Upload folder using huggingface_hub

.gitattributes

@@ -40,3 +40,6 @@ newton/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 davinci/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 davinci/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 davinci/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+empathy/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+empathy/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+empathy/tokenizer.json filter=lfs diff=lfs merge=lfs -text

empathy/README.md

@@ -0,0 +1,62 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+model_name: empathy
+tags:
+- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for empathy
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.29.0
+- Transformers: 5.3.0
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

empathy/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": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

empathy/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae48e5ab42f5024f6e9ac24cbbc8e54d07a151740a4c6c5ea834fcaf78101d45
+size 27297544

empathy/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-500/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-500/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": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

empathy/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b363fb47e7bc49ee535548078e136edbf60c8cbde25a51319be8e00c5b1deaf
+size 27297544

empathy/checkpoint-500/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-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf1d1e0cabd9f52f8c0d4d73721bfc9bea7825fc4bde641425de27f1f77ccba
+size 54745547

empathy/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6daf2865697b5429d29f0477ad615fdf3874eaecc852e74fe108011ff0eb9a9
+size 14645

empathy/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820927e41cd14e86356818cda9df54ef4ef3f4c3a4d4b7a28cbf4df629afd0fd
+size 1465

empathy/checkpoint-500/tokenizer.json

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

empathy/checkpoint-500/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-500/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5984,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.7027451276779173,
+      "epoch": 0.032,
+      "grad_norm": 0.263671875,
+      "learning_rate": 6.206896551724138e-05,
+      "loss": 2.8736827850341795,
+      "mean_token_accuracy": 0.45954256504774094,
+      "num_tokens": 55882.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.2726758420467377,
+      "epoch": 0.064,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 0.00013103448275862068,
+      "loss": 2.4437068939208983,
+      "mean_token_accuracy": 0.5048861749470234,
+      "num_tokens": 111677.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.816487193107605,
+      "epoch": 0.096,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.0002,
+      "loss": 1.7309745788574218,
+      "mean_token_accuracy": 0.6087440773844719,
+      "num_tokens": 167580.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1870245933532715,
+      "epoch": 0.128,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.0001978021978021978,
+      "loss": 1.1468750953674316,
+      "mean_token_accuracy": 0.7256016343832016,
+      "num_tokens": 223679.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8109098121523857,
+      "epoch": 0.16,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00019560439560439562,
+      "loss": 0.7429761409759521,
+      "mean_token_accuracy": 0.8220725610852242,
+      "num_tokens": 279556.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5473626285791398,
+      "epoch": 0.192,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00019340659340659342,
+      "loss": 0.4774918556213379,
+      "mean_token_accuracy": 0.8853456184267998,
+      "num_tokens": 335848.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.35489378273487093,
+      "epoch": 0.224,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00019120879120879122,
+      "loss": 0.2937335968017578,
+      "mean_token_accuracy": 0.9316855490207672,
+      "num_tokens": 392355.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.25775772109627726,
+      "epoch": 0.256,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00018901098901098903,
+      "loss": 0.21065135002136232,
+      "mean_token_accuracy": 0.9512736469507217,
+      "num_tokens": 448792.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.20272715911269187,
+      "epoch": 0.288,
+      "grad_norm": 0.1953125,
+      "learning_rate": 0.00018681318681318683,
+      "loss": 0.1630323886871338,
+      "mean_token_accuracy": 0.9601437523961067,
+      "num_tokens": 505118.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.15652943775057793,
+      "epoch": 0.32,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.13783388137817382,
+      "mean_token_accuracy": 0.9648320719599723,
+      "num_tokens": 562043.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.13883790336549282,
+      "epoch": 0.352,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.0001824175824175824,
+      "loss": 0.1205636978149414,
+      "mean_token_accuracy": 0.9679180562496186,
+      "num_tokens": 618572.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.1294231442734599,
+      "epoch": 0.384,
+      "grad_norm": 0.142578125,
+      "learning_rate": 0.00018021978021978024,
+      "loss": 0.10652012825012207,
