Upload folder using huggingface_hub

.gitattributes

@@ -46,3 +46,6 @@ empathy/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 philosophy/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 philosophy/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 philosophy/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+quantum/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+quantum/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+quantum/tokenizer.json filter=lfs diff=lfs merge=lfs -text

quantum/README.md

@@ -0,0 +1,62 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+model_name: quantum
+tags:
+- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for quantum
+
+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}
+}
+```

quantum/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
+}

quantum/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daba59d3101ca1d0b42077187173d137c7894ff810c91e08e276ae0b3877bab9
+size 27297544

quantum/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 %}

quantum/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

quantum/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
+}

quantum/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5fbff570532ef2ed5d1c567a87f04e2d774adc879a14b0f8b99b24240875d5c
+size 27297544

quantum/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 %}

quantum/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548cd71d3acb628e49e4978c5d4f6e94a0670c6c4bcf1b1754c6802844387f10
+size 54745547

quantum/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f236a9c3350a4934ac64660483579d1ba3f9c41841ad20be10061a453545498d
+size 14645

quantum/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9112a0b881e5deafd2aa5f4f7fa0120abe4d3a263a4a28ed2d9bd5be41f60e5f
+size 1465

quantum/checkpoint-500/tokenizer.json

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

quantum/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"
+}

quantum/checkpoint-500/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.656589758396149,
+      "epoch": 0.04,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 2.784135627746582,
+      "mean_token_accuracy": 0.47858900427818296,
+      "num_tokens": 58831.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.130512335896492,
+      "epoch": 0.08,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00016521739130434784,
+      "loss": 2.2649614334106447,
+      "mean_token_accuracy": 0.5313303798437119,
+      "num_tokens": 117426.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.6294835805892944,
+      "epoch": 0.12,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00019834938101788172,
+      "loss": 1.5735199928283692,
+      "mean_token_accuracy": 0.6429987847805023,
+      "num_tokens": 176834.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1312334761023521,
+      "epoch": 0.16,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00019559834938101788,
+      "loss": 1.0732216835021973,
+      "mean_token_accuracy": 0.7459557801485062,
+      "num_tokens": 236514.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8465340793132782,
+      "epoch": 0.2,
+      "grad_norm": 0.302734375,
+      "learning_rate": 0.00019284731774415407,
+      "loss": 0.785353136062622,
+      "mean_token_accuracy": 0.8123098656535148,
+      "num_tokens": 296192.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5795673660933971,
+      "epoch": 0.24,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00019009628610729023,
+      "loss": 0.5051940441131592,
+      "mean_token_accuracy": 0.8781622618436813,
+      "num_tokens": 355215.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.40687272399663926,
+      "epoch": 0.28,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00018734525447042642,
+      "loss": 0.33609719276428224,
+      "mean_token_accuracy": 0.9220139101147652,
+      "num_tokens": 414445.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.2907550849020481,
+      "epoch": 0.32,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.0001845942228335626,
+      "loss": 0.2400279998779297,
+      "mean_token_accuracy": 0.946020171046257,
+      "num_tokens": 472587.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.20616337098181248,
+      "epoch": 0.36,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.00018184319119669877,
+      "loss": 0.16702178716659546,
+      "mean_token_accuracy": 0.9592987820506096,
+      "num_tokens": 531382.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.1737002834677696,
+      "epoch": 0.4,
+      "grad_norm": 0.21875,
+      "learning_rate": 0.00017909215955983493,
+      "loss": 0.1450087308883667,
+      "mean_token_accuracy": 0.9636144921183586,
+      "num_tokens": 590952.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.15012313090264798,
+      "epoch": 0.44,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.00017634112792297112,
+      "loss": 0.12923150062561034,
+      "mean_token_accuracy": 0.9657299771904946,
+      "num_tokens": 649294.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.1399887653067708,
+      "epoch": 0.48,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 0.00017359009628610728,
+      "loss": 0.11557692289352417,
+      "mean_token_accuracy": 0.9665726378560067,
+      "num_tokens": 707250.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.13480644691735505,
