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:f514bff1a545d9ccc495b6974dab4107a39b0300c7c848087a663682f8787768
+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 +1,2624 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005405405405405406,
+      "grad_norm": 166.34339904785156,
+      "learning_rate": 0.0,
+      "loss": 7.4172,
+      "step": 1
+    },
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 187.5918731689453,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 7.5679,
+      "step": 2
+    },
+    {
+      "epoch": 0.016216216216216217,
+      "grad_norm": 52.4649658203125,
+      "learning_rate": 1.0810810810810812e-05,
+      "loss": 7.0005,
+      "step": 3
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 37.77447509765625,
+      "learning_rate": 1.6216216216216218e-05,
+      "loss": 6.5778,
+      "step": 4
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 29.47389793395996,
+      "learning_rate": 2.1621621621621624e-05,
+      "loss": 6.1619,
+      "step": 5
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "grad_norm": 11.992705345153809,
+      "learning_rate": 2.702702702702703e-05,
+      "loss": 5.8593,
+      "step": 6
+    },
+    {
+      "epoch": 0.03783783783783784,
+      "grad_norm": 8.19919490814209,
+      "learning_rate": 3.2432432432432436e-05,
+      "loss": 5.5268,
+      "step": 7
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 6.438775062561035,
+      "learning_rate": 3.783783783783784e-05,
+      "loss": 5.2354,
+      "step": 8
+    },
+    {
+      "epoch": 0.04864864864864865,
+      "grad_norm": 3.4555141925811768,
+      "learning_rate": 4.324324324324325e-05,
+      "loss": 4.9956,
+      "step": 9
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 3.111621856689453,
+      "learning_rate": 4.8648648648648654e-05,
+      "loss": 4.7073,
+      "step": 10
+    },
+    {
+      "epoch": 0.05945945945945946,
+      "grad_norm": 2.309434413909912,
+      "learning_rate": 5.405405405405406e-05,
+      "loss": 4.5115,
+      "step": 11
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 1.941659927368164,
+      "learning_rate": 5.9459459459459466e-05,
+      "loss": 4.2527,
+      "step": 12
+    },
+    {
+      "epoch": 0.07027027027027027,
+      "grad_norm": 1.9665441513061523,
+      "learning_rate": 6.486486486486487e-05,
+      "loss": 4.0545,
+      "step": 13
+    },
+    {
+      "epoch": 0.07567567567567568,
+      "grad_norm": 1.7107363939285278,
+      "learning_rate": 7.027027027027028e-05,
+      "loss": 3.8214,
+      "step": 14
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 1.6905264854431152,
+      "learning_rate": 7.567567567567568e-05,
+      "loss": 3.6188,
+      "step": 15
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 1.2384110689163208,
+      "learning_rate": 8.108108108108109e-05,
+      "loss": 3.3663,
+      "step": 16
+    },
+    {
+      "epoch": 0.0918918918918919,
+      "grad_norm": 1.080546498298645,
+      "learning_rate": 8.64864864864865e-05,
+      "loss": 3.181,
+      "step": 17
+    },
+    {
+      "epoch": 0.0972972972972973,
+      "grad_norm": 0.9721872806549072,
+      "learning_rate": 9.18918918918919e-05,
+      "loss": 2.9672,
+      "step": 18
+    },
+    {
+      "epoch": 0.10270270270270271,
+      "grad_norm": 0.8164976239204407,
+      "learning_rate": 9.729729729729731e-05,
+      "loss": 2.7709,
+      "step": 19
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.8994714021682739,
+      "learning_rate": 0.0001027027027027027,
+      "loss": 2.553,
+      "step": 20
+    },
+    {
+      "epoch": 0.11351351351351352,
+      "grad_norm": 0.9458346366882324,
+      "learning_rate": 0.00010810810810810812,
+      "loss": 2.3567,
+      "step": 21
+    },
+    {
+      "epoch": 0.11891891891891893,
+      "grad_norm": 1.1655299663543701,
+      "learning_rate": 0.00011351351351351351,
+      "loss": 2.1531,
+      "step": 22
+    },
+    {
+      "epoch": 0.12432432432432433,
+      "grad_norm": 1.1697014570236206,
+      "learning_rate": 0.00011891891891891893,
+      "loss": 1.9005,
+      "step": 23
+    },
+    {
+      "epoch": 0.12972972972972974,
+      "grad_norm": 1.003651738166809,
+      "learning_rate": 0.00012432432432432433,
+      "loss": 1.6242,
+      "step": 24
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.8397846817970276,
+      "learning_rate": 0.00012972972972972974,
+      "loss": 1.4416,
+      "step": 25
+    },
+    {
+      "epoch": 0.14054054054054055,
+      "grad_norm": 0.6541157960891724,
+      "learning_rate": 0.00013513513513513514,
+      "loss": 1.2792,
+      "step": 26
+    },
+    {
+      "epoch": 0.14594594594594595,
+      "grad_norm": 0.612557590007782,
+      "learning_rate": 0.00014054054054054056,
+      "loss": 1.1801,
+      "step": 27
+    },
+    {
+      "epoch": 0.15135135135135136,
+      "grad_norm": 0.4974724352359772,
+      "learning_rate": 0.00014594594594594595,
+      "loss": 1.0689,
+      "step": 28
+    },
+    {
+      "epoch": 0.15675675675675677,
+      "grad_norm": 0.4679795205593109,
+      "learning_rate": 0.00015135135135135137,
+      "loss": 1.0099,
+      "step": 29
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.3515791893005371,
+      "learning_rate": 0.00015675675675675676,
+      "loss": 0.9363,
+      "step": 30
+    },
+    {
+      "epoch": 0.16756756756756758,
+      "grad_norm": 0.30370157957077026,
+      "learning_rate": 0.00016216216216216218,
+      "loss": 0.8544,
+      "step": 31
+    },
+    {
+      "epoch": 0.17297297297297298,
+      "grad_norm": 0.28620409965515137,
+      "learning_rate": 0.00016756756756756757,
+      "loss": 0.8724,
+      "step": 32
+    },
+    {
+      "epoch": 0.1783783783783784,
+      "grad_norm": 0.23916271328926086,
+      "learning_rate": 0.000172972972972973,
+      "loss": 0.8163,
+      "step": 33
+    },
+    {
+      "epoch": 0.1837837837837838,
+      "grad_norm": 0.24133414030075073,
+      "learning_rate": 0.00017837837837837839,
+      "loss": 0.8094,
+      "step": 34
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 0.20248687267303467,
+      "learning_rate": 0.0001837837837837838,
+      "loss": 0.7914,
+      "step": 35
+    },
+    {
+      "epoch": 0.1945945945945946,
+      "grad_norm": 0.16612087190151215,
+      "learning_rate": 0.0001891891891891892,
+      "loss": 0.7721,
+      "step": 36
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.16773800551891327,
+      "learning_rate": 0.00019459459459459462,
+      "loss": 0.7746,
+      "step": 37
+    },
+    {
+      "epoch": 0.20540540540540542,
+      "grad_norm": 0.13932561874389648,
+      "learning_rate": 0.0002,
+      "loss": 0.7444,
+      "step": 38
+    },
+    {
+      "epoch": 0.21081081081081082,
+      "grad_norm": 0.1528484970331192,
+      "learning_rate": 0.0001999955498150411,
+      "loss": 0.7434,
+      "step": 39
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.12268492579460144,
+      "learning_rate": 0.00019998219965624734,
+      "loss": 0.7278,
+      "step": 40
+    },
+    {
+      "epoch": 0.22162162162162163,
+      "grad_norm": 0.11921179294586182,
+      "learning_rate": 0.0001999599507118322,
+      "loss": 0.71,
+      "step": 41
+    },
+    {
+      "epoch": 0.22702702702702704,
+      "grad_norm": 0.11119277030229568,
+      "learning_rate": 0.000199928804962034,
+      "loss": 0.6873,
+      "step": 42
+    },
+    {
+      "epoch": 0.23243243243243245,
+      "grad_norm": 0.10249276459217072,
+      "learning_rate": 0.0001998887651789398,
+      "loss": 0.6887,
+      "step": 43
+    },
+    {
+      "epoch": 0.23783783783783785,
+      "grad_norm": 0.1001831665635109,
+      "learning_rate": 0.00019983983492623833,
+      "loss": 0.6915,
+      "step": 44
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 0.10323046892881393,
+      "learning_rate": 0.00019978201855890308,
+      "loss": 0.6763,
+      "step": 45
+    },
+    {
+      "epoch": 0.24864864864864866,
+      "grad_norm": 0.10003294050693512,
+      "learning_rate": 0.00019971532122280464,
+      "loss": 0.6561,
+      "step": 46
+    },
+    {
+      "epoch": 0.25405405405405407,
+      "grad_norm": 0.08443877846002579,
