Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+dpo_run/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+dpo_run/checkpoint-192/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter/README.md

@@ -0,0 +1,209 @@
+---
+base_model: ./checkpoints/ft_jais_paper/merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./checkpoints/ft_jais_paper/merged
+- dpo
+- lora
+- 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 0.19.1

adapter/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./checkpoints/ft_jais_paper/merged",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d4100efca27bc77f47040e82b338dcc0e20a2fe7e5bc8a325ae77af2eb607e
+size 27297032

adapter/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 %}

adapter/ref/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./checkpoints/ft_jais_paper/merged",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/ref/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57db2b296bc7290f18c750843e4280daf15135b126a73cbfdad9b171a581a4e3
+size 27297032

adapter/tokenizer.json

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

adapter/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

dpo_run/README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+model_name: dpo_run
+tags:
+- generated_from_trainer
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for dpo_run
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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 DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 1.7.1
+- Transformers: 5.13.0
+- Pytorch: 2.12.0+cu130
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+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}
+}
+```

dpo_run/checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: ./checkpoints/ft_jais_paper/merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./checkpoints/ft_jais_paper/merged
+- dpo
+- lora
+- 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 0.19.1

dpo_run/checkpoint-100/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./checkpoints/ft_jais_paper/merged",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo_run/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e862962a6bc122e3a27c5385e5be355d611ac8336ec9d8be00a37868fd24be
+size 27297032

dpo_run/checkpoint-100/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 %}

dpo_run/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1917c37272304c307399b4c607011befca959e9f0db5d4619853025fa409b8
+size 54680139

dpo_run/checkpoint-100/ref/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./checkpoints/ft_jais_paper/merged",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo_run/checkpoint-100/ref/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57db2b296bc7290f18c750843e4280daf15135b126a73cbfdad9b171a581a4e3
+size 27297032

dpo_run/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+size 14645

dpo_run/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b14909a0f0138023fc5a1a2a595ead21962ba33aa04cc7226670ad9ec1cc66
+size 1465