+      "epoch": 0.52,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00017083906464924347,
+      "loss": 0.10591565370559693,
+      "mean_token_accuracy": 0.96910200715065,
+      "num_tokens": 765329.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.1241924112662673,
+      "epoch": 0.56,
+      "grad_norm": 0.1484375,
+      "learning_rate": 0.00016808803301237966,
+      "loss": 0.10353405475616455,
+      "mean_token_accuracy": 0.9683606043457985,
+      "num_tokens": 824273.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.11277825795114041,
+      "epoch": 0.6,
+      "grad_norm": 0.10986328125,
+      "learning_rate": 0.00016533700137551582,
+      "loss": 0.09382225871086121,
+      "mean_token_accuracy": 0.9702155590057373,
+      "num_tokens": 882872.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.10969954002648592,
+      "epoch": 0.64,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.000162585969738652,
+      "loss": 0.09240695238113403,
+      "mean_token_accuracy": 0.9704399675130844,
+      "num_tokens": 940980.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.10195165053009987,
+      "epoch": 0.68,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 0.00015983493810178817,
+      "loss": 0.08729770183563232,
+      "mean_token_accuracy": 0.971330963075161,
+      "num_tokens": 999648.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.10189895406365394,
+      "epoch": 0.72,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00015708390646492434,
+      "loss": 0.08697207570075989,
+      "mean_token_accuracy": 0.9706669732928276,
+      "num_tokens": 1058258.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.0982053680345416,
+      "epoch": 0.76,
+      "grad_norm": 0.146484375,
+      "learning_rate": 0.00015433287482806052,
+      "loss": 0.08617557287216186,
+      "mean_token_accuracy": 0.9712221831083298,
+      "num_tokens": 1116552.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.09435265585780143,
+      "epoch": 0.8,
+      "grad_norm": 0.1064453125,
+      "learning_rate": 0.0001515818431911967,
+      "loss": 0.0837143063545227,
+      "mean_token_accuracy": 0.9719299852848053,
+      "num_tokens": 1176273.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.09587750304490328,
+      "epoch": 0.84,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 0.00014883081155433287,
+      "loss": 0.08407689332962036,
+      "mean_token_accuracy": 0.971569187939167,
+      "num_tokens": 1235151.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.0908985884860158,
+      "epoch": 0.88,
+      "grad_norm": 0.07421875,
+      "learning_rate": 0.00014607977991746906,
+      "loss": 0.08094486594200134,
+      "mean_token_accuracy": 0.9715604752302169,
+      "num_tokens": 1294009.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.08810036238282919,
+      "epoch": 0.92,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00014332874828060522,
+      "loss": 0.08071699142456054,
+      "mean_token_accuracy": 0.9727177411317826,
+      "num_tokens": 1352581.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.09025063011795283,
+      "epoch": 0.96,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 0.0001405777166437414,
+      "loss": 0.07819713950157166,
+      "mean_token_accuracy": 0.9728495046496392,
+      "num_tokens": 1411471.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.08711748849600554,
+      "epoch": 1.0,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.00013782668500687757,
+      "loss": 0.07690830826759339,
+      "mean_token_accuracy": 0.9727286458015442,
+      "num_tokens": 1470323.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.08317579198628663,
+      "epoch": 1.04,
+      "grad_norm": 0.11376953125,
+      "learning_rate": 0.00013507565337001376,
+      "loss": 0.07629346251487731,
+      "mean_token_accuracy": 0.9728547275066376,
+      "num_tokens": 1528025.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.08498188965022564,
+      "epoch": 1.08,
+      "grad_norm": 0.08984375,
+      "learning_rate": 0.00013232462173314995,
+      "loss": 0.0764327347278595,
+      "mean_token_accuracy": 0.9724415943026543,
+      "num_tokens": 1586684.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.0807153021916747,
+      "epoch": 1.12,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.0001295735900962861,
+      "loss": 0.07380666732788085,
+      "mean_token_accuracy": 0.9741398721933365,
+      "num_tokens": 1645327.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.08144337944686413,
+      "epoch": 1.16,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00012682255845942227,
+      "loss": 0.07288264632225036,
+      "mean_token_accuracy": 0.9744224503636361,
+      "num_tokens": 1704753.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.07854557279497384,
+      "epoch": 1.2,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 0.00012407152682255846,
+      "loss": 0.07169762253761292,
+      "mean_token_accuracy": 0.9740740984678269,
+      "num_tokens": 1764019.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.07972831521183252,
+      "epoch": 1.24,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00012132049518569464,
+      "loss": 0.07355321049690247,
+      "mean_token_accuracy": 0.9732201337814331,
+      "num_tokens": 1823105.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.08080395516008139,