+      "mean_token_accuracy": 0.9696741059422493,
+      "num_tokens": 674953.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.12372843902558088,
+      "epoch": 0.416,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00017802197802197802,
+      "loss": 0.09909504652023315,
+      "mean_token_accuracy": 0.9700024798512459,
+      "num_tokens": 730476.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.11392448395490647,
+      "epoch": 0.448,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.00017582417582417582,
+      "loss": 0.09517329335212707,
+      "mean_token_accuracy": 0.9697632819414139,
+      "num_tokens": 786626.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.10535773131996393,
+      "epoch": 0.48,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.00017362637362637365,
+      "loss": 0.08859028220176697,
+      "mean_token_accuracy": 0.9710599616169929,
+      "num_tokens": 842780.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.1028441235423088,
+      "epoch": 0.512,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.08795538544654846,
+      "mean_token_accuracy": 0.9719248920679092,
+      "num_tokens": 898828.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.09524063598364592,
+      "epoch": 0.544,
+      "grad_norm": 0.17578125,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.0860197126865387,
+      "mean_token_accuracy": 0.9718463212251663,
+      "num_tokens": 955109.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.09921295028179884,
+      "epoch": 0.576,
+      "grad_norm": 0.11328125,
+      "learning_rate": 0.00016703296703296706,
+      "loss": 0.08638875484466553,
+      "mean_token_accuracy": 0.9711567848920822,
+      "num_tokens": 1010735.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.09508467447012663,
+      "epoch": 0.608,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.00016483516483516484,
+      "loss": 0.08325063586235046,
+      "mean_token_accuracy": 0.9720648273825645,
+      "num_tokens": 1067222.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.09094681274145841,
+      "epoch": 0.64,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.00016263736263736264,
+      "loss": 0.0826878547668457,
+      "mean_token_accuracy": 0.9720210924744606,
+      "num_tokens": 1122748.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.09381346199661493,
+      "epoch": 0.672,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.00016043956043956044,
+      "loss": 0.08256186246871948,
+      "mean_token_accuracy": 0.9720484882593154,
+      "num_tokens": 1178643.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.09017684925347566,
+      "epoch": 0.704,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00015824175824175824,
+      "loss": 0.08275171518325805,
+      "mean_token_accuracy": 0.9719254687428475,
+      "num_tokens": 1234871.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.08761313948780299,
+      "epoch": 0.736,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.00015604395604395605,
+      "loss": 0.08114268779754638,
+      "mean_token_accuracy": 0.9720645502209664,
+      "num_tokens": 1290368.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.08477144911885262,
+      "epoch": 0.768,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.07812036871910095,
+      "mean_token_accuracy": 0.9725761353969574,
+      "num_tokens": 1347259.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.0840575411915779,
+      "epoch": 0.8,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 0.00015164835164835165,
+      "loss": 0.07779947519302369,
+      "mean_token_accuracy": 0.9721481159329415,
+      "num_tokens": 1404092.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.08560035470873117,
+      "epoch": 0.832,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 0.00014945054945054946,
+      "loss": 0.07757753729820252,
+      "mean_token_accuracy": 0.9719480901956559,
+      "num_tokens": 1460432.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.08481895942240954,
+      "epoch": 0.864,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 0.00014725274725274726,
+      "loss": 0.07894231081008911,
+      "mean_token_accuracy": 0.9720895797014236,
+      "num_tokens": 1516153.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.08592585939913988,
+      "epoch": 0.896,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 0.00014505494505494506,
+      "loss": 0.07765401601791382,
+      "mean_token_accuracy": 0.973065185546875,
+      "num_tokens": 1572583.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.0848662929609418,
+      "epoch": 0.928,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.07779905796051026,
+      "mean_token_accuracy": 0.9732325404882431,
+      "num_tokens": 1628569.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.08204772900789976,
+      "epoch": 0.96,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00014065934065934067,
+      "loss": 0.07686090469360352,
+      "mean_token_accuracy": 0.9732487082481385,
+      "num_tokens": 1684838.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.08476632833480835,
+      "epoch": 0.992,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.076432603597641,
+      "mean_token_accuracy": 0.9719811454415321,
+      "num_tokens": 1741902.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.07945429298438524,