+      "learning_rate": 0.00019963974885425266,
+      "loss": 0.6784,
+      "step": 47
+    },
+    {
+      "epoch": 0.2594594594594595,
+      "grad_norm": 0.09182324260473251,
+      "learning_rate": 0.00019955530817946748,
+      "loss": 0.6587,
+      "step": 48
+    },
+    {
+      "epoch": 0.2648648648648649,
+      "grad_norm": 0.13076290488243103,
+      "learning_rate": 0.0001994620067139815,
+      "loss": 0.6483,
+      "step": 49
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.08880296349525452,
+      "learning_rate": 0.0001993598527619703,
+      "loss": 0.6451,
+      "step": 50
+    },
+    {
+      "epoch": 0.2756756756756757,
+      "grad_norm": 0.07715742290019989,
+      "learning_rate": 0.0001992488554155135,
+      "loss": 0.6329,
+      "step": 51
+    },
+    {
+      "epoch": 0.2810810810810811,
+      "grad_norm": 0.077003113925457,
+      "learning_rate": 0.00019912902455378556,
+      "loss": 0.6397,
+      "step": 52
+    },
+    {
+      "epoch": 0.2864864864864865,
+      "grad_norm": 0.06974707543849945,
+      "learning_rate": 0.00019900037084217637,
+      "loss": 0.619,
+      "step": 53
+    },
+    {
+      "epoch": 0.2918918918918919,
+      "grad_norm": 0.06869279593229294,
+      "learning_rate": 0.00019886290573134228,
+      "loss": 0.6326,
+      "step": 54
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 0.06709641218185425,
+      "learning_rate": 0.00019871664145618657,
+      "loss": 0.6305,
+      "step": 55
+    },
+    {
+      "epoch": 0.3027027027027027,
+      "grad_norm": 0.07039665430784225,
+      "learning_rate": 0.00019856159103477086,
+      "loss": 0.6058,
+      "step": 56
+    },
+    {
+      "epoch": 0.3081081081081081,
+      "grad_norm": 0.07261249423027039,
+      "learning_rate": 0.00019839776826715614,
+      "loss": 0.6133,
+      "step": 57
+    },
+    {
+      "epoch": 0.31351351351351353,
+      "grad_norm": 0.07141660153865814,
+      "learning_rate": 0.0001982251877341748,
+      "loss": 0.6136,
+      "step": 58
+    },
+    {
+      "epoch": 0.31891891891891894,
+      "grad_norm": 0.06658609956502914,
+      "learning_rate": 0.0001980438647961327,
+      "loss": 0.6407,
+      "step": 59
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.07396089285612106,
+      "learning_rate": 0.00019785381559144196,
+      "loss": 0.601,
+      "step": 60
+    },
+    {
+      "epoch": 0.32972972972972975,
+      "grad_norm": 0.08898008614778519,
+      "learning_rate": 0.00019765505703518496,
+      "loss": 0.6149,
+      "step": 61
+    },
+    {
+      "epoch": 0.33513513513513515,
+      "grad_norm": 0.1093701645731926,
+      "learning_rate": 0.00019744760681760832,
+      "loss": 0.6014,
+      "step": 62
+    },
+    {
+      "epoch": 0.34054054054054056,
+      "grad_norm": 0.1039031520485878,
+      "learning_rate": 0.00019723148340254892,
+      "loss": 0.6126,
+      "step": 63
+    },
+    {
+      "epoch": 0.34594594594594597,
+      "grad_norm": 0.14217646420001984,
+      "learning_rate": 0.00019700670602579008,
+      "loss": 0.6057,
+      "step": 64
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 0.11971811205148697,
+      "learning_rate": 0.0001967732946933499,
+      "loss": 0.6041,
+      "step": 65
+    },
+    {
+      "epoch": 0.3567567567567568,
+      "grad_norm": 0.12108401209115982,
+      "learning_rate": 0.00019653127017970034,
+      "loss": 0.5906,
+      "step": 66
+    },
+    {
+      "epoch": 0.3621621621621622,
+      "grad_norm": 0.0906200259923935,
+      "learning_rate": 0.00019628065402591845,
+      "loss": 0.6014,
+      "step": 67
+    },
+    {
+      "epoch": 0.3675675675675676,
+      "grad_norm": 0.0969948098063469,
+      "learning_rate": 0.00019602146853776894,
+      "loss": 0.5973,
+      "step": 68
+    },
+    {
+      "epoch": 0.372972972972973,
+      "grad_norm": 0.10772716253995895,
+      "learning_rate": 0.00019575373678371909,
+      "loss": 0.594,
+      "step": 69
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.12335596233606339,
+      "learning_rate": 0.00019547748259288536,
+      "loss": 0.6009,
+      "step": 70
+    },
+    {
+      "epoch": 0.3837837837837838,
+      "grad_norm": 0.14136555790901184,
+      "learning_rate": 0.00019519273055291266,
+      "loss": 0.5985,
+      "step": 71
+    },
+    {
+      "epoch": 0.3891891891891892,
+      "grad_norm": 0.10604984313249588,
+      "learning_rate": 0.0001948995060077859,
+      "loss": 0.5982,
+      "step": 72
+    },
+    {
+      "epoch": 0.3945945945945946,
+      "grad_norm": 0.08961839228868484,
+      "learning_rate": 0.00019459783505557424,
+      "loss": 0.5706,
+      "step": 73
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.10604697465896606,
+      "learning_rate": 0.00019428774454610843,
+      "loss": 0.5898,
+      "step": 74
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.10985071957111359,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.5952,
+      "step": 75
+    },
+    {
+      "epoch": 0.41081081081081083,
+      "grad_norm": 0.11850868165493011,
+      "learning_rate": 0.00019364241599913924,
+      "loss": 0.5803,
+      "step": 76
+    },
+    {
+      "epoch": 0.41621621621621624,
+      "grad_norm": 0.1549469530582428,
+      "learning_rate": 0.00019330723539826375,
+      "loss": 0.5776,
+      "step": 77
+    },
+    {
+      "epoch": 0.42162162162162165,
+      "grad_norm": 0.18124178051948547,
+      "learning_rate": 0.00019296375010827773,
+      "loss": 0.5757,
+      "step": 78
+    },
+    {
+      "epoch": 0.42702702702702705,
+      "grad_norm": 0.16211983561515808,
+      "learning_rate": 0.0001926119907006426,
+      "loss": 0.5942,
+      "step": 79
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.2041509449481964,
+      "learning_rate": 0.0001922519884832469,
+      "loss": 0.5946,
+      "step": 80
+    },
+    {
+      "epoch": 0.43783783783783786,
+      "grad_norm": 0.1953067183494568,
+      "learning_rate": 0.00019188377549761963,
+      "loss": 0.6017,
+      "step": 81
+    },
+    {
+      "epoch": 0.44324324324324327,
+      "grad_norm": 0.19392773509025574,
+      "learning_rate": 0.0001915073845160786,
+      "loss": 0.5896,
+      "step": 82
+    },
+    {
+      "epoch": 0.4486486486486487,
+      "grad_norm": 0.1343798190355301,
+      "learning_rate": 0.0001911228490388136,
+      "loss": 0.5771,
+      "step": 83
+    },
+    {
+      "epoch": 0.4540540540540541,
+      "grad_norm": 0.22122260928153992,
+      "learning_rate": 0.00019073020329090444,
+      "loss": 0.5948,
+      "step": 84
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 0.23926760256290436,
+      "learning_rate": 0.00019032948221927524,
+      "loss": 0.5894,
+      "step": 85
+    },
+    {
+      "epoch": 0.4648648648648649,
+      "grad_norm": 0.3518514335155487,
+      "learning_rate": 0.00018992072148958368,
+      "loss": 0.6073,
+      "step": 86
+    },
+    {
+      "epoch": 0.4702702702702703,
+      "grad_norm": 0.46678459644317627,
+      "learning_rate": 0.00018950395748304678,
+      "loss": 0.6006,
+      "step": 87
+    },
+    {
+      "epoch": 0.4756756756756757,
+      "grad_norm": 0.3574659824371338,
+      "learning_rate": 0.00018907922729320285,
+      "loss": 0.5843,
+      "step": 88
+    },
+    {
+      "epoch": 0.4810810810810811,
+      "grad_norm": 0.1582118421792984,
+      "learning_rate": 0.00018864656872260985,
+      "loss": 0.5856,
+      "step": 89
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.41187095642089844,
+      "learning_rate": 0.00018820602027948114,
+      "loss": 0.6022,
+      "step": 90
+    },
+    {
+      "epoch": 0.4918918918918919,
+      "grad_norm": 0.26722782850265503,
+      "learning_rate": 0.00018775762117425777,
+      "loss": 0.5737,
+      "step": 91
+    },
+    {
+      "epoch": 0.4972972972972973,
+      "grad_norm": 0.2423318475484848,
+      "learning_rate": 0.00018730141131611882,
+      "loss": 0.5646,
+      "step": 92
+    },
+    {
+      "epoch": 0.5027027027027027,
+      "grad_norm": 0.3524855673313141,
+      "learning_rate": 0.00018683743130942928,
+      "loss": 0.5733,
+      "step": 93
+    },
+    {
+      "epoch": 0.5081081081081081,