+      "epoch": 1.28,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.00011856946354883083,
+      "loss": 0.0732525646686554,
+      "mean_token_accuracy": 0.9736150786280632,
+      "num_tokens": 1881613.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.07835352420806885,
+      "epoch": 1.32,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 0.000115818431911967,
+      "loss": 0.07361866235733032,
+      "mean_token_accuracy": 0.9739573955535888,
+      "num_tokens": 1939954.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.07962071467190981,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 0.00011306740027510316,
+      "loss": 0.07115083336830139,
+      "mean_token_accuracy": 0.9738854169845581,
+      "num_tokens": 1999104.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.07753032837063074,
+      "epoch": 1.4,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.00011031636863823935,
+      "loss": 0.07132790684700012,
+      "mean_token_accuracy": 0.9740729615092277,
+      "num_tokens": 2058086.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.07756854929029941,
+      "epoch": 1.44,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00010756533700137553,
+      "loss": 0.07140335440635681,
+      "mean_token_accuracy": 0.9735552534461022,
+      "num_tokens": 2116832.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.07727070953696966,
+      "epoch": 1.48,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 0.00010481430536451169,
+      "loss": 0.0708472490310669,
+      "mean_token_accuracy": 0.9730932384729385,
+      "num_tokens": 2175363.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.07725130897015334,
+      "epoch": 1.52,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00010206327372764788,
+      "loss": 0.0706408977508545,
+      "mean_token_accuracy": 0.9745364651083946,
+      "num_tokens": 2234249.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.07416967656463384,
+      "epoch": 1.56,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 9.931224209078405e-05,
+      "loss": 0.07005369067192077,
+      "mean_token_accuracy": 0.9741830781102181,
+      "num_tokens": 2293472.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.07707195524126291,
+      "epoch": 1.6,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 9.656121045392023e-05,
+      "loss": 0.07068833112716674,
+      "mean_token_accuracy": 0.9736332967877388,
+      "num_tokens": 2352115.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.07442550137639045,
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 9.38101788170564e-05,
+      "loss": 0.06983445286750793,
+      "mean_token_accuracy": 0.9745775699615479,
+      "num_tokens": 2410823.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.07408876791596412,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 9.105914718019258e-05,
+      "loss": 0.0696213722229004,
+      "mean_token_accuracy": 0.9745879158377647,
+      "num_tokens": 2469755.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.07369720749557018,
+      "epoch": 1.72,
+      "grad_norm": 0.06982421875,
+      "learning_rate": 8.830811554332875e-05,
+      "loss": 0.0684428870677948,
+      "mean_token_accuracy": 0.974769426882267,
+      "num_tokens": 2529125.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.07348712086677552,
+      "epoch": 1.76,
+      "grad_norm": 0.050048828125,
+      "learning_rate": 8.555708390646493e-05,
+      "loss": 0.06892426013946533,
+      "mean_token_accuracy": 0.9747400760650635,
+      "num_tokens": 2588493.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.07465939875692129,
+      "epoch": 1.8,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 8.28060522696011e-05,
+      "loss": 0.07028486132621765,
+      "mean_token_accuracy": 0.9742415577173233,
+      "num_tokens": 2646682.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07388942837715148,
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 8.005502063273728e-05,
+      "loss": 0.06874784231185913,
+      "mean_token_accuracy": 0.9752144053578377,
+      "num_tokens": 2705754.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.07370481453835964,
+      "epoch": 1.88,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 7.730398899587345e-05,
+      "loss": 0.06871609091758728,
+      "mean_token_accuracy": 0.9748002246022225,
+      "num_tokens": 2764663.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.07374548772349954,
+      "epoch": 1.92,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 7.455295735900963e-05,
+      "loss": 0.06881117820739746,
+      "mean_token_accuracy": 0.9741248309612274,
+      "num_tokens": 2823742.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.07451288178563117,
+      "epoch": 1.96,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 7.180192572214582e-05,
+      "loss": 0.06924532651901245,
+      "mean_token_accuracy": 0.9737852603197098,
+      "num_tokens": 2882364.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.07393263652920723,
+      "epoch": 2.0,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 6.905089408528198e-05,
+      "loss": 0.06974378228187561,
+      "mean_token_accuracy": 0.9740638837218285,
+      "num_tokens": 2940646.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "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": 1.3795263376785408e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