+      "epoch": 1.0224,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.00013626373626373628,
+      "loss": 0.07495068311691284,
+      "mean_token_accuracy": 0.9731942399551994,
+      "num_tokens": 1795784.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.0806297117844224,
+      "epoch": 1.0544,
+      "grad_norm": 0.076171875,
+      "learning_rate": 0.00013406593406593405,
+      "loss": 0.07468733191490173,
+      "mean_token_accuracy": 0.9737721592187881,
+      "num_tokens": 1852266.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.07759423423558473,
+      "epoch": 1.0864,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 0.00013186813186813188,
+      "loss": 0.07366250157356262,
+      "mean_token_accuracy": 0.9733460173010826,
+      "num_tokens": 1908148.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.08119724169373513,
+      "epoch": 1.1184,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 0.0001296703296703297,
+      "loss": 0.07312369346618652,
+      "mean_token_accuracy": 0.97357087880373,
+      "num_tokens": 1964791.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.07786643356084824,
+      "epoch": 1.1504,
+      "grad_norm": 0.04833984375,
+      "learning_rate": 0.00012747252747252746,
+      "loss": 0.07509608864784241,
+      "mean_token_accuracy": 0.9725616052746773,
+      "num_tokens": 2020416.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.07941898722201586,
+      "epoch": 1.1824,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.00012527472527472527,
+      "loss": 0.0736158847808838,
+      "mean_token_accuracy": 0.9736046925187111,
+      "num_tokens": 2076384.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.0761857332661748,
+      "epoch": 1.2144,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.07236781120300292,
+      "mean_token_accuracy": 0.9739944905042648,
+      "num_tokens": 2132795.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.07662795521318913,
+      "epoch": 1.2464,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.00012087912087912087,
+      "loss": 0.07198388576507568,
+      "mean_token_accuracy": 0.9738625854253768,
+      "num_tokens": 2189096.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.07697693575173617,
+      "epoch": 1.2784,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.00011868131868131869,
+      "loss": 0.07262890338897705,
+      "mean_token_accuracy": 0.9728588461875916,
+      "num_tokens": 2245179.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.07774264849722386,
+      "epoch": 1.3104,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 0.0001164835164835165,
+      "loss": 0.07280476689338684,
+      "mean_token_accuracy": 0.9733426690101623,
+      "num_tokens": 2300662.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.07713319007307291,
+      "epoch": 1.3424,
+      "grad_norm": 0.048583984375,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.07291589379310608,
+      "mean_token_accuracy": 0.9731875821948052,
+      "num_tokens": 2356598.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.07562742829322815,
+      "epoch": 1.3744,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 0.0001120879120879121,
+      "loss": 0.0718300998210907,
+      "mean_token_accuracy": 0.9734191030263901,
+      "num_tokens": 2412737.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.07663317285478115,
+      "epoch": 1.4064,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 0.0001098901098901099,
+      "loss": 0.0707779049873352,
+      "mean_token_accuracy": 0.9742564350366593,
+      "num_tokens": 2469165.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.07312421463429927,
+      "epoch": 1.4384000000000001,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.07058998346328735,
+      "mean_token_accuracy": 0.9742231473326683,
+      "num_tokens": 2525741.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07522066552191972,
+      "epoch": 1.4704,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 0.0001054945054945055,
+      "loss": 0.07139057517051697,
+      "mean_token_accuracy": 0.9742771983146667,
+      "num_tokens": 2582350.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.07417810596525669,
+      "epoch": 1.5024,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 0.00010329670329670331,
+      "loss": 0.0715557336807251,
+      "mean_token_accuracy": 0.9731055706739425,
+      "num_tokens": 2638763.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.07531943805515766,
+      "epoch": 1.5344,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 0.0001010989010989011,
+      "loss": 0.07040765285491943,
+      "mean_token_accuracy": 0.9743428856134415,
+      "num_tokens": 2695023.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.0734874278306961,
+      "epoch": 1.5664,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 9.89010989010989e-05,
+      "loss": 0.07134199142456055,
+      "mean_token_accuracy": 0.9733200684189797,
+      "num_tokens": 2751169.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.07535444647073745,
+      "epoch": 1.5984,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 9.670329670329671e-05,
+      "loss": 0.07132225036621094,
+      "mean_token_accuracy": 0.9734165251255036,
+      "num_tokens": 2807473.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.308143060299776e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