+      "grad_norm": 0.13441210985183716,
+      "learning_rate": 0.00018636572245012606,
+      "loss": 0.5813,
+      "step": 94
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.30515116453170776,
+      "learning_rate": 0.00018588632672204264,
+      "loss": 0.5542,
+      "step": 95
+    },
+    {
+      "epoch": 0.518918918918919,
+      "grad_norm": 0.17132249474525452,
+      "learning_rate": 0.0001853992867931721,
+      "loss": 0.5838,
+      "step": 96
+    },
+    {
+      "epoch": 0.5243243243243243,
+      "grad_norm": 0.28823599219322205,
+      "learning_rate": 0.0001849046460118698,
+      "loss": 0.588,
+      "step": 97
+    },
+    {
+      "epoch": 0.5297297297297298,
+      "grad_norm": 0.31162044405937195,
+      "learning_rate": 0.00018440244840299506,
+      "loss": 0.5747,
+      "step": 98
+    },
+    {
+      "epoch": 0.5351351351351351,
+      "grad_norm": 0.1594020426273346,
+      "learning_rate": 0.00018389273866399275,
+      "loss": 0.572,
+      "step": 99
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.27514341473579407,
+      "learning_rate": 0.00018337556216091517,
+      "loss": 0.5828,
+      "step": 100
+    },
+    {
+      "epoch": 0.5459459459459459,
+      "grad_norm": 0.30611446499824524,
+      "learning_rate": 0.00018285096492438424,
+      "loss": 0.5731,
+      "step": 101
+    },
+    {
+      "epoch": 0.5513513513513514,
+      "grad_norm": 0.4014338552951813,
+      "learning_rate": 0.00018231899364549455,
+      "loss": 0.5715,
+      "step": 102
+    },
+    {
+      "epoch": 0.5567567567567567,
+      "grad_norm": 0.5616762042045593,
+      "learning_rate": 0.0001817796956716578,
+      "loss": 0.605,
+      "step": 103
+    },
+    {
+      "epoch": 0.5621621621621622,
+      "grad_norm": 0.5975009202957153,
+      "learning_rate": 0.0001812331190023886,
+      "loss": 0.5571,
+      "step": 104
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.34755927324295044,
+      "learning_rate": 0.00018067931228503246,
+      "loss": 0.5662,
+      "step": 105
+    },
+    {
+      "epoch": 0.572972972972973,
+      "grad_norm": 0.4398202896118164,
+      "learning_rate": 0.00018011832481043576,
+      "loss": 0.5827,
+      "step": 106
+    },
+    {
+      "epoch": 0.5783783783783784,
+      "grad_norm": 0.520788848400116,
+      "learning_rate": 0.000179550206508559,
+      "loss": 0.5825,
+      "step": 107
+    },
+    {
+      "epoch": 0.5837837837837838,
+      "grad_norm": 0.3554728627204895,
+      "learning_rate": 0.0001789750079440326,
+      "loss": 0.5745,
+      "step": 108
+    },
+    {
+      "epoch": 0.5891891891891892,
+      "grad_norm": 0.4278441369533539,
+      "learning_rate": 0.00017839278031165658,
+      "loss": 0.5901,
+      "step": 109
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.5219722390174866,
+      "learning_rate": 0.00017780357543184397,
+      "loss": 0.5574,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.24311627447605133,
+      "learning_rate": 0.00017720744574600863,
+      "loss": 0.5721,
+      "step": 111
+    },
+    {
+      "epoch": 0.6054054054054054,
+      "grad_norm": 0.37851300835609436,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.5522,
+      "step": 112
+    },
+    {
+      "epoch": 0.6108108108108108,
+      "grad_norm": 0.2819484770298004,
+      "learning_rate": 0.00017599462479886974,
+      "loss": 0.5762,
+      "step": 113
+    },
+    {
+      "epoch": 0.6162162162162163,
+      "grad_norm": 0.4176675081253052,
+      "learning_rate": 0.00017537804148311695,
+      "loss": 0.5871,
+      "step": 114
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 0.5771986842155457,
+      "learning_rate": 0.00017475474924283536,
+      "loss": 0.5898,
+      "step": 115
+    },
+    {
+      "epoch": 0.6270270270270271,
+      "grad_norm": 0.5216075778007507,
+      "learning_rate": 0.00017412480355334005,
+      "loss": 0.5817,
+      "step": 116
+    },
+    {
+      "epoch": 0.6324324324324324,
+      "grad_norm": 0.48448437452316284,
+      "learning_rate": 0.0001734882604821276,
+      "loss": 0.5815,
+      "step": 117
+    },
+    {
+      "epoch": 0.6378378378378379,
+      "grad_norm": 0.42380860447883606,
+      "learning_rate": 0.0001728451766838861,
+      "loss": 0.5781,
+      "step": 118
+    },
+    {
+      "epoch": 0.6432432432432432,
+      "grad_norm": 0.27722859382629395,
+      "learning_rate": 0.00017219560939545246,
+      "loss": 0.5797,
+      "step": 119
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.3511153757572174,
+      "learning_rate": 0.0001715396164307182,
+      "loss": 0.5978,
+      "step": 120
+    },
+    {
+      "epoch": 0.654054054054054,
+      "grad_norm": 0.3476790189743042,
+      "learning_rate": 0.00017087725617548385,
+      "loss": 0.5633,
+      "step": 121
+    },
+    {
+      "epoch": 0.6594594594594595,
+      "grad_norm": 0.359022319316864,
+      "learning_rate": 0.00017020858758226229,
+      "loss": 0.5767,
+      "step": 122
+    },
+    {
+      "epoch": 0.6648648648648648,
+      "grad_norm": 0.3652413487434387,
+      "learning_rate": 0.00016953367016503182,
+      "loss": 0.5803,
+      "step": 123
+    },
+    {
+      "epoch": 0.6702702702702703,
+      "grad_norm": 0.3911918103694916,
+      "learning_rate": 0.00016885256399393924,
+      "loss": 0.5669,
+      "step": 124
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.29855138063430786,
+      "learning_rate": 0.00016816532968995328,
+      "loss": 0.5701,
+      "step": 125
+    },
+    {
+      "epoch": 0.6810810810810811,
+      "grad_norm": 0.3289024531841278,
+      "learning_rate": 0.00016747202841946928,
+      "loss": 0.5691,
+      "step": 126
+    },
+    {
+      "epoch": 0.6864864864864865,
+      "grad_norm": 0.43118664622306824,
+      "learning_rate": 0.00016677272188886483,
+      "loss": 0.595,
+      "step": 127
+    },
+    {
+      "epoch": 0.6918918918918919,
+      "grad_norm": 0.48039013147354126,
+      "learning_rate": 0.00016606747233900815,
+      "loss": 0.5894,
+      "step": 128
+    },
+    {
+      "epoch": 0.6972972972972973,
+      "grad_norm": 0.5704895853996277,
+      "learning_rate": 0.00016535634253971794,
+      "loss": 0.571,
+      "step": 129
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.4907408356666565,
+      "learning_rate": 0.00016463939578417692,
+      "loss": 0.5705,
+      "step": 130
+    },
+    {
+      "epoch": 0.7081081081081081,
+      "grad_norm": 0.40252187848091125,
+      "learning_rate": 0.0001639166958832985,
+      "loss": 0.565,
+      "step": 131
+    },
+    {
+      "epoch": 0.7135135135135136,
+      "grad_norm": 0.5997945070266724,
+      "learning_rate": 0.00016318830716004722,
+      "loss": 0.5746,
+      "step": 132
+    },
+    {
+      "epoch": 0.7189189189189189,
+      "grad_norm": 0.6897152066230774,
+      "learning_rate": 0.0001624542944437139,
+      "loss": 0.5744,
+      "step": 133
+    },
+    {
+      "epoch": 0.7243243243243244,
+      "grad_norm": 0.6489009857177734,
+      "learning_rate": 0.00016171472306414554,
+      "loss": 0.5905,
+      "step": 134
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 0.5703084468841553,
+      "learning_rate": 0.0001609696588459307,
+      "loss": 0.5893,
+      "step": 135
+    },
+    {
+      "epoch": 0.7351351351351352,
+      "grad_norm": 0.5917540192604065,
+      "learning_rate": 0.00016021916810254097,
+      "loss": 0.5878,
+      "step": 136
+    },
+    {
+      "epoch": 0.7405405405405405,
+      "grad_norm": 0.6699403524398804,
+      "learning_rate": 0.00015946331763042867,
+      "loss": 0.5776,
+      "step": 137
+    },
+    {
+      "epoch": 0.745945945945946,
+      "grad_norm": 0.6214162111282349,
+      "learning_rate": 0.00015870217470308188,
+      "loss": 0.5866,
+      "step": 138
+    },
+    {
+      "epoch": 0.7513513513513513,
+      "grad_norm": 0.5269213914871216,
+      "learning_rate": 0.0001579358070650367,
+      "loss": 0.5797,
+      "step": 139
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.5156534910202026,
+      "learning_rate": 0.00015716428292584787,
+      "loss": 0.5837,
+      "step": 140
+    },
+    {
+      "epoch": 0.7621621621621621,
