Upload folder using huggingface_hub

.gitattributes

@@ -61,3 +61,4 @@ systems_architecture/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs
 systems_architecture/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 newton/checkpoint-309/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 davinci/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+empathy/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text

empathy/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

empathy/adapter_config.json

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

empathy/adapter_metadata.json

@@ -0,0 +1,33 @@
+{
+  "adapter_name": "empathy",
+  "framework_version": "Phase6+",
+  "system_prompt": "You are Codette reasoning through the Empathy perspective \u2014 deep emotional intelligence and compassionate understanding. Consider human impact, emotional dynamics, and relational contexts. Monitor the \u0393 (gamma) coherence field for signs of emotional collapse or groupthink, and ensure diverse emotional perspectives are heard in multi-agent synthesis.",
+  "training_loss": 0.2755344698164198,
+  "global_step": 225,
+  "training_time_seconds": 586.899035692215,
+  "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": "2026-03-21T04:31:13.631938",
+  "dataset_examples": 600
+}

empathy/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae48e5ab42f5024f6e9ac24cbbc8e54d07a151740a4c6c5ea834fcaf78101d45
+oid sha256:135a18e8e1dac45587863efd24951eb569a086873f671a9374855ee9eae569bc
 size 27297544

empathy/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

empathy/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
+}

empathy/checkpoint-225/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135a18e8e1dac45587863efd24951eb569a086873f671a9374855ee9eae569bc
+size 27297544

empathy/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 %}

empathy/checkpoint-225/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d0bceedfb958cb8b39013adde5eb1d56523a59c207b7a37b3405abd668ac67
+size 54745547

empathy/checkpoint-225/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a91976ae606e5b25f6d20196e69161e83b50d52f37f8d66a866475d512ada0c
+size 14645

empathy/checkpoint-225/scheduler.pt

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

empathy/checkpoint-225/tokenizer.json

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

empathy/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"
+}

empathy/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": 2.897894632816315,
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.68359375,
+      "learning_rate": 0.0001981651376146789,
+      "loss": 3.3895343780517577,
+      "mean_token_accuracy": 0.39105663225054743,
+      "num_tokens": 19397.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.30903180539608,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.0001889908256880734,
+      "loss": 1.1704865455627442,
+      "mean_token_accuracy": 0.7269252099096775,
+      "num_tokens": 38750.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.2904857821762562,
+      "epoch": 0.4,
+      "grad_norm": 0.2265625,
+      "learning_rate": 0.0001798165137614679,
+      "loss": 0.2687561273574829,
+      "mean_token_accuracy": 0.9464940577745438,
+      "num_tokens": 58118.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.19717175513505936,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.216796875,
+      "learning_rate": 0.0001706422018348624,
+      "loss": 0.17607879638671875,
+      "mean_token_accuracy": 0.963988620042801,
+      "num_tokens": 77367.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.1757684949785471,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.00016146788990825688,
+      "loss": 0.1459679365158081,
+      "mean_token_accuracy": 0.9703710302710533,
+      "num_tokens": 96686.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.1548028452321887,
+      "epoch": 0.8,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00015229357798165138,
+      "loss": 0.11948602199554444,
+      "mean_token_accuracy": 0.973386998474598,
+      "num_tokens": 116049.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.11460858676582575,
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.0001431192660550459,
+      "loss": 0.09452807307243347,
+      "mean_token_accuracy": 0.9758242100477219,
+      "num_tokens": 135467.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.10981992147862911,
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.00013394495412844036,
+      "loss": 0.077480947971344,
+      "mean_token_accuracy": 0.9775464102625847,
+      "num_tokens": 154804.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.09666569568216801,
+      "epoch": 1.2,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00012477064220183488,
+      "loss": 0.06523213386535645,
+      "mean_token_accuracy": 0.9759517714381218,
+      "num_tokens": 174285.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.08109560571610927,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.00011559633027522936,
+      "loss": 0.05769284963607788,
+      "mean_token_accuracy": 0.9774119958281517,
+      "num_tokens": 193589.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.0701230232603848,
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.00010642201834862387,
+      "loss": 0.05422154664993286,
+      "mean_token_accuracy": 0.9776731297373772,
+      "num_tokens": 212972.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.06490475619211793,
+      "epoch": 1.6,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 9.724770642201836e-05,
+      "loss": 0.05352028608322144,
+      "mean_token_accuracy": 0.9779922246932984,
+      "num_tokens": 232250.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.06063666203990579,
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.0703125,
+      "learning_rate": 8.807339449541285e-05,
+      "loss": 0.05314930081367493,
+      "mean_token_accuracy": 0.9777614757418632,
+      "num_tokens": 251569.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.05910242944955826,
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 7.889908256880735e-05,
+      "loss": 0.051131260395050046,
+      "mean_token_accuracy": 0.9775439739227295,
+      "num_tokens": 270955.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.05751125598326325,
+      "epoch": 2.0,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 6.972477064220184e-05,
+      "loss": 0.05118877291679382,
+      "mean_token_accuracy": 0.9780693486332893,
+      "num_tokens": 290352.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.05718929748982191,
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 6.055045871559634e-05,
+      "loss": 0.049891358613967894,
+      "mean_token_accuracy": 0.977837698161602,
+      "num_tokens": 309584.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05678784549236297,
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 5.137614678899083e-05,
+      "loss": 0.050064748525619505,
+      "mean_token_accuracy": 0.9775785893201828,
+      "num_tokens": 328990.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.05620679594576359,
+      "epoch": 2.4,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 4.2201834862385324e-05,
+      "loss": 0.04963530302047729,
+      "mean_token_accuracy": 0.9776954010128975,
+      "num_tokens": 348313.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.05504842037335038,
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 3.302752293577982e-05,
+      "loss": 0.04906564950942993,
+      "mean_token_accuracy": 0.9781395196914673,
+      "num_tokens": 367855.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.05551012922078371,
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 2.3853211009174313e-05,
+      "loss": 0.04961824715137482,
+      "mean_token_accuracy": 0.9774622082710266,
+      "num_tokens": 387132.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.054633275233209135,
+      "epoch": 2.8,
+      "grad_norm": 0.080078125,
+      "learning_rate": 1.4678899082568809e-05,
+      "loss": 0.04972724318504333,
+      "mean_token_accuracy": 0.9787201777100563,
+      "num_tokens": 406498.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.05616894159466028,
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.05859375,
+      "learning_rate": 5.504587155963303e-06,
+      "loss": 0.04895650148391724,
+      "mean_token_accuracy": 0.9786889955401421,
+      "num_tokens": 425872.0,
+      "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": 2.005595907637248e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

empathy/checkpoint-225/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64d4e636d5c0eb6e65352529689dee60289c387b4536f3e0b17f48b352ee585
+size 5585