empathy/checkpoint-500/training_args.bin

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

empathy/checkpoint-939/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-939/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": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

empathy/checkpoint-939/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae48e5ab42f5024f6e9ac24cbbc8e54d07a151740a4c6c5ea834fcaf78101d45
+size 27297544

empathy/checkpoint-939/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-939/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379490fef5b9bf34f48733bc7918abffb9a3c4850e88d06eb7df9d048b190c1a
+size 54745547

empathy/checkpoint-939/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306e875b35c7ba49c246721674926c4364905aba32560771a2e499d5f56edc8f
+size 14645

empathy/checkpoint-939/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85b9d8d75b43f2deffbdf4c4ecce548860c65bc59c665b7c0dfc2918984f3a7
+size 1465

empathy/checkpoint-939/tokenizer.json

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

empathy/checkpoint-939/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-939/trainer_state.json

@@ -0,0 +1,964 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.7027451276779173,
+      "epoch": 0.032,
+      "grad_norm": 0.263671875,
+      "learning_rate": 6.206896551724138e-05,
+      "loss": 2.8736827850341795,
+      "mean_token_accuracy": 0.45954256504774094,
+      "num_tokens": 55882.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.2726758420467377,
+      "epoch": 0.064,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 0.00013103448275862068,
+      "loss": 2.4437068939208983,
+      "mean_token_accuracy": 0.5048861749470234,
+      "num_tokens": 111677.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.816487193107605,
+      "epoch": 0.096,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.0002,
+      "loss": 1.7309745788574218,
+      "mean_token_accuracy": 0.6087440773844719,
+      "num_tokens": 167580.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1870245933532715,
+      "epoch": 0.128,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.0001978021978021978,
+      "loss": 1.1468750953674316,
+      "mean_token_accuracy": 0.7256016343832016,
+      "num_tokens": 223679.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8109098121523857,
+      "epoch": 0.16,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00019560439560439562,
+      "loss": 0.7429761409759521,
+      "mean_token_accuracy": 0.8220725610852242,
+      "num_tokens": 279556.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5473626285791398,
+      "epoch": 0.192,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00019340659340659342,
+      "loss": 0.4774918556213379,
+      "mean_token_accuracy": 0.8853456184267998,
+      "num_tokens": 335848.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.35489378273487093,
+      "epoch": 0.224,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00019120879120879122,
+      "loss": 0.2937335968017578,
+      "mean_token_accuracy": 0.9316855490207672,
+      "num_tokens": 392355.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.25775772109627726,
+      "epoch": 0.256,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00018901098901098903,
+      "loss": 0.21065135002136232,
+      "mean_token_accuracy": 0.9512736469507217,
+      "num_tokens": 448792.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.20272715911269187,
+      "epoch": 0.288,
+      "grad_norm": 0.1953125,
+      "learning_rate": 0.00018681318681318683,
+      "loss": 0.1630323886871338,
+      "mean_token_accuracy": 0.9601437523961067,
+      "num_tokens": 505118.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.15652943775057793,
+      "epoch": 0.32,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.13783388137817382,
+      "mean_token_accuracy": 0.9648320719599723,
+      "num_tokens": 562043.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.13883790336549282,
+      "epoch": 0.352,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.0001824175824175824,
+      "loss": 0.1205636978149414,
+      "mean_token_accuracy": 0.9679180562496186,
+      "num_tokens": 618572.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.1294231442734599,
+      "epoch": 0.384,
+      "grad_norm": 0.142578125,
+      "learning_rate": 0.00018021978021978024,
+      "loss": 0.10652012825012207,
+      "mean_token_accuracy": 0.9696741059422493,
+      "num_tokens": 674953.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.12372843902558088,
+      "epoch": 0.416,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00017802197802197802,
+      "loss": 0.09909504652023315,
+      "mean_token_accuracy": 0.9700024798512459,
+      "num_tokens": 730476.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.11392448395490647,
+      "epoch": 0.448,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.00017582417582417582,
+      "loss": 0.09517329335212707,
+      "mean_token_accuracy": 0.9697632819414139,
+      "num_tokens": 786626.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.10535773131996393,
+      "epoch": 0.48,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.00017362637362637365,
+      "loss": 0.08859028220176697,
+      "mean_token_accuracy": 0.9710599616169929,
+      "num_tokens": 842780.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.1028441235423088,
+      "epoch": 0.512,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.08795538544654846,
+      "mean_token_accuracy": 0.9719248920679092,