+      "grad_norm": 0.3855270445346832,
+      "learning_rate": 0.0001563876709540178,
+      "loss": 0.5794,
+      "step": 141
+    },
+    {
+      "epoch": 0.7675675675675676,
+      "grad_norm": 0.42134228348731995,
+      "learning_rate": 0.00015560604027088477,
+      "loss": 0.5607,
+      "step": 142
+    },
+    {
+      "epoch": 0.772972972972973,
+      "grad_norm": 0.2681983709335327,
+      "learning_rate": 0.00015481946044447099,
+      "loss": 0.5887,
+      "step": 143
+    },
+    {
+      "epoch": 0.7783783783783784,
+      "grad_norm": 0.5026779174804688,
+      "learning_rate": 0.00015402800148329071,
+      "loss": 0.5951,
+      "step": 144
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 0.5202389359474182,
+      "learning_rate": 0.0001532317338301192,
+      "loss": 0.5963,
+      "step": 145
+    },
+    {
+      "epoch": 0.7891891891891892,
+      "grad_norm": 0.43367475271224976,
+      "learning_rate": 0.00015243072835572318,
+      "loss": 0.563,
+      "step": 146
+    },
+    {
+      "epoch": 0.7945945945945946,
+      "grad_norm": 0.4822995960712433,
+      "learning_rate": 0.00015162505635255287,
+      "loss": 0.5675,
+      "step": 147
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4385891854763031,
+      "learning_rate": 0.00015081478952839693,
+      "loss": 0.5672,
+      "step": 148
+    },
+    {
+      "epoch": 0.8054054054054054,
+      "grad_norm": 0.27161282300949097,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5564,
+      "step": 149
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.47754400968551636,
+      "learning_rate": 0.0001491807602866442,
+      "loss": 0.5865,
+      "step": 150
+    },
+    {
+      "epoch": 0.8162162162162162,
+      "grad_norm": 0.6711156368255615,
+      "learning_rate": 0.00014835714330369446,
+      "loss": 0.5818,
+      "step": 151
+    },
+    {
+      "epoch": 0.8216216216216217,
+      "grad_norm": 0.713715136051178,
+      "learning_rate": 0.000147529222356109,
+      "loss": 0.5807,
+      "step": 152
+    },
+    {
+      "epoch": 0.827027027027027,
+      "grad_norm": 0.7641165852546692,
+      "learning_rate": 0.00014669707113191483,
+      "loss": 0.5604,
+      "step": 153
+    },
+    {
+      "epoch": 0.8324324324324325,
+      "grad_norm": 0.6011711955070496,
+      "learning_rate": 0.00014586076369564908,
+      "loss": 0.5778,
+      "step": 154
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 0.43020206689834595,
+      "learning_rate": 0.00014502037448176734,
+      "loss": 0.5785,
+      "step": 155
+    },
+    {
+      "epoch": 0.8432432432432433,
+      "grad_norm": 0.4680975377559662,
+      "learning_rate": 0.00014417597828801832,
+      "loss": 0.5785,
+      "step": 156
+    },
+    {
+      "epoch": 0.8486486486486486,
+      "grad_norm": 0.5653423070907593,
+      "learning_rate": 0.00014332765026878687,
+      "loss": 0.5913,
+      "step": 157
+    },
+    {
+      "epoch": 0.8540540540540541,
+      "grad_norm": 0.6896083354949951,
+      "learning_rate": 0.0001424754659284048,
+      "loss": 0.5769,
+      "step": 158
+    },
+    {
+      "epoch": 0.8594594594594595,
+      "grad_norm": 0.5635109543800354,
+      "learning_rate": 0.00014161950111443077,
+      "loss": 0.5552,
+      "step": 159
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.44970378279685974,
+      "learning_rate": 0.00014075983201089964,
+      "loss": 0.5716,
+      "step": 160
+    },
+    {
+      "epoch": 0.8702702702702703,
+      "grad_norm": 0.8098542094230652,
+      "learning_rate": 0.00013989653513154165,
+      "loss": 0.5913,
+      "step": 161
+    },
+    {
+      "epoch": 0.8756756756756757,
+      "grad_norm": 0.7309775948524475,
+      "learning_rate": 0.00013902968731297255,
+      "loss": 0.593,
+      "step": 162
+    },
+    {
+      "epoch": 0.8810810810810811,
+      "grad_norm": 0.7028838992118835,
+      "learning_rate": 0.00013815936570785487,
+      "loss": 0.5623,
+      "step": 163
+    },
+    {
+      "epoch": 0.8864864864864865,
+      "grad_norm": 0.6845377087593079,
+      "learning_rate": 0.00013728564777803088,
+      "loss": 0.5829,
+      "step": 164
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 0.43059009313583374,
+      "learning_rate": 0.0001364086112876284,
+      "loss": 0.5786,
+      "step": 165
+    },
+    {
+      "epoch": 0.8972972972972973,
+      "grad_norm": 0.8795806765556335,
+      "learning_rate": 0.00013552833429613938,
+      "loss": 0.5714,
+      "step": 166
+    },
+    {
+      "epoch": 0.9027027027027027,
+      "grad_norm": 1.0658906698226929,
+      "learning_rate": 0.00013464489515147238,
+      "loss": 0.5688,
+      "step": 167
+    },
+    {
+      "epoch": 0.9081081081081082,
+      "grad_norm": 0.7074139714241028,
+      "learning_rate": 0.00013375837248297926,
+      "loss": 0.5736,
+      "step": 168
+    },
+    {
+      "epoch": 0.9135135135135135,
+      "grad_norm": 0.5696041584014893,
+      "learning_rate": 0.0001328688451944569,
+      "loss": 0.5862,
+      "step": 169
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 0.46176642179489136,
+      "learning_rate": 0.00013197639245712454,
+      "loss": 0.5806,
+      "step": 170
+    },
+    {
+      "epoch": 0.9243243243243243,
+      "grad_norm": 0.6477006673812866,
+      "learning_rate": 0.00013108109370257712,
+      "loss": 0.5508,
+      "step": 171
+    },
+    {
+      "epoch": 0.9297297297297298,
+      "grad_norm": 0.6348613500595093,
+      "learning_rate": 0.0001301830286157157,
+      "loss": 0.5763,
+      "step": 172
+    },
+    {
+      "epoch": 0.9351351351351351,
+      "grad_norm": 0.3889661729335785,
+      "learning_rate": 0.00012928227712765504,
+      "loss": 0.5795,
+      "step": 173
+    },
+    {
+      "epoch": 0.9405405405405406,
+      "grad_norm": 0.7158688306808472,
+      "learning_rate": 0.00012837891940860972,
+      "loss": 0.5504,
+      "step": 174
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.49243494868278503,
+      "learning_rate": 0.0001274730358607583,
+      "loss": 0.5628,
+      "step": 175
+    },
+    {
+      "epoch": 0.9513513513513514,
+      "grad_norm": 0.4271713197231293,
+      "learning_rate": 0.00012656470711108764,
+      "loss": 0.5696,
+      "step": 176
+    },
+    {
+      "epoch": 0.9567567567567568,
+      "grad_norm": 0.6557771563529968,
+      "learning_rate": 0.00012565401400421651,
+      "loss": 0.5895,
+      "step": 177
+    },
+    {
+      "epoch": 0.9621621621621622,
+      "grad_norm": 0.39298897981643677,
+      "learning_rate": 0.00012474103759520027,
+      "loss": 0.5669,
+      "step": 178
+    },
+    {
+      "epoch": 0.9675675675675676,
+      "grad_norm": 0.4338141083717346,
+      "learning_rate": 0.0001238258591423165,
+      "loss": 0.5595,
+      "step": 179
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 0.4943206012248993,
+      "learning_rate": 0.000122908560099833,
+      "loss": 0.5636,
+      "step": 180
+    },
+    {
+      "epoch": 0.9783783783783784,
+      "grad_norm": 0.3071780502796173,
+      "learning_rate": 0.00012198922211075778,
+      "loss": 0.5771,
+      "step": 181
+    },
+    {
+      "epoch": 0.9837837837837838,
+      "grad_norm": 0.3990117907524109,
+      "learning_rate": 0.00012106792699957263,
+      "loss": 0.5546,
+      "step": 182
+    },
+    {
+      "epoch": 0.9891891891891892,
+      "grad_norm": 0.3104795217514038,
+      "learning_rate": 0.00012014475676495052,
+      "loss": 0.5523,
+      "step": 183
+    },
+    {
+      "epoch": 0.9945945945945946,
+      "grad_norm": 0.40355923771858215,
+      "learning_rate": 0.0001192197935724573,
+      "loss": 0.5621,
+      "step": 184
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.42520806193351746,
+      "learning_rate": 0.00011829311974723867,
+      "loss": 0.5742,
+      "step": 185
+    },
+    {
+      "epoch": 1.0054054054054054,
+      "grad_norm": 0.2284257560968399,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.5681,
+      "step": 186
+    },
+    {
+      "epoch": 1.0108108108108107,
+      "grad_norm": 0.35243916511535645,
+      "learning_rate": 0.00011643497025313061,
+      "loss": 0.5641,
+      "step": 187
+    },
+    {