dpo_run/checkpoint-100/tokenizer.json

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

dpo_run/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

dpo_run/checkpoint-100/trainer_state.json

@@ -0,0 +1,252 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.6545524597167969,
+  "best_model_checkpoint": "checkpoints/ft_jais_simdpo/dpo_run/checkpoint-100",
+  "epoch": 1.5625,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8328714728355407,
+      "epoch": 0.15625,
+      "grad_norm": 3.5907697677612305,
+      "learning_rate": 2.25e-05,
+      "logits/chosen": 0.9851744980764,
+      "logits/rejected": 0.9132862824057325,
+      "logps/chosen": -80.49798936843872,
+      "logps/rejected": -87.13544521331787,
+      "loss": 0.691208028793335,
+      "mean_token_accuracy": 0.8373994886875152,
+      "num_tokens": 16910.0,
+      "rewards/accuracies": 0.4125,
+      "rewards/chosen": 0.005871815676800907,
+      "rewards/margins": 0.0046546274214051666,
+      "rewards/rejected": 0.0012171887326985597,
+      "step": 10
+    },
+    {
+      "entropy": 0.8236085653305054,
+      "epoch": 0.3125,
+      "grad_norm": 3.045801877975464,
+      "learning_rate": 4.75e-05,
+      "logits/chosen": 0.9432169298637705,
+      "logits/rejected": 0.9300128951388309,
+      "logps/chosen": -80.01706008911133,
+      "logps/rejected": -86.19765682220459,
+      "loss": 0.6912835597991943,
+      "mean_token_accuracy": 0.8420414581894875,
+      "num_tokens": 33876.0,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.046248766069766134,
+      "rewards/margins": 0.0050085548544302584,
+      "rewards/rejected": 0.04124021101742983,
+      "step": 20
+    },
+    {
+      "entropy": 0.8710977151989937,
+      "epoch": 0.46875,
+      "grad_norm": 4.131756782531738,
+      "learning_rate": 4.9662976890711167e-05,
+      "logits/chosen": 0.952295882064034,
+      "logits/rejected": 0.8837412199420139,
+      "logps/chosen": -83.00751543045044,
+      "logps/rejected": -89.77082118988037,
+      "loss": 0.6836707592010498,
+      "mean_token_accuracy": 0.830362756550312,
+      "num_tokens": 51751.0,
+      "rewards/accuracies": 0.55,
+      "rewards/chosen": 0.19173650545999407,
+      "rewards/margins": 0.02175652077421546,
+      "rewards/rejected": 0.1699799854774028,
+      "step": 30
+    },
+    {
+      "entropy": 0.8702168866991997,
+      "epoch": 0.625,
+      "grad_norm": 3.4390907287597656,
+      "learning_rate": 4.850961997099892e-05,
+      "logits/chosen": 0.9335240972164126,
+      "logits/rejected": 0.8931220467287231,
+      "logps/chosen": -78.64973669052124,
+      "logps/rejected": -83.12959709167481,
+      "loss": 0.680081558227539,
+      "mean_token_accuracy": 0.8323500514030456,
+      "num_tokens": 68855.0,
+      "rewards/accuracies": 0.575,
+      "rewards/chosen": 0.5641312405467034,
+      "rewards/margins": 0.03580198623239994,
+      "rewards/rejected": 0.5283292587846518,
+      "step": 40
+    },
+    {
+      "entropy": 0.8412925243377686,
+      "epoch": 0.78125,
+      "grad_norm": 3.696289539337158,
+      "learning_rate": 4.657412981885862e-05,
+      "logits/chosen": 0.9247626503111631,
+      "logits/rejected": 0.9220718661915835,
+      "logps/chosen": -68.65432586669922,
+      "logps/rejected": -82.09786891937256,
+      "loss": 0.628887414932251,
+      "mean_token_accuracy": 0.8538857877254487,
+      "num_tokens": 86484.0,
+      "rewards/accuracies": 0.775,
+      "rewards/chosen": 1.0782162077724933,
+      "rewards/margins": 0.16525846347212791,
+      "rewards/rejected": 0.9129577524960041,
+      "step": 50
+    },
+    {
+      "epoch": 0.78125,
+      "eval_entropy": 0.8311625965710344,
+      "eval_logits/chosen": 0.9525682816067235,
+      "eval_logits/rejected": 0.9378524862311701,
+      "eval_logps/chosen": -70.774687273749,
+      "eval_logps/rejected": -77.4474421534045,
+      "eval_loss": 0.663590133190155,
+      "eval_mean_token_accuracy": 0.8474541881988789,
+      "eval_num_tokens": 86484.0,
+      "eval_rewards/accuracies": 0.6724137931034483,
+      "eval_rewards/chosen": 1.197298473325269,
+      "eval_rewards/margins": 0.1253269150339324,
+      "eval_rewards/rejected": 1.0719715516115058,