+      "num_tokens": 898828.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.09524063598364592,
+      "epoch": 0.544,
+      "grad_norm": 0.17578125,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.0860197126865387,
+      "mean_token_accuracy": 0.9718463212251663,
+      "num_tokens": 955109.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.09921295028179884,
+      "epoch": 0.576,
+      "grad_norm": 0.11328125,
+      "learning_rate": 0.00016703296703296706,
+      "loss": 0.08638875484466553,
+      "mean_token_accuracy": 0.9711567848920822,
+      "num_tokens": 1010735.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.09508467447012663,
+      "epoch": 0.608,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.00016483516483516484,
+      "loss": 0.08325063586235046,
+      "mean_token_accuracy": 0.9720648273825645,
+      "num_tokens": 1067222.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.09094681274145841,
+      "epoch": 0.64,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.00016263736263736264,
+      "loss": 0.0826878547668457,
+      "mean_token_accuracy": 0.9720210924744606,
+      "num_tokens": 1122748.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.09381346199661493,
+      "epoch": 0.672,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.00016043956043956044,
+      "loss": 0.08256186246871948,
+      "mean_token_accuracy": 0.9720484882593154,
+      "num_tokens": 1178643.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.09017684925347566,
+      "epoch": 0.704,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00015824175824175824,
+      "loss": 0.08275171518325805,
+      "mean_token_accuracy": 0.9719254687428475,
+      "num_tokens": 1234871.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.08761313948780299,
+      "epoch": 0.736,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.00015604395604395605,
+      "loss": 0.08114268779754638,
+      "mean_token_accuracy": 0.9720645502209664,
+      "num_tokens": 1290368.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.08477144911885262,
+      "epoch": 0.768,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.07812036871910095,
+      "mean_token_accuracy": 0.9725761353969574,
+      "num_tokens": 1347259.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.0840575411915779,
+      "epoch": 0.8,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 0.00015164835164835165,
+      "loss": 0.07779947519302369,
+      "mean_token_accuracy": 0.9721481159329415,
+      "num_tokens": 1404092.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.08560035470873117,
+      "epoch": 0.832,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 0.00014945054945054946,
+      "loss": 0.07757753729820252,
+      "mean_token_accuracy": 0.9719480901956559,
+      "num_tokens": 1460432.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.08481895942240954,
+      "epoch": 0.864,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 0.00014725274725274726,
+      "loss": 0.07894231081008911,
+      "mean_token_accuracy": 0.9720895797014236,
+      "num_tokens": 1516153.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.08592585939913988,
+      "epoch": 0.896,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 0.00014505494505494506,
+      "loss": 0.07765401601791382,
+      "mean_token_accuracy": 0.973065185546875,
+      "num_tokens": 1572583.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.0848662929609418,
+      "epoch": 0.928,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.07779905796051026,
+      "mean_token_accuracy": 0.9732325404882431,
+      "num_tokens": 1628569.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.08204772900789976,
+      "epoch": 0.96,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00014065934065934067,
+      "loss": 0.07686090469360352,
+      "mean_token_accuracy": 0.9732487082481385,
+      "num_tokens": 1684838.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.08476632833480835,
+      "epoch": 0.992,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.076432603597641,
+      "mean_token_accuracy": 0.9719811454415321,
+      "num_tokens": 1741902.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.07945429298438524,
+      "epoch": 1.0224,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.00013626373626373628,
+      "loss": 0.07495068311691284,
+      "mean_token_accuracy": 0.9731942399551994,
+      "num_tokens": 1795784.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.0806297117844224,
+      "epoch": 1.0544,
+      "grad_norm": 0.076171875,
+      "learning_rate": 0.00013406593406593405,
+      "loss": 0.07468733191490173,
+      "mean_token_accuracy": 0.9737721592187881,
+      "num_tokens": 1852266.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.07759423423558473,
+      "epoch": 1.0864,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 0.00013186813186813188,
+      "loss": 0.07366250157356262,
+      "mean_token_accuracy": 0.9733460173010826,
+      "num_tokens": 1908148.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.08119724169373513,
+      "epoch": 1.1184,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 0.0001296703296703297,
+      "loss": 0.07312369346618652,
+      "mean_token_accuracy": 0.97357087880373,
+      "num_tokens": 1964791.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.07786643356084824,
+      "epoch": 1.1504,
+      "grad_norm": 0.04833984375,
+      "learning_rate": 0.00012747252747252746,
+      "loss": 0.07509608864784241,
