Upload folder using huggingface_hub

.gitattributes

@@ -66,3 +66,4 @@ philosophy/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 quantum/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 consciousness/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 multi_perspective/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+systems_architecture/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text

systems_architecture/README.md

@@ -39,10 +39,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - PEFT 0.18.1
-- TRL: 0.29.0
+- TRL: 0.29.1
 - Transformers: 5.3.0
 - Pytorch: 2.10.0
-- Datasets: 4.6.1
+- Datasets: 4.8.3
 - Tokenizers: 0.22.2
 
 ## Citations

systems_architecture/adapter_config.json

@@ -29,10 +29,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "o_proj",
     "v_proj",
-    "k_proj",
-    "o_proj"
+    "q_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

systems_architecture/adapter_metadata.json

@@ -0,0 +1,33 @@
+{
+  "adapter_name": "systems_architecture",
+  "framework_version": "Phase6+",
+  "system_prompt": "You are Codette reasoning through the Systems Architecture perspective \u2014 designing robust, scalable AI systems with multi-agent coordination. Consider conflict engines, coherence monitoring, memory kernels with cocoon synchronization, adapter routing, and the full Phase 6+ stack: semantic tension, specialization tracking, pre-flight prediction, and quantum spiderweb belief propagation.",
+  "training_loss": 0.3040390544467502,
+  "global_step": 225,
+  "training_time_seconds": 663.0670442581177,
+  "lora_config": {
+    "r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj"
+    ],
+    "bias": "none"
+  },
+  "training_config": {
+    "per_device_train_batch_size": 2,
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 0.0002,
+    "warmup_ratio": 0.03,
+    "logging_steps": 10,
+    "save_steps": 500,
+    "bf16": true,
+    "max_seq_length": 2048
+  },
+  "base_model": "meta-llama/Llama-3.1-8B-Instruct",
+  "trained_at": "2026-03-21T05:27:36.965534",
+  "dataset_examples": 600
+}

systems_architecture/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efee471763195d927b69b997ce0241b1da6d5364ba980cdc28a2d3ef1306bc07
+oid sha256:b4ccde16ad0db5d86cd141e83c24cf4669a786b9c1bdbeee61725c6c1119b804
 size 27297544

systems_architecture/checkpoint-225/README.md

@@ -0,0 +1,209 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

systems_architecture/checkpoint-225/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

systems_architecture/checkpoint-225/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ccde16ad0db5d86cd141e83c24cf4669a786b9c1bdbeee61725c6c1119b804
+size 27297544

systems_architecture/checkpoint-225/chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

systems_architecture/checkpoint-225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f55b4841c53cc63f30ad5cdcd61986d01c604be841d8817fe290605bed0c26
+size 54745547

systems_architecture/checkpoint-225/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b337e239dd6a62e57515601667baa54878263cc9866086714b01384d8b3490
+size 14645

systems_architecture/checkpoint-225/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06eb2e4f2392d5cff7633897aae6c92765ee0ff18fac8b62001d1a06409563d4
+size 1465

systems_architecture/checkpoint-225/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

systems_architecture/checkpoint-225/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