quantum/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23936680c6aa38f0881055cbef17d9546ee79c0924110452d372c113f99cdf46
+size 5585

quantum/checkpoint-750/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

quantum/checkpoint-750/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
+}

quantum/checkpoint-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daba59d3101ca1d0b42077187173d137c7894ff810c91e08e276ae0b3877bab9
+size 27297544

quantum/checkpoint-750/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 %}

quantum/checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c07086c1dda039753f67fade8e8997c07ba71e4fe4c252d117c94550fb5f17
+size 54745547

quantum/checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbfb3f2d3b1c9994c5639fcf9b72501475c561bb11054c488d64ac9b0eae140
+size 14645

quantum/checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6cffd29d107485fd65a3291d66df7b87424f25de973bb529c2fbe605d9c752
+size 1465

quantum/checkpoint-750/tokenizer.json

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

quantum/checkpoint-750/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"
+}

quantum/checkpoint-750/trainer_state.json

@@ -0,0 +1,784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.656589758396149,
+      "epoch": 0.04,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 2.784135627746582,
+      "mean_token_accuracy": 0.47858900427818296,
+      "num_tokens": 58831.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.130512335896492,
+      "epoch": 0.08,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00016521739130434784,
+      "loss": 2.2649614334106447,
+      "mean_token_accuracy": 0.5313303798437119,
+      "num_tokens": 117426.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.6294835805892944,
+      "epoch": 0.12,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00019834938101788172,
+      "loss": 1.5735199928283692,
+      "mean_token_accuracy": 0.6429987847805023,
+      "num_tokens": 176834.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1312334761023521,
+      "epoch": 0.16,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00019559834938101788,
+      "loss": 1.0732216835021973,
+      "mean_token_accuracy": 0.7459557801485062,
+      "num_tokens": 236514.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8465340793132782,
+      "epoch": 0.2,
+      "grad_norm": 0.302734375,
+      "learning_rate": 0.00019284731774415407,
+      "loss": 0.785353136062622,
+      "mean_token_accuracy": 0.8123098656535148,
+      "num_tokens": 296192.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5795673660933971,
+      "epoch": 0.24,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00019009628610729023,
+      "loss": 0.5051940441131592,
+      "mean_token_accuracy": 0.8781622618436813,
+      "num_tokens": 355215.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.40687272399663926,
+      "epoch": 0.28,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00018734525447042642,
+      "loss": 0.33609719276428224,
+      "mean_token_accuracy": 0.9220139101147652,
+      "num_tokens": 414445.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.2907550849020481,
+      "epoch": 0.32,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.0001845942228335626,
+      "loss": 0.2400279998779297,
+      "mean_token_accuracy": 0.946020171046257,
+      "num_tokens": 472587.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.20616337098181248,
+      "epoch": 0.36,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.00018184319119669877,
+      "loss": 0.16702178716659546,
+      "mean_token_accuracy": 0.9592987820506096,
+      "num_tokens": 531382.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.1737002834677696,
+      "epoch": 0.4,
+      "grad_norm": 0.21875,
+      "learning_rate": 0.00017909215955983493,
+      "loss": 0.1450087308883667,
+      "mean_token_accuracy": 0.9636144921183586,
+      "num_tokens": 590952.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.15012313090264798,
+      "epoch": 0.44,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.00017634112792297112,
+      "loss": 0.12923150062561034,
+      "mean_token_accuracy": 0.9657299771904946,
+      "num_tokens": 649294.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.1399887653067708,
+      "epoch": 0.48,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 0.00017359009628610728,
+      "loss": 0.11557692289352417,
+      "mean_token_accuracy": 0.9665726378560067,
+      "num_tokens": 707250.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.13480644691735505,