+      "mean_token_accuracy": 0.9725616052746773,
+      "num_tokens": 2020416.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.07941898722201586,
+      "epoch": 1.1824,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.00012527472527472527,
+      "loss": 0.0736158847808838,
+      "mean_token_accuracy": 0.9736046925187111,
+      "num_tokens": 2076384.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.0761857332661748,
+      "epoch": 1.2144,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.07236781120300292,
+      "mean_token_accuracy": 0.9739944905042648,
+      "num_tokens": 2132795.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.07662795521318913,
+      "epoch": 1.2464,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.00012087912087912087,
+      "loss": 0.07198388576507568,
+      "mean_token_accuracy": 0.9738625854253768,
+      "num_tokens": 2189096.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.07697693575173617,
+      "epoch": 1.2784,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.00011868131868131869,
+      "loss": 0.07262890338897705,
+      "mean_token_accuracy": 0.9728588461875916,
+      "num_tokens": 2245179.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.07774264849722386,
+      "epoch": 1.3104,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 0.0001164835164835165,
+      "loss": 0.07280476689338684,
+      "mean_token_accuracy": 0.9733426690101623,
+      "num_tokens": 2300662.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.07713319007307291,
+      "epoch": 1.3424,
+      "grad_norm": 0.048583984375,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.07291589379310608,
+      "mean_token_accuracy": 0.9731875821948052,
+      "num_tokens": 2356598.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.07562742829322815,
+      "epoch": 1.3744,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 0.0001120879120879121,
+      "loss": 0.0718300998210907,
+      "mean_token_accuracy": 0.9734191030263901,
+      "num_tokens": 2412737.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.07663317285478115,
+      "epoch": 1.4064,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 0.0001098901098901099,
+      "loss": 0.0707779049873352,
+      "mean_token_accuracy": 0.9742564350366593,
+      "num_tokens": 2469165.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.07312421463429927,
+      "epoch": 1.4384000000000001,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.07058998346328735,
+      "mean_token_accuracy": 0.9742231473326683,
+      "num_tokens": 2525741.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07522066552191972,
+      "epoch": 1.4704,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 0.0001054945054945055,
+      "loss": 0.07139057517051697,
+      "mean_token_accuracy": 0.9742771983146667,
+      "num_tokens": 2582350.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.07417810596525669,
+      "epoch": 1.5024,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 0.00010329670329670331,
+      "loss": 0.0715557336807251,
+      "mean_token_accuracy": 0.9731055706739425,
+      "num_tokens": 2638763.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.07531943805515766,
+      "epoch": 1.5344,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 0.0001010989010989011,
+      "loss": 0.07040765285491943,
+      "mean_token_accuracy": 0.9743428856134415,
+      "num_tokens": 2695023.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.0734874278306961,
+      "epoch": 1.5664,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 9.89010989010989e-05,
+      "loss": 0.07134199142456055,
+      "mean_token_accuracy": 0.9733200684189797,
+      "num_tokens": 2751169.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.07535444647073745,
+      "epoch": 1.5984,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 9.670329670329671e-05,
+      "loss": 0.07132225036621094,
+      "mean_token_accuracy": 0.9734165251255036,
+      "num_tokens": 2807473.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.07486743628978729,
+      "epoch": 1.6303999999999998,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 9.450549450549451e-05,
+      "loss": 0.0716746211051941,
+      "mean_token_accuracy": 0.9733885332942009,
+      "num_tokens": 2863590.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.07372102495282888,
+      "epoch": 1.6623999999999999,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 0.0713922917842865,
+      "mean_token_accuracy": 0.973819674551487,
+      "num_tokens": 2919811.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.07463319394737482,
+      "epoch": 1.6944,
+      "grad_norm": 0.0419921875,
+      "learning_rate": 9.010989010989012e-05,
+      "loss": 0.0703410565853119,
+      "mean_token_accuracy": 0.9737539097666741,
+      "num_tokens": 2976301.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.0717978198081255,
+      "epoch": 1.7264,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 8.791208791208791e-05,
+      "loss": 0.06898372173309326,
+      "mean_token_accuracy": 0.974400269985199,
+      "num_tokens": 3032771.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.07407103907316923,
+      "epoch": 1.7584,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.07060829997062683,
+      "mean_token_accuracy": 0.9738653019070626,
+      "num_tokens": 3088405.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.07348943576216697,
+      "epoch": 1.7904,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 8.351648351648353e-05,