+      "eval_runtime": 3.6052,
+      "eval_samples_per_second": 15.811,
+      "eval_steps_per_second": 8.044,
+      "step": 50
+    },
+    {
+      "entropy": 0.9258149698376655,
+      "epoch": 0.9375,
+      "grad_norm": 9.48177433013916,
+      "learning_rate": 4.392089757165841e-05,
+      "logits/chosen": 0.9196924747627211,
+      "logits/rejected": 0.9150918054479149,
+      "logps/chosen": -69.63652791976929,
+      "logps/rejected": -74.67644653320312,
+      "loss": 0.6724472045898438,
+      "mean_token_accuracy": 0.8314912617206573,
+      "num_tokens": 103165.0,
+      "rewards/accuracies": 0.6,
+      "rewards/chosen": 1.612139716744423,
+      "rewards/margins": 0.10208179727196694,
+      "rewards/rejected": 1.5100578874349595,
+      "step": 60
+    },
+    {
+      "entropy": 0.9276665955781936,
+      "epoch": 1.09375,
+      "grad_norm": 4.742893218994141,
+      "learning_rate": 4.0638192674691136e-05,
+      "logits/chosen": 0.9372565226225635,
+      "logits/rejected": 0.8758297012073308,
+      "logps/chosen": -72.57800025939942,
+      "logps/rejected": -75.22021579742432,
+      "loss": 0.5596485137939453,
+      "mean_token_accuracy": 0.8355538666248321,
+      "num_tokens": 120923.0,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.6647123485803603,
+      "rewards/margins": 0.3873647030442953,
+      "rewards/rejected": 1.2773476531729102,
+      "step": 70
+    },
+    {
+      "entropy": 0.9321356564760208,
+      "epoch": 1.25,
+      "grad_norm": 3.8452413082122803,
+      "learning_rate": 3.683522627621608e-05,
+      "logits/chosen": 0.9183959182419773,
+      "logits/rejected": 0.8850714484434743,
+      "logps/chosen": -73.9180368423462,
+      "logps/rejected": -87.95330810546875,
+      "loss": 0.4759009838104248,
+      "mean_token_accuracy": 0.8352961301803589,
+      "num_tokens": 138825.0,
+      "rewards/accuracies": 0.8,
+      "rewards/chosen": 1.2514840960502625,
+      "rewards/margins": 0.6839764896780253,
+      "rewards/rejected": 0.5675076065585017,
+      "step": 80
+    },
+    {
+      "entropy": 0.9279324404895306,
+      "epoch": 1.40625,
+      "grad_norm": 5.118920803070068,
+      "learning_rate": 3.263851792039109e-05,
+      "logits/chosen": 0.8924988958553159,
+      "logits/rejected": 0.8284702619552127,
+      "logps/chosen": -71.48162698745728,
+      "logps/rejected": -83.52158260345459,
+      "loss": 0.39791891574859617,
+      "mean_token_accuracy": 0.8307904973626137,
+      "num_tokens": 155378.0,
+      "rewards/accuracies": 0.8875,
+      "rewards/chosen": 1.317165607213974,
+      "rewards/margins": 0.9690214801579714,
+      "rewards/rejected": 0.34814412128180267,
+      "step": 90
+    },
+    {
+      "entropy": 0.9241503536701202,
+      "epoch": 1.5625,
+      "grad_norm": 7.398733615875244,
+      "learning_rate": 2.81876864133027e-05,
+      "logits/chosen": 0.9289504257072073,
+      "logits/rejected": 0.9161463222864651,
+      "logps/chosen": -62.29160423278809,
+      "logps/rejected": -79.298428440094,
+      "loss": 0.41886510848999026,
+      "mean_token_accuracy": 0.8381225109100342,
+      "num_tokens": 171778.0,
+      "rewards/accuracies": 0.7875,
+      "rewards/chosen": 1.9696232751011848,
+      "rewards/margins": 1.0112529575824738,
+      "rewards/rejected": 0.9583703201264143,
+      "step": 100
+    },
+    {
+      "epoch": 1.5625,
+      "eval_entropy": 0.8753328939964031,
+      "eval_logits/chosen": 0.980303409740094,
+      "eval_logits/rejected": 0.9663606126464863,
+      "eval_logps/chosen": -59.93091070240941,
+      "eval_logps/rejected": -69.91863198115908,
+      "eval_loss": 0.6545524597167969,
+      "eval_mean_token_accuracy": 0.8393763550396623,
+      "eval_num_tokens": 171778.0,
+      "eval_rewards/accuracies": 0.6551724137931034,
+      "eval_rewards/chosen": 2.281676158822816,
+      "eval_rewards/margins": 0.45682352164696005,
+      "eval_rewards/rejected": 1.8248526556738491,
+      "eval_runtime": 3.6534,
+      "eval_samples_per_second": 15.602,
+      "eval_steps_per_second": 7.938,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.070816827686912e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