+      "epoch": 0.52,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00017083906464924347,
+      "loss": 0.10591565370559693,
+      "mean_token_accuracy": 0.96910200715065,
+      "num_tokens": 765329.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.1241924112662673,
+      "epoch": 0.56,
+      "grad_norm": 0.1484375,
+      "learning_rate": 0.00016808803301237966,
+      "loss": 0.10353405475616455,
+      "mean_token_accuracy": 0.9683606043457985,
+      "num_tokens": 824273.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.11277825795114041,
+      "epoch": 0.6,
+      "grad_norm": 0.10986328125,
+      "learning_rate": 0.00016533700137551582,
+      "loss": 0.09382225871086121,
+      "mean_token_accuracy": 0.9702155590057373,
+      "num_tokens": 882872.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.10969954002648592,
+      "epoch": 0.64,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.000162585969738652,
+      "loss": 0.09240695238113403,
+      "mean_token_accuracy": 0.9704399675130844,
+      "num_tokens": 940980.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.10195165053009987,
+      "epoch": 0.68,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 0.00015983493810178817,
+      "loss": 0.08729770183563232,
+      "mean_token_accuracy": 0.971330963075161,
+      "num_tokens": 999648.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.10189895406365394,
+      "epoch": 0.72,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00015708390646492434,
+      "loss": 0.08697207570075989,
+      "mean_token_accuracy": 0.9706669732928276,
+      "num_tokens": 1058258.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.0982053680345416,
+      "epoch": 0.76,
+      "grad_norm": 0.146484375,
+      "learning_rate": 0.00015433287482806052,
+      "loss": 0.08617557287216186,
+      "mean_token_accuracy": 0.9712221831083298,
+      "num_tokens": 1116552.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.09435265585780143,
+      "epoch": 0.8,
+      "grad_norm": 0.1064453125,
+      "learning_rate": 0.0001515818431911967,
+      "loss": 0.0837143063545227,
+      "mean_token_accuracy": 0.9719299852848053,
+      "num_tokens": 1176273.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.09587750304490328,
+      "epoch": 0.84,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 0.00014883081155433287,
+      "loss": 0.08407689332962036,
+      "mean_token_accuracy": 0.971569187939167,
+      "num_tokens": 1235151.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.0908985884860158,
+      "epoch": 0.88,
+      "grad_norm": 0.07421875,
+      "learning_rate": 0.00014607977991746906,
+      "loss": 0.08094486594200134,
+      "mean_token_accuracy": 0.9715604752302169,
+      "num_tokens": 1294009.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.08810036238282919,
+      "epoch": 0.92,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00014332874828060522,
+      "loss": 0.08071699142456054,
+      "mean_token_accuracy": 0.9727177411317826,
+      "num_tokens": 1352581.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.09025063011795283,
+      "epoch": 0.96,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 0.0001405777166437414,
+      "loss": 0.07819713950157166,
+      "mean_token_accuracy": 0.9728495046496392,
+      "num_tokens": 1411471.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.08711748849600554,
+      "epoch": 1.0,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.00013782668500687757,
+      "loss": 0.07690830826759339,
+      "mean_token_accuracy": 0.9727286458015442,
+      "num_tokens": 1470323.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.08317579198628663,
+      "epoch": 1.04,
+      "grad_norm": 0.11376953125,
+      "learning_rate": 0.00013507565337001376,
+      "loss": 0.07629346251487731,
+      "mean_token_accuracy": 0.9728547275066376,
+      "num_tokens": 1528025.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.08498188965022564,
+      "epoch": 1.08,
+      "grad_norm": 0.08984375,
+      "learning_rate": 0.00013232462173314995,
+      "loss": 0.0764327347278595,
+      "mean_token_accuracy": 0.9724415943026543,
+      "num_tokens": 1586684.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.0807153021916747,
+      "epoch": 1.12,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.0001295735900962861,
+      "loss": 0.07380666732788085,
+      "mean_token_accuracy": 0.9741398721933365,
+      "num_tokens": 1645327.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.08144337944686413,