+      "loss": 0.06981388926506042,
+      "mean_token_accuracy": 0.973979789018631,
+      "num_tokens": 3144186.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.07443872913718223,
+      "epoch": 1.8224,
+      "grad_norm": 0.04638671875,
+      "learning_rate": 8.131868131868132e-05,
+      "loss": 0.07104510068893433,
+      "mean_token_accuracy": 0.97396722137928,
+      "num_tokens": 3200274.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.07258394770324231,
+      "epoch": 1.8544,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 7.912087912087912e-05,
+      "loss": 0.06858785152435302,
+      "mean_token_accuracy": 0.9745583027601242,
+      "num_tokens": 3257100.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.07335705403238535,
+      "epoch": 1.8864,
+      "grad_norm": 0.04296875,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.0689892292022705,
+      "mean_token_accuracy": 0.9740391105413437,
+      "num_tokens": 3313764.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.0722169006243348,
+      "epoch": 1.9184,
+      "grad_norm": 0.052734375,
+      "learning_rate": 7.472527472527473e-05,
+      "loss": 0.06918958425521851,
+      "mean_token_accuracy": 0.9745689764618873,
+      "num_tokens": 3370053.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.0719969030469656,
+      "epoch": 1.9504000000000001,
+      "grad_norm": 0.05078125,
+      "learning_rate": 7.252747252747253e-05,
+      "loss": 0.07059705257415771,
+      "mean_token_accuracy": 0.9735003352165222,
+      "num_tokens": 3425403.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.07328992187976838,
+      "epoch": 1.9824000000000002,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 7.032967032967034e-05,
+      "loss": 0.06893991827964782,
+      "mean_token_accuracy": 0.974341906607151,
+      "num_tokens": 3481888.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.07355283553663053,
+      "epoch": 2.0128,
+      "grad_norm": 0.05419921875,
+      "learning_rate": 6.813186813186814e-05,
+      "loss": 0.06852576732635499,
+      "mean_token_accuracy": 0.9741844628986559,
+      "num_tokens": 3535234.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.07177970744669437,
+      "epoch": 2.0448,
+      "grad_norm": 0.0458984375,
+      "learning_rate": 6.593406593406594e-05,
+      "loss": 0.06823881268501282,
+      "mean_token_accuracy": 0.9741811975836754,
+      "num_tokens": 3590735.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.07052574083209037,
+      "epoch": 2.0768,
+      "grad_norm": 0.047119140625,
+      "learning_rate": 6.373626373626373e-05,
+      "loss": 0.06783221364021301,
+      "mean_token_accuracy": 0.9742385044693946,
+      "num_tokens": 3647317.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.07118275295943022,
+      "epoch": 2.1088,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.06789056658744812,
+      "mean_token_accuracy": 0.9747925192117691,
+      "num_tokens": 3704190.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.07141004446893931,
+      "epoch": 2.1408,
+      "grad_norm": 0.046630859375,
+      "learning_rate": 5.9340659340659345e-05,
+      "loss": 0.06710809469223022,
+      "mean_token_accuracy": 0.9745214998722076,
+      "num_tokens": 3760496.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.06936982274055481,
+      "epoch": 2.1728,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.06704961657524108,
+      "mean_token_accuracy": 0.9749385923147201,
+      "num_tokens": 3817106.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.0714575270190835,
+      "epoch": 2.2048,
+      "grad_norm": 0.04833984375,
+      "learning_rate": 5.494505494505495e-05,
+      "loss": 0.06737448573112488,
+      "mean_token_accuracy": 0.9740116745233536,
+      "num_tokens": 3873694.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.07101229522377253,
+      "epoch": 2.2368,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 5.274725274725275e-05,
+      "loss": 0.0672797441482544,
+      "mean_token_accuracy": 0.974830585718155,
+      "num_tokens": 3929897.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.0700510073453188,
+      "epoch": 2.2688,
+      "grad_norm": 0.052734375,
+      "learning_rate": 5.054945054945055e-05,
+      "loss": 0.06735477447509766,
+      "mean_token_accuracy": 0.9748806655406952,
+      "num_tokens": 3985906.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.07011591829359531,
+      "epoch": 2.3008,
+      "grad_norm": 0.0478515625,
+      "learning_rate": 4.8351648351648355e-05,
+      "loss": 0.06764240264892578,
+      "mean_token_accuracy": 0.9744778007268906,
+      "num_tokens": 4042082.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.07075654622167349,
+      "epoch": 2.3327999999999998,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0661679446697235,
+      "mean_token_accuracy": 0.9753401562571525,
+      "num_tokens": 4098909.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.07101095058023929,
+      "epoch": 2.3648,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 4.3956043956043955e-05,
+      "loss": 0.06830476522445679,
+      "mean_token_accuracy": 0.9741760551929474,
+      "num_tokens": 4154222.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.07036219611763954,
+      "epoch": 2.3968,
+      "grad_norm": 0.046875,
+      "learning_rate": 4.1758241758241765e-05,
+      "loss": 0.06679952144622803,
+      "mean_token_accuracy": 0.9747874498367309,