dpo_run/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2f5c93a150a28b433b4deecef1c96d772331f7a6843d129188a66b41666003
+size 5841

dpo_run/checkpoint-192/README.md

@@ -0,0 +1,209 @@
+---
+base_model: ./checkpoints/ft_jais_paper/merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./checkpoints/ft_jais_paper/merged
+- dpo
+- lora
+- 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 0.19.1

dpo_run/checkpoint-192/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./checkpoints/ft_jais_paper/merged",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo_run/checkpoint-192/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d4100efca27bc77f47040e82b338dcc0e20a2fe7e5bc8a325ae77af2eb607e
+size 27297032

dpo_run/checkpoint-192/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 %}

dpo_run/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea895e56e2d1d0aa65c07ee1ff3c9a811707cb52e769c2518afaf34820d3e358
+size 54680139

dpo_run/checkpoint-192/ref/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./checkpoints/ft_jais_paper/merged",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo_run/checkpoint-192/ref/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57db2b296bc7290f18c750843e4280daf15135b126a73cbfdad9b171a581a4e3
+size 27297032

dpo_run/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0
+size 14645

dpo_run/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8caff6c4ce3bd764f4450dcf25ad72fb2330bcf7e768724f2d73c08c3ad61c6
+size 1465

dpo_run/checkpoint-192/tokenizer.json

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

dpo_run/checkpoint-192/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

dpo_run/checkpoint-192/trainer_state.json

@@ -0,0 +1,452 @@
+{
+  "best_global_step": 192,
+  "best_metric": 0.6124392151832581,
+  "best_model_checkpoint": "checkpoints/ft_jais_simdpo/dpo_run/checkpoint-192",
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8328714728355407,
+      "epoch": 0.15625,
+      "grad_norm": 3.5907697677612305,
+      "learning_rate": 2.25e-05,
+      "logits/chosen": 0.9851744980764,
+      "logits/rejected": 0.9132862824057325,
+      "logps/chosen": -80.49798936843872,
+      "logps/rejected": -87.13544521331787,
+      "loss": 0.691208028793335,
+      "mean_token_accuracy": 0.8373994886875152,
+      "num_tokens": 16910.0,
+      "rewards/accuracies": 0.4125,
+      "rewards/chosen": 0.005871815676800907,
+      "rewards/margins": 0.0046546274214051666,
+      "rewards/rejected": 0.0012171887326985597,
+      "step": 10
+    },
+    {
+      "entropy": 0.8236085653305054,
+      "epoch": 0.3125,
+      "grad_norm": 3.045801877975464,
+      "learning_rate": 4.75e-05,
+      "logits/chosen": 0.9432169298637705,
+      "logits/rejected": 0.9300128951388309,
+      "logps/chosen": -80.01706008911133,
+      "logps/rejected": -86.19765682220459,
+      "loss": 0.6912835597991943,
+      "mean_token_accuracy": 0.8420414581894875,
+      "num_tokens": 33876.0,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.046248766069766134,
+      "rewards/margins": 0.0050085548544302584,
+      "rewards/rejected": 0.04124021101742983,
+      "step": 20
+    },
+    {
+      "entropy": 0.8710977151989937,
+      "epoch": 0.46875,
+      "grad_norm": 4.131756782531738,
+      "learning_rate": 4.9662976890711167e-05,
+      "logits/chosen": 0.952295882064034,
+      "logits/rejected": 0.8837412199420139,
+      "logps/chosen": -83.00751543045044,
+      "logps/rejected": -89.77082118988037,
+      "loss": 0.6836707592010498,
+      "mean_token_accuracy": 0.830362756550312,
+      "num_tokens": 51751.0,