+      "epoch": 1.16,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00012682255845942227,
+      "loss": 0.07288264632225036,
+      "mean_token_accuracy": 0.9744224503636361,
+      "num_tokens": 1704753.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.07854557279497384,
+      "epoch": 1.2,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 0.00012407152682255846,
+      "loss": 0.07169762253761292,
+      "mean_token_accuracy": 0.9740740984678269,
+      "num_tokens": 1764019.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.07972831521183252,
+      "epoch": 1.24,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00012132049518569464,
+      "loss": 0.07355321049690247,
+      "mean_token_accuracy": 0.9732201337814331,
+      "num_tokens": 1823105.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.08080395516008139,
+      "epoch": 1.28,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.00011856946354883083,
+      "loss": 0.0732525646686554,
+      "mean_token_accuracy": 0.9736150786280632,
+      "num_tokens": 1881613.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.07835352420806885,
+      "epoch": 1.32,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 0.000115818431911967,
+      "loss": 0.07361866235733032,
+      "mean_token_accuracy": 0.9739573955535888,
+      "num_tokens": 1939954.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.07962071467190981,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 0.00011306740027510316,
+      "loss": 0.07115083336830139,
+      "mean_token_accuracy": 0.9738854169845581,
+      "num_tokens": 1999104.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.07753032837063074,
+      "epoch": 1.4,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.00011031636863823935,
+      "loss": 0.07132790684700012,
+      "mean_token_accuracy": 0.9740729615092277,
+      "num_tokens": 2058086.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.07756854929029941,
+      "epoch": 1.44,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00010756533700137553,
+      "loss": 0.07140335440635681,
+      "mean_token_accuracy": 0.9735552534461022,
+      "num_tokens": 2116832.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.07727070953696966,
+      "epoch": 1.48,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 0.00010481430536451169,
+      "loss": 0.0708472490310669,
+      "mean_token_accuracy": 0.9730932384729385,
+      "num_tokens": 2175363.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.07725130897015334,
+      "epoch": 1.52,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00010206327372764788,
+      "loss": 0.0706408977508545,
+      "mean_token_accuracy": 0.9745364651083946,
+      "num_tokens": 2234249.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.07416967656463384,
+      "epoch": 1.56,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 9.931224209078405e-05,
+      "loss": 0.07005369067192077,
+      "mean_token_accuracy": 0.9741830781102181,
+      "num_tokens": 2293472.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.07707195524126291,
+      "epoch": 1.6,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 9.656121045392023e-05,
+      "loss": 0.07068833112716674,
+      "mean_token_accuracy": 0.9736332967877388,
+      "num_tokens": 2352115.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.07442550137639045,
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 9.38101788170564e-05,
+      "loss": 0.06983445286750793,
+      "mean_token_accuracy": 0.9745775699615479,
+      "num_tokens": 2410823.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.07408876791596412,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 9.105914718019258e-05,
+      "loss": 0.0696213722229004,
+      "mean_token_accuracy": 0.9745879158377647,
+      "num_tokens": 2469755.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.07369720749557018,
+      "epoch": 1.72,
+      "grad_norm": 0.06982421875,
+      "learning_rate": 8.830811554332875e-05,
+      "loss": 0.0684428870677948,
+      "mean_token_accuracy": 0.974769426882267,
+      "num_tokens": 2529125.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.07348712086677552,
+      "epoch": 1.76,
+      "grad_norm": 0.050048828125,
+      "learning_rate": 8.555708390646493e-05,
+      "loss": 0.06892426013946533,
+      "mean_token_accuracy": 0.9747400760650635,
+      "num_tokens": 2588493.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.07465939875692129,
+      "epoch": 1.8,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 8.28060522696011e-05,