+      "num_tokens": 4209907.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.06965819718316198,
+      "epoch": 2.4288,
+      "grad_norm": 0.0478515625,
+      "learning_rate": 3.956043956043956e-05,
+      "loss": 0.06658568978309631,
+      "mean_token_accuracy": 0.9753396198153496,
+      "num_tokens": 4266708.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.07088542385026812,
+      "epoch": 2.4608,
+      "grad_norm": 0.047607421875,
+      "learning_rate": 3.7362637362637365e-05,
+      "loss": 0.06808845400810241,
+      "mean_token_accuracy": 0.9744594439864158,
+      "num_tokens": 4322203.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.07002440262585878,
+      "epoch": 2.4928,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 3.516483516483517e-05,
+      "loss": 0.06674610376358033,
+      "mean_token_accuracy": 0.9749701410531998,
+      "num_tokens": 4378286.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.07156520402058959,
+      "epoch": 2.5248,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 3.296703296703297e-05,
+      "loss": 0.06783879399299622,
+      "mean_token_accuracy": 0.9742916822433472,
+      "num_tokens": 4433890.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.07110334262251854,
+      "epoch": 2.5568,
+      "grad_norm": 0.05078125,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.06623314619064331,
+      "mean_token_accuracy": 0.9757025733590126,
+      "num_tokens": 4490228.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.07086261715739965,
+      "epoch": 2.5888,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.06686291694641114,
+      "mean_token_accuracy": 0.974934495985508,
+      "num_tokens": 4546293.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.06940543595701457,
+      "epoch": 2.6208,
+      "grad_norm": 0.048583984375,
+      "learning_rate": 2.6373626373626374e-05,
+      "loss": 0.06693726181983947,
+      "mean_token_accuracy": 0.9744124352931977,
+      "num_tokens": 4602398.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.07065027058124543,
+      "epoch": 2.6528,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 2.4175824175824177e-05,
+      "loss": 0.06692788600921631,
+      "mean_token_accuracy": 0.9747064486145973,
+      "num_tokens": 4658249.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.0688671569339931,
+      "epoch": 2.6848,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.1978021978021977e-05,
+      "loss": 0.06544087529182434,
+      "mean_token_accuracy": 0.9749023050069809,
+      "num_tokens": 4714387.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.06899926522746683,
+      "epoch": 2.7168,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 1.978021978021978e-05,
+      "loss": 0.06681140065193177,
+      "mean_token_accuracy": 0.975035460293293,
+      "num_tokens": 4770700.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.06984850689768791,
+      "epoch": 2.7488,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.7582417582417584e-05,
+      "loss": 0.06549346446990967,
+      "mean_token_accuracy": 0.9752413630485535,
+      "num_tokens": 4827270.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.07006102437153458,
+      "epoch": 2.7808,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.06601048707962036,
+      "mean_token_accuracy": 0.9751122385263443,
+      "num_tokens": 4883287.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.07032166775316,
+      "epoch": 2.8128,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 1.3186813186813187e-05,
+      "loss": 0.06602610349655151,
+      "mean_token_accuracy": 0.9746679022908211,
+      "num_tokens": 4939190.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.06937383627519011,
+      "epoch": 2.8448,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 1.0989010989010989e-05,
+      "loss": 0.06518557667732239,
+      "mean_token_accuracy": 0.9755709722638131,
+      "num_tokens": 4995747.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.07017751513049006,
+      "epoch": 2.8768000000000002,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 8.791208791208792e-06,
+      "loss": 0.06582036018371581,
+      "mean_token_accuracy": 0.9752513289451599,
+      "num_tokens": 5052336.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.06967417653650046,
+      "epoch": 2.9088000000000003,
+      "grad_norm": 0.05419921875,
+      "learning_rate": 6.5934065934065935e-06,
+      "loss": 0.06589003205299378,
+      "mean_token_accuracy": 0.9749706491827965,
+      "num_tokens": 5108592.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.06899928543716669,
+      "epoch": 2.9408,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 4.395604395604396e-06,
+      "loss": 0.06553114652633667,
+      "mean_token_accuracy": 0.9755852162837982,
+      "num_tokens": 5165398.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.06951060444116593,
+      "epoch": 2.9728,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 2.197802197802198e-06,
+      "loss": 0.06614152193069459,
+      "mean_token_accuracy": 0.9750266820192337,
+      "num_tokens": 5221349.0,
+      "step": 930
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "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": 2.4543986745581568e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

empathy/checkpoint-939/training_args.bin

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

empathy/tokenizer.json

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

empathy/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"
+}