": 0.5576688647270203,
+      "learning_rate": 0.0001513085386565758,
+      "loss": 0.6421,
+      "step": 183
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4000707268714905,
+      "learning_rate": 0.00015065572779171432,
+      "loss": 0.6398,
+      "step": 184
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 0.4978863298892975,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6456,
+      "step": 185
+    },
+    {
+      "epoch": 0.808695652173913,
+      "grad_norm": 0.4530424177646637,
+      "learning_rate": 0.00014934139304044033,
+      "loss": 0.6453,
+      "step": 186
+    },
+    {
+      "epoch": 0.8130434782608695,
+      "grad_norm": 0.29163071513175964,
+      "learning_rate": 0.00014867994483783485,
+      "loss": 0.6558,
+      "step": 187
+    },
+    {
+      "epoch": 0.8173913043478261,
+      "grad_norm": 0.33445900678634644,
+      "learning_rate": 0.00014801569348059157,
+      "loss": 0.6291,
+      "step": 188
+    },
+    {
+      "epoch": 0.8217391304347826,
+      "grad_norm": 0.3891032934188843,
+      "learning_rate": 0.0001473486772185334,
+      "loss": 0.6458,
+      "step": 189
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.4320944845676422,
+      "learning_rate": 0.00014667893446069588,
+      "loss": 0.6275,
+      "step": 190
+    },
+    {
+      "epoch": 0.8304347826086956,
+      "grad_norm": 0.3652418553829193,
+      "learning_rate": 0.00014600650377311522,
+      "loss": 0.6434,
+      "step": 191
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 0.2939096689224243,
+      "learning_rate": 0.00014533142387660773,
+      "loss": 0.6462,
+      "step": 192
+    },
+    {
+      "epoch": 0.8391304347826087,
+      "grad_norm": 0.36094796657562256,
+      "learning_rate": 0.00014465373364454001,
+      "loss": 0.6259,
+      "step": 193
+    },
+    {
+      "epoch": 0.8434782608695652,
+      "grad_norm": 0.503746747970581,
+      "learning_rate": 0.00014397347210059057,
+      "loss": 0.6565,
+      "step": 194
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.501377522945404,
+      "learning_rate": 0.00014329067841650274,
+      "loss": 0.6358,
+      "step": 195
+    },
+    {
+      "epoch": 0.8521739130434782,
+      "grad_norm": 0.40720251202583313,
+      "learning_rate": 0.00014260539190982886,
+      "loss": 0.636,
+      "step": 196
+    },
+    {
+      "epoch": 0.8565217391304348,
+      "grad_norm": 0.3170947730541229,
+      "learning_rate": 0.00014191765204166643,
+      "loss": 0.6343,
+      "step": 197
+    },
+    {
+      "epoch": 0.8608695652173913,
+      "grad_norm": 0.43554455041885376,
+      "learning_rate": 0.00014122749841438575,
+      "loss": 0.6319,
+      "step": 198
+    },
+    {
+      "epoch": 0.8652173913043478,
+      "grad_norm": 0.5128415822982788,
+      "learning_rate": 0.00014053497076934948,
+      "loss": 0.6326,
+      "step": 199
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.44992515444755554,
+      "learning_rate": 0.00013984010898462416,
+      "loss": 0.6343,
+      "step": 200
+    },
+    {
+      "epoch": 0.8739130434782608,
+      "grad_norm": 0.506968080997467,
+      "learning_rate": 0.00013914295307268396,
+      "loss": 0.6472,
+      "step": 201
+    },
+    {
+      "epoch": 0.8782608695652174,
+      "grad_norm": 0.6257392764091492,
+      "learning_rate": 0.0001384435431781065,
+      "loss": 0.6535,
+      "step": 202
+    },
+    {
+      "epoch": 0.8826086956521739,
+      "grad_norm": 0.9480230808258057,
+      "learning_rate": 0.00013774191957526143,
+      "loss": 0.6628,
+      "step": 203
+    },
+    {
+      "epoch": 0.8869565217391304,
+      "grad_norm": 1.2171893119812012,
+      "learning_rate": 0.00013703812266599113,
+      "loss": 0.6585,
+      "step": 204
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 0.3134421110153198,
+      "learning_rate": 0.00013633219297728416,
+      "loss": 0.6629,
+      "step": 205
+    },
+    {
+      "epoch": 0.8956521739130435,
+      "grad_norm": 1.003349781036377,
+      "learning_rate": 0.00013562417115894172,
+      "loss": 0.6516,
+      "step": 206
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.246419906616211,
+      "learning_rate": 0.00013491409798123687,
+      "loss": 0.6418,