+      "rewards/accuracies": 0.55,
+      "rewards/chosen": 0.19173650545999407,
+      "rewards/margins": 0.02175652077421546,
+      "rewards/rejected": 0.1699799854774028,
+      "step": 30
+    },
+    {
+      "entropy": 0.8702168866991997,
+      "epoch": 0.625,
+      "grad_norm": 3.4390907287597656,
+      "learning_rate": 4.850961997099892e-05,
+      "logits/chosen": 0.9335240972164126,
+      "logits/rejected": 0.8931220467287231,
+      "logps/chosen": -78.64973669052124,
+      "logps/rejected": -83.12959709167481,
+      "loss": 0.680081558227539,
+      "mean_token_accuracy": 0.8323500514030456,
+      "num_tokens": 68855.0,
+      "rewards/accuracies": 0.575,
+      "rewards/chosen": 0.5641312405467034,
+      "rewards/margins": 0.03580198623239994,
+      "rewards/rejected": 0.5283292587846518,
+      "step": 40
+    },
+    {
+      "entropy": 0.8412925243377686,
+      "epoch": 0.78125,
+      "grad_norm": 3.696289539337158,
+      "learning_rate": 4.657412981885862e-05,
+      "logits/chosen": 0.9247626503111631,
+      "logits/rejected": 0.9220718661915835,
+      "logps/chosen": -68.65432586669922,
+      "logps/rejected": -82.09786891937256,
+      "loss": 0.628887414932251,
+      "mean_token_accuracy": 0.8538857877254487,
+      "num_tokens": 86484.0,
+      "rewards/accuracies": 0.775,
+      "rewards/chosen": 1.0782162077724933,
+      "rewards/margins": 0.16525846347212791,
+      "rewards/rejected": 0.9129577524960041,
+      "step": 50
+    },
+    {
+      "epoch": 0.78125,
+      "eval_entropy": 0.8311625965710344,
+      "eval_logits/chosen": 0.9525682816067235,
+      "eval_logits/rejected": 0.9378524862311701,
+      "eval_logps/chosen": -70.774687273749,
+      "eval_logps/rejected": -77.4474421534045,
+      "eval_loss": 0.663590133190155,
+      "eval_mean_token_accuracy": 0.8474541881988789,
+      "eval_num_tokens": 86484.0,
+      "eval_rewards/accuracies": 0.6724137931034483,
+      "eval_rewards/chosen": 1.197298473325269,
+      "eval_rewards/margins": 0.1253269150339324,
+      "eval_rewards/rejected": 1.0719715516115058,
+      "eval_runtime": 3.6052,
+      "eval_samples_per_second": 15.811,
+      "eval_steps_per_second": 8.044,
+      "step": 50
+    },
+    {
+      "entropy": 0.9258149698376655,
+      "epoch": 0.9375,
+      "grad_norm": 9.48177433013916,
+      "learning_rate": 4.392089757165841e-05,
+      "logits/chosen": 0.9196924747627211,
+      "logits/rejected": 0.9150918054479149,
+      "logps/chosen": -69.63652791976929,
+      "logps/rejected": -74.67644653320312,
+      "loss": 0.6724472045898438,
+      "mean_token_accuracy": 0.8314912617206573,
+      "num_tokens": 103165.0,
+      "rewards/accuracies": 0.6,
+      "rewards/chosen": 1.612139716744423,
+      "rewards/margins": 0.10208179727196694,
+      "rewards/rejected": 1.5100578874349595,
+      "step": 60
+    },
+    {
+      "entropy": 0.9276665955781936,
+      "epoch": 1.09375,
+      "grad_norm": 4.742893218994141,
+      "learning_rate": 4.0638192674691136e-05,
+      "logits/chosen": 0.9372565226225635,
+      "logits/rejected": 0.8758297012073308,
+      "logps/chosen": -72.57800025939942,
+      "logps/rejected": -75.22021579742432,
+      "loss": 0.5596485137939453,
+      "mean_token_accuracy": 0.8355538666248321,
+      "num_tokens": 120923.0,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.6647123485803603,
+      "rewards/margins": 0.3873647030442953,
+      "rewards/rejected": 1.2773476531729102,
+      "step": 70
+    },
+    {
+      "entropy": 0.9321356564760208,
+      "epoch": 1.25,
+      "grad_norm": 3.8452413082122803,