+      "epoch": 1.0162162162162163,
+      "grad_norm": 0.42704927921295166,
+      "learning_rate": 0.00011550365996641979,
+      "loss": 0.5634,
+      "step": 188
+    },
+    {
+      "epoch": 1.0216216216216216,
+      "grad_norm": 0.3367633819580078,
+      "learning_rate": 0.00011457096979662114,
+      "loss": 0.5705,
+      "step": 189
+    },
+    {
+      "epoch": 1.027027027027027,
+      "grad_norm": 0.38994061946868896,
+      "learning_rate": 0.00011363698275661001,
+      "loss": 0.5522,
+      "step": 190
+    },
+    {
+      "epoch": 1.0324324324324325,
+      "grad_norm": 0.3361996114253998,
+      "learning_rate": 0.00011270178197468789,
+      "loss": 0.5688,
+      "step": 191
+    },
+    {
+      "epoch": 1.037837837837838,
+      "grad_norm": 0.29897335171699524,
+      "learning_rate": 0.00011176545068718385,
+      "loss": 0.5619,
+      "step": 192
+    },
+    {
+      "epoch": 1.0432432432432432,
+      "grad_norm": 0.44845789670944214,
+      "learning_rate": 0.0001108280722310462,
+      "loss": 0.5599,
+      "step": 193
+    },
+    {
+      "epoch": 1.0486486486486486,
+      "grad_norm": 0.3990190923213959,
+      "learning_rate": 0.00010988973003642499,
+      "loss": 0.5887,
+      "step": 194
+    },
+    {
+      "epoch": 1.054054054054054,
+      "grad_norm": 0.4176868796348572,
+      "learning_rate": 0.00010895050761924668,
+      "loss": 0.5816,
+      "step": 195
+    },
+    {
+      "epoch": 1.0594594594594595,
+      "grad_norm": 0.5121976733207703,
+      "learning_rate": 0.00010801048857378071,
+      "loss": 0.5629,
+      "step": 196
+    },
+    {
+      "epoch": 1.0648648648648649,
+      "grad_norm": 0.42421454191207886,
+      "learning_rate": 0.00010706975656519946,
+      "loss": 0.5549,
+      "step": 197
+    },
+    {
+      "epoch": 1.0702702702702702,
+      "grad_norm": 0.34359657764434814,
+      "learning_rate": 0.00010612839532213164,
+      "loss": 0.554,
+      "step": 198
+    },
+    {
+      "epoch": 1.0756756756756758,
+      "grad_norm": 0.2899879813194275,
+      "learning_rate": 0.00010518648862921012,
+      "loss": 0.5679,
+      "step": 199
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.3595804274082184,
+      "learning_rate": 0.00010424412031961484,
+      "loss": 0.5765,
+      "step": 200
+    },
+    {
+      "epoch": 1.0864864864864865,
+      "grad_norm": 0.4479254484176636,
+      "learning_rate": 0.00010330137426761135,
+      "loss": 0.5824,
+      "step": 201
+    },
+    {
+      "epoch": 1.0918918918918918,
+      "grad_norm": 0.4118141829967499,
+      "learning_rate": 0.00010235833438108571,
+      "loss": 0.5684,
+      "step": 202
+    },
+    {
+      "epoch": 1.0972972972972972,
+      "grad_norm": 0.3013007640838623,
+      "learning_rate": 0.00010141508459407623,
+      "loss": 0.5634,
+      "step": 203
+    },
+    {
+      "epoch": 1.1027027027027028,
+      "grad_norm": 0.32391178607940674,
+      "learning_rate": 0.00010047170885930324,
+      "loss": 0.5702,
+      "step": 204
+    },
+    {
+      "epoch": 1.1081081081081081,
+      "grad_norm": 0.35440289974212646,
+      "learning_rate": 9.95282911406968e-05,
+      "loss": 0.5679,
+      "step": 205
+    },
+    {
+      "epoch": 1.1135135135135135,
+      "grad_norm": 0.3799758851528168,
+      "learning_rate": 9.858491540592382e-05,
+      "loss": 0.5769,
+      "step": 206
+    },
+    {
+      "epoch": 1.118918918918919,
+      "grad_norm": 0.37513500452041626,
+      "learning_rate": 9.764166561891432e-05,
+      "loss": 0.5669,
+      "step": 207
+    },
+    {
+      "epoch": 1.1243243243243244,
+      "grad_norm": 0.4138847291469574,
+      "learning_rate": 9.669862573238863e-05,
+      "loss": 0.5883,
+      "step": 208
+    },
+    {
+      "epoch": 1.1297297297297297,
+      "grad_norm": 0.4087463915348053,
+      "learning_rate": 9.57558796803852e-05,
+      "loss": 0.5564,
+      "step": 209
+    },
+    {
+      "epoch": 1.135135135135135,
+      "grad_norm": 0.3634737432003021,
+      "learning_rate": 9.48135113707899e-05,
+      "loss": 0.5623,
+      "step": 210
+    },
+    {
+      "epoch": 1.1405405405405404,
+      "grad_norm": 0.28195977210998535,
+      "learning_rate": 9.38716046778684e-05,
+      "loss": 0.5632,
+      "step": 211
+    },
+    {
+      "epoch": 1.145945945945946,
+      "grad_norm": 0.26449114084243774,
+      "learning_rate": 9.293024343480055e-05,
+      "loss": 0.5664,
+      "step": 212
+    },
+    {
+      "epoch": 1.1513513513513514,
+      "grad_norm": 0.3275916576385498,
+      "learning_rate": 9.198951142621929e-05,
+      "loss": 0.5582,
+      "step": 213
+    },
+    {
+      "epoch": 1.1567567567567567,
+      "grad_norm": 0.2918509840965271,
+      "learning_rate": 9.104949238075336e-05,
+      "loss": 0.5595,
+      "step": 214
+    },
+    {
+      "epoch": 1.1621621621621623,
+      "grad_norm": 0.31472450494766235,
+      "learning_rate": 9.011026996357503e-05,
+      "loss": 0.5579,
+      "step": 215
+    },
+    {
+      "epoch": 1.1675675675675676,
+      "grad_norm": 0.251597136259079,
+      "learning_rate": 8.917192776895382e-05,
+      "loss": 0.5248,
+      "step": 216
+    },
+    {
+      "epoch": 1.172972972972973,
+      "grad_norm": 0.364433228969574,
+      "learning_rate": 8.823454931281616e-05,
+      "loss": 0.5691,
+      "step": 217
+    },
+    {
+      "epoch": 1.1783783783783783,
+      "grad_norm": 0.4497614800930023,
+      "learning_rate": 8.729821802531212e-05,
+      "loss": 0.5468,
+      "step": 218
+    },
+    {
+      "epoch": 1.1837837837837837,
+      "grad_norm": 0.3149522542953491,
+      "learning_rate": 8.636301724339004e-05,
+      "loss": 0.5561,
+      "step": 219
+    },
+    {
+      "epoch": 1.1891891891891893,
+      "grad_norm": 0.3531090021133423,
+      "learning_rate": 8.542903020337887e-05,
+      "loss": 0.5607,
+      "step": 220
+    },
+    {
+      "epoch": 1.1945945945945946,
+      "grad_norm": 0.36666902899742126,
+      "learning_rate": 8.449634003358022e-05,
+      "loss": 0.5629,
+      "step": 221
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.27004843950271606,
+      "learning_rate": 8.356502974686941e-05,
+      "loss": 0.5759,
+      "step": 222
+    },
+    {
+      "epoch": 1.2054054054054055,
+      "grad_norm": 0.38194379210472107,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.5626,
+      "step": 223
+    },
+    {
+      "epoch": 1.2108108108108109,
+      "grad_norm": 0.42150571942329407,
+      "learning_rate": 8.170688025276134e-05,
+      "loss": 0.5692,
+      "step": 224
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.3516136407852173,
+      "learning_rate": 8.078020642754274e-05,
+      "loss": 0.5656,
+      "step": 225
+    },
+    {
+      "epoch": 1.2216216216216216,
+      "grad_norm": 0.2839685082435608,
+      "learning_rate": 7.985524323504948e-05,
+      "loss": 0.5591,
+      "step": 226
+    },
+    {
+      "epoch": 1.227027027027027,
+      "grad_norm": 0.2869662046432495,
+      "learning_rate": 7.89320730004274e-05,
+      "loss": 0.5482,
+      "step": 227
+    },
+    {
+      "epoch": 1.2324324324324325,
+      "grad_norm": 0.3703990578651428,
+      "learning_rate": 7.801077788924224e-05,
+      "loss": 0.5596,
+      "step": 228
+    },
+    {
+      "epoch": 1.2378378378378379,
+      "grad_norm": 0.36322546005249023,
+      "learning_rate": 7.709143990016702e-05,
+      "loss": 0.5678,
+      "step": 229
+    },
+    {
+      "epoch": 1.2432432432432432,
+      "grad_norm": 0.33027511835098267,
+      "learning_rate": 7.617414085768351e-05,
+      "loss": 0.5607,
+      "step": 230
+    },
+    {
+      "epoch": 1.2486486486486488,
+      "grad_norm": 0.2999548316001892,
+      "learning_rate": 7.525896240479976e-05,
+      "loss": 0.5468,
+      "step": 231
+    },
+    {
+      "epoch": 1.2540540540540541,
+      "grad_norm": 0.2634562849998474,
+      "learning_rate": 7.434598599578351e-05,
+      "loss": 0.5731,
+      "step": 232
+    },
+    {
+      "epoch": 1.2594594594594595,
+      "grad_norm": 0.3004055917263031,
+      "learning_rate": 7.343529288891239e-05,
+      "loss": 0.5608,
+      "step": 233
+    },
+    {
+      "epoch": 1.2648648648648648,