+      "step": 207
+    },
+    {
+      "epoch": 0.9043478260869565,
+      "grad_norm": 0.46948862075805664,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.6441,
+      "step": 208
+    },
+    {
+      "epoch": 0.908695652173913,
+      "grad_norm": 1.628340244293213,
+      "learning_rate": 0.00013348796121709862,
+      "loss": 0.6661,
+      "step": 209
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.4027623236179352,
+      "learning_rate": 0.0001327719797524075,
+      "loss": 0.6342,
+      "step": 210
+    },
+    {
+      "epoch": 0.9173913043478261,
+      "grad_norm": 1.3196384906768799,
+      "learning_rate": 0.00013205411116710972,
+      "loss": 0.6724,
+      "step": 211
+    },
+    {
+      "epoch": 0.9217391304347826,
+      "grad_norm": 0.561631977558136,
+      "learning_rate": 0.00013133439679848823,
+      "loss": 0.6541,
+      "step": 212
+    },
+    {
+      "epoch": 0.9260869565217391,
+      "grad_norm": 0.7715569734573364,
+      "learning_rate": 0.00013061287809011242,
+      "loss": 0.6419,
+      "step": 213
+    },
+    {
+      "epoch": 0.9304347826086956,
+      "grad_norm": 0.8591257333755493,
+      "learning_rate": 0.0001298895965894516,
+      "loss": 0.6197,
+      "step": 214
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 0.4229847192764282,
+      "learning_rate": 0.0001291645939454825,
+      "loss": 0.6472,
+      "step": 215
+    },
+    {
+      "epoch": 0.9391304347826087,
+      "grad_norm": 0.7943733930587769,
+      "learning_rate": 0.0001284379119062912,
+      "loss": 0.6576,
+      "step": 216
+    },
+    {
+      "epoch": 0.9434782608695652,
+      "grad_norm": 0.7454273104667664,
+      "learning_rate": 0.0001277095923166689,
+      "loss": 0.6245,
+      "step": 217
+    },
+    {
+      "epoch": 0.9478260869565217,
+      "grad_norm": 0.4976602792739868,
+      "learning_rate": 0.00012697967711570242,
+      "loss": 0.644,
+      "step": 218
+    },
+    {
+      "epoch": 0.9521739130434783,
+      "grad_norm": 0.6845293641090393,
+      "learning_rate": 0.00012624820833435937,
+      "loss": 0.6412,
+      "step": 219
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.7265484929084778,
+      "learning_rate": 0.0001255152280930676,
+      "loss": 0.6438,
+      "step": 220
+    },
+    {
+      "epoch": 0.9608695652173913,
+      "grad_norm": 0.4346272647380829,
+      "learning_rate": 0.00012478077859929,
+      "loss": 0.6116,
+      "step": 221
+    },
+    {
+      "epoch": 0.9652173913043478,
+      "grad_norm": 0.5768253803253174,
+      "learning_rate": 0.00012404490214509386,
+      "loss": 0.6242,
+      "step": 222
+    },
+    {
+      "epoch": 0.9695652173913043,
+      "grad_norm": 0.688556969165802,
+      "learning_rate": 0.00012330764110471566,
+      "loss": 0.6546,
+      "step": 223
+    },
+    {
+      "epoch": 0.9739130434782609,
+      "grad_norm": 0.6147114634513855,
+      "learning_rate": 0.00012256903793212107,
+      "loss": 0.6286,
+      "step": 224
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.6598117351531982,
+      "learning_rate": 0.00012182913515856015,
+      "loss": 0.65,
+      "step": 225
+    },
+    {
+      "epoch": 0.9826086956521739,
+      "grad_norm": 0.6232290863990784,
+      "learning_rate": 0.00012108797539011847,
+      "loss": 0.6465,
+      "step": 226
+    },
+    {
+      "epoch": 0.9869565217391304,
+      "grad_norm": 0.3764599561691284,
+      "learning_rate": 0.0001203456013052634,
+      "loss": 0.6397,
+      "step": 227
+    },
+    {
+      "epoch": 0.991304347826087,
+      "grad_norm": 0.4177006781101227,
+      "learning_rate": 0.00011960205565238684,
+      "loss": 0.6324,
+      "step": 228
+    },
+    {
+      "epoch": 0.9956521739130435,
+      "grad_norm": 0.6632861495018005,
+      "learning_rate": 0.00011885738124734358,
+      "loss": 0.6394,
+      "step": 229
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8406037092208862,
+      "learning_rate": 0.00011811162097098558,
+      "loss": 0.6563,
+      "step": 230
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.970864260913562e+18,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debcc36fa997a64e53b1abfa40a63b54aa6e2835df049b95a7525a5de910eac8
+size 15032