+      "learning_rate": 3.683522627621608e-05,
+      "logits/chosen": 0.9183959182419773,
+      "logits/rejected": 0.8850714484434743,
+      "logps/chosen": -73.9180368423462,
+      "logps/rejected": -87.95330810546875,
+      "loss": 0.4759009838104248,
+      "mean_token_accuracy": 0.8352961301803589,
+      "num_tokens": 138825.0,
+      "rewards/accuracies": 0.8,
+      "rewards/chosen": 1.2514840960502625,
+      "rewards/margins": 0.6839764896780253,
+      "rewards/rejected": 0.5675076065585017,
+      "step": 80
+    },
+    {
+      "entropy": 0.9279324404895306,
+      "epoch": 1.40625,
+      "grad_norm": 5.118920803070068,
+      "learning_rate": 3.263851792039109e-05,
+      "logits/chosen": 0.8924988958553159,
+      "logits/rejected": 0.8284702619552127,
+      "logps/chosen": -71.48162698745728,
+      "logps/rejected": -83.52158260345459,
+      "loss": 0.39791891574859617,
+      "mean_token_accuracy": 0.8307904973626137,
+      "num_tokens": 155378.0,
+      "rewards/accuracies": 0.8875,
+      "rewards/chosen": 1.317165607213974,
+      "rewards/margins": 0.9690214801579714,
+      "rewards/rejected": 0.34814412128180267,
+      "step": 90
+    },
+    {
+      "entropy": 0.9241503536701202,
+      "epoch": 1.5625,
+      "grad_norm": 7.398733615875244,
+      "learning_rate": 2.81876864133027e-05,
+      "logits/chosen": 0.9289504257072073,
+      "logits/rejected": 0.9161463222864651,
+      "logps/chosen": -62.29160423278809,
+      "logps/rejected": -79.298428440094,
+      "loss": 0.41886510848999026,
+      "mean_token_accuracy": 0.8381225109100342,
+      "num_tokens": 171778.0,
+      "rewards/accuracies": 0.7875,
+      "rewards/chosen": 1.9696232751011848,
+      "rewards/margins": 1.0112529575824738,
+      "rewards/rejected": 0.9583703201264143,
+      "step": 100
+    },
+    {
+      "epoch": 1.5625,
+      "eval_entropy": 0.8753328939964031,
+      "eval_logits/chosen": 0.980303409740094,
+      "eval_logits/rejected": 0.9663606126464863,
+      "eval_logps/chosen": -59.93091070240941,
+      "eval_logps/rejected": -69.91863198115908,
+      "eval_loss": 0.6545524597167969,
+      "eval_mean_token_accuracy": 0.8393763550396623,
+      "eval_num_tokens": 171778.0,
+      "eval_rewards/accuracies": 0.6551724137931034,
+      "eval_rewards/chosen": 2.281676158822816,
+      "eval_rewards/margins": 0.45682352164696005,
+      "eval_rewards/rejected": 1.8248526556738491,
+      "eval_runtime": 3.6534,
+      "eval_samples_per_second": 15.602,
+      "eval_steps_per_second": 7.938,
+      "step": 100
+    },
+    {
+      "entropy": 0.925814239680767,
+      "epoch": 1.71875,
+      "grad_norm": 8.321379661560059,
+      "learning_rate": 2.363080489428391e-05,
+      "logits/chosen": 0.9598024684886474,
+      "logits/rejected": 0.9392234660386203,
+      "logps/chosen": -56.625073719024655,
+      "logps/rejected": -75.99530391693115,
+      "loss": 0.4041135311126709,
+      "mean_token_accuracy": 0.8366730898618698,
+      "num_tokens": 189000.0,
+      "rewards/accuracies": 0.8,
+      "rewards/chosen": 2.5931301951408385,
+      "rewards/margins": 1.1382387332618236,
+      "rewards/rejected": 1.4548914805054665,
+      "step": 110
+    },
+    {
+      "entropy": 0.9351913735270501,
+      "epoch": 1.875,
+      "grad_norm": 4.9336466789245605,
+      "learning_rate": 1.911947464300911e-05,
+      "logits/chosen": 0.956082177662182,
+      "logits/rejected": 0.9381028811702933,
+      "logps/chosen": -54.52532286643982,
+      "logps/rejected": -76.56493139266968,
+      "loss": 0.34934821128845217,