+      "grad_norm": 0.3801259994506836,
+      "learning_rate": 7.252696413924174e-05,
+      "loss": 0.5561,
+      "step": 234
+    },
+    {
+      "epoch": 1.2702702702702702,
+      "grad_norm": 0.297504186630249,
+      "learning_rate": 7.162108059139032e-05,
+      "loss": 0.5571,
+      "step": 235
+    },
+    {
+      "epoch": 1.2756756756756757,
+      "grad_norm": 0.2872467637062073,
+      "learning_rate": 7.071772287234497e-05,
+      "loss": 0.5487,
+      "step": 236
+    },
+    {
+      "epoch": 1.281081081081081,
+      "grad_norm": 0.3155842423439026,
+      "learning_rate": 6.981697138428434e-05,
+      "loss": 0.5582,
+      "step": 237
+    },
+    {
+      "epoch": 1.2864864864864864,
+      "grad_norm": 0.27752622961997986,
+      "learning_rate": 6.891890629742288e-05,
+      "loss": 0.5403,
+      "step": 238
+    },
+    {
+      "epoch": 1.291891891891892,
+      "grad_norm": 0.3249455690383911,
+      "learning_rate": 6.802360754287547e-05,
+      "loss": 0.5583,
+      "step": 239
+    },
+    {
+      "epoch": 1.2972972972972974,
+      "grad_norm": 0.308685302734375,
+      "learning_rate": 6.713115480554313e-05,
+      "loss": 0.5597,
+      "step": 240
+    },
+    {
+      "epoch": 1.3027027027027027,
+      "grad_norm": 0.2561638355255127,
+      "learning_rate": 6.624162751702076e-05,
+      "loss": 0.5391,
+      "step": 241
+    },
+    {
+      "epoch": 1.308108108108108,
+      "grad_norm": 0.4116757810115814,
+      "learning_rate": 6.535510484852767e-05,
+      "loss": 0.5485,
+      "step": 242
+    },
+    {
+      "epoch": 1.3135135135135134,
+      "grad_norm": 0.3048592805862427,
+      "learning_rate": 6.447166570386063e-05,
+      "loss": 0.5495,
+      "step": 243
+    },
+    {
+      "epoch": 1.318918918918919,
+      "grad_norm": 0.26773855090141296,
+      "learning_rate": 6.35913887123716e-05,
+      "loss": 0.5816,
+      "step": 244
+    },
+    {
+      "epoch": 1.3243243243243243,
+      "grad_norm": 0.4389781653881073,
+      "learning_rate": 6.271435222196916e-05,
+      "loss": 0.5456,
+      "step": 245
+    },
+    {
+      "epoch": 1.3297297297297297,
+      "grad_norm": 0.2906099855899811,
+      "learning_rate": 6.184063429214515e-05,
+      "loss": 0.5579,
+      "step": 246
+    },
+    {
+      "epoch": 1.3351351351351353,
+      "grad_norm": 0.29588866233825684,
+      "learning_rate": 6.097031268702746e-05,
+      "loss": 0.5451,
+      "step": 247
+    },
+    {
+      "epoch": 1.3405405405405406,
+      "grad_norm": 0.37067651748657227,
+      "learning_rate": 6.010346486845837e-05,
+      "loss": 0.5613,
+      "step": 248
+    },
+    {
+      "epoch": 1.345945945945946,
+      "grad_norm": 0.28503182530403137,
+      "learning_rate": 5.924016798910037e-05,
+      "loss": 0.5541,
+      "step": 249
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.2947586178779602,
+      "learning_rate": 5.838049888556925e-05,
+      "loss": 0.5543,
+      "step": 250
+    },
+    {
+      "epoch": 1.3567567567567567,
+      "grad_norm": 0.2248247265815735,
+      "learning_rate": 5.752453407159522e-05,
+      "loss": 0.5423,
+      "step": 251
+    },
+    {
+      "epoch": 1.3621621621621622,
+      "grad_norm": 0.2677771747112274,
+      "learning_rate": 5.667234973121317e-05,
+      "loss": 0.5573,
+      "step": 252
+    },
+    {
+      "epoch": 1.3675675675675676,
+      "grad_norm": 0.22564172744750977,
+      "learning_rate": 5.5824021711981686e-05,
+      "loss": 0.5543,
+      "step": 253
+    },
+    {
+      "epoch": 1.372972972972973,
+      "grad_norm": 0.23986554145812988,
+      "learning_rate": 5.497962551823266e-05,
+      "loss": 0.5529,
+      "step": 254
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 0.2411298155784607,
+      "learning_rate": 5.4139236304350935e-05,
+      "loss": 0.5596,
+      "step": 255
+    },
+    {
+      "epoch": 1.3837837837837839,
+      "grad_norm": 0.22724369168281555,
+      "learning_rate": 5.33029288680852e-05,
+      "loss": 0.5603,
+      "step": 256
+    },
+    {
+      "epoch": 1.3891891891891892,
+      "grad_norm": 0.21808037161827087,
+      "learning_rate": 5.247077764389099e-05,
+      "loss": 0.5581,
+      "step": 257
+    },
+    {
+      "epoch": 1.3945945945945946,
+      "grad_norm": 0.20949189364910126,
+      "learning_rate": 5.1642856696305575e-05,
+      "loss": 0.5318,
+      "step": 258
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.20597508549690247,
+      "learning_rate": 5.081923971335582e-05,
+      "loss": 0.5507,
+      "step": 259
+    },
+    {
+      "epoch": 1.4054054054054055,
+      "grad_norm": 0.27058327198028564,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5589,
+      "step": 260
+    },
+    {
+      "epoch": 1.4108108108108108,
+      "grad_norm": 0.22068722546100616,
+      "learning_rate": 4.918521047160308e-05,
+      "loss": 0.5444,
+      "step": 261
+    },
+    {
+      "epoch": 1.4162162162162162,
+      "grad_norm": 0.33482491970062256,
+      "learning_rate": 4.837494364744711e-05,
+      "loss": 0.5403,
+      "step": 262
+    },
+    {
+      "epoch": 1.4216216216216218,
+      "grad_norm": 0.22971421480178833,
+      "learning_rate": 4.756927164427685e-05,
+      "loss": 0.54,
+      "step": 263
+    },
+    {
+      "epoch": 1.427027027027027,
+      "grad_norm": 0.22710531949996948,
+      "learning_rate": 4.6768266169880804e-05,
+      "loss": 0.5614,
+      "step": 264
+    },
+    {
+      "epoch": 1.4324324324324325,
+      "grad_norm": 0.2634375989437103,
+      "learning_rate": 4.597199851670932e-05,
+      "loss": 0.5588,
+      "step": 265
+    },
+    {
+      "epoch": 1.4378378378378378,
+      "grad_norm": 0.22090476751327515,
+      "learning_rate": 4.518053955552903e-05,
+      "loss": 0.5664,
+      "step": 266
+    },
+    {
+      "epoch": 1.4432432432432432,
+      "grad_norm": 0.2724359333515167,
+      "learning_rate": 4.4393959729115244e-05,
+      "loss": 0.5539,
+      "step": 267
+    },
+    {
+      "epoch": 1.4486486486486487,
+      "grad_norm": 0.20361758768558502,
+      "learning_rate": 4.3612329045982236e-05,
+      "loss": 0.5434,
+      "step": 268
+    },
+    {
+      "epoch": 1.454054054054054,
+      "grad_norm": 0.22764244675636292,
+      "learning_rate": 4.283571707415214e-05,
+      "loss": 0.5617,
+      "step": 269
+    },
+    {
+      "epoch": 1.4594594594594594,
+      "grad_norm": 0.2354433387517929,
+      "learning_rate": 4.206419293496333e-05,
+      "loss": 0.5568,
+      "step": 270
+    },
+    {
+      "epoch": 1.464864864864865,
+      "grad_norm": 0.23961907625198364,
+      "learning_rate": 4.129782529691815e-05,
+      "loss": 0.5705,
+      "step": 271
+    },
+    {
+      "epoch": 1.4702702702702704,
+      "grad_norm": 0.20233069360256195,
+      "learning_rate": 4.053668236957134e-05,
+      "loss": 0.5673,
+      "step": 272
+    },
+    {
+      "epoch": 1.4756756756756757,
+      "grad_norm": 0.22353792190551758,
+      "learning_rate": 3.978083189745907e-05,
+      "loss": 0.5505,
+      "step": 273
+    },
+    {
+      "epoch": 1.481081081081081,
+      "grad_norm": 0.20876029133796692,
+      "learning_rate": 3.903034115406931e-05,
+      "loss": 0.5569,
+      "step": 274
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.22701065242290497,
+      "learning_rate": 3.828527693585451e-05,
+      "loss": 0.5719,
+      "step": 275
+    },
+    {
+      "epoch": 1.491891891891892,
+      "grad_norm": 0.21358339488506317,
+      "learning_rate": 3.7545705556286126e-05,
+      "loss": 0.546,
+      "step": 276
+    },
+    {
+      "epoch": 1.4972972972972973,
+      "grad_norm": 0.21339459717273712,
+      "learning_rate": 3.681169283995279e-05,
+      "loss": 0.533,
+      "step": 277
+    },
+    {
+      "epoch": 1.5027027027027027,
+      "grad_norm": 0.22355295717716217,
+      "learning_rate": 3.6083304116701535e-05,
+      "loss": 0.5425,
+      "step": 278
+    },
+    {
+      "epoch": 1.5081081081081082,
+      "grad_norm": 0.2224012166261673,
+      "learning_rate": 3.536060421582309e-05,
+      "loss": 0.5545,
+      "step": 279
+    },
+    {
+      "epoch": 1.5135135135135136,
+      "grad_norm": 0.2069329172372818,