systems_architecture/checkpoint-225/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 3.3168428897857667,
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.0001981651376146789,
+      "loss": 3.7326873779296874,
+      "mean_token_accuracy": 0.4232572212815285,
+      "num_tokens": 22402.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.6598962008953095,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.0001889908256880734,
+      "loss": 1.474141788482666,
+      "mean_token_accuracy": 0.6977864518761635,
+      "num_tokens": 44840.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.32826780080795287,
+      "epoch": 0.4,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 0.0001798165137614679,
+      "loss": 0.2932713747024536,
+      "mean_token_accuracy": 0.9431452080607414,
+      "num_tokens": 67271.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.20731838978827,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.130859375,
+      "learning_rate": 0.0001706422018348624,
+      "loss": 0.18721930980682372,
+      "mean_token_accuracy": 0.9637655198574067,
+      "num_tokens": 89665.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.17729159593582153,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 0.00016146788990825688,
+      "loss": 0.15150076150894165,
+      "mean_token_accuracy": 0.9707357078790665,
+      "num_tokens": 112054.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.15239670984447,
+      "epoch": 0.8,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00015229357798165138,
+      "loss": 0.12725087404251098,
+      "mean_token_accuracy": 0.9726672366261482,
+      "num_tokens": 134487.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.1229453705251217,
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 0.0001431192660550459,
+      "loss": 0.1012193202972412,
+      "mean_token_accuracy": 0.9769004106521606,
+      "num_tokens": 156897.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.08543421998620034,
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.00013394495412844036,
+      "loss": 0.08416919708251953,
+      "mean_token_accuracy": 0.979321151971817,
+      "num_tokens": 179260.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.08846638891845941,
+      "epoch": 1.2,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00012477064220183488,
+      "loss": 0.07037656307220459,
+      "mean_token_accuracy": 0.9801889300346375,
+      "num_tokens": 201692.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.08574241194874048,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 0.00011559633027522936,
+      "loss": 0.05919719934463501,
+      "mean_token_accuracy": 0.980514743924141,
+      "num_tokens": 224049.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.08276224136352539,
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.00010642201834862387,
+      "loss": 0.05210116505622864,
+      "mean_token_accuracy": 0.9806599587202072,
+      "num_tokens": 246511.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.07124831397086381,
+      "epoch": 1.6,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 9.724770642201836e-05,
+      "loss": 0.04895032346248627,
+      "mean_token_accuracy": 0.9810128688812256,
+      "num_tokens": 268928.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.06570714842528105,
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 8.807339449541285e-05,
+      "loss": 0.04789784550666809,
+      "mean_token_accuracy": 0.9804875090718269,
+      "num_tokens": 291299.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.05858572842553258,
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.064453125,
+      "learning_rate": 7.889908256880735e-05,
+      "loss": 0.04485383927822113,
+      "mean_token_accuracy": 0.9811065629124641,
+      "num_tokens": 313720.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.05700928270816803,
+      "epoch": 2.0,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 6.972477064220184e-05,
+      "loss": 0.04462524354457855,
+      "mean_token_accuracy": 0.9801488563418388,
+      "num_tokens": 336120.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.053518883883953094,
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 6.055045871559634e-05,
+      "loss": 0.043404501676559445,
+      "mean_token_accuracy": 0.9804914385080338,
+      "num_tokens": 358557.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05389656974002719,
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.07373046875,
+      "learning_rate": 5.137614678899083e-05,
+      "loss": 0.042660146951675415,
+      "mean_token_accuracy": 0.9813649311661721,
+      "num_tokens": 380965.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.05118206962943077,
+      "epoch": 2.4,
+      "grad_norm": 0.06982421875,
+      "learning_rate": 4.2201834862385324e-05,
+      "loss": 0.043095368146896365,
+      "mean_token_accuracy": 0.9810103073716163,
+      "num_tokens": 403375.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.05230644857510924,
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 3.302752293577982e-05,
+      "loss": 0.04297981262207031,
+      "mean_token_accuracy": 0.9805112361907959,
+      "num_tokens": 425827.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.05161624262109399,
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 2.3853211009174313e-05,
+      "loss": 0.04285256862640381,
+      "mean_token_accuracy": 0.9807584524154663,
+      "num_tokens": 448146.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.052343995217233895,
+      "epoch": 2.8,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 1.4678899082568809e-05,
+      "loss": 0.04282132387161255,
+      "mean_token_accuracy": 0.9799860909581184,
+      "num_tokens": 470550.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.05234320750460029,
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.06640625,
+      "learning_rate": 5.504587155963303e-06,
+      "loss": 0.042635363340377805,
+      "mean_token_accuracy": 0.9812853425741196,
+      "num_tokens": 492952.0,
+      "step": 220
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.291403294081024e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

systems_architecture/checkpoint-225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7adf5366e1f3a3d177f0801d84e2b0efb8b20382389e4d5d492b16ad5565e16
+size 5649