+      "mean_token_accuracy": 0.8426205664873123,
+      "num_tokens": 205690.0,
+      "rewards/accuracies": 0.8625,
+      "rewards/chosen": 2.6219111740589143,
+      "rewards/margins": 1.4122635282576084,
+      "rewards/rejected": 1.2096476439386605,
+      "step": 120
+    },
+    {
+      "entropy": 0.8790753468871116,
+      "epoch": 2.03125,
+      "grad_norm": 5.272885322570801,
+      "learning_rate": 1.4803781510135723e-05,
+      "logits/chosen": 0.9955120400997179,
+      "logits/rejected": 0.9845384123605191,
+      "logps/chosen": -53.220950508117674,
+      "logps/rejected": -79.19157724380493,
+      "loss": 0.3726229429244995,
+      "mean_token_accuracy": 0.8485471993684769,
+      "num_tokens": 223246.0,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 2.459031768143177,
+      "rewards/margins": 1.4352195501327514,
+      "rewards/rejected": 1.023812212049961,
+      "step": 130
+    },
+    {
+      "entropy": 0.9056376986205578,
+      "epoch": 2.1875,
+      "grad_norm": 3.285874605178833,
+      "learning_rate": 1.0827302764217886e-05,
+      "logits/chosen": 0.9938021062549278,
+      "logits/rejected": 0.9681679116775106,
+      "logps/chosen": -57.816345596313475,
+      "logps/rejected": -82.39878702163696,
+      "loss": 0.2858810186386108,
+      "mean_token_accuracy": 0.8472737610340119,
+      "num_tokens": 241397.0,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 2.5517143607139587,
+      "rewards/margins": 1.8401621930301189,
+      "rewards/rejected": 0.7115521389991045,
+      "step": 140
+    },
+    {
+      "entropy": 0.909576078504324,
+      "epoch": 2.34375,
+      "grad_norm": 6.196996688842773,
+      "learning_rate": 7.3223304703363135e-06,
+      "logits/chosen": 1.0399517872536237,
+      "logits/rejected": 1.0104635176610677,
+      "logps/chosen": -58.187259101867674,
+      "logps/rejected": -77.37480745315551,
+      "loss": 0.2617202281951904,
+      "mean_token_accuracy": 0.8451652511954307,
+      "num_tokens": 258092.0,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 2.578557401895523,
+      "rewards/margins": 1.8622532173991204,
+      "rewards/rejected": 0.7163041835650802,
+      "step": 150
+    },
+    {
+      "epoch": 2.34375,
+      "eval_entropy": 0.8786308087151626,
+      "eval_logits/chosen": 1.059930572001866,
+      "eval_logits/rejected": 1.046939485793307,
+      "eval_logps/chosen": -62.954081962848534,
+      "eval_logps/rejected": -75.78464692214439,
+      "eval_loss": 0.6239838004112244,
+      "eval_mean_token_accuracy": 0.838767409324646,
+      "eval_num_tokens": 258092.0,
+      "eval_rewards/accuracies": 0.6379310344827587,
+      "eval_rewards/chosen": 1.979359085189885,
+      "eval_rewards/margins": 0.7411079571164888,
+      "eval_rewards/rejected": 1.2382511147137345,
+      "eval_runtime": 3.4745,
+      "eval_samples_per_second": 16.405,
+      "eval_steps_per_second": 8.346,
+      "step": 150
+    },
+    {
+      "entropy": 0.9093523040413857,
+      "epoch": 2.5,
+      "grad_norm": 7.856006622314453,
+      "learning_rate": 4.405470312171392e-06,
+      "logits/chosen": 1.0332511449254072,
+      "logits/rejected": 0.9843762032343205,
+      "logps/chosen": -58.752701950073245,
+      "logps/rejected": -90.71653842926025,
+      "loss": 0.1804887056350708,
+      "mean_token_accuracy": 0.8449469625949859,
+      "num_tokens": 276174.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.356126905232668,
+      "rewards/margins": 2.361818128824234,
+      "rewards/rejected": -0.005691254138946533,
+      "step": 160
+    },
+    {
+      "entropy": 0.9203343503177166,