+      "learning_rate": 3.464365746028208e-05,
+      "loss": 0.5269,
+      "step": 280
+    },
+    {
+      "epoch": 1.518918918918919,
+      "grad_norm": 0.2479923665523529,
+      "learning_rate": 3.393252766099187e-05,
+      "loss": 0.5583,
+      "step": 281
+    },
+    {
+      "epoch": 1.5243243243243243,
+      "grad_norm": 0.22443261742591858,
+      "learning_rate": 3.322727811113516e-05,
+      "loss": 0.5602,
+      "step": 282
+    },
+    {
+      "epoch": 1.5297297297297296,
+      "grad_norm": 0.24400541186332703,
+      "learning_rate": 3.252797158053077e-05,
+      "loss": 0.548,
+      "step": 283
+    },
+    {
+      "epoch": 1.535135135135135,
+      "grad_norm": 0.1754683256149292,
+      "learning_rate": 3.1834670310046734e-05,
+      "loss": 0.5437,
+      "step": 284
+    },
+    {
+      "epoch": 1.5405405405405406,
+      "grad_norm": 0.1994575560092926,
+      "learning_rate": 3.114743600606078e-05,
+      "loss": 0.5526,
+      "step": 285
+    },
+    {
+      "epoch": 1.545945945945946,
+      "grad_norm": 0.22562991082668304,
+      "learning_rate": 3.0466329834968233e-05,
+      "loss": 0.5436,
+      "step": 286
+    },
+    {
+      "epoch": 1.5513513513513515,
+      "grad_norm": 0.18434454500675201,
+      "learning_rate": 2.979141241773775e-05,
+      "loss": 0.5442,
+      "step": 287
+    },
+    {
+      "epoch": 1.5567567567567568,
+      "grad_norm": 0.2776215970516205,
+      "learning_rate": 2.9122743824516195e-05,
+      "loss": 0.5697,
+      "step": 288
+    },
+    {
+      "epoch": 1.5621621621621622,
+      "grad_norm": 0.17563948035240173,
+      "learning_rate": 2.8460383569281824e-05,
+      "loss": 0.5298,
+      "step": 289
+    },
+    {
+      "epoch": 1.5675675675675675,
+      "grad_norm": 0.22039195895195007,
+      "learning_rate": 2.7804390604547557e-05,
+      "loss": 0.5405,
+      "step": 290
+    },
+    {
+      "epoch": 1.572972972972973,
+      "grad_norm": 0.19329974055290222,
+      "learning_rate": 2.7154823316113932e-05,
+      "loss": 0.5485,
+      "step": 291
+    },
+    {
+      "epoch": 1.5783783783783782,
+      "grad_norm": 0.1922396570444107,
+      "learning_rate": 2.6511739517872426e-05,
+      "loss": 0.554,
+      "step": 292
+    },
+    {
+      "epoch": 1.5837837837837838,
+      "grad_norm": 0.22808901965618134,
+      "learning_rate": 2.587519644666001e-05,
+      "loss": 0.5453,
+      "step": 293
+    },
+    {
+      "epoch": 1.5891891891891892,
+      "grad_norm": 0.17797237634658813,
+      "learning_rate": 2.5245250757164663e-05,
+      "loss": 0.554,
+      "step": 294
+    },
+    {
+      "epoch": 1.5945945945945947,
+      "grad_norm": 0.2405869960784912,
+      "learning_rate": 2.462195851688306e-05,
+      "loss": 0.5283,
+      "step": 295
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.17364168167114258,
+      "learning_rate": 2.4005375201130274e-05,
+      "loss": 0.5506,
+      "step": 296
+    },
+    {
+      "epoch": 1.6054054054054054,
+      "grad_norm": 0.19880247116088867,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.5295,
+      "step": 297
+    },
+    {
+      "epoch": 1.6108108108108108,
+      "grad_norm": 0.15347057580947876,
+      "learning_rate": 2.2792554253991415e-05,
+      "loss": 0.5462,
+      "step": 298
+    },
+    {
+      "epoch": 1.6162162162162161,
+      "grad_norm": 0.192508727312088,
+      "learning_rate": 2.2196424568156073e-05,
+      "loss": 0.5531,
+      "step": 299
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.1681094914674759,
+      "learning_rate": 2.160721968834344e-05,
+      "loss": 0.5553,
+      "step": 300
+    },
+    {
+      "epoch": 1.627027027027027,
+      "grad_norm": 0.17024287581443787,
+      "learning_rate": 2.102499205596743e-05,
+      "loss": 0.5511,
+      "step": 301
+    },
+    {
+      "epoch": 1.6324324324324324,
+      "grad_norm": 0.17030170559883118,
+      "learning_rate": 2.0449793491441028e-05,
+      "loss": 0.5479,
+      "step": 302
+    },
+    {
+      "epoch": 1.637837837837838,
+      "grad_norm": 0.17550453543663025,
+      "learning_rate": 1.9881675189564254e-05,
+      "loss": 0.549,
+      "step": 303
+    },
+    {
+      "epoch": 1.6432432432432433,
+      "grad_norm": 0.1620909720659256,
+      "learning_rate": 1.93206877149676e-05,
+      "loss": 0.5547,
+      "step": 304
+    },
+    {
+      "epoch": 1.6486486486486487,
+      "grad_norm": 0.18618185818195343,
+      "learning_rate": 1.8766880997611424e-05,
+      "loss": 0.5649,
+      "step": 305
+    },
+    {
+      "epoch": 1.654054054054054,
+      "grad_norm": 0.16562554240226746,
+      "learning_rate": 1.8220304328342252e-05,
+      "loss": 0.5274,
+      "step": 306
+    },
+    {
+      "epoch": 1.6594594594594594,
+      "grad_norm": 0.16524571180343628,
+      "learning_rate": 1.7681006354505493e-05,
+      "loss": 0.5461,
+      "step": 307
+    },
+    {
+      "epoch": 1.6648648648648647,
+      "grad_norm": 0.14831188321113586,
+      "learning_rate": 1.7149035075615794e-05,
+      "loss": 0.5544,
+      "step": 308
+    },
+    {
+      "epoch": 1.6702702702702703,
+      "grad_norm": 0.1687830537557602,
+      "learning_rate": 1.6624437839084862e-05,
+      "loss": 0.5393,
+      "step": 309
+    },
+    {
+      "epoch": 1.6756756756756757,
+      "grad_norm": 0.1825455278158188,
+      "learning_rate": 1.6107261336007285e-05,
+      "loss": 0.5389,
+      "step": 310
+    },
+    {
+      "epoch": 1.6810810810810812,
+      "grad_norm": 0.16670149564743042,
+      "learning_rate": 1.5597551597004966e-05,
+      "loss": 0.5369,
+      "step": 311
+    },
+    {
+      "epoch": 1.6864864864864866,
+      "grad_norm": 0.1589886099100113,
+      "learning_rate": 1.5095353988130235e-05,
+      "loss": 0.5592,
+      "step": 312
+    },
+    {
+      "epoch": 1.691891891891892,
+      "grad_norm": 0.17790549993515015,
+      "learning_rate": 1.4600713206827932e-05,
+      "loss": 0.5612,
+      "step": 313
+    },
+    {
+      "epoch": 1.6972972972972973,
+      "grad_norm": 0.15449143946170807,
+      "learning_rate": 1.4113673277957395e-05,
+      "loss": 0.5439,
+      "step": 314
+    },
+    {
+      "epoch": 1.7027027027027026,
+      "grad_norm": 0.14207641780376434,
+      "learning_rate": 1.3634277549873953e-05,
+      "loss": 0.5411,
+      "step": 315
+    },
+    {
+      "epoch": 1.708108108108108,
+      "grad_norm": 0.16680589318275452,
+      "learning_rate": 1.3162568690570743e-05,
+      "loss": 0.5333,
+      "step": 316
+    },
+    {
+      "epoch": 1.7135135135135136,
+      "grad_norm": 0.16983501613140106,
+      "learning_rate": 1.2698588683881186e-05,
+      "loss": 0.5374,
+      "step": 317
+    },
+    {
+      "epoch": 1.718918918918919,
+      "grad_norm": 0.14857017993927002,
+      "learning_rate": 1.224237882574224e-05,
+      "loss": 0.5399,
+      "step": 318
+    },
+    {
+      "epoch": 1.7243243243243245,
+      "grad_norm": 0.14769425988197327,
+      "learning_rate": 1.1793979720518866e-05,
+      "loss": 0.5586,
+      "step": 319
+    },
+    {
+      "epoch": 1.7297297297297298,
+      "grad_norm": 0.17530100047588348,
+      "learning_rate": 1.1353431277390126e-05,
+      "loss": 0.5618,
+      "step": 320
+    },
+    {
+      "epoch": 1.7351351351351352,
+      "grad_norm": 0.156886026263237,
+      "learning_rate": 1.0920772706797167e-05,
+      "loss": 0.5622,
+      "step": 321
+    },
+    {
+      "epoch": 1.7405405405405405,
+      "grad_norm": 0.14536841213703156,
+      "learning_rate": 1.0496042516953209e-05,
+      "loss": 0.5428,
+      "step": 322
+    },
+    {
+      "epoch": 1.7459459459459459,
+      "grad_norm": 0.162484809756279,
+      "learning_rate": 1.0079278510416313e-05,
+      "loss": 0.5443,
+      "step": 323
+    },
+    {
+      "epoch": 1.7513513513513512,
+      "grad_norm": 0.16919377446174622,
+      "learning_rate": 9.670517780724775e-06,
+      "loss": 0.5431,
+      "step": 324
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.1344226747751236,
+      "learning_rate": 9.269796709095558e-06,
+      "loss": 0.5556,
+      "step": 325
+    },
+    {
+      "epoch": 1.7621621621621621,
+      "grad_norm": 0.14219771325588226,