+      "loss": 0.07028486132621765,
+      "mean_token_accuracy": 0.9742415577173233,
+      "num_tokens": 2646682.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.07388942837715148,
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 8.005502063273728e-05,
+      "loss": 0.06874784231185913,
+      "mean_token_accuracy": 0.9752144053578377,
+      "num_tokens": 2705754.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.07370481453835964,
+      "epoch": 1.88,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 7.730398899587345e-05,
+      "loss": 0.06871609091758728,
+      "mean_token_accuracy": 0.9748002246022225,
+      "num_tokens": 2764663.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.07374548772349954,
+      "epoch": 1.92,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 7.455295735900963e-05,
+      "loss": 0.06881117820739746,
+      "mean_token_accuracy": 0.9741248309612274,
+      "num_tokens": 2823742.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.07451288178563117,
+      "epoch": 1.96,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 7.180192572214582e-05,
+      "loss": 0.06924532651901245,
+      "mean_token_accuracy": 0.9737852603197098,
+      "num_tokens": 2882364.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.07393263652920723,
+      "epoch": 2.0,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 6.905089408528198e-05,
+      "loss": 0.06974378228187561,
+      "mean_token_accuracy": 0.9740638837218285,
+      "num_tokens": 2940646.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.07165123773738742,
+      "epoch": 2.04,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 6.629986244841817e-05,
+      "loss": 0.06680834889411927,
+      "mean_token_accuracy": 0.9748308375477791,
+      "num_tokens": 2998916.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.07095922846347094,
+      "epoch": 2.08,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 6.354883081155434e-05,
+      "loss": 0.06595931053161622,
+      "mean_token_accuracy": 0.9754224255681038,
+      "num_tokens": 3058365.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.0720227850601077,
+      "epoch": 2.12,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 6.0797799174690516e-05,
+      "loss": 0.067144775390625,
+      "mean_token_accuracy": 0.9746366187930107,
+      "num_tokens": 3116986.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.07073751464486122,
+      "epoch": 2.16,
+      "grad_norm": 0.05078125,
+      "learning_rate": 5.8046767537826685e-05,
+      "loss": 0.06626754403114318,
+      "mean_token_accuracy": 0.9748034983873367,
+      "num_tokens": 3175913.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.07113336315378546,
+      "epoch": 2.2,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 5.5295735900962866e-05,
+      "loss": 0.06611629724502563,
+      "mean_token_accuracy": 0.9757323890924454,
+      "num_tokens": 3234770.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.07078722622245551,
+      "epoch": 2.24,
+      "grad_norm": 0.047119140625,
+      "learning_rate": 5.254470426409904e-05,
+      "loss": 0.06645765900611877,
+      "mean_token_accuracy": 0.9749927267432212,
+      "num_tokens": 3293609.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.07144544133916497,
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 4.9793672627235217e-05,
+      "loss": 0.06597168445587158,
+      "mean_token_accuracy": 0.9753631532192231,
+      "num_tokens": 3352426.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.07122885715216398,
+      "epoch": 2.32,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 4.704264099037139e-05,
+      "loss": 0.06688882112503051,
+      "mean_token_accuracy": 0.9748361185193062,
+      "num_tokens": 3411185.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.0705800049006939,
+      "epoch": 2.36,
+      "grad_norm": 0.06640625,
+      "learning_rate": 4.429160935350757e-05,
+      "loss": 0.06566575169563293,
+      "mean_token_accuracy": 0.9755433648824692,
+      "num_tokens": 3469959.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.07156918346881866,
+      "epoch": 2.4,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 4.154057771664374e-05,
+      "loss": 0.06604508757591247,
+      "mean_token_accuracy": 0.9750233232975006,
+      "num_tokens": 3528922.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.07152145858854056,
+      "epoch": 2.44,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 3.8789546079779924e-05,