+      "epoch": 2.65625,
+      "grad_norm": 3.6486051082611084,
+      "learning_rate": 2.1737622787514593e-06,
+      "logits/chosen": 1.0113762496618601,
+      "logits/rejected": 0.957087860211527,
+      "logps/chosen": -63.05948009490967,
+      "logps/rejected": -90.06522645950318,
+      "loss": 0.20636234283447266,
+      "mean_token_accuracy": 0.8281458497047425,
+      "num_tokens": 292776.0,
+      "rewards/accuracies": 0.975,
+      "rewards/chosen": 2.0332263819873333,
+      "rewards/margins": 2.1697853356599808,
+      "rewards/rejected": -0.13655893383547663,
+      "step": 170
+    },
+    {
+      "entropy": 0.8908936537802219,
+      "epoch": 2.8125,
+      "grad_norm": 7.6800007820129395,
+      "learning_rate": 7.014522753768848e-07,
+      "logits/chosen": 1.0685504340633458,
+      "logits/rejected": 1.004012635665606,
+      "logps/chosen": -59.97100772857666,
+      "logps/rejected": -83.78988523483277,
+      "loss": 0.30030596256256104,
+      "mean_token_accuracy": 0.8450306236743927,
+      "num_tokens": 309430.0,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 2.085699033737183,
+      "rewards/margins": 1.9329860083758832,
+      "rewards/rejected": 0.152713031694293,
+      "step": 180
+    },
+    {
+      "entropy": 0.9806399837136268,
+      "epoch": 2.96875,
+      "grad_norm": 6.668964862823486,
+      "learning_rate": 3.7522062854356e-08,
+      "logits/chosen": 1.0495178805180392,
+      "logits/rejected": 1.0239107221934693,
+      "logps/chosen": -63.53562860488891,
+      "logps/rejected": -97.54202632904052,
+      "loss": 0.17719583511352538,
+      "mean_token_accuracy": 0.8237368956208229,
+      "num_tokens": 326322.0,
+      "rewards/accuracies": 0.9625,
+      "rewards/chosen": 2.103805848956108,
+      "rewards/margins": 2.5391295909881593,
+      "rewards/rejected": -0.43532373029738664,
+      "step": 190
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.8723657192855045,
+      "eval_logits/chosen": 1.0758996205438673,
+      "eval_logits/rejected": 1.0639617696113528,
+      "eval_logps/chosen": -67.85506097201643,
+      "eval_logps/rejected": -81.96065271311792,
+      "eval_loss": 0.6124392151832581,
+      "eval_mean_token_accuracy": 0.8315057775069927,
+      "eval_num_tokens": 329799.0,
+      "eval_rewards/accuracies": 0.6724137931034483,
+      "eval_rewards/chosen": 1.4892611256961166,
+      "eval_rewards/margins": 0.868610680103302,
+      "eval_rewards/rejected": 0.6206504702568054,
+      "eval_runtime": 3.4723,
+      "eval_samples_per_second": 16.416,
+      "eval_steps_per_second": 8.352,
+      "step": 192
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.040512082444288e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

dpo_run/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2f5c93a150a28b433b4deecef1c96d772331f7a6843d129188a66b41666003
+size 5841

dpo_run/runs/Jul08_10-32-30_704022de3b85/events.out.tfevents.1783506750.704022de3b85.12455.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908125c075ecaf8ffba995480dc4f8f157a7508cf8b99d8d0d6b2aaf3cde14d8
+size 25303

merged/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 %}

merged/config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

merged/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.13.0"
+}

merged/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7083cf9a27da0ba2afbf22f012784bbcf5c582ce269de259925977feedd6e0c
+size 16060556328

merged/tokenizer.json

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

merged/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}