+      "learning_rate": 8.87715096118642e-06,
+      "loss": 0.5542,
+      "step": 326
+    },
+    {
+      "epoch": 1.7675675675675677,
+      "grad_norm": 0.14828014373779297,
+      "learning_rate": 8.492615483921395e-06,
+      "loss": 0.5307,
+      "step": 327
+    },
+    {
+      "epoch": 1.772972972972973,
+      "grad_norm": 0.15327297151088715,
+      "learning_rate": 8.116224502380387e-06,
+      "loss": 0.5572,
+      "step": 328
+    },
+    {
+      "epoch": 1.7783783783783784,
+      "grad_norm": 0.13973894715309143,
+      "learning_rate": 7.74801151675314e-06,
+      "loss": 0.5585,
+      "step": 329
+    },
+    {
+      "epoch": 1.7837837837837838,
+      "grad_norm": 0.14004996418952942,
+      "learning_rate": 7.3880092993574125e-06,
+      "loss": 0.5583,
+      "step": 330
+    },
+    {
+      "epoch": 1.7891891891891891,
+      "grad_norm": 0.14245465397834778,
+      "learning_rate": 7.03624989172228e-06,
+      "loss": 0.5327,
+      "step": 331
+    },
+    {
+      "epoch": 1.7945945945945945,
+      "grad_norm": 0.13383865356445312,
+      "learning_rate": 6.692764601736268e-06,
+      "loss": 0.5423,
+      "step": 332
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.13818518817424774,
+      "learning_rate": 6.357584000860761e-06,
+      "loss": 0.5416,
+      "step": 333
+    },
+    {
+      "epoch": 1.8054054054054054,
+      "grad_norm": 0.15666233003139496,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.5258,
+      "step": 334
+    },
+    {
+      "epoch": 1.810810810810811,
+      "grad_norm": 0.13427962362766266,
+      "learning_rate": 5.71225545389158e-06,
+      "loss": 0.551,
+      "step": 335
+    },
+    {
+      "epoch": 1.8162162162162163,
+      "grad_norm": 0.4789113402366638,
+      "learning_rate": 5.402164944425758e-06,
+      "loss": 0.5499,
+      "step": 336
+    },
+    {
+      "epoch": 1.8216216216216217,
+      "grad_norm": 0.13906101882457733,
+      "learning_rate": 5.100493992214128e-06,
+      "loss": 0.5499,
+      "step": 337
+    },
+    {
+      "epoch": 1.827027027027027,
+      "grad_norm": 0.13979266583919525,
+      "learning_rate": 4.807269447087348e-06,
+      "loss": 0.5273,
+      "step": 338
+    },
+    {
+      "epoch": 1.8324324324324324,
+      "grad_norm": 0.14405637979507446,
+      "learning_rate": 4.5225174071146455e-06,
+      "loss": 0.5469,
+      "step": 339
+    },
+    {
+      "epoch": 1.8378378378378377,
+      "grad_norm": 0.1318741887807846,
+      "learning_rate": 4.24626321628091e-06,
+      "loss": 0.5507,
+      "step": 340
+    },
+    {
+      "epoch": 1.8432432432432433,
+      "grad_norm": 0.1360122561454773,
+      "learning_rate": 3.9785314622310495e-06,
+      "loss": 0.5467,
+      "step": 341
+    },
+    {
+      "epoch": 1.8486486486486486,
+      "grad_norm": 0.15425017476081848,
+      "learning_rate": 3.7193459740815674e-06,
+      "loss": 0.5557,
+      "step": 342
+    },
+    {
+      "epoch": 1.8540540540540542,
+      "grad_norm": 0.13652145862579346,
+      "learning_rate": 3.4687298202996655e-06,
+      "loss": 0.5512,
+      "step": 343
+    },
+    {
+      "epoch": 1.8594594594594596,
+      "grad_norm": 0.13713712990283966,
+      "learning_rate": 3.226705306650113e-06,
+      "loss": 0.5333,
+      "step": 344
+    },
+    {
+      "epoch": 1.864864864864865,
+      "grad_norm": 0.19826094806194305,
+      "learning_rate": 2.9932939742099208e-06,
+      "loss": 0.5419,
+      "step": 345
+    },
+    {
+      "epoch": 1.8702702702702703,
+      "grad_norm": 0.13193316757678986,
+      "learning_rate": 2.7685165974510986e-06,
+      "loss": 0.5494,
+      "step": 346
+    },
+    {
+      "epoch": 1.8756756756756756,
+      "grad_norm": 0.13418689370155334,
+      "learning_rate": 2.552393182391677e-06,
+      "loss": 0.5572,
+      "step": 347
+    },
+    {
+      "epoch": 1.881081081081081,
+      "grad_norm": 0.1294754445552826,
+      "learning_rate": 2.3449429648150665e-06,
+      "loss": 0.5414,
+      "step": 348
+    },
+    {
+      "epoch": 1.8864864864864865,
+      "grad_norm": 0.12898264825344086,
+      "learning_rate": 2.1461844085580385e-06,
+      "loss": 0.5634,
+      "step": 349
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.12305044382810593,
+      "learning_rate": 1.9561352038673263e-06,
+      "loss": 0.5484,
+      "step": 350
+    },
+    {
+      "epoch": 1.8972972972972975,
+      "grad_norm": 0.14300554990768433,
+      "learning_rate": 1.7748122658251876e-06,
+      "loss": 0.5359,
+      "step": 351
+    },
+    {
+      "epoch": 1.9027027027027028,
+      "grad_norm": 0.12813441455364227,
+      "learning_rate": 1.6022317328438506e-06,
+      "loss": 0.5343,
+      "step": 352
+    },
+    {
+      "epoch": 1.9081081081081082,
+      "grad_norm": 0.12812206149101257,
+      "learning_rate": 1.4384089652291543e-06,
+      "loss": 0.547,
+      "step": 353
+    },
+    {
+      "epoch": 1.9135135135135135,
+      "grad_norm": 0.12215188145637512,
+      "learning_rate": 1.2833585438134287e-06,
+      "loss": 0.561,
+      "step": 354
+    },
+    {
+      "epoch": 1.9189189189189189,
+      "grad_norm": 0.1359054297208786,
+      "learning_rate": 1.1370942686577347e-06,
+      "loss": 0.553,
+      "step": 355
+    },
+    {
+      "epoch": 1.9243243243243242,
+      "grad_norm": 0.13287091255187988,
+      "learning_rate": 9.996291578236228e-07,
+      "loss": 0.5247,
+      "step": 356
+    },
+    {
+      "epoch": 1.9297297297297298,
+      "grad_norm": 0.12276577204465866,
+      "learning_rate": 8.709754462144615e-07,
+      "loss": 0.5427,
+      "step": 357
+    },
+    {
+      "epoch": 1.9351351351351351,
+      "grad_norm": 0.13017451763153076,
+      "learning_rate": 7.511445844864962e-07,
+      "loss": 0.5476,
+      "step": 358
+    },
+    {
+      "epoch": 1.9405405405405407,
+      "grad_norm": 0.12089353799819946,
+      "learning_rate": 6.401472380297091e-07,
+      "loss": 0.5236,
+      "step": 359
+    },
+    {
+      "epoch": 1.945945945945946,
+      "grad_norm": 0.12430868297815323,
+      "learning_rate": 5.379932860185122e-07,
+      "loss": 0.5372,
+      "step": 360
+    },
+    {
+      "epoch": 1.9513513513513514,
+      "grad_norm": 0.11779884248971939,
+      "learning_rate": 4.44691820532539e-07,
+      "loss": 0.5464,
+      "step": 361
+    },
+    {
+      "epoch": 1.9567567567567568,
+      "grad_norm": 0.1252037137746811,
+      "learning_rate": 3.6025114574734785e-07,
+      "loss": 0.564,
+      "step": 362
+    },
+    {
+      "epoch": 1.962162162162162,
+      "grad_norm": 0.11790075153112411,
+      "learning_rate": 2.846787771953574e-07,
+      "loss": 0.5419,
+      "step": 363
+    },
+    {
+      "epoch": 1.9675675675675675,
+      "grad_norm": 0.11766640096902847,
+      "learning_rate": 2.179814410969261e-07,
+      "loss": 0.5334,
+      "step": 364
+    },
+    {
+      "epoch": 1.972972972972973,
+      "grad_norm": 0.11944753676652908,
+      "learning_rate": 1.6016507376169777e-07,
+      "loss": 0.5384,
+      "step": 365
+    },
+    {
+      "epoch": 1.9783783783783784,
+      "grad_norm": 0.12327762693166733,
+      "learning_rate": 1.1123482106021322e-07,
+      "loss": 0.5508,
+      "step": 366
+    },
+    {
+      "epoch": 1.983783783783784,
+      "grad_norm": 0.1193946972489357,
+      "learning_rate": 7.119503796599868e-08,
+      "loss": 0.5294,
+      "step": 367
+    },
+    {
+      "epoch": 1.9891891891891893,
+      "grad_norm": 0.12587259709835052,
+      "learning_rate": 4.0049288167842705e-08,
+      "loss": 0.5297,
+      "step": 368
+    },
+    {
+      "epoch": 1.9945945945945946,
+      "grad_norm": 0.1217728778719902,
+      "learning_rate": 1.7800343752683023e-08,
+      "loss": 0.5367,
+      "step": 369
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.12325151264667511,
+      "learning_rate": 4.4501849589040355e-09,
+      "loss": 0.5457,
+      "step": 370
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 370,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.443139033277399e+19,
+  "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 sha256:8376e5fb3b5233d7c6df79281a4f8ecb4f6315eb253aed76489e1c8a0c5600f6
+size 15032