+      "loss": 0.06587186455726624,
+      "mean_token_accuracy": 0.9750920787453652,
+      "num_tokens": 3587481.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.0699362089857459,
+      "epoch": 2.48,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 3.603851444291609e-05,
+      "loss": 0.06582777500152588,
+      "mean_token_accuracy": 0.9753644019365311,
+      "num_tokens": 3646133.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.07039630739018321,
+      "epoch": 2.52,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 3.3287482806052274e-05,
+      "loss": 0.06508519053459168,
+      "mean_token_accuracy": 0.974852642416954,
+      "num_tokens": 3704870.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.07073354339227081,
+      "epoch": 2.56,
+      "grad_norm": 0.046142578125,
+      "learning_rate": 3.053645116918845e-05,
+      "loss": 0.06597902178764344,
+      "mean_token_accuracy": 0.9750823274254798,
+      "num_tokens": 3763130.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.07001532316207885,
+      "epoch": 2.6,
+      "grad_norm": 0.047607421875,
+      "learning_rate": 2.7785419532324624e-05,
+      "loss": 0.06426129937171936,
+      "mean_token_accuracy": 0.9758271887898445,
+      "num_tokens": 3822705.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.07013930734246969,
+      "epoch": 2.64,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 2.50343878954608e-05,
+      "loss": 0.06570706367492676,
+      "mean_token_accuracy": 0.9747341394424438,
+      "num_tokens": 3881186.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.07004177290946245,
+      "epoch": 2.68,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.2283356258596974e-05,
+      "loss": 0.06568543314933777,
+      "mean_token_accuracy": 0.9752050325274467,
+      "num_tokens": 3939850.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.07051089331507683,
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 1.953232462173315e-05,
+      "loss": 0.06640489101409912,
+      "mean_token_accuracy": 0.9754770487546921,
+      "num_tokens": 3998032.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.06977471075952053,
+      "epoch": 2.76,
+      "grad_norm": 0.052734375,
+      "learning_rate": 1.6781292984869327e-05,
+      "loss": 0.06518170833587647,
+      "mean_token_accuracy": 0.9750692203640938,
+      "num_tokens": 4056625.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.0697881813161075,
+      "epoch": 2.8,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 1.4030261348005502e-05,
+      "loss": 0.06471436619758605,
+      "mean_token_accuracy": 0.9756176814436912,
+      "num_tokens": 4116174.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.07102781580761075,
+      "epoch": 2.84,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 1.127922971114168e-05,
+      "loss": 0.06581937670707702,
+      "mean_token_accuracy": 0.9749741673469543,
+      "num_tokens": 4174286.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.07014696691185236,
+      "epoch": 2.88,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 8.528198074277854e-06,
+      "loss": 0.0643849492073059,
+      "mean_token_accuracy": 0.9756950348615646,
+      "num_tokens": 4233470.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.06872736243531108,
+      "epoch": 2.92,
+      "grad_norm": 0.05078125,
+      "learning_rate": 5.77716643741403e-06,
+      "loss": 0.06423060894012451,
+      "mean_token_accuracy": 0.975555220246315,
+      "num_tokens": 4292239.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.06862422479316592,
+      "epoch": 2.96,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 3.0261348005502065e-06,
+      "loss": 0.06354117393493652,
+      "mean_token_accuracy": 0.9763716101646424,
+      "num_tokens": 4351953.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.06982343215495349,
+      "epoch": 3.0,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.751031636863824e-07,
+      "loss": 0.0649968683719635,
+      "mean_token_accuracy": 0.9751548632979393,
+      "num_tokens": 4410969.0,
+      "step": 750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "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": 2.0699580565315584e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

quantum/checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23936680c6aa38f0881055cbef17d9546ee79c0924110452d372c113f99cdf46
+size 5585

quantum/tokenizer.json

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

quantum/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"
+}